Zhengxi Lu

LZXzju

·

https://lll6gg.github.io/

lll6gg

AI & ML interests

None yet

Recent Activity

upvoted a paper 26 minutes ago

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

upvoted a paper about 3 hours ago

EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning

upvoted a paper about 5 hours ago

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

View all activity

Organizations

Papers 21

arxiv:2608.00782

arxiv:2607.28590

arxiv:2607.26784

arxiv:2607.14777

models 2

LZXzju/Qwen2.5-VL-3B-UI-R1-E

Visual Question Answering • 4B • Updated May 18, 2025 • 111 • 5

LZXzju/Qwen2.5-VL-3B-UI-R1

Visual Question Answering • 4B • Updated May 18, 2025 • 38 • 8

datasets 1

LZXzju/UI-R1-3B-Train

Viewer • Updated Apr 2, 2025 • 115 • 73 • 7