3-day current streak·18-day longest streak
Hi, this is Xiaozhe. (Homepage) I am currently a PhD student at the School of Computer Science and Technology, Tongji University. I am currently an intern at Tencent, focusing on…
Hi, this is Xiaozhe. (Homepage)
I am currently a PhD student at the School of Computer Science and Technology, Tongji University. I am currently an intern at Tencent, focusing on post-training for coding and computer-use agents. Previously, I interned with the Post-Training Group of the OpenLM team at Shanghai AI Lab (January 2025 – Jul 2026, focusing on (V)LLMs/agentic evaluation and post-training. If you are interested in collaboration, please feel free to reach out to me.
-
VLMEvalKit ★ PINNED ⑂
Open-source evaluation toolkit of large vision-language models (LVLMs), support 160+ VLMs, 50+ benchmarks
Python ★ 1 4mo agoExplain → -
OPT-BENCH ★ PINNED
[ACL 2026] OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces
Python ★ 126 2mo agoExplain → -
NP-Engine ★ PINNED
[ACL 2026] Official implement on 'Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs'
Python ★ 55 1mo agoExplain → -
SERL ★ PINNED
Official implement on 'What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents'
Python ★ 68 22d agoExplain → -
DMPO ★ PINNED
[ICML 2026] Official implement on 'Beyond Mode Collapse: Distribution Matching for Diverse Reasoning'
Python ★ 45 1mo agoExplain → -
InternBootcamp ★ PINNED ⑂
No description.
★ 1 10mo agoExplain → -
COINBench
No description.
Python ★ 2 9mo agoExplain → -
OliverLeeXZ
No description.
★ 1 8d agoExplain → -
OliverLeeXZ.github.io
No description.
CSS ★ 1 1mo agoExplain → -
Cinemadiff.github.io
No description.
★ 1 1y agoExplain → -
OpenClaw-RL ⑂
OpenClaw-RL: Train any agent simply by talking
Python ★ 1 3mo agoExplain → -
verl ⑂
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
★ 1 1mo agoExplain → -
verl-recipe ⑂
A set of examples based on verl for end-to-end RL training recipes.
★ 0 1mo agoExplain →
No repos match these filters.