Research

Working papers

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

Publications

  • 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. (ICML2026 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. (ICML2026 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 (ICML2026). [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 (ICML2025). [arXiv]

  • 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 (ICML2025). [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]

  • Dake Bu, Wei Huang, Taiji Suzuki, Ji Cheng, Qingfu Zhang, Zhiqiang Xu, Hau-San Wong: Provably Neural Active Learning SucceedsviaPrioritizing Perplexing Samples (ICML2024). [arXiv]