Paper Notes
Topic All
Venue All
Year All years
Biology
Protein models, molecular design, and biomedical AI
NLP / Agents
LLMs, scientific agents, and language-model tooling
Vision
Video understanding, multimodal vision-language models
ML
Representation learning, graphs, and general ML methods
Software
Code models, summarization, and program analysis
Retrieval
Search, recommendation, and neural indexing
Systems
Distributed systems and systems for ML
2014
2015
2016
2017
IJCNLP-2017 A parallel corpus of Python functions and documentation strings for automated code documentation and code generation
ICML-2017 Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Bioinformatics-2017 DeepLoc:prediction of protein subcellular localization using deep learning
CVPR-2017 Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
AAAI-2017 SeqGAN:Sequence Generative Adversarial Nets with Policy Gradient
2018
OpenAI-2018 Improving Language Understanding by Generative Pre-Training
ACL-2018 Improving Abstraction in Text Summarization
ICLR-2019 Graph2Seq:Graph to Sequence Learning with Attention-based Neural Networks
DeepMind-2018 Representation Learning with Contrastive Predictive Coding
ICPC-2018 Deep code comment generation
ICSE-2018 Deep code search
CVPR-2018 Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
CVPR-2018 Non-local Neural Networks
CVPR-2018 A Closer Look at Spatiotemporal Convolutions for Action Recognition
AAAI-2018 Generative Adversarial Network for Abstractive Text Summarization
2019
NeurIPS-2019 GPipe:Efficient Training of Giant Neural Networks using Pipeline Parallelism
ICCV-2019 SlowFast Networks for Video Recognition
IJCAI-2019 Commit Message Generation for Source Code Changes
ACL-2019 Improving Robustness of Neural Machine Translation with Multi-task Learning
arXiv-2019 RoBERTa:A Robustly Optimized BERT Pretraining Approach
KDD-2019 MeLU:Meta-Learned User Preference Estimator for Cold-Start Recommendation
OpenAI-2019 Language Models are Unsupervised Multitask Learners
ICSE-2019 A Neural Model for Generating Natural Language Summaries of Program Subroutines
ICSE-2019 A Novel Neural Source Code Representation Based on Abstract Syntax Tree
arXiv-2019 Unified Language Model Pre-training for Natural Language Understanding and Generation
CVPR-2019 Unsupervised Embedding Learning via Invariant and Spreading Instance Feature
ICML-2019 Parameter-Efficient Transfer Learning for NLP
ACS Synthetic Biology-2019 Machine Learning Applied to Predicting Microorganism Growth Temperatures and Enzyme Catalytic Optima
NeurIPS-2019 Evaluating Protein Transfer Learning with TAPE
2020
ECCV-2020 CMC: Contrastive Multiview Coding
NeurIPS-2020 Big Self-Supervised Models are Strong Semi-Supervised Learners
NeurIPS-2020 Bootstrap your own latent:A new approach to self-supervised Learning
NeurIPS-2020 Graph Contrastive Learning with Augmentations
NeurIPS-2020 Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
MSR-2020 Improved Automatic Summarization of Subroutines via Attention to File Context
SC-2020 ZeRO:Memory Optimizations Toward Training Trillion Parameter Models
arXiv-2020 BYOL works even without batch statistics
KDD-2020 GCC:Graph Contrastive Coding for Graph Neural Network Pre-Training
SIGIR-2020 How to Retrain Recommender System?A Sequential Meta-Learning Method
ACL-2020 Contrastive Code Representation Learning
NeurIPS-2020 Deep Graph Contrastive Representation Learning
ICML-2020 Graph-based, Self-Supervised Program Repair from Diagnostic Feedback
arXiv-2020 Neural Subgraph Matching
ICML-2020 A Simple Framework for Contrastive Learning of Visual Representations
ICML-2020 Contrastive Multi-View Representation Learning on Graphs
ECCV-2020 End-to-End Object Detection with Transformers
OpenAI-2020 Language Models are Few-Shot Learners
ACL-2020 A Transformer-based Approach for Source Code Summarization
ICLR-2020 DivideMix:Learning with Noisy Labels as Semi-supervised Learning
Transactions on Neural Networks and Learning Systems-2020 A Comprehensive Survey on Graph Neural Networks
