Yu-Huai Wu

Most-cited papers

On the Opportunities and Risks of Foundation Models
Rishi Bommasani, Drew A. Hudson, E. Adeli, R. Altman +110 more
2021arXiv.org7,623 citations
Semantic Scholar
Grandmaster level in StarCraft II using multi-agent reinforcement learning
O. Vinyals, Igor Babuschkin, W. Czarnecki, Michaël Mathieu +38 more
2019Nature4,581 citations
Semantic Scholar
Holistic Evaluation of Language Models
Percy Liang, Rishi Bommasani, Tony Lee, Dimitris Tsipras +46 more
2023Trans. Mach. Learn. Res.2,197 citations Open access
Semantic Scholar
Solving Quantitative Reasoning Problems with Language Models
Aitor Lewkowycz, Anders Andreassen, David Dohan, Ethan Dyer +10 more
2022Neural Information Processing Systems2,095 citations Open access
Semantic Scholar
PaLM 2 Technical Report
Rohan Anil, Andrew M. Dai, O. Firat, Melvin Johnson +124 more
2023arXiv.org1,569 citations
Semantic Scholar
STaR: Bootstrapping Reasoning With Reasoning
E. Zelikman, Yu-Huai Wu, Jesse Mu, Noah D. Goodman
20221,191 citations
Semantic Scholar
Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
Yu-Huai Wu, Elman Mansimov, R. Grosse, Shun Liao +1 more
2017Neural Information Processing Systems682 citations
Semantic Scholar
Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
Albert Qiaochu Jiang, S. Welleck, Jin-Peng Zhou, Timothée Lacroix +5 more
2022International Conference on Learning Representations385 citations Open access
Semantic Scholar
Autoformalization with Large Language Models
Yu-Huai Wu, Albert Qiaochu Jiang, Wenda Li, M. Rabe +3 more
2022Neural Information Processing Systems380 citations Open access
Semantic Scholar
Backpropagation through the Void: Optimizing control variates for black-box gradient estimation
Will Grathwohl, Da-Mi Choi, Yu-Huai Wu, Geoffrey Roeder +1 more
2017International Conference on Learning Representations324 citations
Semantic Scholar
Memorizing Transformers
Yu-Huai Wu, M. Rabe, DeLesley S. Hutchins, C. Szegedy
2022International Conference on Learning Representations281 citations Open access
Semantic Scholar
Exploring Length Generalization in Large Language Models
Cem Anil, Yu-Huai Wu, Anders Andreassen, Aitor Lewkowycz +6 more
2022Neural Information Processing Systems270 citations Open access
Semantic Scholar
Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference
Geoffrey Roeder, Yu-Huai Wu, D. Duvenaud
2017Neural Information Processing Systems230 citations
Semantic Scholar
On the Quantitative Analysis of Decoder-Based Generative Models
Yu-Huai Wu, Yuri Burda, R. Salakhutdinov, R. Grosse
2016International Conference on Learning Representations227 citations
Semantic Scholar
Focused Transformer: Contrastive Training for Context Scaling
Szymon Tworkowski, Konrad Staniszewski, Mikolaj Pacek, Yu-Huai Wu +2 more
2023Neural Information Processing Systems190 citations Open access
Semantic Scholar
Proof Artifact Co-training for Theorem Proving with Language Models
Jesse Michael Han, Jason M. Rute, Yu-Huai Wu, Edward W. Ayers +1 more
2021International Conference on Learning Representations181 citations
Semantic Scholar
Block-Recurrent Transformers
DeLesley S. Hutchins, Imanol Schlag, Yu-Huai Wu, Ethan Dyer +1 more
2022Neural Information Processing Systems168 citations Open access
Semantic Scholar
On Multiplicative Integration with Recurrent Neural Networks
Yu-Huai Wu, Sai-Zheng Zhang, Y. Zhang, Yoshua Bengio +1 more
2016Neural Information Processing Systems167 citations
Semantic Scholar
Architectural Complexity Measures of Recurrent Neural Networks
Sai-Zheng Zhang, Yu-Huai Wu, Tong Che, Zhouhan Lin +3 more
2016Neural Information Processing Systems164 citations
Semantic Scholar
Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers
Albert Qiaochu Jiang, Wenda Li, Szymon Tworkowski, K. Czechowski +4 more
2022Neural Information Processing Systems160 citations Open access
Semantic Scholar
Understanding Short-Horizon Bias in Stochastic Meta-Optimization
Yu-Huai Wu, Mengye Ren, Renjie Liao, R. Grosse
2018International Conference on Learning Representations150 citations
Semantic Scholar
Invariant Causal Representation Learning for Out-of-Distribution Generalization
Chaochao Lu, Yu-Huai Wu, José Miguel Hernández-Lobato, B. Schölkopf
2022International Conference on Learning Representations136 citations
Semantic Scholar
Hierarchical Transformers Are More Efficient Language Models
Piotr Nawrot, Szymon Tworkowski, Michał Tyrolski, Lukasz Kaiser +3 more
2021NAACL-HLT133 citations Open access
Semantic Scholar
Some Considerations on Learning to Explore via Meta-Reinforcement Learning
Bradly C. Stadie, Ge Yang, Rein Houthooft, Xi Chen +4 more
2018International Conference on Learning Representations132 citations
Semantic Scholar
Evaluating language models for mathematics through interactions
Katherine M. Collins, Albert Qiaochu Jiang, Simon Frieder, Lionel Wong +10 more
