This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Title | Tweets | Citations | Organization | Country | Org Type | |
|---|---|---|---|---|---|---|
| AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models | 1331 | DeepMind, European Molecular Biology Laboratory | UK | academia | ||
| ColabFold: making protein folding accessible to all | 1138 | Harvard University, Max Planck Institute for Multidisciplinary Sciences, Michigan State University, Seoul National University, University of Tokyo | Germany, Japan, South Korea, USA | academia | ||
| A ConvNet for the 2020s | 857 | 835 | Meta, UC Berkeley | USA | industry | |
| Hierarchical Text-Conditional Image Generation with CLIP Latents | 105 | 718 | OpenAI | USA | industry | |
| PaLM: Scaling Language Modeling with Pathways | 445 | 426 | USA | industry | ||
| Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding | 2462 | 390 | USA | industry | ||
| Instant Neural Graphics Primitives with a Multiresolution Hash Encoding | 11 | 342 | NVIDIA | USA | industry | |
| SignalP 6.0 predicts all five types of signal peptides using protein language models | 274 | Copenhagen University Hospital, ETH Zurich, Stanford University, Stockholm University, Technical University of Denmark, University of Copenhagen, Wellcome Genome Campus | Denmark, Sweden, Switzerland, UK, USA | academia | ||
| Swin Transformer V2: Scaling Up Capacity and Resolution | 87 | 266 | Huazhong University of Science and Technology, Microsoft, Tsinghua University, University of Science and Technology of China, Xi’an Jiaotong University | China, USA | industry | |
| Training language models to follow instructions with human feedback | 448 | 254 | OpenAI | USA | industry | |
| Chain of Thought Prompting Elicits Reasoning in Large Language Models | 378 | 224 | USA | industry | ||
| Flamingo: a Visual Language Model for Few-Shot Learning | 71 | 218 | DeepMind | UK | industry | |
| Classifier-Free Diffusion Guidance | 53 | 194 | Netherlands, USA | industry | ||
| Magnetic control of tokamak plasmas through deep reinforcement learning | 194 | DeepMind, École Polytechnique Fédérale de Lausanne, Meta | Switzerland, UK, USA | industry | ||
| data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language | 191 | Meta | USA | industry | ||
| OPT: Open Pre-trained Transformer Language Models | 812 | 187 | Meta | USA | industry | |
| BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation | 79 | 184 | Salesforce | USA | industry | |
| A Generalist Agent | 231 | 180 | DeepMind | UK | industry | |
| LaMDA: Language Models for Dialog Applications | 473 | 180 | USA | industry | ||
| CMT: Convolutional Neural Networks Meet Vision Transformers | 172 | Huawei, University of Sydney | Australia, China | academia | ||
| Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model | 271 | 158 | Microsoft, NVIDIA | USA | industry | |
| What Makes Good In-Context Examples for GPT-3? | 157 | Duke University, Meta, Microsoft | USA | industry | ||
| Ensemble unsupervised autoencoders and Gaussian mixture model for cyberattack detection | 145 | Ningbo University of Technology, Tongji University | China | academia | ||
| Training Compute-Optimal Large Language Models | 144 | DeepMind | UK | industry | ||
| Learning robust perceptive locomotion for quadrupedal robots in the wild | 3 | 141 | ETH Zurich, Intel, Korea Advanced Institute of Science and Technology | South Korea, Switzerland, USA | academia | |
| Do As I Can, Not As I Say: Grounding Language in Robotic Affordances | 82 | 135 | Everyday Robots, Google | USA | industry | |
| How Do Vision Transformers Work? | 193 | 129 | NAVER, Yonsei University | South Korea | academia | |
| Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs | 30 | 127 | Aberystwyth University, Megvii, Tsinghua University | China, UK | industry | |
| Large Language Models are Zero-Shot Reasoners | 862 | 124 | Google, University of Tokyo | Japan, USA | academia | |
| Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time | 122 | Columbia University, Google, Meta, Tel Aviv University, University of Washington | Israel, USA | academia | ||
| Patches Are All You Need? | 117 | 116 | Bosch, Carnegie Mellon University | USA | academia, industry | |
| Competition-Level Code Generation with AlphaCode | 113 | DeepMind | UK | industry | ||
| TensoRF: Tensorial Radiance Fields | 73 | 110 | Adobe, ShanghaiTech University, UC San Diego, University of Tubingen | China, Germany, USA | academia | |
| Video Diffusion Models | 103 | Netherlands, USA | industry | |||
| Data Analytics for the Identification of Fake Reviews Using Supervised Learning | 102 | Albaha University, Dr. Babasaheb Ambedkar Marathwada University, King Faisal University, Nahrain University | India, Iraq, Saudi Arabia | academia | ||
