Research

Working papers

  • Dake Bu, Xiajie Huang, Nana Liu, Atsushi Nitanda, Hau-San Wong, Qingfu Zhang. ASPBE: Automatic State Preparation and Block Encoding for Quantum Computing. [GitHub] [arXiv under Preparation]

  • Dake Bu, Ji Cheng, Bo Xue, Atsushi Nitanda, Hau-San Wong, Qingfu Zhang. ABRL: A Target-Faithful Autoformalization Harness and Lean 4 Library for Bandit and Reinforcement Learning Theory. [GitHub] [arXiv under Preparation]

Publications

  • Dake Bu, Ji Cheng, Huanjian Zhou, Andi Han, Zonghao Chen, Sinho Chewi, Matthew S. Zhang, Hau-San Wong, Qingfu Zhang, Atsushi Nitanda. An Automated Theorem Proving System and Visualized Lean Library for Sampling Theory, Optimisation and Geometry. (NeurIPS 2026 Workshop MATH-AI) [OpenReview] [GitHub] [Samplinglib]

  • Atsushi Nitanda, Dake Bu, Yueming Lyu, Tanya Veeravalli. Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation. (NeurIPS 2026) [arXiv] [code]

  • Dake Bu, Wei Huang, Andi Han, Hau-San Wong, Qingfu Zhang, Taiji Suzuki, and Atsushi Nitanda. DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Diffusion Language Models. (ICML 2026 FoGen Oral) [arXiv] [code]

  • Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Bo Xue, Qingfu Zhang, Hau-San Wong, and Taiji Suzuki. Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories. (ICML 2026 FoGen Spotlight) [arXiv] [code]

  • Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Qingfu Zhang, Hau-San Wong, and Taiji Suzuki. Provable Sample Efficiency of Curriculum Post-Training for Transformer Reasoning. (ICML 2026) [arXiv] [code]

  • Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Qingfu Zhang, Hau-San Wong, and Taiji Suzuki. Provable In-Context Vector Arithmetic via Retrieving Task Concepts. The 42nd International Conference on Machine Learning (ICML 2025). [arXiv] [code]

  • Bo Xue, Dake Bu, Ji Cheng, Yuanyu Wan, Qingfu Zhang. Multi-objective Linear Reinforcement Learning with Lexicographic Rewards. The 42nd International Conference on Machine Learning (ICML 2025). [openreview]

  • Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Taiji Suzuki, Qingfu Zhang, Hau-San Wong. Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning. Advances in Neural Information Processing Systems 37 (NeurIPS 2024). [arXiv] [code]

  • Dake Bu, Wei Huang, Taiji Suzuki, Ji Cheng, Qingfu Zhang, Zhiqiang Xu, Hau-San Wong. Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples. (ICML 2024) [arXiv] [code]