Research Papers List

• Papers List
• Seminal Papers / Need-to-know
  • Computer Vision
    • 2010
      • Noise-contrastive Estimation: a New Estimation Principle for Unnormalized Statistical Models
    • 2012
      • ImageNet Classification with Deep Convolutional Neural Networks
      • 3D Convolutional Neural Networks for Human Action Recognition
    • 2013
      • Visualizing and Understanding Convolutional Networks
      • Learning Factored Representations in a Deep Mixture of Experts
    • 2014
      • Generative Adversarial Networks
    • 2015
      • Very Deep Convolutional Networks for Large-Scale Image Recognition
      • Going Deeper with Convolutions
      • FaceNet: a Unified Embedding for Face Recognition and Clustering
      • Distilling the Knowledge in a Neural Network
      • Deep Unsupervised Learning Using Nonequilibrium Thermodynamics
    • 2016
      • Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
      • Rethinking the Inception Architecture for Computer Vision
      • Deep Residual Learning for Image Recognition
      • Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
      • You Only Look Once: Unified, Real-Time Object Detection
    • 2017
      • Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
      • Photo-Realistic Single Image Super-Resolution Using a GAN
      • Understanding Intermediate Layers Using Linear Classifier Probes
      • Image-to-Image Translation with Conditional Adversarial Networks
      • Improved Image Captioning Via Policy Gradient Optimization of SPIDEr
    • 2018
      • From Recognition to Cognition: Visual Commonsense Reasoning
      • Focal Loss for Dense Object Detection
      • Relational Inductive Biases, Deep Learning, and Graph Networks
      • Squeeze-and-Excitation Networks
      • When Does Label Smoothing Help?
      • Unsupervised Feature Learning Via Non-Parametric Instance Discrimination
    • 2019
      • Objects As Points
      • RandAugment: Practical Automated Data Augmentation with a Reduced Search Space
      • Semantic Image Synthesis with Spatially-Adaptive Normalization
      • Generative Modeling by Estimating Gradients of the Data Distribution
    • 2020
      • Denoising Diffusion Probabilistic Models
      • Designing Network Design Spaces
      • Training Data-efficient Image Transformers & Distillation Through Attention
      • NeRF: Representing Scenes As Neural Radiance Fields for View Synthesis
      • Bootstrap Your Own Latent: a New Approach to Self-supervised Learning
      • A Simple Framework for Contrastive Learning of Visual Representations
      • Conditional Negative Sampling for Contrastive Learning of Visual Representations
      • Momentum Contrast for Unsupervised Visual Representation Learning
      • Generative Pretraining from Pixels
      • Random Erasing Data Augmentation
    • 2021
      • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
      • RepVGG: Making VGG-style ConvNets Great Again
      • ArcFace: Additive Angular Margin Loss for Deep Face Recognition
      • Do Vision Transformers See Like Convolutional Neural Networks?
      • BEiT: BERT Pre-Training of Image Transformers
      • Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows
      • CvT: Introducing Convolutions to Vision Transformers
      • An Empirical Study of Training Self-Supervised Vision Transformers
      • Diffusion Models Beat GANs on Image Synthesis
      • GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
      • Multiscale Vision Transformers
      • Score-Based Generative Modeling Through Stochastic Differential Equations
      • Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
      • Scaling Vision with Sparse Mixture of Experts
      • MLP-Mixer: an All-MLP Architecture for Vision
    • 2022
      • A ConvNet for the 2020s
      • Natural Language Descriptions of Deep Visual Features
      • Vision Models are More Robust and Fair When Pretrained on Uncurated Images Without Supervision
      • Block-NeRF: Scalable Large Scene Neural View Synthesis
      • VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
      • Masked Autoencoders are Scalable Vision Learners
      • The Effects of Regularization and Data Augmentation are Class Dependent
      • Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
      • Pix2seq: a Language Modeling Framework for Object Detection
      • An Improved One Millisecond Mobile Backbone
      • Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
      • Swin Transformer V2: Scaling up Capacity and Resolution
      • Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
      • Sequencer: Deep LSTM for Image Classification
      • High-Resolution Image Synthesis with Latent Diffusion Models
      • Make-A-Video: Text-to-Video Generation Without Text-Video Data
      • Denoising Diffusion Implicit Models
      • CSWin Transformer: a General Vision Transformer Backbone with Cross-Shaped Windows
      • MViTv2: Improved Multiscale Vision Transformers for Classification and Detection
      • IBOT: Image BERT Pre-training with Online Tokenizer
      • Imagen Video: High Definition Video Generation with Diffusion Models
    • 2023
      • Hiera: a Hierarchical Vision Transformer Without the Bells-and-Whistles
      • Tree-Ring Watermarks: Fingerprints for Diffusion Images That are Invisible and Robust
      • From Sparse to Soft Mixtures of Experts
      • Estimating Example Difficulty Using Variance of Gradients
      • EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
      • Initializing Models with Larger Ones
      • Rethinking FID: Towards a Better Evaluation Metric for Image Generation
      • Patch N’ Pack: NaViT, a Vision Transformer for Any Aspect Ratio and Resolution
  • NLP
    • 1997
      • Long Short-Term Memory
    • 2003
      • A Neural Probabilistic Language Model
    • 2004
      • ROUGE: a Package for Automatic Evaluation of Summaries
    • 2005
      • METEOR: an Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments
    • 2010
      • Recurrent Neural Network Based Language Model
    • 2011
      • Generating Text with Recurrent Neural Networks
    • 2013
      • Efficient Estimation of Word Representations in Vector Space
      • Distributed Representations of Words and Phrases and Their Compositionality
    • 2014
      • On the Properties of Neural Machine Translation: Encoder–Decoder Approaches
      • GloVe: Global Vectors for Word Representation
      • Sequence to Sequence Learning with Neural Networks
      • Learning Phrase Representations Using RNN Encoder–Decoder for Statistical Machine Translation
    • 2015
      • Neural Machine Translation by Jointly Learning to Align and Translate
      • Effective Approaches to Attention-based Neural Machine Translation
      • Skip-Thought Vectors
    • 2016
      • Google’s Neural Machine Translation System: Bridging the Gap Between Human and Machine Translation
      • Neural Machine Translation of Rare Words with Subword Units
      • HyperNetworks
    • 2017
      • Attention is All You Need
      • Outrageously Large Neural Networks: the Sparsely-Gated Mixture-of-Experts Layer
      • Using the Output Embedding to Improve Language Models
      • Enriching Word Vectors with Subword Information
    • 2018
      • Deep Contextualized Word Representations
      • Improving Language Understanding by Generative Pre-Training
      • SentencePiece: a Simple and Language Independent Subword Tokenizer and Detokenizer for Neural Text Processing
      • Self-Attention with Relative Position Representations
      • Blockwise Parallel Decoding for Deep Autoregressive Models
      • Universal Language Model Fine-tuning for Text Classification
      • Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
      • MS MARCO: a Human Generated MAchine Reading COmprehension Dataset
    • 2019
      • BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
      • RoBERTa: a Robustly Optimized BERT Pretraining Approach
      • BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
      • DistilBERT, a Distilled Version of BERT: Smaller, Faster, Cheaper and Lighter
      • Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
