Yaolun Zhang's picture

Yaolun Zhang

Mercury7353

·

https://mercury7353.github.io/Yaolun-Zhang.github.io/

Mercury7353

AI & ML interests

Code LLM, LLM Agent, Multi-Agent System

Recent Activity

authored a paper 13 days ago

Live-Evo: Online Evolution of Agentic Memory from Continuous Feedback

authored a paper 14 days ago

EVA: Efficient Reinforcement Learning for End-to-End Video Agent

liked a model 14 days ago

WRHC/EfficientVideoAgent

View all activity

Organizations

authored a paper 13 days ago

Live-Evo: Online Evolution of Agentic Memory from Continuous Feedback

Paper • 2602.02369 • Published Feb 2

authored a paper 14 days ago

EVA: Efficient Reinforcement Learning for End-to-End Video Agent

Paper • 2603.22918 • Published 16 days ago • 43

submitted a paper to Daily Papers 14 days ago

EVA: Efficient Reinforcement Learning for End-to-End Video Agent

Paper • 2603.22918 • Published 16 days ago • 43

authored 2 papers 7 months ago

PyBench: Evaluating LLM Agent on various real-world coding tasks

Paper • 2407.16732 • Published Jul 23, 2024 • 1

ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding

Paper • 2508.21496 • Published Aug 29, 2025 • 55