Publication

    (Google Scholar)


    2023

  1. ICLR

    Oral

    Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs

    Albert Qiaochu Jiang*, Sean Welleck*, Jin Peng Zhou*, Timothee Lacroix, Jiacheng Liu, Wenda Li,
    Mateja Jamnik, Guillaume Lample, Yuhuai Wu

    The 10th International Conference on Learning Representations, 2023.

    PDF
  2. ICLR

    Oral

    Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search.

    Michał Zawalski, Michał Tyrolski, Konrad Czechowski, Damian Stachura, Piotr Piękos,
    Tomasz Odrzygóźdź, Yuhuai Wu, Łukasz Kuciński, Piotr Miłoś

    The 10th International Conference on Learning Representations, 2023.

    PDF
  3. 2022

  4. NeurIPS

    Minerva: Solving Quantitative Reasoning Problems with Language Models

    Aitor Lewkowycz, Anders Andreassen, David Dohan, Ethan Dyer, Henryk Michalewski,
    Vinay Ramasesh, Ambrose Slone, Cem Anil, Imanol Schlag, Theo Gutman-Solo,
    Yuhuai Wu, Behnam Neyshabur, Guy Gur-Ari, Vedant Misra

    The 36th Conference on Neural Information Processing Systems, 2022.

    PDF Google AI Blog
  5. NeurIPS

    Insights into Pre-training via Simpler Synthetic Tasks

    Yuhuai Wu*, Felix Li*, Percy Liang

    The 36th Conference on Neural Information Processing Systems, 2022.

    PDF
  6. NeurIPS

    Autoformalization with Large Language Models.

    Yuhuai Wu, Albert Q. Jiang, Wenda Li, Markus Rabe, Charles Staats, Mateja Jamnik, Christian Szegedy

    The 36th Conference on Neural Information Processing Systems, 2022.

    PDF Interview with NewScientist
  7. NeurIPS

    Oral

    Exploring Length Generalization in Large Language Models

    Cem Anil, Yuhuai Wu, Anders Andreassen, Aitor Lewkowycz, Vedant Misra,
    Vinay Ramasesh, Ambrose Slone, Guy Gur-Ari, Ethan Dyer, Behnam Neyshabur

    The 36th Conference on Neural Information Processing Systems, 2022.

    PDF
  8. NeurIPS

    Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers.

    Albert Q. Jiang, Wenda Li, Szymon Tworkowski, Konrad Czechowski, Tomasz Odrzygóźdź, Piotr Miłoś,

    Yuhuai Wu, Mateja Jamnik

    The 36th Conference on Neural Information Processing Systems, 2022.

    PDF
  9. NeurIPS

    STaR: Bootstrapping Reasoning With Reasoning.

    Eric Zelikman*, Yuhuai Wu*, Noah D. Goodman

    The 36th Conference on Neural Information Processing Systems, 2022.

    PDF
  10. NeurIPS

    Block-Recurrent Transformers.

    DeLesley Hutchins*, Imanol Schlag*, Yuhuai Wu, Ethan Dyer, Behnam Neyshabur

    The 36th Conference on Neural Information Processing Systems, 2022.

    PDF
  11. ICML

    Workshop

    Language Model Cascades.

    David Dohan, Winnie Xu, Aitor Lewkowycz, Jacob Austin, David Bieber,
    Raphael Gontijo Lopes, Yuhuai Wu, Henryk Michalewski, Rif A. Saurous,
    Jascha Sohl-dickstein, Kevin Murphy, Charles Sutton

    Beyond Bayes: Paths Towards Universal Reasoning Systems, ICML, 2022.

    PDF
  12. Findings of NAACL

    Hierarchical Transformers Are More Efficient Language Models.

    Piotr Nawrot, Szymon Tworkowski, Michał Tyrolski, Łukasz Kaiser, Yuhuai Wu, Christian Szegedy, Henryk Michalewski


    PDF
  13. ICLR

    Spotlight

    Memorizing Transformers.

    Yuhuai Wu, Markus Rabe, DeLesley Hutchins, Christian Szegedy

    The 10th International Conference on Learning Representations, 2022.

    PDF #4 on HackerNews
  14. ICLR

    Proof Artifact Co-training for Theorem Proving with Language Model.

    Jesse Michael Han, Jason Rute, Yuhuai Wu, Edward W. Ayers, Stanislas Polu

    The 10th International Conference on Learning Representations, 2022.

    PDF
  15. ICLR

    Nonlinear Invariant Risk Minimization: A Causal Approach.

