arxiv:2608.22274
Yan Zhan
YanZhanPKU
ยท
AI & ML interests
LLM
Recent Activity
upvoted a paper 21 days ago
RefineSVG: Visual Feedback-Driven Reinforcement Learning for Image-to-SVG Generation upvoted a paper about 1 month ago
TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward Models submitted a paper about 1 month ago
Length-Adaptive Decoding for Masked Diffusion Machine TranslationOrganizations
None yet