| Visual Prompt Tuning | 26 | 102 | Cornell University, Meta, University of Copenhagen | Denmark, USA | industry | |
| DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection | 15 | 100 | Hong Kong University of Science and Technology, International Digital Economy Academy, Tsinghua University | China | academia | |
| VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training | 66 | 100 | Nanjing University, Shanghai AI Lab, Tencent | China | academia | |
| Rethinking the Role of Demonstrations: What Makes In-Context Learning Work? | 199 | 99 | Allen Institute for Artificial Intelligence, Meta, University of Washington | USA | academia, industry | |
| BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers | 11 | 96 | Nanjing University, Shanghai AI Lab, University of Hong Kong | China | academia | |
| Conditional Prompt Learning for Vision-Language Models | 51 | 93 | Nanyang Technological University | Singapore | academia | |
| Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution | 151 | 93 | Stanford University | USA | academia | |
| Measuring and Improving the Use of Graph Information in Graph Neural Networks | 1 | 93 | Chinese University of Hong Kong, National University of Singapore | China, Singapore | academia | |
| Exploring Plain Vision Transformer Backbones for Object Detection | 205 | 91 | Meta | USA | industry | |
| GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation | 26 | 90 | CIFAR, HEC Montreal, Mila, Stanford University, University of Montreal | Canada, USA | academia | |
| OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework | 91 | 88 | Alibaba Group | China | industry | |
| Block-NeRF: Scalable Large Scene Neural View Synthesis | 641 | 86 | Google, UC Berkeley, Waymo | USA | industry | |
| Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents | 24 | 86 | Carnegie Mellon University, Google, UC Berkeley | USA | industry | |
| Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models | 881 | 81 | AI Objectives Institute, Allen Institute for Artificial Intelligence, Amazon, Amelia, Amirkabir University of Technology, Anthropic, Apergo, Arizona State University, Bauhaus-Universität Weimar, Bluevine, Carnegie Mellon University, Carnegie Robotics, Charles River Analytics, Columbia University, Complutense University of Madrid, Conjecture, Cornell University, De Anza College, DeepMind, Duke Kunshan University, Duke University, ETH Zurich, EleutherAI, Ford Motor Company, Fraunhofer Institute for Integrated Circuits, Georgia Institute of Technology, Google, Hacettepe University, Harker School, Harvard University, Heidelberg Institute for Theoretical Studies, Hong Kong University of Science and Technology, IBM, Illinois Mathematics and Science Academy, Imperial College London, Indian Institute of Technology Madras, Juelich Research Center, KU Leuven, Karlsruhe Institute of Technology, King’s College London, Koç University, Lawrence Berkeley National Laboratory, Leipzig University, Ludwig Maximilian University of Munich, MIT, ML Collective, Martin-Luther-University Halle-Wittenberg, Max Planck Institute for Intelligent Systems, Max Planck Institute for Mathematics in the Sciences, McGill University, McMaster University, Meta, Microsoft, Mila, MosaicML, NAVER, NUST School of Electrical Engineering and Computer Science, National Public School, HSR, National Research Council Canada, National University of Singapore, NeuralSpace, Neurospin, New York University, NoOverfitting Lab, OpenAI, Ought, Peking University, Penn State University, Princeton University, Queen’s University, Research Institutes of Sweden, Rice University, Rutgers University, Saarland University, Salesforce, Sapienza University of Rome, Sharif University of Technology, Stanford University, Strathmore University, Synthego Corporation, Technion, Tel Aviv University, Thapar Institute of Engineering and Technology, Thomson Reuters Special Services, TomTom, Toyota Technological Institute at Chicago, Tufts University, UC Berkeley, UC Irvine, UC Los Angeles, UC San Diego, Umeå University, UnifyID labs, University of Amsterdam, University of Bristol, University of Cambridge, University of Edinburgh, University of Hamburg, University of Heidelberg, University of Hong Kong, University of Illinois Urbana-Champaign, University of Memphis, University of Michigan, University of Milano-Bicocca, University of North Carolina at Chapel Hill, University of Notre Dame, University of Oxford, University of Pennsylvania, University of Potsdam, University of Southern California, University of Tehran, University of Texas at Austin, University of Toronto, University of Tsukuba, University of Tubingen, University of Utah, University of Virginia, University of Washington, University of Wisconsin-Madison, Valencia Polytechnic University, Wrocław University of Science and Technology, Yale University | Belgium, Canada, China, France, Germany, India, Iran, Israel, Italy, Japan, Kenya, Netherlands, Pakistan, Poland, Singapore, South Korea, Spain, Sweden, Switzerland, Turkey, UK, USA | academia | |
