Public record
What do ML papers claim, and has anyone reproduced it?
Claims from 100 widely read machine learning papers, each with its source passage and whether anyone has reproduced it.
- A ConvNet for the 2020sZhuang Liu, Hanzi Mao, Chao-Yuan Wu, and 3 morearXiv 2201.03545 · 40 claims · 0 with reviewed reproductions · 0 reports
- A Simple Framework for Contrastive Learning of Visual RepresentationsTing Chen, Simon Kornblith, Mohammad Norouzi, and 1 morearXiv 2002.05709 · 36 claims · 0 with reviewed reproductions · 0 reports
- A Style-Based Generator Architecture for Generative Adversarial NetworksTero Karras, Samuli Laine, Timo AilaarXiv 1812.04948 · 18 claims · 0 with reviewed reproductions · 0 reports
- Adam: A Method for Stochastic OptimizationDiederik P. Kingma, Jimmy BaarXiv 1412.6980 · 8 claims · 0 with reviewed reproductions · 0 reports
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, and 9 morearXiv 2010.11929 · 23 claims · 0 with reviewed reproductions · 0 reports
- Attention Is All You NeedAshish Vaswani, Noam Shazeer, Niki Parmar, and 5 morearXiv 1706.03762 · 12 claims · 0 with reviewed reproductions · 0 reports
- Auto-Encoding Variational BayesDiederik P Kingma, Max WellingarXiv 1312.6114 · 5 claims · 0 with reviewed reproductions · 0 reports
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftSergey Ioffe, Christian SzegedyarXiv 1502.03167 · 19 claims · 0 with reviewed reproductions · 0 reports
- BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingJacob Devlin, Ming-Wei Chang, Kenton Lee, and 1 morearXiv 1810.04805 · 25 claims · 0 with reviewed reproductions · 0 reports
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, and 6 morearXiv 2201.11903 · 27 claims · 0 with reviewed reproductions · 0 reports
- Classifier-Free Diffusion GuidanceJonathan Ho, Tim SalimansarXiv 2207.12598 · 5 claims · 0 with reviewed reproductions · 0 reports
- Constitutional AI: Harmlessness from AI FeedbackYuntao Bai, Saurav Kadavath, Sandipan Kundu, and 48 morearXiv 2212.08073 · 14 claims · 0 with reviewed reproductions · 0 reports
- Continuous control with deep reinforcement learningTimothy P. Lillicrap, Jonathan J. Hunt, Alexander Pritzel, and 5 morearXiv 1509.02971 · 0 claims · 0 with reviewed reproductions · 0 reports
- Decoupled Weight Decay RegularizationIlya Loshchilov, Frank HutterarXiv 1711.05101 · 24 claims · 0 with reviewed reproductions · 0 reports
- Deep contextualized word representationsMatthew E. Peters, Mark Neumann, Mohit Iyyer, and 4 morearXiv 1802.05365 · 30 claims · 0 with reviewed reproductions · 0 reports
- Deep Residual Learning for Image RecognitionKaiming He, Xiangyu Zhang, Shaoqing Ren, and 1 morearXiv 1512.03385 · 34 claims · 0 with reviewed reproductions · 0 reports
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonarXiv 2010.02502 · 11 claims · 0 with reviewed reproductions · 0 reports
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelarXiv 2006.11239 · 9 claims · 0 with reviewed reproductions · 0 reports
- Densely Connected Convolutional NetworksGao Huang, Zhuang Liu, Laurens van der Maaten, and 1 morearXiv 1608.06993 · 19 claims · 0 with reviewed reproductions · 0 reports
- Diffusion Models Beat GANs on Image SynthesisPrafulla Dhariwal, Alex NicholarXiv 2105.05233 · 27 claims · 0 with reviewed reproductions · 0 reports