    Chaochao Lu, Yuhuai Wu, Jose Miguel Hernandez-Lobato, Bernhard Scholkopf


    The 10th International Conference on Learning Representations, 2022.

    PDF



  16. 2021

  17. arXiv

    On the Opportunities and Risks of Foundation Models.

    Rishi Bommasani, Drew A. Hudson, Percy Liang et. al.


    PDF
  18. NeurIPS

    Subgoal Search For Complex Reasoning Tasks.

    Konrad Czechowski, Tomasz Odrzygozdz, Marek Zbysinski, Michal Zawalski,
    Krzysztof Olejnik, Yuhuai Wu, Lukasz Kucinski, Piotr Miłoś

    The 35th Conference on Neural Information Processing Systems, 2021.

    PDF
  19. arXiv'21

    Learning to Give Checkable Answers with Prover-Verifier Games.

    Cem Anil, Guodong Zhang, Yuhuai Wu, Roger Grosse

    2021

    PDF
  20. NeurIPS

    Workshop

    Learning Neural Discrete Reaction Classes to Improve Retrosynthesis.

    Théophile Gaudin, Yuhuai Wu, Robert Pollice, Animesh Garg, Alán Aspuru-Guzik

    Machine Learning and the Physical Sciences, NeurIPS 2021

    PDF
  21. ICML

    LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning.

    Yuhuai Wu, Markus Rabe, Wenda Li, Jimmy Ba, Roger Grosse, Christian Szegedy

    The 38th International Conference on Machine Learning, 2021.

    PDF
  22. ICML

    Efficient Statistical Tests: A Neural Tangent Kernel Approach.

    Sheng Jia, Ehsan Nezhadarya, Yuhuai Wu, Jimmy Ba

    The 38th International Conference on Machine Learning, 2021.

    PDF
  23. ICML

    Workshop

    Out-of-Distribution Generalization with Deep Equilibrium Models.

    Cem Anil, Kaiqu Liang, Yuhuai Wu, Roger Grosse

    Uncertainty and Robustness in Deep Learning, ICML 2021.

    PDF
  24. ICLR

    INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving.

    Yuhuai Wu*, Albert Q. Jiang*, Jimmy Ba, Roger Grosse

    The 9th International Conference on Learning Representations, 2021.

    PDF
  25. ICLR

    Modelling High-Level Mathematical Reasoning in Mechanised Declarative Proofs.

    Wenda Li, Lei Yu, Yuhuai Wu, Lawrence C. Paulson

    The 9th International Conference on Learning Representations, 2021.

    PDF
  26. ICLR

    Workshop

    REFACTOR: Learning to Extract Theorems from Proofs.

    Jin Peng Zhou, Yuhuai Wu, Colin Li, Roger Grosse

    The Role of Mathematical Reasoning in General Artificial Intelligence, ICLR 2021.

    PDF
  27. AAAI

    Learning Branching Heuristics for Propositional Model Counting.

    Pashootan Vaezipoor*, Gil Lederman*, Yuhuai Wu, Chris J. Maddison, Roger Grosse, Edward Lee, Sanjit A. Seshia, Fahiem Bacchus.

    The 35th AAAI Conference on Artificial Intelligence, 2021.

    PDF
  28. AITP

    LISA: Language models of ISAbelle Proofs.

    Albert Q. Jiang, Wenda Li, Jesse Michael Han, Yuhuai Wu

    The 6th Conference on Artificial Intelligence and Theorem Proving, 2021.

    PDF
  29. AITP

    Latent Action Space for Efficient Planning in Theorem Proving.

    Minchao Wu*, Yuhuai Wu*

    The 6th Conference on Artificial Intelligence and Theorem Proving, 2021.

    PDF



  30. 2020

  31. arXiv

    The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning.

    Yuhuai Wu*, Honghua Dong*, Roger Grosse, Jimmy Ba


    PDF
  32. ICML

    Options as REsponses: Grounding Behavioural Hierarchies in Multi-agent Reinforcement Learning.

    Yuhuai Wu*, Alexander Sasha Vezhnevets*, Maria Eckstein, Remi Leblond, Joel Z. Leibo.

    The 37th International Conference on Machine Learning, 2020.

    PDF
  33. AITP

    Neural Theorem Proving on Inequality Problems.

    Yuhuai Wu*, Albert Q. Jiang*, Roger Grosse, Jimmy Ba

    The 5th Conference on Artificial Intelligence and Theorem Proving, 2020.

    PDF
  34. AITP

    Learning Clause Deletion Heuristics with Reinforcement Learning.

