Yu Zeng's picture

Open to Collab

Yu Zeng

YuZeng260

·

https://scholar.google.com/citations?user=XJmAr8EAAAAJ&hl=en&oi=sra

AI & ML interests

VLMs, LLMs, RL, Agent, Reasoning

Recent Activity

upvoted a paper about 15 hours ago

Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning

liked a Space 9 days ago

HuggingFaceH4/on-policy-distillation

upvoted a paper 13 days ago

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

View all activity

Organizations

Papers 11

arxiv:2602.12735

arxiv:2602.10224

arxiv:2602.02185

arxiv:2601.22060

models 0

None public yet

datasets 1

YuZeng260/AGILE

Preview • Updated Sep 30, 2025 • 6 • 1