- DINOv2: Learning Robust Visual Features without SupervisionMaxime Oquab, Timothée Darcet, Théo Moutakanni, and 23 morearXiv 2304.07193 · 37 claims · 0 with reviewed reproductions · 0 reports
- Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, and 3 morearXiv 2305.18290 · 24 claims · 0 with reviewed reproductions · 0 reports
- Distilling the Knowledge in a Neural NetworkGeoffrey Hinton, Oriol Vinyals, Jeff DeanarXiv 1503.02531 · 10 claims · 0 with reviewed reproductions · 0 reports
- Efficient Estimation of Word Representations in Vector SpaceTomas Mikolov, Kai Chen, Greg Corrado, and 1 morearXiv 1301.3781 · 9 claims · 0 with reviewed reproductions · 0 reports
- Efficient Memory Management for Large Language Model Serving with PagedAttentionWoosuk Kwon, Zhuohan Li, Siyuan Zhuang, and 6 morearXiv 2309.06180 · 20 claims · 0 with reviewed reproductions · 0 reports
- Efficiently Modeling Long Sequences with Structured State SpacesAlbert Gu, Karan Goel, Christopher RéarXiv 2111.00396 · 28 claims · 0 with reviewed reproductions · 0 reports
- EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksMingxing Tan, Quoc V. LearXiv 1905.11946 · 30 claims · 0 with reviewed reproductions · 0 reports
- Emergent Abilities of Large Language ModelsJason Wei, Yi Tay, Rishi Bommasani, and 13 morearXiv 2206.07682 · 10 claims · 0 with reviewed reproductions · 0 reports
- Emerging Properties in Self-Supervised Vision TransformersMathilde Caron, Hugo Touvron, Ishan Misra, and 4 morearXiv 2104.14294 · 36 claims · 0 with reviewed reproductions · 0 reports
- Evaluating Large Language Models Trained on CodeMark Chen, Jerry Tworek, Heewoo Jun, and 55 morearXiv 2107.03374 · 20 claims · 0 with reviewed reproductions · 0 reports
- Explaining and Harnessing Adversarial ExamplesIan J. Goodfellow, Jonathon Shlens, Christian SzegedyarXiv 1412.6572 · 5 claims · 0 with reviewed reproductions · 0 reports
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerColin Raffel, Noam Shazeer, Adam Roberts, and 6 morearXiv 1910.10683 · 40 claims · 0 with reviewed reproductions · 0 reports
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick, and 1 morearXiv 1506.01497 · 26 claims · 0 with reviewed reproductions · 0 reports
- Finetuned Language Models Are Zero-Shot LearnersJason Wei, Maarten Bosma, Vincent Y. Zhao, and 6 morearXiv 2109.01652 · 28 claims · 0 with reviewed reproductions · 0 reports
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-AwarenessTri Dao, Daniel Y. Fu, Stefano Ermon, and 2 morearXiv 2205.14135 · 30 claims · 0 with reviewed reproductions · 0 reports
- Gaussian Error Linear Units (GELUs)Dan Hendrycks, Kevin GimpelarXiv 1606.08415 · 10 claims · 0 with reviewed reproductions · 0 reports
- Generative Adversarial NetworksIan J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, and 5 morearXiv 1406.2661 · 7 claims · 0 with reviewed reproductions · 0 reports
- GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language UnderstandingAlex Wang, Amanpreet Singh, Julian Michael, and 3 morearXiv 1804.07461 · 13 claims · 0 with reviewed reproductions · 0 reports
- Going Deeper with ConvolutionsChristian Szegedy, Wei Liu, Yangqing Jia, and 6 morearXiv 1409.4842 · 11 claims · 0 with reviewed reproductions · 0 reports
- Graph Attention NetworksPetar Veličković, Guillem Cucurull, Arantxa Casanova, and 3 morearXiv 1710.10903 · 8 claims · 0 with reviewed reproductions · 0 reports
- Hierarchical Text-Conditional Image Generation with CLIP LatentsAditya Ramesh, Prafulla Dhariwal, Alex Nichol, and 2 morearXiv 2204.06125 · 13 claims · 0 with reviewed reproductions · 0 reports
