qingyang zhang's picture

qingyang zhang

qingyangzhang

·

https://qingyangzhang.github.io

AI & ML interests

LLM Reasoning

Recent Activity

upvoted a paper 6 days ago

Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows

authored a paper 16 days ago

P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads

authored a paper 16 days ago

TEMPO: Scaling Test-time Training for Large Reasoning Models

View all activity

Organizations

None yet

authored 2 papers 16 days ago

P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads

Paper • 2602.09443 • Published Feb 10 • 59

TEMPO: Scaling Test-time Training for Large Reasoning Models

Paper • 2604.19295 • Published 17 days ago • 34

submitted a paper to Daily Papers 16 days ago

TEMPO: Scaling Test-time Training for Large Reasoning Models

Paper • 2604.19295 • Published 17 days ago • 34

authored a paper 6 months ago

P1: Mastering Physics Olympiads with Reinforcement Learning

Paper • 2511.13612 • Published Nov 17, 2025 • 134

authored a paper 7 months ago

Provable Dynamic Fusion for Low-Quality Multimodal Data

Paper • 2306.02050 • Published Jun 3, 2023

authored a paper 12 months ago

Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization

Paper • 2504.05812 • Published Apr 8, 2025 • 3