On the Off-Policy Teacher in On-Policy Distillation
Paper • 2609.38360 • Published • 16
Huang's INTelligence lab
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
shrango
submitted a
paper to Daily Papers 1 day ago
ChengsongHuang
authored a
paper 9 days ago
ChengsongHuang
authored 6
papers 10 days ago
Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling
Paper • 2606.03102 • Published • 14
MoCo: A One-Stop Shop for Model Collaboration Research
Paper • 2601.21257 • Published
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
Paper • 2605.21468 • Published • 51
Process Rewards with Learned Reliability
Paper • 2605.15529 • Published • 52
G-Zero: Self-Play for Open-Ended Generation from Zero Data
Paper • 2605.09959 • Published • 18
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
Paper • 2605.08083 • Published • 71
ChengsongHuang
submitted a
paper to Daily Papers 28 days ago
ChengsongHuang
authored a
paper about 1 month ago
jinyuan222
authored 2
papers 3 months ago
ChengsongHuang
submitted a
paper to Daily Papers 4 months ago
jinyuan222
submitted a
paper to Daily Papers 5 months ago
teapot123
authored 6
papers 5 months ago
Generating Training Data with Language Models: Towards Zero-Shot Language Understanding
Paper • 2202.04538 • Published
Efficient Test-Time Scaling via Self-Calibration
Paper • 2503.00031 • Published • 15
CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation
Paper • 2504.00043 • Published • 10
POSS: Position Specialist Generates Better Draft for Speculative Decoding
Paper • 2506.03566 • Published • 6
R-Zero: Self-Evolving Reasoning LLM from Zero Data
Paper • 2508.05004 • Published • 135
VisPlay: Self-Evolving Vision-Language Models from Images
Paper • 2511.15661 • Published • 45