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, and 2 morearXiv 2112.10752 · 23 claims · 0 with reviewed reproductions · 0 reports
- Holistic Evaluation of Language ModelsPercy Liang, Rishi Bommasani, Tony Lee, and 47 morearXiv 2211.09110 · 40 claims · 0 with reviewed reproductions · 0 reports
- Improved Training of Wasserstein GANsIshaan Gulrajani, Faruk Ahmed, Martin Arjovsky, and 2 morearXiv 1704.00028 · 12 claims · 0 with reviewed reproductions · 0 reports
- Inductive Representation Learning on Large GraphsWilliam L. Hamilton, Rex Ying, Jure LeskovecarXiv 1706.02216 · 19 claims · 0 with reviewed reproductions · 0 reports
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, and 28 morearXiv 2005.14165 · 40 claims · 0 with reviewed reproductions · 0 reports
- Layer NormalizationJimmy Lei Ba, Jamie Ryan Kiros, Geoffrey E. HintonarXiv 1607.06450 · 11 claims · 0 with reviewed reproductions · 0 reports
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, and 9 morearXiv 2103.00020 · 40 claims · 0 with reviewed reproductions · 0 reports
- Llama 2: Open Foundation and Fine-Tuned Chat ModelsHugo Touvron, Louis Martin, Kevin Stone, and 65 morearXiv 2307.09288 · 40 claims · 0 with reviewed reproductions · 0 reports
- LLaMA: Open and Efficient Foundation Language ModelsHugo Touvron, Thibaut Lavril, Gautier Izacard, and 11 morearXiv 2302.13971 · 23 claims · 0 with reviewed reproductions · 0 reports
- Longformer: The Long-Document TransformerIz Beltagy, Matthew E. Peters, Arman CohanarXiv 2004.05150 · 21 claims · 0 with reviewed reproductions · 0 reports
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, and 5 morearXiv 2106.09685 · 17 claims · 0 with reviewed reproductions · 0 reports
- Mamba: Linear-Time Sequence Modeling with Selective State SpacesAlbert Gu, Tri DaoarXiv 2312.00752 · 38 claims · 0 with reviewed reproductions · 0 reports
- Mask R-CNNKaiming He, Georgia Gkioxari, Piotr Dollár, and 1 morearXiv 1703.06870 · 36 claims · 0 with reviewed reproductions · 0 reports
- Masked Autoencoders Are Scalable Vision LearnersKaiming He, Xinlei Chen, Saining Xie, and 3 morearXiv 2111.06377 · 37 claims · 0 with reviewed reproductions · 0 reports
- Measuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, and 4 morearXiv 2009.03300 · 14 claims · 0 with reviewed reproductions · 0 reports
- Megatron-LM: Training Multi-Billion Parameter Language Models Using Model ParallelismMohammad Shoeybi, Mostofa Patwary, Raul Puri, and 3 morearXiv 1909.08053 · 25 claims · 0 with reviewed reproductions · 0 reports
- Mixed Precision TrainingPaulius Micikevicius, Sharan Narang, Jonah Alben, and 8 morearXiv 1710.03740 · 12 claims · 0 with reviewed reproductions · 0 reports
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep NetworksChelsea Finn, Pieter Abbeel, Sergey LevinearXiv 1703.03400 · 16 claims · 0 with reviewed reproductions · 0 reports
- Momentum Contrast for Unsupervised Visual Representation LearningKaiming He, Haoqi Fan, Yuxin Wu, and 2 morearXiv 1911.05722 · 21 claims · 0 with reviewed reproductions · 0 reports
- NeRF: Representing Scenes as Neural Radiance Fields for View SynthesisBen Mildenhall, Pratul P. Srinivasan, Matthew Tancik, and 3 morearXiv 2003.08934 · 20 claims · 0 with reviewed reproductions · 0 reports