2023Proceedings of the National Academy of Sciences of the United States of America128 citations Open access
Semantic Scholar
Language Model Cascades
David Dohan, Winnie Xu, Aitor Lewkowycz, Jacob Austin +8 more
2022arXiv.org127 citations Open access
Semantic Scholar
STDP-Compatible Approximation of Backpropagation in an Energy-Based Model
Yoshua Bengio, Thomas Mesnard, Asja Fischer, Sai-Zheng Zhang +1 more
2017Neural Computation94 citations
Semantic Scholar
The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning
Yu-Huai Wu, Hong-Hua Dong, R. Grosse, Jimmy Ba
2020arXiv.org81 citations
Semantic Scholar
Magnushammer: A Transformer-based Approach to Premise Selection
Maciej Mikuła, Szymon Tworkowski, Szymon Antoniak, Bartosz Piotrowski +6 more
2023International Conference on Learning Representations76 citations Open access
Semantic Scholar
LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning
Yu-Huai Wu, M. Rabe, Wenda Li, Jimmy Ba +2 more
2021International Conference on Machine Learning73 citations
Semantic Scholar
IsarStep: a Benchmark for High-level Mathematical Reasoning
Wenda Li, Lei Yu, Yu-Huai Wu, Lawrence Charles Paulson
2021International Conference on Learning Representations72 citations
Semantic Scholar
Length Generalization in Arithmetic Transformers
Samy Jelassi, Stéphane d'Ascoli, Carles Domingo-Enrich, Yu-Huai Wu +2 more
2023arXiv.org63 citations Open access
Semantic Scholar
Nonlinear Invariant Risk Minimization: A Causal Approach
Chaochao Lu, Yu-Huai Wu, José Miguel Hernández-Lobato, B. Schölkopf
2021arXiv.org60 citations
Semantic Scholar
INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving
Yu-Huai Wu, Albert Qiaochu Jiang, Jimmy Ba, R. Grosse
2020International Conference on Learning Representations60 citations
Semantic Scholar
Path Independent Equilibrium Models Can Better Exploit Test-Time Computation
Cem Anil, A. Pokle, Kaiqu Liang, Johannes Treutlein +4 more
2022Neural Information Processing Systems49 citations Open access
Semantic Scholar
STDP as presynaptic activity times rate of change of postsynaptic activity
Yoshua Bengio, Thomas Mesnard, Asja Fischer, Sai-Zheng Zhang +1 more
201549 citations
Semantic Scholar
OPtions as REsponses: Grounding behavioural hierarchies in multi-agent reinforcement learning
A. Vezhnevets, Yu-Huai Wu, Maria K. Eckstein, R. Leblond +1 more
2020International Conference on Machine Learning48 citations
Semantic Scholar
Subgoal Search For Complex Reasoning Tasks
K. Czechowski, Tomasz Odrzyg'o'zd'z, Marek Zbysinski, Michał Zawalski +4 more
2021Neural Information Processing Systems41 citations
Semantic Scholar
ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement Learning
Harris Chan, Yu-Huai Wu, J. Kiros, S. Fidler +1 more
2019arXiv.org37 citations
Semantic Scholar
Learning to Give Checkable Answers with Prover-Verifier Games
Cem Anil, Guodong Zhang, Yu-Huai Wu, R. Grosse
2021arXiv.org34 citations
Semantic Scholar
Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations
Behnam Neyshabur, Yu-Huai Wu, R. Salakhutdinov, N. Srebro
2016Neural Information Processing Systems32 citations
Semantic Scholar
Insights into Pre-training via Simpler Synthetic Tasks
Yu-Huai Wu, Felix Li, Percy Liang
2022Neural Information Processing Systems30 citations Open access
Semantic Scholar
Sticking the Landing: An Asymptotically Zero-Variance Gradient Estimator for Variational Inference
Geoffrey Roeder, Yu-Huai Wu, D. Duvenaud
2017arXiv.org24 citations
Semantic Scholar
The Importance of Sampling inMeta-Reinforcement Learning
Bradly C. Stadie, Ge Yang, Rein Houthooft, Xi Chen +4 more
2018Neural Information Processing Systems23 citations
Semantic Scholar
Options as responses: Grounding behavioural hierarchies in multi-agent RL
A. Vezhnevets, Yu-Huai Wu, R. Leblond, J. Leibo
2019arXiv.org19 citations
Semantic Scholar
Concurrent Meta Reinforcement Learning
Emilio Parisotto, Soham Ghosh, S. Yalamanchi, Varsha Chinnaobireddy +2 more
2019arXiv.org18 citations
Semantic Scholar
Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search
Michał Zawalski, Michał Tyrolski, K. Czechowski, Damian Stachura +5 more
2022International Conference on Learning Representations15 citations Open access
Semantic Scholar
Learning Branching Heuristics for Propositional Model Counting
Pashootan Vaezipoor, Gil Lederman, Yu-Huai Wu, Chris J. Maddison +4 more
2020AAAI Conference on Artificial Intelligence14 citations Open access
Semantic Scholar
Formal Premise Selection With Language Models
Szymon Tworkowski, Maciej Miku la, Tomasz Odrzyg'o'zd'z, K. Czechowski +6 more
202211 citations
Semantic Scholar
Efficient Statistical Tests: A Neural Tangent Kernel Approach
Sheng Jia, E. Nezhadarya, Yu-Huai Wu, Jimmy Ba
2021International Conference on Machine Learning10 citations
Semantic Scholar