Siyuan Huang's picture

4 11 6

Siyuan Huang

chamber111

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 26 days ago

Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning

upvoted a paper about 1 month ago

TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models

upvoted a paper about 1 month ago

P1: Mastering Physics Olympiads with Reinforcement Learning

View all activity

Organizations

authored 3 papers 2 months ago

Spotlight on Token Perception for Multimodal Reinforcement Learning

Paper • 2510.09285 • Published Oct 10 • 36

FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting

Paper • 2509.24304 • Published Sep 29 • 4

Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding

Paper • 2503.01422 • Published Mar 3