Zeng

YimingZeng

·

AI & ML interests

Efficient ML, Code LLM, Diffusion LLM, LLM4NLP

Recent Activity

authored a paper 1 day ago

Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry

authored a paper 1 day ago

FineEdit: Unlock Instruction-Based Text Editing for LLMs

authored a paper 1 day ago

TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces

View all activity

Organizations

upvoted a paper 2 days ago

MoEGen: Mixture-of-Experts for Instance-Adaptive LoRA Generation

Paper • 2608.03275 • Published 4 days ago • 1

upvoted a paper 3 days ago

InternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data

Paper • 2609.31394 • Published 8 days ago • 28

upvoted a paper 4 days ago

TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces

Paper • 2609.33295 • Published 6 days ago • 69

upvoted a paper about 1 year ago

FineEdit: Unlock Instruction-Based Text Editing for LLMs

Paper • 2502.13358 • Published Feb 19, 2025 • 1