Yuhuai Wu

Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization ICLR 2024 Magnushammer: A Transformer-Based Approach to Premise Selection ICLR 2024 REFACTOR: Learning to Extract Theorems from Proofs ICLR 2024 Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs ICLR 2023 Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search ICLR 2023 Focused Transformer: Contrastive Training for Context Scaling NeurIPS 2023 Lexinvariant Language Models NeurIPS 2023 Autoformalization with Large Language Models NeurIPS 2022 Block-Recurrent Transformers NeurIPS 2022 Exploring Length Generalization in Large Language Models NeurIPS 2022 Hierarchical Transformers Are More Efficient Language Models NAACL 2022 Insights into Pre-training via Simpler Synthetic Tasks NeurIPS 2022 Invariant Causal Representation Learning for Out-of-Distribution Generalization ICLR 2022 Memorizing Transformers ICLR 2022 Path Independent Equilibrium Models Can Better Exploit Test-Time Computation NeurIPS 2022 Proof Artifact Co-Training for Theorem Proving with Language Models ICLR 2022 Solving Quantitative Reasoning Problems with Language Models NeurIPS 2022 STaR: Bootstrapping Reasoning With Reasoning NeurIPS 2022 Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers NeurIPS 2022 Efficient Statistical Tests: A Neural Tangent Kernel Approach ICML 2021 INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving ICLR 2021 IsarStep: a Benchmark for High-level Mathematical Reasoning ICLR 2021 Learning Branching Heuristics for Propositional Model Counting AAAI 2021 LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning ICML 2021 Subgoal Search For Complex Reasoning Tasks NeurIPS 2021 OPtions as REsponses: Grounding behavioural hierarchies in multi-agent reinforcement learning ICML 2020 Backpropagation through the Void: Optimizing control variates for black-box gradient estimation ICLR 2018 The Importance of Sampling inMeta-Reinforcement Learning NeurIPS 2018 Understanding Short-Horizon Bias in Stochastic Meta-Optimization ICLR 2018 Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation NeurIPS 2017 Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference NeurIPS 2017 Architectural Complexity Measures of Recurrent Neural Networks NeurIPS 2016 On Multiplicative Integration with Recurrent Neural Networks NeurIPS 2016 Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations NeurIPS 2016