CVPR-2020 Momentum Contrast for Unsupervised Visual Representation Learning
GTC-2020 Megatron-LM:Training Multi-Billion Parameter Language Models Using Model Parallelism
2021
Human Genetics-2021 Embeddings from protein language models predict conservation and variant effects
KDD-2021 Modeling Protein Using Large-scale Pretrain Language Model
NeurIPS-2021 VLMo:Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts
NeurIPS-2021 Intriguing Properties of Vision Transformers
NeurIPS-2021 Language models enable zero-shot prediction of the effects of mutations on protein function
NeurIPS-2021 Align before Fuse:Vision and Language Representation Learning with Momentum Distillation
Bioinformatics Advances-2021 Light attention predicts protein location from the language of life
CVPR-2021 Masked Autoencoders Are Scalable Vision Learners
EMNLP-2021 Rethinking Data Augmentation for Low-Resource Neural Machine Translation:A Multi-Task Learning Approach
NeurIPS-2021 FLIP:Benchmark tasks in fitness landscape inference for proteins
arXiv-2021 ActionCLIP:A New Paradigm for Video Action Recognition
ICLR-2021 GraphCodeBERT:Pre-training Code Representations with Data Flow
EMNLP-2021 CodeT5:Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation
bioRxiv-2021 Toward More General Embeddings for Protein Design:Harnessing Joint Representations of Sequence and Structure
ICCV-2021 Swin Transformer:Hierarchical Vision Transformer using Shifted Windows
ACL-2021 Learning Sequential and Structural Information for Source Code Summarization
ICSME-2021 Ensemble Models for Neural Source Code Summarization of Subroutines
IJCAI-2021 Graph-Augmented Code Summarization in Computational Notebooks
Nature-2021 Highly accurate protein structure prediction with AlphaFold
OpenAI-2021 Evaluating Large Language Models Trained on Code
arXiv-2021 How Much Can CLIP Benefit Vision-and-Language Tasks?
IEEE Transactions on Pattern Analysis and Machine Intelligence-2021 ProtTrans:Towards Cracking the Language of Life’s Code Through Self-Supervised Learning
ICML-2021 Perceiver:General Perception with Iterative Attention
arXiv-2021 CLIP4Clip:An Empirical Study of CLIP for End to End Video Clip Retrieval
Proceedings of the National Academy of Sciences-2021 Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences
ICCV-2021 An Empirical Study of Training Self-Supervised Vision Transformers
ICPC-2021 A Multi-Modal Transformer-based Code Summarization Approach for Smart Contracts
ICML-2021 Learning Transferable Visual Models From Natural Language Supervision
ICML-2021 E(n) Equivariant Graph Neural Networks
ICML-2021 MSA Transformer
ICML-2021 ViLT:Vision-and-Language Transformer Without Convolution or Region Supervision
Bioinformatics-2021 DNABERT:pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome
ICML-2021 Learning inverse folding from millions of predicted structures
Automated Software Engineering-2021 Automating just-in-time comment updating
GCPR-2021 AudioCLIP:Extending CLIP to Image, Text and Audio
ICLR-2021 Learning from Protein Structure with Geometric Vector Perceptrons
ICLR-2021 Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning
ICLR-2021 An Image is Worth 16x16 Words:Transformers for Image Recognition at Scale
ICML-2021 Is Space-Time Attention All You Need for Video Understanding
ACL-2021 Code Summarization with Structure-induced Transformer
2022
NeurIPS-2022 PEER:A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding
bioRxiv-2022 Fast protein structure searching using structure graph embeddings
NeurIPS-2022 Transformer Memory as a Differentiable Search Index
EMNLP-2021 HAConvGNN:Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in Jupyter Notebooks
arXiv-2022 Holistic Evaluation of Language Models
NeurIPS-2022 Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein Structures
NeurIPS-2022 A Neural Corpus Indexer for Document Retrieval
PEDS-2022 Masked inverse folding with sequence transfer for protein representation learning
ICPC-2022 HELoC:Hierarchical Contrastive Learning of Source Code Representation
MM-2022 Can Language Understand Depth?