      • XLNet: Generalized Autoregressive Pretraining for Language Understanding
      • Adaptive Input Representations for Neural Language Modeling
      • Attention Interpretability Across NLP Tasks
      • Grad-CAM: Visual Explanations from Deep Networks Via Gradient-based Localization
      • Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
      • GLUE: a Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
      • Parameter-Efficient Transfer Learning for NLP
      • Cross-lingual Language Model Pretraining
      • MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance
      • Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data
      • Latent Retrieval for Weakly Supervised Open Domain Question Answering
      • Multi-Stage Document Ranking with BERT
      • Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts
      • Synthetic QA Corpora Generation with Roundtrip Consistency
      • Towards VQA Models That Can Read
    • 2020
      • Language Models are Few-Shot Learners
      • Longformer: the Long-Document Transformer
      • Big Bird: Transformers for Longer Sequences
      • Beyond Accuracy: Behavioral Testing of NLP Models with CheckList
      • The Curious Case of Neural Text Degeneration
      • ELECTRA: Pre-training Text Encoders As Discriminators Rather Than Generators
      • TinyBERT: Distilling BERT for Natural Language Understanding
      • MPNet: Masked and Permuted Pre-training for Language Understanding
      • Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
      • Scaling Laws for Neural Language Models
      • Unsupervised Cross-lingual Representation Learning at Scale
      • SpanBERT: Improving Pre-training by Representing and Predicting Spans
      • Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning
      • Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
      • Document Ranking with a Pretrained Sequence-to-Sequence Model
      • ColBERT: Efficient and Effective Passage Search Via Contextualized Late Interaction Over BERT
      • REALM: Retrieval-Augmented Language Model Pre-Training
      • Linformer: Self-Attention with Linear Complexity
      • BLEURT: Learning Robust Metrics for Text Generation
      • Query-Key Normalization for Transformers
    • 2021
      • Towards a Unified View of Parameter-Efficient Transfer Learning
      • BinaryBERT: Pushing the Limit of BERT Quantization
      • Towards Zero-Label Language Learning
      • Improving Language Models by Retrieving from Trillions of Tokens
      • WebGPT: Browser-assisted Question-answering with Human Feedback
      • The Power of Scale for Parameter-Efficient Prompt Tuning
      • Prefix-Tuning: Optimizing Continuous Prompts for Generation
      • LoRA: Low-Rank Adaptation of Large Language Models
      • Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm
      • Muppet: Massive Multi-task Representations with Pre-Finetuning
      • Synthesizer: Rethinking Self-Attention in Transformer Models
      • CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation
      • Extracting Training Data from Large Language Models
      • Large Dual Encoders are Generalizable Retrievers
      • Text Generation by Learning from Demonstrations
      • Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering
      • A General Language Assistant As a Laboratory for Alignment
    • 2022
      • Formal Mathematics Statement Curriculum Learning
      • Survey of Hallucination in Natural Language Generation
      • Transformer Quality in Linear Time
      • Chain of Thought Prompting Elicits Reasoning in Large Language Models
      • PaLM: Scaling Language Modeling with Pathways
      • Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity
      • Beyond the Imitation Game: Quantifying and Extrapolating the Capabilities of Language Models
      • Training Compute-Optimal Large Language Models
      • Large Language Models Still Can’t Plan (A Benchmark for LLMs on Planning and Reasoning about Change)
      • OPT: Open Pre-trained Transformer Language Models
      • Diffusion-LM Improves Controllable Text Generation
      • DeepPERF: a Deep Learning-Based Approach for Improving Software Performance
      • No Language Left Behind: Scaling Human-Centered Machine Translation
      • Efficient Few-Shot Learning Without Prompts
      • Large Language Models are Different
      • Solving Quantitative Reasoning Problems with Language Models
      • AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning
      • Why Can GPT Learn In-Context? Language Models Secretly Perform Gradient Descent As Meta-Optimizers
      • Finetuned Language Models are Zero-shot Learners
      • Learning to Summarize from Human Feedback
      • Training Language Models to Follow Instructions with Human Feedback
      • Constitutional AI: Harmlessness from AI Feedback
      • RoFormer: Enhanced Transformer with Rotary Position Embedding
      • Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation
      • Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
      • Locating and Editing Factual Associations in GPT
      • Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers
      • Holistic Evaluation of Language Models
      • SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization
      • InCoder: a Generative Model for Code Infilling and Synthesis
      • Large Language Models are Zero-Shot Reasoners
      • An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks
      • Unsupervised Dense Information Retrieval with Contrastive Learning
      • Implicit Relation Linking for Question Answering Over Knowledge Graph
      • Galactica: a Large Language Model for Science
      • MuRAG: Multimodal Retrieval-Augmented Generator
      • Distilling Knowledge from Reader to Retriever for Question Answering
      • Learn to Explain: Multimodal Reasoning Via Thought Chains for Science Question Answering
      • BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
      • Recurrent Memory Transformer
    • 2023
      • ReAct: Synergizing Reasoning and Acting in Language Models
      • LLaMA: Open and Efficient Foundation Language Models
      • Alpaca: a Strong, Replicable Instruction-Following Model
      • Transformer Models: an Introduction and Catalog
      • Learning to Compress Prompts with Gist Tokens
      • LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
      • LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
      • LIMA: Less is More for Alignment
      • Language is Not All You Need: Aligning Perception with Language Models
      • QLoRA: Efficient Finetuning of Quantized LLMs
      • Direct Preference Optimization: Your Language Model is Secretly a Reward Model
      • Deduplicating Training Data Makes Language Models Better
      • Llama 2: Open Foundation and Fine-Tuned Chat Models
      • Retentive Network: a Successor to Transformer for Large Language Models
      • The Case for 4-bit Precision: K-bit Inference Scaling Laws
      • DeBERTa: Decoding-enhanced BERT with Disentangled Attention
      • UL2: Unifying Language Learning Paradigms
      • Graph of Thoughts: Solving Elaborate Problems with Large Language Models
      • Accelerating Large Language Model Decoding with Speculative Sampling
      • Pretraining Language Models with Human Preferences
      • Large Language Models As Optimizers
      • G-Eval: NLG Evaluation Using GPT-4 with Better Human Alignment
      • Chain-of-Verification Reduces Hallucination in Large Language Models
      • LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
      • Mass-Editing Memory in a Transformer
      • MTEB: Massive Text Embedding Benchmark
      • Language Modeling is Compression
      • SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
      • Zephyr: Direct Distillation of LM Alignment
        • Intuitions
        • Weights’s Alignment Handbook
      • Evaluating Large Language Models: a Comprehensive Survey
      • Tamil-LLaMA: a New Tamil Language Model Based on LLaMA 2
      • Think Before You Speak: Training Language Models with Pause Tokens
      • YaRN: Efficient Context Window Extension of Large Language Models
      • StarCoder: May the Source be with You!
