Zhi Zheng

zz1358m

·

https://zz1358m.github.io/zhizheng.github.io/

AI & ML interests

LLM reasoning, Trustworthy LLM, LLM application, Neural combinatorial optimization.

Recent Activity

liked a model 3 days ago

zz1358m/Qwen3.5-4B-MATH-ReAct-Agentic-ESOpt

upvoted a paper 4 days ago

Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements

updated a collection 4 days ago

Agentic-ESOpt Checkpoints Collection

View all activity

Organizations

liked a model 3 days ago

zz1358m/Qwen3.5-4B-MATH-ReAct-Agentic-ESOpt

Text Generation • 4B • Updated 12 days ago • 417 • 2

upvoted a paper 4 days ago

Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements

Paper • 2608.17310 • Published 5 days ago • 103

updated a collection 4 days ago

Agentic-ESOpt Checkpoints Collection

5 items • Updated 4 days ago • 1

authored a paper 4 days ago

Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements

Paper • 2608.17310 • Published 5 days ago • 103

submitted a paper to Daily Papers 4 days ago

Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements

Paper • 2608.17310 • Published 5 days ago • 103

updated 3 models 12 days ago

zz1358m/Qwen3.5-4B-MATH-ReAct-Agentic-ESOpt

Text Generation • 4B • Updated 12 days ago • 417 • 2

zz1358m/Qwen3.5-4B-DocVQA-ReAct-Agentic-ESOpt

Text Generation • 4B • Updated 12 days ago • 320

zz1358m/Qwen3.5-4B-Sudoku-Mask15-Agentic-ESOpt

Text Generation • 4B • Updated 12 days ago • 287

upvoted a collection 14 days ago

Agentic-ESOpt Checkpoints Collection

5 items • Updated 4 days ago • 1

updated a collection 14 days ago

SofT-GRPO

1 item • Updated 14 days ago

updated a model 14 days ago

zz1358m/Qwen3.5-27B-WebArena-Agentic-ESOpt

Text Generation • 27B • Updated 14 days ago • 157

updated a collection 14 days ago

Agentic-ESOpt Checkpoints Collection

5 items • Updated 4 days ago • 1

published 4 models 14 days ago

zz1358m/Qwen3.5-4B-DocVQA-ReAct-Agentic-ESOpt

Text Generation • 4B • Updated 12 days ago • 320

zz1358m/Qwen3.5-4B-MATH-ReAct-Agentic-ESOpt

Text Generation • 4B • Updated 12 days ago • 417 • 2

zz1358m/Qwen3.5-27B-WebArena-Agentic-ESOpt

Text Generation • 27B • Updated 14 days ago • 157

zz1358m/Qwen3.5-4B-Sudoku-Mask15-Agentic-ESOpt

Text Generation • 4B • Updated 12 days ago • 287

upvoted a paper 2 months ago

Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR

Paper • 2605.19282 • Published May 19 • 9