OpenAI-2022 Robust Speech Recognition via Large-Scale Weak Supervision
Nature Biotechnology-2022 Single-sequence protein structure prediction using a language model and deep learning
EMNLP-2020 CodeBERT:A Pre-Trained Model for Programming and Natural Languages
NeurIPS-2022 CoCa:Contrastive Captioners are Image-Text Foundation Models
NAACL-2022 MoEBERT:from BERT to Mixture-of-Experts via Importance-Guided Adaptation
SIGGRAPH-2022 CLIPasso:Semantically-Aware Object Sketching
CVPR-2022 GroupViT:Semantic Segmentation Emerges from Text Supervision
ECCV-2022 CDS:Contrastive Deep Supervision
ICSE-2022 AST-trans:code summarization with efficient tree-structured attention
ICSE-2022 Cross-Domain Deep Code Search with Few-Shot Meta Learning
AAAI-2022 Hierarchical Heterogeneous Graph Attention Network for Syntax-Aware Summarization
CVPR-2022 PointCLIP:Point Cloud Understanding by CLIP
arXiv-2022 Learning code summarization from a small and local dataset
arXiv-2022 GLIPv2:Unifying Localization and Vision-Language Understanding
Journal of Systems and Software-2022 Automatic source code summarization with graph attention networks
ICML-2022 Tranception:protein fitness prediction with autoregressive transformers and inference-time retrieval
ICML-2016 A Convolutional Attention Network for Extreme Summarization of Source Code
ACL-2022 Impact of Evaluation Methodologies on Code Summarization
NAACL-2022 CODE-MVP:Learning to Represent Source Code from Multiple Views with Contrastive Pre-Training
arXiv-2022 A Survey of Deep Learning Models for Structural Code Understanding
NAR-2022 DeepLoc 2.0:multi-label subcellular localization prediction using protein language models
arXiv-2022 Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
OpenAI-2022 Hierarchical Text-Conditional Image Generation with CLIP Latents
MLSys-2022 Pathways:Asynchronous Distributed Dataflow for ML
Nature Machine Intelligence-2022 Learning functional properties of proteins with language models
OpenAI-2022 Training language models to follow instructions with human feedback
DeepMind-2022 Competition-Level Code Generation with AlphaCode
Stanford-2022 AI Index Report
Report: AI Index Report. Most statistics are drawn from Papers with Code. Because the report contains a large number of figures, individual screenshots are not included here.
Frontiers in Microbiology-2022 iThermo:A Sequence-Based Model for Identifying Thermophilic Proteins Using a Multi-Feature Fusion Strategy
ICLR-2022 Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design
ICLR-2022 OntoProtein:Protein Pretraining With Gene Ontology Embedding
ICLR-2022 LoRA:Low-Rank Adaptation of Large Language Models
ICLR-2022 Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
ICLR-2022 Perceiver IO:A General Architecture for Structured Inputs & Outputs
NeurIPS-2022 Chain of Thought Prompting Elicits Reasoning in Large Language Models
ICML-2022 BLIP:Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
Nature Biotechnology-2022 Learning protein fitness models from evolutionary and assay-labeled data
CVPR-2022 Grounded Language-Image Pre-trainin
Journal of Machine Learning Research-2022 Switch Transformers:Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
ICLR-2022 Language-driven Semantic Segmentation
ACM Computing Surveys-2022 Deep Meta-learning in Recommendation Systems:A Survey
2023
bioRxiv-2023 IgDesign-In vitro validated antibody design against multiple therapeutic antigens using inverse folding
bioRxiv-2023 Learning sequence, structure, and function representations of proteins with language models
Nature Biotechnology-2023 Protein remote homology detection and structural alignment using deep learning
NeurIPS-2023 PoET:A generative model of protein families as sequences-of-sequences
EMNLP-2023 BioPlanner:Automatic Evaluation of LLMs on Protocol Planning in Biology
NeurIPS-2023 ProteinGym:Large-Scale Benchmarks for Protein Design and Fitness Prediction
NeurIPS-2023 Predicting a Protein’s Stability under a Million Mutations
bioRxiv-2023 Protein generation with evolutionary diffusion:sequence is all you need
KDD-2023 Pre-training Antibody Language Models for Antigen-Specific Computational Antibody Design
ICML-2023 End-to-End Full-Atom Antibody Design