      • Let’s Verify Step by Step
      • Scalable Extraction of Training Data from (Production) Language Models
      • Gemini: a Family of Highly Capable Multimodal Models
      • Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
      • Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
      • Human-Centered Loss Functions (HALOs)
      • Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs Through a Global Scale Prompt Hacking Competition
      • Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs
      • Tuning Language Models by Proxy
      • Group Preference Optimization: Few-shot Alignment of Large Language Models
      • Large Language Models are Neurosymbolic Reasoners
      • LM-Infinite: Simple On-The-Fly Length Generalization for Large Language Models
      • LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
      • Large Language Models are Null-Shot Learners
      • Knowledge Fusion of Large Language Models
      • MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models
      • ChatQA: Building GPT-4 Level Conversational QA Models
      • Parameter-efficient Tuning for Large Language Model Without Calculating Its Gradients
      • Mathematical Discoveries from Program Search with Large Language Models
      • Gaussian Error Linear Units (GELUs)
      • BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining
      • AutoGen: Enabling Next-Gen LLM Applications Via Multi-Agent Conversation
      • Towards Expert-Level Medical Question Answering with Large Language Models
      • Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs
      • Least-to-Most Prompting Enables Complex Reasoning in Large Language Models
      • BitNet: Scaling 1-bit Transformers for Large Language Models
    • 2024
      • Relying on the Unreliable: the Impact of Language Models’ Reluctance to Express Uncertainty
      • Matryoshka Representation Learning
      • Self-Refine: Iterative Refinement with Self-Feedback
      • The Claude 3 Model Family: Opus, Sonnet, Haiku
      • ORPO: Monolithic Preference Optimization Without Reference Model
      • Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
      • Stealing Part of a Production Language Model
      • OneBit: Towards Extremely Low-bit Large Language Models
      • The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
      • Multilingual E5 Text Embeddings: a Technical Report
      • MambaByte: Token-free Selective State Space Model
      • How Faithful are RAG Models? Quantifying the Tug-of-war Between RAG and LLMs’ Internal Prior
      • Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models Through Question Complexity
      • Many-Shot In-Context Learning
      • Gemma 2: Improving Open Language Models at a Practical Size
      • The Llama 3 Herd of Models
      • MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
  • Speech
    • 2006
      • Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks
    • 2010
      • Front-end Factor Analysis for Speaker Verification
    • 2012
      • Sequence Transduction with Recurrent Neural Networks
    • 2013
      • Hybrid Speech Recognition with Deep Bidirectional LSTM
    • 2014
      • Towards End-To-End Speech Recognition with Recurrent Neural Networks
      • Deep Neural Networks for Small Footprint Text-dependent Speaker Verification
    • 2015
      • Listen, Attend and Spell
    • 2017
      • CNN Architectures for Large-Scale Audio Classification
    • 2018
      • X-Vectors: Robust DNN Embeddings for Speaker Recognition
      • WaveGlow: a Flow-based Generative Network for Speech Synthesis
      • Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
    • 2019
      • Wav2vec: Unsupervised Pre-training for Speech Recognition
      • SpecAugment: a Simple Data Augmentation Method for Automatic Speech Recognition
      • Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition
      • Fréchet Audio Distance: a Metric for Evaluating Music Enhancement Algorithms
    • 2020
      • Conformer: Convolution-augmented Transformer for Speech Recognition
      • Wav2vec 2.0: a Framework for Self-Supervised Learning of Speech Representations
      • HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
      • GAN-based Data Generation for Speech Emotion Recognition
      • Generalized End-to-end Loss for Speaker Verification
    • 2021
      • Generative Spoken Language Modeling from Raw Audio
      • Text-Free Prosody-Aware Generative Spoken Language Modeling
      • Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
      • WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
      • Recent Advances in End-to-End Automatic Speech Recognition
      • W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training
      • SUPERB: Speech Processing Universal PERformance Benchmark
    • 2022
      • Direct Speech-to-speech Translation with Discrete Units
      • Textless Speech Emotion Conversion Using Discrete and Decomposed Representations
      • Generative Spoken Dialogue Language Modeling
      • Textless-lib: a Library for Textless Spoken Language Processing
      • Self-Supervised Speech Representation Learning: a Review
      • Masked Autoencoders That Listen
      • Robust Speech Recognition Via Large-Scale Weak Supervision
      • AudioGen: Textually Guided Audio Generation
      • AudioLM: a Language Modeling Approach to Audio Generation
      • SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing
      • Scaling Speech Technology to 1,000+ Languages
      • Distil-Whisper: Robust Knowledge Distillation Via Large-Scale Pseudo Labelling
      • Matcha-TTS: a Fast TTS Architecture with Conditional Flow Matching
      • Audiobox: Unified Audio Generation with Natural Language Prompts
  • Multimodal
    • 2015
      • CIDEr: Consensus-based Image Description Evaluation
    • 2016
      • “Why Should I Trust You?” Explaining the Predictions of Any Classifier
      • SPICE: Semantic Propositional Image Caption Evaluation
    • 2017
      • A Unified Approach to Interpreting Model Predictions
      • Mixup: Beyond Empirical Risk Minimization
      • Multimodal Machine Learning: a Survey and Taxonomy
    • 2019
      • Representation Learning with Contrastive Predictive Coding
    • 2020
      • Modality Dropout for Improved Performance-driven Talking Faces
      • Augmentation Adversarial Training for Self-supervised Speaker Recognition
      • BERTScore: Evaluating Text Generation with BERT
    • 2021
      • Comparing Data Augmentation and Annotation Standardization to Improve End-to-end Spoken Language Understanding Models
      • Learning Transferable Visual Models from Natural Language Supervision
      • Zero-Shot Text-to-Image Generation
      • ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
      • MLIM: Vision-and-language Model Pre-training with Masked Language and Image Modeling
      • MURAL: Multimodal, Multi-task Retrieval Across Languages
      • Perceiver: General Perception with Iterative Attention
      • Multimodal Few-Shot Learning with Frozen Language Models
      • On the Opportunities and Risks of Foundation Models
      • CLIPScore: a Reference-free Evaluation Metric for Image Captioning
      • VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding
    • 2022
      • DeepNet: Scaling Transformers to 1,000 Layers
      • Data2vec: a General Framework for Self-supervised Learning in Speech, Vision and Language
      • Hierarchical Text-Conditional Image Generation with CLIP Latents
      • AutoDistill: an End-to-End Framework to Explore and Distill Hardware-Efficient Language Models
      • A Generalist Agent
      • Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors
      • I-Code: an Integrative and Composable Multimodal Learning Framework
      • VL-BEIT: Generative Vision-Language Pretraining
      • FLAVA: a Foundational Language and Vision Alignment Model
      • Flamingo: a Visual Language Model for Few-Shot Learning
      • Stable and Latent Diffusion Model
      • DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
      • UniT: Multimodal Multitask Learning with a Unified Transform
      • Perceiver IO: a General Architecture for Structured Inputs & Outputs
      • Foundation Transformers
      • Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language
      • Imagic: Text-Based Real Image Editing with Diffusion Models
      • EDICT: Exact Diffusion Inversion Via Coupled Transformations
      • CLAP: Learning Audio Concepts from Natural Language Supervision
      • An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA
      • OCR-free Document Understanding Transformer
      • PubTables-1M: Towards Comprehensive Table Extraction from Unstructured Documents
      • CoCa: Contrastive Captioners are Image-Text Foundation Models
      • BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
      • VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
      • Grounded Language-Image Pre-training (GLIP)
      • LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
    • 2023
      • Pix2Video: Video Editing Using Image Diffusion
      • TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs
      • HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends in HuggingFace
      • Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation
      • ImageBind: One Embedding Space to Bind Them All
      • BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
      • InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
      • AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation
      • Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models
      • MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action
      • PaLM-E: an Embodied Multimodal Language Model
      • MIMIC-IT: Multi-Modal In-Context Instruction Tuning
      • Visual Instruction Tuning
      • Multimodal Chain-of-Thought Reasoning in Language Models
      • Dreamix: Video Diffusion Models are General Video Editors
      • Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
      • OpenFlamingo: an Open-Source Framework for Training Large Autoregressive Vision-Language Models
      • Med-Flamingo: a Multimodal Medical Few-shot Learner
      • Towards Generalist Biomedical AI
      • PaLI: a Jointly-Scaled Multilingual Language-Image Model
      • Nougat: Neural Optical Understanding for Academic Documents
      • Text-Conditional Contextualized Avatars for Zero-Shot Personalization
      • Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation
      • AnyMAL: an Efficient and Scalable Any-Modality Augmented Language Model
      • Phenaki: Variable Length Video Generation from Open Domain Textual Description
      • Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators
      • SeamlessM4T – Massively Multilingual & Multimodal Machine Translation
      • PaLI-X: on Scaling up a Multilingual Vision and Language Model
      • The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)
      • Sparks of Artificial General Intelligence: Early Experiments with GPT-4
      • MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
      • MiniGPT-v2: Large Language Model As a Unified Interface for Vision-Language Multi-task Learning
      • SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
      • Diffusion Model Alignment Using Direct Preference Optimization
      • Seamless: Multilingual Expressive and Streaming Speech Translation
      • VideoPoet: a Large Language Model for Zero-Shot Video Generation
      • LLaMA-VID: an Image is Worth 2 Tokens in Large Language Models
      • FERRET: Refer and Ground Anything Anywhere at Any Granularity
      • StarVector: Generating Scalable Vector Graphics Code from Images
      • KOSMOS-2: Grounding Multimodal Large Language Models to the World
      • Generative Multimodal Models are In-Context Learners
      • Alpha-CLIP: a CLIP Model Focusing on Wherever You Want
    • 2024
      • MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
      • Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language
      • Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference
  • Core ML
    • 1991
      • What Every Computer Scientist Should Know about Floating-Point Arithmetic
    • 1997
      • Bidirectional Recurrent Neural Networks
    • 2001
      • Obtaining Calibrated Probability Estimates from Decision Trees and Naive Bayesian Classifiers
    • 2002
      • Transforming Classifier Scores Into Accurate Multiclass Probability Estimates
      • Dimensionality Reduction by Learning an Invariant Mapping
    • 2006
      • Reducing the Dimensionality of Data with Neural Networks
    • 2007
      • What Every Programmer Should Know about Memory
    • 2008
      • ADASYN: Adaptive Synthetic Sampling Approach for Imbalanced Learning
    • 2009
      • Large-scale Deep Unsupervised Learning Using Graphics Processors
      • Practical Guide to Controlled Experiments on the Web: Listen to Your Customers Not to the HiPPO
      • Curriculum Learning
    • 2011
      • SMOTE: Synthetic Minority Over-sampling Technique
    • 2012
      • Acoustic Modeling Using Deep Belief Networks
      • Improving Neural Networks by Preventing Co-adaptation of Feature Detectors
      • Trustworthy Online Controlled Experiments: Five Puzzling Outcomes Explained
    • 2014
      • Dropout: a Simple Way to Prevent Neural Networks from Overfitting
      • Intriguing Properties of Neural Networks
    • 2015
      • ADAM: a Method for Stochastic Optimization
      • Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
    • 2016
      • XGBoost: a Scalable Tree Boosting System
      • Layer Normalization
      • Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs
    • 2017
      • Axiomatic Attribution for Deep Networks
      • Decoupled Weight Decay Regularization
      • On Calibration of Modern Neural Networks
      • Beta Calibration: a Well-founded and Easily Implemented Improvement on Logistic Calibration for Binary Classifiers
      • Understanding Black-box Predictions Via Influence Functions
      • Mixed Precision Training
      • StarSpace: Embed All the Things!
