Kai Yang's picture

Kai Yang

yangkaiSIGS

·

https://yk7333.github.io/

yk7333

AI & ML interests

None yet

Recent Activity

upvoted a paper about 14 hours ago

Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models

upvoted a paper about 14 hours ago

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

upvoted a paper 27 days ago

ProAct: Agentic Lookahead in Interactive Environments

View all activity

Organizations

Papers 10

arxiv:2511.15248

arxiv:2509.26226

arxiv:2505.11044

arxiv:2412.15517

spaces 1

Entropic

Display research findings on EntroPIC for LLM training

models 1

yangkaiSIGS/EntroPIC-Nemotron-1.5b

Text Generation • 2B • Updated 30 days ago • 13 • 1

datasets 1

yangkaiSIGS/d3po_datasets

Viewer • Updated Mar 19, 2024 • 1.2k • 23 • 5