    Pashootan Vaezipoor, Gil Lederman, Yuhuai Wu, Albert Q. Jiang, Roger Grosse, Fahiem Bacchus

    The 5th Conference on Artificial Intelligence and Theorem Proving, 2020.

    PDF
  35. DCG (Journal)

    Discrete Equidecomposability and Ehrhart Theory of Polygons.

    Paxton Turner, Yuhuai Wu

    Discrete & Computational Geometry, 2020.

    PDF



  36. 2019

  37. Nature

    Grandmaster Level in StarCraft II using Multi-gent Reinforcement Learning.

    Vinyals, O., Babuschkin, I., Czarnecki, W.M. et al.

    Nature, 2019.

    PDF
  38. arXiv

    Concurrent Meta Reinforcement Learning.

    Emilio Parisotto, Soham Ghosh, Sai Bhargav Yalamanchi, Varsha Chinnaobireddy,Yuhuai Wu*, Ruslan Salakhutdinov


    PDF



  39. 2018

  40. arXiv

    An Empirical Analysis of Proximal Policy Optimization with Kronecker-factored Natural Gradients.

    Jiaming Song, Yuhuai Wu


    PDF
  41. NeurIPS

    The Importance of Sampling in Meta-Reinforcement Learning.

    Bradly Stadie, Ge Yang, Rein Houthooft, Xi Chen, Yan Duan, Yuhuai Wu, Pieter Abbeel, Ilya Sutskever

    The 32nd Conference on Neural Information Processing Systems, 2018.

    PDF
  42. ICLR

    Understanding Short-Horizon Bias in Stochastic Meta-Optimization.

    Yuhuai Wu*, Mengye Ren*, Renjie Liao, Roger Grosse

    The 6th International Conference on Learning Representations, 2018.

    PDF
  43. ICLR

    Backpropagation through the Void: Optimizing Control Variates for Black-Box Gradient Estimation.

    Will Grathwohl, Dami Choi, Yuhuai Wu, Geoffrey Roeder David Duvenaud

    The 6th International Conference on Learning Representations, 2018.

    PDF
  44. ICML

    Workshop

    ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement Learning.

    Yuhuai Wu*, Harris Chan*, Jamie Kiros, Sanja Fidler, Jimmy Ba


    Goal Specifications for Reinforcement Learning, ICML 2018.

    PDF



  45. 2017

  46. NeurIPS

    Spotlight

    Scalable Trust-Region Method for Deep Reinforcement Learning using Kronecker-Factored Approximation.

    Yuhuai Wu*, Elman Mansimov*, Shun Liao, Roger Grosse, Jimmy Ba

    The 31st Annual Conference on Neural Information Processing Systems, 2017

    PDF
  47. NeurIPS

    Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference.

    Geoffrey Roeder, Yuhuai Wu, David Duvenaud

    The 31st Annual Conference on Neural Information Processing Systems, 2017

    PDF
  48. ICLR

    On the Quantitative Analysis of Decoder-Based Generative Models

    Yuhuai Wu, Yuri Burda, Ruslan Salakhutdinov, Roger Grosse

    The 5th International Conference on Learning Representations, 2017

    PDF
  49. Neural Computation

    STDP Based Approximation of Back-Propagation in an Energy Based Model

    Yoshua Bengio, Thomas Mesnard, Asja Fischer, Saizheng Zhang, Yuhuai Wu

    Neural computation, 2017

    PDF



  50. 2016

  51. NeurIPS

    On Multiplicative Integration with Recurrent Neural Networks.

    Yuhuai Wu*, Saizheng Zhang*, Ying Zhang, Yoshua Bengio, Ruslan Salakhutdinov

    The 30th Annual Conference on Neural Information Processing Systems, 2016

    PDF
  52. NeurIPS

    Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations.

    Yuhuai Wu*, Behnam Neyshabur*, Ruslan Salakhutdinov, Nathan Srebro

    The 30th Annual Conference on Neural Information Processing Systems, 2016

    PDF
  53. NeurIPS

    Architectural Complexity Measures of Recurrent Neural Networks.

    Saizheng Zhang*, Yuhuai Wu*, Tong Che, Zhouhan Lin, Roland Memisevic, Ruslan Salakhutdinov, Yoshua Bengio

    The 30th Annual Conference on Neural Information Processing Systems, 2016

    PDF



  54. 2014

  55. arXiv

    Conditions for Discrete Equidecomposability of Polygons.

    Paxton Turner, Yuhuai Wu

    PDF