    • 2018
      • Model Cards for Model Reporting
      • Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
      • Representer Point Selection for Explaining Deep Neural Networks
      • Mixed Precision Training
    • 2019
      • Fast Transformer Decoding: One Write-Head is All You Need
      • Similarity of Neural Network Representations Revisited
      • Toward a Better Trade-off Between Performance and Fairness with Kernel-based Distribution Matching
      • Root Mean Square Layer Normalization
      • Generating Long Sequences with Sparse Transformers
      • Understanding and Improving Layer Normalization
    • 2020
      • Estimating Training Data Influence by Tracing Gradient Descent
      • LEEP - Log Expected Empirical Prediction
      • OTDD - Optimal Transport Dataset Distance
      • Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection
      • GLU Variants Improve Transformer
      • ZeRO: Memory Optimizations Toward Training Trillion Parameter Models
    • 2021
      • Efficient Deep Learning: a Survey on Making Deep Learning Models Smaller, Faster, and Better
      • Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth
      • Using AntiPatterns to Avoid MLOps Mistakes
      • Self-attention Does Not Need O(n2)O(n2) Memory
      • Sharpness-Aware Minimization for Efficiently Improving Generalization
      • ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning
      • Efficiently Modeling Long Sequences with Structured State Spaces
    • 2022
      • Pathways: Asynchronous Distributed Dataflow for ML
      • PolyLoss: a Polynomial Expansion Perspective of Classification Loss Functions
      • Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models
      • Federated Learning with Buffered Asynchronous Aggregation
      • Applied Federated Learning: Architectural Design for Robust and Efficient Learning in Privacy Aware Settings
      • Operationalizing Machine Learning: an Interview Study
      • A/B Testing Intuition Busters
      • Effect of Scale on Catastrophic Forgetting in Neural Networks
      • Fine-Tuning Can Distort Pretrained Features and Underperform Out-of-Distribution
      • FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
      • Robust Fine-tuning of Zero-shot Models
      • Efficiently Scaling Transformer Inference
    • 2023
      • FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
      • Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
      • Dataless Knowledge Fusion by Merging Weights of Language Models
      • Weak-to-Strong Generalization: Eliciting Strong Capabilities with Weak Supervision
      • Mamba: Linear-Time Sequence Modeling with Selective State Spaces
      • Kolmogorov–Arnold Networks (KANs): an Alternative to Multi-Layer Perceptrons for Enhanced Interpretability and Accuracy
  • RecSys
    • 2008
      • Calibrated Recommendations
    • 2009
      • The Wisdom of the Few: a Collaborative Filtering Approach Based on Expert Opinions from the Web
    • 2010
      • Factorization Machines
    • 2011
      • Unbiased Offline Evaluation of Contextual-bandit-based News Article Recommendation Algorithms
    • 2015
      • Collaborative Deep Learning for Recommender Systems
    • 2016
      • Wide & Deep Learning for Recommender Systems
      • Deep Neural Networks for YouTube Recommendations
      • Product-based Neural Networks for User Response Prediction
    • 2017
      • Neural Collaborative Filtering
      • Deep & Cross Network for Ad Click Predictions
      • DeepFM: a Factorization-Machine Based Neural Network for CTR Prediction
    • 2018
      • Deep Interest Network for Click-Through Rate Prediction
    • 2019
      • Behavior Sequence Transformer for E-commerce Recommendation in Alibaba
      • BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
    • 2020
    • DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems
      • Neural Collaborative Filtering vs. Matrix Factorization Revisited
    • 2022
      • PinnerFormer: Sequence Modeling for User Representation at Pinterest
  • RL
    • 2015
      • Trust Region Policy Optimization
    • 2016
      • Mastering the Game of Go with Deep Neural Networks & Tree Search
    • 2017
      • Proximal Policy Optimization Algorithms
      • Evolution Strategies As a Scalable Alternative to Reinforcement Learning
      • Playing FPS Games with Deep Reinforcement Learning
      • Mastering the Game of Go Without Human Knowledge
      • Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
    • 2019
      • AlphaStar: Grandmaster Level in StarCraft II Using Multi-agent Reinforcement Learning
    • 2020
      • Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
    • 2021
      • Highly Accurate Protein Structure Prediction with AlphaFold
    • 2023
      • Faster Sorting Algorithms Discovered Using Deep Reinforcement Learning
  • Graph ML
    • 2000
      • Nonlinear Dimensionality Reduction by Locally Linear Embedding
      • A Global Geometric Framework for Nonlinear Dimensionality Reduction
    • 2001
      • Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering
    • 2014
      • DeepWalk: Online Learning of Social Representations
    • 2016
      • Asymmetric Transitivity Preserving Graph Embedding
      • Structural Deep Network Embedding
      • Node2vec: Scalable Feature Learning for Networks
    • 2017
      • Inductive Representation Learning on Large Graphs
      • Semi-Supervised Classification with Graph Convolutional Networks
    • 2018
      • Graph Attention Networks
    • 2019
      • Exploiting Edge Features for Graph Neural Networks
• Selected Papers / Good-to-know
  • Computer Vision
    • 2015
      • Learning Deep Features for Discriminative Localization
    • 2016
      • Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
    • 2017
      • Quo Vadis, Action Recognition? a New Model and the Kinetics Dataset
      • Densely Connected Convolutional Networks
    • 2018
      • Neural Discrete Representation Learning
    • 2019
      • EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
    • 2020
      • Taming Transformers for High-Resolution Image Synthesis
      • Self-training with Noisy Student Improves ImageNet Classification
      • Big Transfer (BiT): General Visual Representation Learning
      • Multi-modal Dense Video Captioning
      • Efficient Saliency Maps for Explainable AI
    • 2021
      • Finetuning Pretrained Transformers Into RNNs
      • VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
      • Self-supervised Learning for Fast and Scalable Time Series Hyper-parameter Tuning.
      • Accelerating SLIDE Deep Learning on Modern CPUs: Vectorization, Quantizations, Memory Optimizations, and More
      • Emerging Properties in Self-Supervised Vision Transformers
      • Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples
      • Enhancing Photorealism Enhancement
      • FNet: Mixing Tokens with Fourier Transforms
      • Are Convolutional Neural Networks or Transformers More Like Human Vision?
