Siyuan Huang

chamber111's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 20 hours ago

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

Paper • 2511.20549 • Published 8 days ago • 22

upvoted 2 papers 15 days ago

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

Paper • 2511.13704 • Published 15 days ago • 42

P1: Mastering Physics Olympiads with Reinforcement Learning

Paper • 2511.13612 • Published 16 days ago • 131

upvoted a paper 21 days ago

VideoSSR: Video Self-Supervised Reinforcement Learning

Paper • 2511.06281 • Published 24 days ago • 24

upvoted a paper 30 days ago

ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning

Paper • 2510.27492 • Published Oct 30 • 80

upvoted 2 collections about 2 months ago

VPPO Data

Collection

Official training and evaluation datasets for the VPPO project. • 4 items • Updated Oct 13 • 3

VPPO Model

Collection

SOTA models for multimodal reasoning, fine-tuned with VPPO. Achieves superior performance by focusing on critical visual tokens. • 4 items • Updated 26 days ago • 4

upvoted 2 papers about 2 months ago

Spotlight on Token Perception for Multimodal Reinforcement Learning

Paper • 2510.09285 • Published Oct 10 • 36

Native Hybrid Attention for Efficient Sequence Modeling

Paper • 2510.07019 • Published Oct 8 • 16

upvoted a paper 2 months ago

Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration

Paper • 2509.14760 • Published Sep 18 • 53

upvoted a paper 4 months ago

Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

Paper • 2508.09834 • Published Aug 13 • 53