| Outracing champion Gran Turismo drivers with deep reinforcement learning | 80 | Sony | Japan | industry | ||
| BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning | 10 | 77 | Everyday Robots, Google, Stanford University, UC Berkeley | USA | academia | |
| DN-DETR: Accelerate DETR Training by Introducing Query DeNoising | 74 | Hong Kong University of Science and Technology, International Digital Economy Academy, Tsinghua University | China | academia | ||
| Emergent Abilities of Large Language Models | 442 | 74 | DeepMind, Google, Stanford University, University of North Carolina at Chapel Hill | UK, USA | academia, industry | |
| Equivariant Diffusion for Molecule Generation in 3D | 131 | 73 | École Polytechnique Fédérale de Lausanne, University of Amsterdam | Netherlands, Switzerland | academia | |
| Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images | 6 | 73 | NVIDIA, Vanderbilt University | USA | industry | |
| GPT-NeoX-20B: An Open-Source Autoregressive Language Model | 50 | 72 | EleutherAI | industry | ||
| Online reinforcement learning multiplayer non-zero sum games of continuous-time Markov jump linear systems | 72 | Anhui University, Chengdu University, Murdoch University, University of Kragujevac | Australia, China, Serbia | academia | ||
| Self-consistency improves chain of thought reasoning in language models | 290 | 71 | USA | industry | ||
| Detecting Twenty-thousand Classes using Image-level Supervision | 35 | 70 | Meta, University of Texas at Austin | USA | industry | |
| Image fusion in the loop of high-level vision tasks: A semantic-aware real-time infrared and visible image fusion network | 68 | Wuhan University | China | academia | ||
| LAION-5B: An open large-scale dataset for training next generation image-text models | 53 | 66 | Juelich Research Center, LAION, Stability AI, Technical University of Darmstadt, Technical University of Munich, UC Berkeley, University of Washington | Germany, USA | industry | |
| Denoising Diffusion Restoration Models | 65 | NVIDIA, Stanford University, Technion | Israel, USA | industry | ||
| VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance | 175 | 64 | AiDock, Booz Allen Hamilton, EleutherAI, Georgia Institute of Technology | Israel, USA | industry | |
| CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields | 33 | 63 | City University of Hong Kong, Microsoft, Snap Inc., University of Southern California | China, USA | academia | |
| Solving Quantitative Reasoning Problems with Language Models | 139 | 63 | USA | industry | ||
| Masked Autoencoders As Spatiotemporal Learners | 120 | 61 | Meta | USA | industry | |
| Why do tree-based models still outperform deep learning on tabular data? | 646 | 60 | CNRS, INRIA, Sorbonne University | France | academia | |
| Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language | 499 | 59 | USA | industry | ||
| ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond | 2 | 59 | JD Explore Academy, University of Sydney | Australia, China | academia, industry | |
| Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks | 178 | 58 | Microsoft | USA | industry | |
| Language-driven Semantic Segmentation | 95 | 57 | Apple, Cornell University, Intel, University of Copenhagen | Denmark, USA | industry | |
| Vision-Language Pre-Training with Triple Contrastive Learning | 34 | 56 | Amazon, University of Texas at Arlington | USA | academia | |
| Deep Reinforcement Learning-Based Path Control and Optimization for Unmanned Ships | 55 | Sipivt, Tongji University | China | industry | ||
| EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction | 208 | 54 | MIT | USA | academia | |
| Omnivore: A Single Model for Many Visual Modalities | 89 | 54 | Meta | USA | industry | |
| Quantifying Memorization Across Neural Language Models | 106 | 54 | Cornell University, Google, University of Pennsylvania | USA | industry | |
| DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection | 36 | 53 | Google, Johns Hopkins University | USA | industry | |
| Genetic Algorithm-Based Trajectory Optimization for Digital Twin Robots | 53 | Wuhan University of Science and Technology | China | academia | ||
| Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors | 280 | 53 | Meta | USA | industry | |
| Discovering faster matrix multiplication algorithms with reinforcement learning | 52 | DeepMind | UK | industry | ||
| DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation | 221 | 52 | Boston University, Google | USA | industry | |
| PETR: Position Embedding Transformation for Multi-View 3D Object Detection | 4 | 52 | Megvii | China | industry | |
| Protein structure predictions to atomic accuracy with AlphaFold | 51 | DeepMind | UK | industry | ||
| ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Multi-Task Learning Challenges | 2 | 50 | Queen Mary University of London | UK | academia | |
| HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video | 72 | 50 | Google, University of Washington | USA | academia, industry | |
| UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models | 38 | 49 | Allen Institute for Artificial Intelligence, Carnegie Mellon University, George Mason University, Google, Meta, Penn State University, Salesforce, ServiceNow Research, Shanghai AI Lab, Stanford University, UC Berkeley, University of Edinburgh, University of Hong Kong, University of Illinois Urbana-Champaign, University of Washington, University of Waterloo, Yale University | Canada, China, UK, USA | academia | |
| A Systematic Evaluation of Large Language Models of Code | 61 | 48 | Carnegie Mellon University | USA | academia | |
| Robust Speech Recognition via Large-Scale Weak Supervision | 40 | 48 | OpenAI | USA | industry | |
| Diffusion Models: A Comprehensive Survey of Methods and Applications | 274 | 47 | Beijing University of Posts and Telecommunications, Carnegie Mellon University, HEC Montreal, Mila, OpenAI, Peking University, UC Los Angeles, UC Merced | Canada, China, USA | academia | |
| Can language models learn from explanations in context? | 113 | 46 | DeepMind | UK | industry | |
| NELA-GT-2021: A Large Multi-Labelled News Dataset for The Study of Misinformation in News Articles | 9 | 46 | Rensselaer Polytechnic Institute, University of Tennessee Knoxville | USA | academia | |
| ActionFormer: Localizing Moments of Actions with Transformers | 44 | 4Paradigm Inc., Nanjing University, University of Wisconsin-Madison | China, USA | academia | ||
| DeiT III: Revenge of the ViT | 115 | 44 | Meta, Sorbonne University | France, USA | academia, industry | |
| Least-to-Most Prompting Enables Complex Reasoning in Large Language Models | 44 | USA | industry | |||
| Diffusion-LM Improves Controllable Text Generation | 253 | 43 | Stanford University | USA | academia | |
| Overview of The Shared Task on Homophobia and Transphobia Detection in Social Media Comments | 41 | Indian Institute of Information Technology and Management, Madurai Kamaraj University, National University of Ireland Galway, SSN College of Engineering | India, Ireland | academia | ||
| Text and Code Embeddings by Contrastive Pre-Training | 23 | 40 | OpenAI | USA | industry | |
| Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality | 125 | 40 | Hugging Face, Meta, University College London, University of Waterloo | Canada, UK, USA | industry | |
| BLOOM: A 176B-Parameter Open-Access Multilingual Language Model | 325 | 39 | BigScience Team | France | industry | |
| Red Teaming Language Models with Language Models | 40 | 39 | DeepMind, New York University | UK, USA | industry | |
| Transformer Memory as a Differentiable Search Index | 372 | 39 | USA | industry | ||
| Torsional Diffusion for Molecular Conformer Generation | 109 | 38 | Harvard University, MIT | USA | academia | |
| Unified Contrastive Learning in Image-Text-Label Space | 66 | 37 | Microsoft | USA | industry | |
| Benchmarking Generalization via In-Context Instructions on 1, 600+ Language Tasks | 149 | 36 | Allen Institute for Artificial Intelligence, Amirkabir University of Technology, Arizona State University, Columbia University, Factored AI, Government Polytechnic Rajkot, Indian Institute of Technology Kharagpur, Indian Institute of Technology Madras, Johns Hopkins University, Microsoft, National Institute of Technology Karnataka, National University of Singapore, PSG College Of Technology, Sharif University of Technology, Stanford University, Tata Consultancy Services, UC Berkeley, University of Amsterdam, University of Massachusetts Amherst, University of Washington, Zycus Infotech | India, Iran, Netherlands, Singapore, USA | academia |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi @sergicastellasape ,
Many thanks for this helpful list! Besides, I would like to recommend our paper MetaFormer (CVPR 2022) which is not listed but has obtained 152 citations according to Google Scholar.
MetaFormer Is Actually What You Need for Vision 168.0 152 Sea AI Lab, National University of Singapore Singapore, Singapore Industry, Academia
Thank you very much for this helpful list.