      • RegNet: Self-Regulated Network for Image Classification
      • Lossy Compression for Lossless Prediction
    • 2022
      • YOLOv6: a Single-Stage Object Detection Framework for Industrial Applications
    • 2023
      • Your Diffusion Model is Secretly a Zero-Shot Classifier
      • DINOv2: Learning Robust Visual Features Without Supervision
      • Consistency Models
      • Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
      • ZipIt! Merging Models from Different Tasks Without Training
      • Self-Consuming Generative Models Go MAD
      • Substance or Style: What Does Your Image Embedding Know?
      • Scaling Vision Transformers to 22 Billion Parameters
      • CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
      • On the Impact of Knowledge Distillation for Model Interpretability
      • Replacing Softmax with ReLU in Vision Transformers
      • Learning Vision from Models Rivals Learning Vision from Data
      • TUTEL: Adaptive Mixture-of-Experts at Scale
    • 2024
      • Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
      • Scalable Diffusion Models with State Space Backbone
        • Towards Evaluating the Robustness of Visual State Space Models
  • NLP
    • 2008
      • ROUGE-C: a Fully Automated Evaluation Method for Multi-document Summarization
    • 2015
      • Effective Approaches to Attention-based Neural Machine Translation
    • 2018
      • Generating Wikipedia by Summarizing Long Sequences
    • 2019
      • Sentence-BERT: Sentence Embeddings Using Siamese BERT-Networks
      • Diversity and Depth in Per-Example Routing Models
      • Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
    • 2020
      • Efficient Transformers: a Survey
      • Towards a Human-like Open-Domain Chatbot
      • MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices
      • Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning
      • Movement Pruning: Adaptive Sparsity by Fine-Tuning
      • Dense Passage Retrieval for Open-domain Question Answering
      • Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
      • Unsupervised Commonsense Question Answering with Self-Talk
      • Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
    • 2021
      • Pretrained Transformers As Universal Computation Engines
      • SimCSE: Simple Contrastive Learning of Sentence Embeddings
      • DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations
      • Transformer Feed-Forward Layers are Key-Value Memories
      • Measuring Massive Multitask Language Understanding
    • 2022
      • A Causal Lens for Controllable Text Generation
      • SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples
      • LaMDA: Language Models for Dialog Applications
      • Causal Inference Principles for Reasoning about Commonsense Causality
      • RescoreBERT: Discriminative Speech Recognition Rescoring with BERT
      • Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, a Large-Scale Generative Language Model
      • Extreme Compression for Pre-trained Transformers Made Simple and Efficient
      • Memorizing Transformers
      • Ask Me Anything: a Simple Strategy for Prompting Language Models
      • Large Language Models Can Self-Improve
      • ∞∞-former: Infinite Memory Transformer
      • Multitask Prompted Training Enables Zero-Shot Task Generalization
      • Large Language Models Encode Clinical Knowledge
      • GLaM: Efficient Scaling of Language Models with Mixture-of-Experts
      • Automatic Chain of Thought Prompting in Large Language Models
      • Less is More: Parameter-Free Text Classification with Gzip
      • A Length-Extrapolatable Transformer
      • Efficient Training of Language Models to Fill in the Middle
      • Language Models of Code are Few-Shot Commonsense Learners
      • A Systematic Investigation of Commonsense Knowledge in Large Language Models
      • MERLOT Reserve: Neural Script Knowledge Through Vision and Language and Sound
      • MegaBlocks: Efficient Sparse Training with Mixture-of-Experts
      • Ask Me Anything: a Simple Strategy for Prompting Language Models
      • STaR: Self-Taught Reasoner: Bootstrapping Reasoning with Reasoning
    • 2023
      • Challenges and Applications of Large Language Models
      • LLM-Adapters: an Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models
      • Accelerating Large Language Model Decoding with Speculative Sampling
      • GPT Detectors are Biased Against Non-native English Writers
      • GPT4All: Training an Assistant-style Chatbot with Large Scale Data Distillation from GPT-3.5-Turbo
      • SELF-INSTRUCT: Aligning Language Model with Self Generated Instructions
      • Efficient Methods for Natural Language Processing: a Survey
      • Better Language Models of Code Through Self-Improvement
      • Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes
      • Active Retrieval Augmented Generation
      • FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
      • Exploring In-Context Learning Capabilities of Foundation Models for Generating Knowledge Graphs from Text
      • How Language Model Hallucinations Can Snowball
      • Unlimiformer: Long-Range Transformers with Unlimited Length Input
      • Gorilla: Large Language Model Connected with Massive APIs
      • SPRING: GPT-4 Out-performs RL Algorithms by Studying Papers and Reasoning
      • Deliberate Then Generate: Enhanced Prompting Framework for Text Generation
      • Enabling Large Language Models to Generate Text with Citations
      • The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only
      • Fine-Tuning Language Models with Just Forward Passes
      • Self-Consistency Improves Chain of Thought Reasoning in Language Models
      • Tree of Thoughts: Deliberate Problem Solving with Large Language Models
      • Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Large Language Models
      • LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
      • RWKV: Reinventing RNNs for the Transformer Era
      • Knowledge Distillation of Large Language Models
      • Unifying Large Language Models and Knowledge Graphs: a Roadmap
      • Orca: Progressive Learning from Complex Explanation Traces of GPT-4
      • Textbooks are All You Need
      • Extending Context Window of Large Language Models Via Positional Interpolation
      • Deep Language Networks: Joint Prompt Training of Stacked LLMs Using Variational Inference
      • A Simple and Effective Pruning Approach for Large Language Models
      • To Repeat or Not to Repeat: Insights from Scaling LLM Under Token-Crisis
      • ART: Automatic Multi-step Reasoning and Tool-use for Large Language Models
      • Lost in the Middle: How Language Models Use Long Contexts
      • Improving Retrieval-Augmented Large Language Models Via Data Importance Learning
      • Scaling Transformer to 1M Tokens and Beyond with RMT
      • Hyena Hierarchy: Towards Larger Convolutional Language Models
      • LongNet: Scaling Transformers to 1,000,000,000 Tokens
      • The Curse of Recursion: Training on Generated Data Makes Models Forget
      • Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Tasks
      • FLASK: Fine-grained Language Model Evaluation Based on Alignment Skill Sets
      • Secrets of RLHF in Large Language Models Part I: PPO
      • WizardLM: Empowering Large Language Models to Follow Complex Instructions
      • Universal and Transferable Adversarial Attacks on Aligned Language Models
      • Scaling TransNormer to 175 Billion Parameters
      • What Learning Algorithm is In-context Learning? Investigations with Linear Models
      • What In-Context Learning “Learns” In-Context: Disentangling Task Recognition and Task Learning
      • PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback
      • Multimodal Neurons in Pretrained Text-Only Transformers
      • ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
      • Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding
      • The Hydra Effect: Emergent Self-repair in Language Model Computations
      • MetaGPT: Meta Programming for Multi-Agent Collaborative Framework
      • XSTest: a Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
      • Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models
      • Jina Embeddings: a Novel Set of High-Performance Sentence Embedding Models
      • SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning
      • Stack More Layers Differently: High-Rank Training Through Low-Rank Updates
      • AlpaGasus: Training a Better Alpaca with Fewer Data
      • How is ChatGPT’s Behavior Changing Over Time?
      • Do Multilingual Language Models Think Better in English?