- Neural Machine Translation by Jointly Learning to Align and TranslateDzmitry Bahdanau, Kyunghyun Cho, Yoshua BengioarXiv 1409.0473 · 14 claims · 0 with reviewed reproductions · 0 reports
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts LayerNoam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, and 4 morearXiv 1701.06538 · 17 claims · 0 with reviewed reproductions · 0 reports
- PaLM: Scaling Language Modeling with PathwaysAakanksha Chowdhery, Sharan Narang, Jacob Devlin, and 64 morearXiv 2204.02311 · 40 claims · 0 with reviewed reproductions · 0 reports
- Parameter-Efficient Transfer Learning for NLPNeil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, and 5 morearXiv 1902.00751 · 16 claims · 0 with reviewed reproductions · 0 reports
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, and 11 morearXiv 2205.11487 · 22 claims · 0 with reviewed reproductions · 0 reports
- Playing Atari with Deep Reinforcement LearningVolodymyr Mnih, Koray Kavukcuoglu, David Silver, and 4 morearXiv 1312.5602 · 7 claims · 0 with reviewed reproductions · 0 reports
- Prefix-Tuning: Optimizing Continuous Prompts for GenerationXiang Lisa Li, Percy LiangarXiv 2101.00190 · 18 claims · 0 with reviewed reproductions · 0 reports
- Proximal Policy Optimization AlgorithmsJohn Schulman, Filip Wolski, Prafulla Dhariwal, and 2 morearXiv 1707.06347 · 9 claims · 0 with reviewed reproductions · 0 reports
- QLoRA: Efficient Finetuning of Quantized LLMsTim Dettmers, Artidoro Pagnoni, Ari Holtzman, and 1 morearXiv 2305.14314 · 36 claims · 0 with reviewed reproductions · 0 reports
- ReAct: Synergizing Reasoning and Acting in Language ModelsShunyu Yao, Jeffrey Zhao, Dian Yu, and 4 morearXiv 2210.03629 · 28 claims · 0 with reviewed reproductions · 0 reports
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, and 9 morearXiv 2005.11401 · 19 claims · 0 with reviewed reproductions · 0 reports
- RoBERTa: A Robustly Optimized BERT Pretraining ApproachYinhan Liu, Myle Ott, Naman Goyal, and 7 morearXiv 1907.11692 · 22 claims · 0 with reviewed reproductions · 0 reports
- Robust Speech Recognition via Large-Scale Weak SupervisionAlec Radford, Jong Wook Kim, Tao Xu, and 3 morearXiv 2212.04356 · 36 claims · 0 with reviewed reproductions · 0 reports
- RoFormer: Enhanced Transformer with Rotary Position EmbeddingJianlin Su, Yu Lu, Shengfeng Pan, and 3 morearXiv 2104.09864 · 16 claims · 0 with reviewed reproductions · 0 reports
- Scaling Instruction-Finetuned Language ModelsHyung Won Chung, Le Hou, Shayne Longpre, and 32 morearXiv 2210.11416 · 38 claims · 0 with reviewed reproductions · 0 reports
- Scaling Laws for Neural Language ModelsJared Kaplan, Sam McCandlish, Tom Henighan, and 7 morearXiv 2001.08361 · 24 claims · 0 with reviewed reproductions · 0 reports
- Score-Based Generative Modeling through Stochastic Differential EquationsYang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, and 3 morearXiv 2011.13456 · 29 claims · 0 with reviewed reproductions · 0 reports
- Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, and 9 morearXiv 2304.02643 · 36 claims · 0 with reviewed reproductions · 0 reports
- Semi-Supervised Classification with Graph Convolutional NetworksThomas N. Kipf, Max WellingarXiv 1609.02907 · 11 claims · 0 with reviewed reproductions · 0 reports
- Sequence to Sequence Learning with Neural NetworksIlya Sutskever, Oriol Vinyals, Quoc V. LearXiv 1409.3215 · 17 claims · 0 with reviewed reproductions · 0 reports
