6 citations · 11 across the 14 of their papers we have counts for
4 papers · 1 filter
Hesitation-Aware On-Policy Distillation for Diffusion Language Models
Jianguo Huang, Lipeng Wan, Yanchen Deng +1
Diffusion large language models (dLLMs) generate text by iterative unmasking. At each denoising step, a dLLM proposes a token at every masked position, but the decoder commits only…
GeoBlock: Inferring Block Granularity from Dependency Geometry in Diffusion Language Models
Lipeng Wan, Junjie Ma, Jianhui Gu +3
Block diffusion enables efficient parallel refinement in diffusion language models, but its decoding behavior depends critically on block size. Existing block-sizing strategies rel…
Progressive Refinement Regulation for Accelerating Diffusion Language Model Decoding
Lipeng Wan, Jianhui Gu, Junjie Ma +4
Diffusion language models generate text through iterative denoising under a uniform refinement rule applied to all tokens. However, tokens stabilize at different rates in practice,…
Task-Aware Exploration via a Predictive Bisimulation Metric
Dayang Liang, Ruihan Liu, Lipeng Wan +2
Accelerating exploration in visual reinforcement learning under sparse rewards remains challenging due to the substantial task-irrelevant variations. Despite advances in intrinsic…