      • Skill-it! a Data-Driven Skills Framework for Understanding and Training Language Models
      • In-context Autoencoder for Context Compression in a Large Language Model
      • No Train No Gain: Revisiting Efficient Training Algorithms for Transformer-based Language Models
      • Leveraging Implicit Feedback from Deployment Data in Dialogue
      • FacTool: Factuality Detection in Generative AI – a Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios
      • The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants
      • Large Language Models Can be Easily Distracted by Irrelevant Context
      • Fast Inference from Transformers Via Speculative Decoding
      • Textbooks are All You Need II
      • Cognitive Mirage: a Review of Hallucinations in Large Language Models
      • Structured Chain-of-Thought Prompting for Code Generation
      • DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
      • QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
      • Editing Commonsense Knowledge in GPT
      • The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models Via Chain-of-Thought Fine-Tuning
      • FinGPT: Open-Source Financial Large Language Models
      • The Reversal Curse: LLMs Trained on “A is B” Fail to Learn “B is A”
      • Less is More: Task-aware Layer-wise Distillation for Language Model Compression
      • Reinforced Self-Training (ReST) for Language Modeling
      • How Do Large Language Models Capture the Ever-changing World Knowledge? a Review of Recent Advances
      • Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning
      • A Reparameterized Discrete Diffusion Model for Text Generation
      • AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation
      • HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers
      • Likelihood-Based Diffusion Language Models
      • Who’s Harry Potter? Approximate Unlearning in LLMs
      • Mistral 7B
      • Take a Step Back: Evoking Reasoning Via Abstraction in Large Language Models
      • Text Generation with Diffusion Language Models: a Pre-training Approach with Continuous Paragraph Denoise
      • JudgeLM: Fine-tuned Large Language Models are Scalable Judges
      • LLMs As Factual Reasoners: Insights from Existing Benchmarks and Beyond
      • Llemma: an Open Language Model for Mathematics
      • CODEFUSION: a Pre-trained Diffusion Model for Code Generation
      • CodeT5+: Open Code Large Language Models for Code Understanding and Generation
      • Augmenting Language Models with Long-Term Memory
      • ALCUNA: Large Language Models Meet New Knowledge
      • The Perils & Promises of Fact-checking with Large Language Models
      • SLoRA: Federated Parameter Efficient Fine-Tuning of Language Models
      • S-LoRA: Serving Thousands of Concurrent LoRA Adapters
      • ChainPoll: a High Efficacy Method for LLM Hallucination Detection
      • Mixture-of-Experts Meets Instruction Tuning: a Winning Combination for Large Language Models
      • LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion
      • Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
      • FACTSCORE: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
      • Fine-tuning Language Models for Factuality
      • Better Zero-Shot Reasoning with Self-Adaptive Prompting
      • Universal Self-Adaptive Prompting for Zero-shot and Few-shot Learning
      • Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models
      • Thread of Thought: Unraveling Chaotic Contexts
      • Large Language Models Understand and Can be Enhanced by Emotional Stimuli
      • Text Embeddings Reveal (Almost) As Much As Text
      • Influence Scores at Scale for Efficient Language Data Sampling
      • TableLlama: Towards Open Large Generalist Models for Tables
      • NEFTune: Noisy Embeddings Improve Instruction Finetuning
      • Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
      • Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
      • Online Speculative Decoding
      • PaSS: Parallel Speculative Sampling
      • System 2 Attention (is Something You Might Need Too)
      • Aligning Large Language Models Through Synthetic Feedback
      • Contrastive Chain-of-Thought Prompting
      • ChipNeMo: Domain-Adapted LLMs for Chip Design
      • Efficient Streaming Language Models with Attention Sinks
      • Precise Zero-Shot Dense Retrieval Without Relevance Labels
      • Tied-LoRA: Enhancing Parameter Efficiency of LoRA with Weight Tying
      • Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning
      • Chain-of-Knowledge: Grounding Large Language Models Via Dynamic Knowledge Adapting Over Heterogeneous Sources
      • Exponentially Faster Language Modeling
      • Prompt Injection Attack Against LLM-integrated Applications
      • Jailbroken: How Does LLM Safety Training Fail?
      • Orca 2: Teaching Small Language Models How to Reason
      • Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves
      • Pythia: a Suite for Analyzing Large Language Models Across Training and Scaling
      • Starling-7B: Increasing LLM Helpfulness & Harmlessness with RLAIF
      • Large Language Models are Human-Level Prompt Engineers
      • A Survey of Graph Meets Large Language Model: Progress and Future Directions
      • Nash Learning from Human Feedback
      • Retrieval-augmented Multi-modal Chain-of-Thoughts Reasoning for Large Language Models
      • Magicoder: Source Code is All You Need
      • TarGEN: Targeted Data Generation with Large Language Models
      • RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
      • The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback
      • Revisiting Large Language Models As Zero-shot Relation Extractors
      • NexusRaven-V2: Surpassing GPT-4 for Zero-shot Function Calling
      • Instruction-Following Evaluation for Large Language Models
      • Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback
      • A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenges
      • FLEEK: Factual Error Detection and Correction with Evidence Retrieved from External Knowledge
      • Automatic Hallucination Assessment for Aligned Large Language Models Via Transferable Adversarial Attacks
      • OLaLa: Ontology Matching with Large Language Models
      • LLM-Pruner: on the Structural Pruning of Large Language Models
      • SparseGPT: Massive Language Models Can be Accurately Pruned in One-Shot
      • RAGAS: Automated Evaluation of Retrieval Augmented Generation
      • EVER: Mitigating Hallucination in Large Language Models Through Real-Time Verification and Rectification
      • Prometheus: Inducing Fine-Grained Evaluation Capability in Language Models
      • AlphaCode 2
      • MediTron-70B: Scaling Medical Pretraining for Large Language Models
      • Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine
      • Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks
      • X-InstructBLIP: a Framework for Aligning X-Modal Instruction-Aware Representations to LLMs and Emergent Cross-modal Reasoning
      • SwiftSage: a Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
      • Evaluating Large Language Models: a Comprehensive Survey
      • Show Your Work: Scratchpads for Intermediate Computation with Language Models
      • Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks
      • Chain of Code: Reasoning with a Language Model-Augmented Code Emulator
      • When Do Generative Query and Document Expansions Fail? a Comprehensive Study Across Methods Retrievers and Datasets
      • MemGPT: Towards LLMs As Operating Systems
      • The Internal State of an LLM Knows When It’s Lying
      • GPT4All: an Ecosystem of Open Source Compressed Language Models
      • The Falcon Series of Open Language Models
      • Promptbase: Elevating the Power of Foundation Models Through Advanced Prompt Engineering
      • Phi-2: the Surprising Power of Small Language Models
      • QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models
      • PromptBench: a Unified Library for Evaluation of Large Language Models
      • Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking
      • Mathematical Language Models: a Survey
      • A Survey of Large Language Models in Medicine: Principles, Applications, and Challenges
      • Language Model Inversion
      • LLM360: Towards Fully Transparent Open-Source LLMs
      • LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
      • Retrieval-Augmented Generation for Large Language Models: a Survey
      • LLM in a Flash: Efficient Large Language Model Inference with Limited Memory
      • ReST Meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent
      • PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU
      • Adversarial Attacks on GPT-4 Via Simple Random Search
      • An In-depth Look at Gemini’s Language Abilities
      • LoRAMoE: Revolutionizing Mixture of Experts for Maintaining World Knowledge in Language Model Alignment
      • Large Language Models are Better Reasoners with Self-Verification
      • PaperMage: a Unified Toolkit for Processing, Representing, and Manipulating Visually-Rich Scientific Documents
      • Large Language Models on Graphs: a Comprehensive Survey
      • An LLM Compiler for Parallel Function Calling
      • Scaling Down, LiTting Up: Efficient Zero-Shot Listwise Reranking with Seq2seq Encoder–Decoder Models
      • Is ChatGPT Good at Search? Investigating Large Language Models As Re-Ranking Agents
      • NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models Via Complexity Classes
      • Robust Knowledge Extraction from Large Language Models Using Social Choice Theory
      • LongQLoRA: Efficient and Effective Method to Extend Context Length of Large Language Models
      • Editing Models with Task Arithmetic
      • Time is Encoded in the Weights of Finetuned Language Models
      • TinyGPT-V: Efficient Multimodal Large Language Model Via Small Backbones
      • OpenChat: Advancing Open-Source Language Models with Mixed-Quality Data
      • What Makes Good Data for Alignment? a Comprehensive Study of Automatic Data Selection in Instruction Tuning
      • Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
      • MultiInstruct: Improving Multi-Modal Zero-Shot Learning Via Instruction Tuning
      • Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models
      • Dense X Retrieval: What Retrieval Granularity Should We Use?
