🤝 Open to Collab

Yuyang Bai

yuyangbai

8

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight

upvoted a paper about 1 month ago

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

upvoted a paper 4 months ago

Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism

View all activity

Organizations

Collections 1

models 5

yuyangbai/graphdancer-dpo-iter1-seed167

Text Generation • 3B • Updated May 8 • 11

yuyangbai/GraphDancer-grpo-curriculum-200steps

3B • Updated Feb 20 • 10

yuyangbai/GraphDancer-Qwen2.5-3B-Instruct-Curriculum-PPO

3B • Updated Jan 24 • 8

yuyangbai/GraphDancer-Qwen2.5-3B-Instruct-Vanilla-PPO

3B • Updated Jan 24 • 13

yuyangbai/Qwen2.5-3B-Iterative-SFT-SearchR1-nq_trained-ppo

3B • Updated Dec 2, 2025 • 10

datasets 2

yuyangbai/GRBench-copy

Updated Feb 17 • 576 • 1

yuyangbai/GraphDancer-data

Viewer • Updated Jan 25 • 1.69k • 26