Nature Machine Intelligence-2023 Structure-inducing pre-training for generalizable representation learning
Nature Biotechnology-2023 Fast and accurate protein structure search with Foldseek
Science-2023 Evolutionary-scale prediction of atomic-level protein structure with a language model
Bioinformatics-2023 Accurate and efficient protein sequence design through learning concise local environment of residues
CVPR-2020 Improved Baselines with Momentum Contrastive Learning
ICLRw-2023 Enhancing Protein Language Models with Structure-based Encoder and Pre-training
ICML-2023 Structure-informed Language Models Are Protein Designers
ICLR-2023 AIM:Adapting Image Models for Efficient Video Action Recognition
ICLR-2023 Conditional Antibody Design as 3D Equivariant Graph Translation
International Journal of Molecular Sciences-2023 DeepTP:A Deep Learning Model for Thermophilic Protein Prediction
bioRxiv-2023 Ankh:Optimized Protein Language Model Unlocks General-Purpose Modelling
CVPR-2023 Image as a Foreign Language:BEiT Pretraining for All Vision and Vision-Language Tasks
WACV-2023 MixGen:A New Multi-Modal Data Augmentation
bioRxiv-2023 When Geometric Deep Learning Meets Pretrained Protein Language Models
2024
PLOS Computational Biology-2024 Large scale paired antibody language models
bioRxiv-2024 Mixture of Experts Enable Efficient and Effective Protein Understanding and Design
Bioinformatics-2024 Expert-guided protein language models enable accurate and blazingly fast fitness prediction
Nature Communications-2024 A joint embedding of protein sequence and structure enables robust variant effect predictions
arXiv-2024 Movie Gen:A Cast of Media Foundation Models
Nature Computational Science-2025 Improving the prediction of protein stability changes upon mutations by geometric learning and a pre-training strategy
NeurIPS-2024 Multi-Scale Representation Learning for Protein Fitness Prediction
Nature Biotechnology-2024 Multistate and functional protein design using RoseTTAFold sequence space diffusion
ACL Demo-2024 LlamaFactory:Unified Efficient Fine-Tuning of 100+ Language Models
ICML-2024 Feature Reuse and Scaling:Understanding Transfer Learning with Protein Language Models
Nature Communications-2024 PLMSearch:Protein language model powers accurate and fast sequence search for remote homology
Cell Systems-2024 Convolutions are competitive with transformers for protein sequence pretraining
eLife-2024 Sensitive remote homology search by local alignment of small positional embeddings from protein language models
AAAI-2024 T2I-Adapter:Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models
Journal of Chemical Information and Modeling-2024 TM-search:An Efficient and Effective Tool for Protein Structure Database Search
ICLR-2024 SaProt:Protein Language Modeling with Structure-aware Vocabulary
Bioinformatics-2024 Embedding-based alignment:combining protein language models with dynamic programming alignment to detect structural similarities in the twilight-zone
2025
arXiv-2025 Evaluating Large Language Models in Scientific Discovery
NeurIPS-2025 AI-Researcher:Autonomous Scientific Innovation
EMNLP-2025 From Automation to Autonomy:A Survey on Large Language Models in Scientific Discovery
Nature Biotechnology-2025 Democratizing protein language model training, sharing and collaboration
ACEBench:Who Wins the Match Point in Tool Usage
Genome Biology-2025 Evaluating the representational power of pre-trained DNA language models for regulatory genomics
ICMLw-2025 ProteinCrow:A Language Model Agent That Can Design Proteins
arXiv-2025 Scaling unlocks broader generation and deeper functional understanding of proteins
arXiv-2025 The AI Scientist-v2:Workshop-Level Automated Scientific Discovery via Agentic Tree Search
arXiv-2025 Prot42:a Novel Family of Protein Language Models for Target-aware Protein Binder Generation
COLING-2025 AutoProteinEngine:A Large Language Model Driven Agent Framework for Multimodal AutoML in Protein Engineering
Nature Computational Science-2025 SciToolAgent:A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration
ICLR-2025 Boltzmann-Aligned Inverse Folding Model as a Predictor of Mutational Effects on Protein-Protein Interactions
ICLR-2025 Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimization
ICLR-2025 ToolACE:Winning the Points of LLM Function Calling