      • ARES: an Automated Evaluation Framework for Retrieval-Augmented Generation Systems
      • A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models
      • A Survey of Reasoning with Foundation Models
      • GPT-4V(ision) is a Generalist Web Agent, If Grounded
      • Large Language Models for Generative Information Extraction: a Survey
      • EQ-Bench: an Emotional Intelligence Benchmark for Large Language Models
      • Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code
      • TrustLLM: Trustworthiness in Large Language Models
      • Blending is All You Need: Cheaper Better Alternative to Trillion-Parameters LLM
      • Enhancing Zero-Shot Chain-of-Thought Reasoning in Large Language Models Through Logic
      • Airavata: Introducing Hindi Instruction-Tuned LLM
      • Chain-of-Symbol Prompting for Spatial Relationships in Large Language Models
      • Continual Pre-training of Language Models
      • Jina Embeddings: a Novel Set of High-Performance Sentence Embedding Models
      • Simplifying Transformer Blocks
      • Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
      • AnglE-Optimized Text Embeddings
      • SLiC-HF: Sequence Likelihood Calibration with Human Feedback
      • Ghostbuster: Detecting Text Ghostwritten by Large Language Models
      • Monarch Mixer: a Simple Sub-Quadratic GEMM-Based Architecture
      • DistillCSE: Distilled Contrastive Learning for Sentence Embeddings
      • The Unlocking Spell on Base LLMs: Rethinking Alignment Via In-Context Learning
      • GLiNER: Generalist Model for Named Entity Recognition Using Bidirectional Transformer
    • 2024
      • BLIVA: a Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions
      • Building a Llama2-finetuned LLM for Odia Language Utilizing Domain Knowledge Instruction Set
      • Leveraging Large Language Models for NLG Evaluation: a Survey
      • Nomic Embed: Training a Reproducible Long Context Text Embedder
      • Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents
      • Seven Failure Points When Engineering a Retrieval Augmented Generation System
      • SALAD-Bench: a Hierarchical and Comprehensive Safety Benchmark for Large Language Models
      • DoRA: Weight-Decomposed Low-Rank Adaptation
      • ICDPO: Effectively Borrowing Alignment Capability of Others Via In-context Direct Preference Optimization
      • A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
      • SliceGPT: Compress Large Language Models by Deleting Rows and Columns
      • Two-dimensional Matryoshka Sentence Embeddings
      • Benchmarking Hallucination in Large Language Models Based on Unanswerable Math Word Problem
      • IndicVoices: Towards Building an Inclusive Multilingual Speech Dataset for Indian Languages
      • ArtPrompt: ASCII Art-based Jailbreak Attacks Against Aligned LLMs
      • The Calibration Gap Between Model and Human Confidence in Large Language Models
      • Fact-Checking the Output of Large Language Models Via Token-Level Uncertainty Quantification
      • RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
      • The Power of Noise: Redefining Retrieval for RAG Systems
      • DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
      • Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
      • MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries
      • Human Alignment of Large Language Models Through Online Preference Optimisation
      • A General Theoretical Paradigm to Understand Learning from Human Preferences
      • Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
      • What are Tools Anyway? a Survey from the Language Model Perspective
      • AutoDev: Automated AI-Driven Development
      • LLM4Decompile: Decompiling Binary Code with Large Language Models
      • OLMo: Accelerating the Science of Language Models
      • Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research
      • MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
      • RAG Vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculture
      • RAFT: Adapting Language Model to Domain Specific RAG
      • Corrective Retrieval Augmented Generation
      • SaulLM-7B: a Pioneering Large Language Model for Law
      • LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement
      • FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions
      • AIOS: LLM Agent Operating System
      • Lumos: a Modular Open-Source LLM-Based Agent Framework
      • A Comparison of Human, GPT-3.5, and GPT-4 Performance in a University-Level Coding Course
      • SDPO: Don’t Use Your Data All at Once
      • RS-DPO: a Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Models
      • Dataverse: Open-Source ETL (Extract Transform Load) Pipeline for Large Language Models
      • Teaching Large Language Models to Reason with Reinforcement Learning
      • Jamba: a Hybrid Transformer-Mamba Language Model
      • Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge
      • LLM2Vec: Large Language Models are Secretly Powerful Text Encoders
      • HGOT: Hierarchical Graph of Thoughts for Retrieval-Augmented In-Context Learning in Factuality Evaluation
      • ReFT: Representation Finetuning for Language Models
      • Towards Conversational Diagnostic AI
      • Reka Core, Flash, and Edge: a Series of Powerful Multimodal Language Models
      • Phi-3 Technical Report: a Highly Capable Language Model Locally on Your Phone
      • Mixtral of Experts
      • BioMistral: a Collection of Open-Source Pretrained Large Language Models for Medical Domains
      • Gemma: Open Models Based on Gemini Research and Technology
      • SPAFIT: Stratified Progressive Adaptation Fine-tuning for Pre-trained Large Language Models
      • Instruction-tuned Language Models are Better Knowledge Learners
      • Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models
      • Prometheus 2: an Open Source Language Model Specialized in Evaluating Other Language Models
      • Mixture of LoRA Experts
      • Teaching Large Language Models to Self-Debug
      • You Only Cache Once: Decoder-Decoder Architectures for Language Models
      • JetMoE: Reaching Llama2 Performance with 0.1M Dollars
      • LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
      • Better & Faster Large Language Models Via Multi-token Prediction
      • When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards
      • Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models
      • Hallucination of Multimodal Large Language Models: a Survey
      • In-Context Learning with Long-Context Models: an In-Depth Exploration
      • NOLA: Compressing LoRA Using Linear Combination of Random Basis
      • Data Selection for Transfer Unlearning
      • A Primer on the Inner Workings of Transformer-Based Language Models
      • MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
      • Nemotron-4 340B Technical Report
      • RewardBench: Evaluating Reward Models for Language Modeling
      • DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
      • Transferring Knowledge from Large Foundation Models to Small Downstream Models
      • Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models
      • In Search of Needles in a 11M Haystack: Recurrent Memory Finds What LLMs Miss
      • MAGPIE: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
      • MDPO: Conditional Preference Optimization for Multimodal Large Language Models
      • Aligning Large Multimodal Models with Factually Augmented RLHF
      • Statistical Rejection Sampling Improves Preference Optimization
      • Chameleon: Mixed-Modal Early-Fusion Foundation Models
      • MMMU: a Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
      • MMBench: is Your Multi-modal Model an All-around Player?