- SGDR: Stochastic Gradient Descent with Warm RestartsIlya Loshchilov, Frank HutterarXiv 1608.03983 · 23 claims · 0 with reviewed reproductions · 0 reports
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic ActorTuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and 1 morearXiv 1801.01290 · 12 claims · 0 with reviewed reproductions · 0 reports
- SQuAD: 100,000+ Questions for Machine Comprehension of TextPranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and 1 morearXiv 1606.05250 · 8 claims · 0 with reviewed reproductions · 0 reports
- Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, and 5 morearXiv 2103.14030 · 23 claims · 0 with reviewed reproductions · 0 reports
- Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient SparsityWilliam Fedus, Barret Zoph, Noam ShazeerarXiv 2101.03961 · 40 claims · 0 with reviewed reproductions · 0 reports
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural NetworksJonathan Frankle, Michael CarbinarXiv 1803.03635 · 40 claims · 0 with reviewed reproductions · 0 reports
- The Power of Scale for Parameter-Efficient Prompt TuningBrian Lester, Rami Al-Rfou, Noah ConstantarXiv 2104.08691 · 24 claims · 0 with reviewed reproductions · 0 reports
- Toolformer: Language Models Can Teach Themselves to Use ToolsTimo Schick, Jane Dwivedi-Yu, Roberto Dessì, and 5 morearXiv 2302.04761 · 22 claims · 0 with reviewed reproductions · 0 reports
- Towards Deep Learning Models Resistant to Adversarial AttacksAleksander Madry, Aleksandar Makelov, Ludwig Schmidt, and 2 morearXiv 1706.06083 · 14 claims · 0 with reviewed reproductions · 0 reports
- Training Compute-Optimal Large Language ModelsJordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, and 19 morearXiv 2203.15556 · 33 claims · 0 with reviewed reproductions · 0 reports
- Training language models to follow instructions with human feedbackLong Ouyang, Jeff Wu, Xu Jiang, and 17 morearXiv 2203.02155 · 32 claims · 0 with reviewed reproductions · 0 reports
- U-Net: Convolutional Networks for Biomedical Image SegmentationOlaf Ronneberger, Philipp Fischer, Thomas BroxarXiv 1505.04597 · 8 claims · 0 with reviewed reproductions · 0 reports
- Understanding deep learning requires rethinking generalizationChiyuan Zhang, Samy Bengio, Moritz Hardt, and 2 morearXiv 1611.03530 · 13 claims · 0 with reviewed reproductions · 0 reports
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial NetworksAlec Radford, Luke Metz, Soumith ChintalaarXiv 1511.06434 · 11 claims · 0 with reviewed reproductions · 0 reports
- Very Deep Convolutional Networks for Large-Scale Image RecognitionKaren Simonyan, Andrew ZissermanarXiv 1409.1556 · 27 claims · 0 with reviewed reproductions · 0 reports
- Wasserstein GANMartin Arjovsky, Soumith Chintala, Léon BottouarXiv 1701.07875 · 9 claims · 0 with reviewed reproductions · 0 reports
- wav2vec 2.0: A Framework for Self-Supervised Learning of Speech RepresentationsAlexei Baevski, Henry Zhou, Abdelrahman Mohamed, and 1 morearXiv 2006.11477 · 29 claims · 0 with reviewed reproductions · 0 reports
- You Only Look Once: Unified, Real-Time Object DetectionJoseph Redmon, Santosh Divvala, Ross Girshick, and 1 morearXiv 1506.02640 · 14 claims · 0 with reviewed reproductions · 0 reports
- ZeRO: Memory Optimizations Toward Training Trillion Parameter ModelsSamyam Rajbhandari, Jeff Rasley, Olatunji Ruwase, and 1 morearXiv 1910.02054 · 21 claims · 0 with reviewed reproductions · 0 reports