collaborators

6 papers

cs.CL2026

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…

cs.AI2026

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,…

cs.MA2026

Greedy-based Value Representation for Optimal Coordination in Multi-agent Reinforcement Learning

Lipeng Wan, Zeyang Liu, Xingyu Chen +2

Due to the representation limitation of the joint Q value function, multi-agent reinforcement learning methods with linear value decomposition (LVD) or monotonic value decompositio…

cs.AI2026

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…

cs.LG2025

MInCo: Mitigating Information Conflicts in Distracted Visual Model-based Reinforcement Learning

Shiguang Sun, Hanbo Zhang, Zeyang Liu +4

Existing visual model-based reinforcement learning (MBRL) algorithms with observation reconstruction often suffer from information conflicts, making it difficult to learn compact r…

cs.LG2025

Playing Non-Embedded Card-Based Games with Reinforcement Learning

Tianyang Wu, Lipeng Wan, Yuhang Wang +2

Significant progress has been made in AI for games, including board games, MOBA, and RTS games. However, complex agents are typically developed in an embedded manner, directly acce…