      • GPQA: a Graduate-Level Google-Proof Q&A Benchmark
      • Sycophancy to Subterfuge: Investigating Reward Tampering in Language Models
      • ReST-MCTS∗∗: LLM Self-Training Via Process Reward Guided Tree Search
      • FLAME: Factuality-Aware Alignment for Large Language Models
      • Is DPO Superior to PPO for LLM Alignment? a Comprehensive Study
      • Improving Multi-step Reasoning for LLMs with Deliberative Planning
      • SAMBA: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
      • RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generation
      • A Careful Examination of Large Language Model Performance on Grade School Arithmetic
      • Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment
      • BPO: Supercharging Online Preference Learning by Adhering to the Proximity of Behavior LLM
      • Instruction Pre-Training: Language Models are Supervised Multitask Learners
      • Improve Mathematical Reasoning in Language Models by Automated Process Supervision
      • Accessing GPT-4 Level Mathematical Olympiad Solutions Via Monte Carlo Tree Self-refine with LLaMa-3 8B: a Technical Report
      • SimPO: Simple Preference Optimization with a Reference-Free Reward
      • Discovering Preference Optimization Algorithms with and for Large Language Models
      • ToRA: a Tool-Integrated Reasoning Agent for Mathematical Problem Solving
      • Scaling LLM Test-Time Compute Optimally Can be More Effective Than Scaling Model Parameters
      • Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
      • Mixture-of-Depths: Dynamically Allocating Compute in Transformer-Based Language Models
      • Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
      • Learn Beyond the Answer: Training Language Models with Reflection for Mathematical Reasoning
      • Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents
      • V-STaR: Training Verifiers for Self-Taught Reasoners
  • Speech
    • 2017
      • On Evaluating and Comparing Conversational Agents
    • 2018
      • Attention-Based Models for Text-Dependent Speaker Verification
      • Efficient Voice Trigger Detection for Low Resource Hardware
    • 2020
      • Automatic Speaker Recognition with Limited Data
      • Speaker Identification for Household Scenarios with Self-attention and Adversarial Training
      • Stacked 1D Convolutional Networks for End-to-end Small Footprint Voice Trigger Detection
      • Optimize What Matters: Training DNN-HMM Keyword Spotting Model Using End Metric
      • MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition
      • HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks
    • 2021
      • Streaming Transformer for Hardware Efficient Voice Trigger Detection and False Trigger Mitigation
      • Joint ASR and Language Identification Using RNN-T: an Efficient Approach to Dynamic Language Switching
      • HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
      • Deep Spoken Keyword Spotting: an Overview
      • BW-EDA-EEND: Streaming End-to-end Neural Speaker Diarization for a Variable Number of Speakers
      • Attentive Contextual Carryover for Multi-turn End-to-end Spoken Language Understanding
      • SmallER: Scaling Neural Entity Resolution for Edge Devices
      • Leveraging Multilingual Neural Language Models for On-Device Natural Language Understanding
      • Comparing Data Augmentation and Annotation Standardization to Improve End-to-end Spoken Language Understanding Models
      • CLAR: Contrastive Learning of Auditory Representations
    • 2022
      • Robust Self-Supervised Audio-Visual Speech Recognition
      • Adaptive Global-Local Context Fusion for Multi-Turn Spoken Language Understanding
      • SpeechMatrix: a Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations
      • GIT: a Generative Image-to-text Transformer for Vision and Language
    • 2023
      • Simple and Controllable Music Generation
      • UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units
      • Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers
      • Joint Audio and Speech Understanding
      • Long-Form Music Generation with Latent Diffusion
  • Multimodal
    • 2021
      • Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models
      • Rethinking Attention with Performers
    • 2022
      • Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction
      • GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
      • Image As a Foreign Language: BEIT Pretraining for All Vision and Vision-Language Tasks
      • Visual Programming: Compositional Visual Reasoning Without Training
      • Video-ChatGPT: Towards Detailed Video Understanding Via Large Vision and Language Models
    • 2023
      • Meta-Transformer: a Unified Framework for Multimodal Learning
      • Any-to-Any Generation Via Composable Diffusion
      • Bytes are All You Need: Transformers Operating Directly on File Bytes
      • Prompting Large Language Models with Answer Heuristics for Knowledge-based Visual Question Answering
      • Sound Reconstruction from Human Brain Activity Via a Generative Model with Brain-like Auditory Features
      • LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day
      • Unified Model for Image, Video, Audio and Language Tasks
      • Qwen-7B: Open Foundation and Human-aligned Models
      • Qwen-VL: a Frontier Large Vision-Language Model with Versatile Abilities
      • NExT-GPT: Any-to-Any Multimodal LLM
      • LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents
      • Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning
      • Demystifying CLIP Data
      • Scalable Diffusion Models with Transformers
      • DeepFloyd IF
      • PIXART-αα: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
      • RAPHAEL: Text-to-Image Generation Via Large Mixture of Diffusion Paths
      • ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts
      • CogVLM: Visual Expert for Pretrained Language Models
      • Improved Baselines with Visual Instruction Tuning
      • Matryoshka Diffusion Models
      • MAViL: Masked Audio-Video Learners
      • TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering
      • CoDi-2: In-Context Interleaved and Interactive Any-to-Any Generation
      • ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs
      • Hyperbolic Image-Text Representations
      • Evaluating Object Hallucination in Large Vision-Language Models
      • Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
      • FLAP: Fast Language-Audio Pre-training
      • Jointly Learning Visual and Auditory Speech Representations from Raw Data
      • MIRASOL3B: a Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities
      • Video-LLaMA: an Instruction-tuned Audio-Visual Language Model for Video Understanding
      • VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners
      • Visual Instruction Inversion: Image Editing Via Visual Prompting
      • A Video is Worth 4096 Tokens: Verbalize Videos to Understand Them in Zero Shot
      • Emu Edit: Precise Image Editing Via Recognition and Generation Tasks
    • 2024
      • CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding
      • MME: a Comprehensive Evaluation Benchmark for Multimodal Large Language Models
      • Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning
      • PALO: a Polyglot Large Multimodal Model for 5B People
      • Sigmoid Loss for Language Image Pre-Training
    • 2024
      • EMO: Emote Portrait Alive - Generating Expressive Portrait Videos with Audio2Video Diffusion Model Under Weak Conditions
      • DeepSeek-VL: Towards Real-World Vision-Language Understanding
      • MPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding
      • OOTDiffusion: Outfitting Fusion Based Latent Diffusion for Controllable Virtual Try-on
      • Glyph-ByT5: a Customized Text Encoder for Accurate Visual Text Rendering
      • Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
      • Mora: Enabling Generalist Video Generation Via a Multi-Agent Framework
      • VILA: on Pre-training for Visual Language Models
      • PaliGemma: a Versatile 3B VLM for Transfer
  • Core ML
    • 2016
      • The Peaking Phenomenon in Semi-supervised Learning
    • 2018
      • Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning
    • 2019
      • Which Algorithmic Choices Matter at Which Batch Sizes? Insights from a Noisy Quadratic Model
    • 2020
      • Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference
    • 2021
      • Tensor Programs V: Tuning Large Neural Networks Via Zero-Shot Hyperparameter Transfer
    • 2022
      • OmniXAI: a Library for Explainable AI
      • VeLO: Training Versatile Learned Optimizers by Scaling up
    • 2023
      • CoLT5: Faster Long-Range Transformers with Conditional Computation
      • GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
      • Sophia: a Scalable Stochastic Second-order Optimizer for Language Model Pre-training
      • DoReMi: Optimizing Data Mixtures Speeds up Language Model Pretraining
      • One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning
      • Tackling the Curse of Dimensionality with Physics-Informed Neural Networks
      • (Ab)using Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs
      • Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
      • DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models
      • The Depth-to-Width Interplay in Self-Attention
      • The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
    • 2024
      • Evolutionary Optimization of Model Merging Recipes
      • BANG: Billion-Scale Approximate Nearest Neighbor Search Using a Single GPU
  • RecSys
    • 2019
      • Deep Learning Recommendation Model for Personalization and Recommendation Systems
      • FiBiNET: Combining Feature Importance and Bilinear Feature Interaction for Click-Through Rate Prediction
      • AutoInt: Automatic Feature Interaction Learning Via Self-Attentive Neural Networks
    • 2020
    • DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems
      • GCN-Based User Representation Learning for Unifying Robust Recommendation and Fraudster Detection
    • 2022
      • DHEN: a Deep and Hierarchical Ensemble Network for Large-Scale Click-Through Rate Prediction
    • 2023
      • Towards Deeper, Lighter, and Interpretable Cross Network for CTR Prediction
      • Do LLMs Understand User Preferences? Evaluating LLMs on User Rating Prediction
      • Fresh Content Needs More Attention: Multi-funnel Fresh Content Recommendation
      • Large Language Models are Zero-Shot Rankers for Recommender Systems
      • How Can Recommender Systems Benefit from Large Language Models: a Survey
  • RL
    • 2022
      • Transdreamer: Reinforcement Learning with Transformer World Models
  • Graph ML
    • 2019
      • RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
    • 2023
      • Graph-Bert: Only Attention is Needed for Learning Graph Representations
    • 2024
      • GraphMaker: Can Diffusion Models Generate Large Attributed Graphs?
      • Generative Diffusion Models on Graphs: Methods and Applications
      • A Survey on Graph Diffusion Models: Generative AI in Science for Molecule Protein and Material

• Seminal papers
• need-to-know
• papers
• research