Siyuan Huang

chamber111's activity

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

upvoted 2 papers 4 days ago

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

Paper • 2511.13704 • Published 4 days ago • 40

P1: Mastering Physics Olympiads with Reinforcement Learning

Paper • 2511.13612 • Published 4 days ago • 125

upvoted a paper 10 days ago

VideoSSR: Video Self-Supervised Reinforcement Learning

Paper • 2511.06281 • Published 13 days ago • 21

updated a collection 15 days ago

VPPO Model

Collection

SOTA models for multimodal reasoning, fine-tuned with VPPO. Achieves superior performance by focusing on critical visual tokens. • 4 items • Updated 15 days ago • 4

liked a model 15 days ago

chamber111/VPPO-8B

Image-Text-to-Text • 9B • Updated 15 days ago • 25 • 2

updated 2 models 15 days ago

chamber111/VPPO-8B

Image-Text-to-Text • 9B • Updated 15 days ago • 25 • 2

chamber111/VPPO-7B

Image-Text-to-Text • 8B • Updated 15 days ago • 37 • 5

published a model 15 days ago

chamber111/VPPO-8B

Image-Text-to-Text • 9B • Updated 15 days ago • 25 • 2

upvoted a paper 19 days ago

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

Paper • 2510.27492 • Published 22 days ago • 79

updated 3 datasets about 1 month ago

chamber111/VPPO-Eval

Preview • Updated Oct 16 • 487 • 1

chamber111/VPPO_MMK12_validation

Viewer • Updated Oct 16 • 2k • 1.16k • 1

chamber111/VPPO_ViRL39K_train

Viewer • Updated Oct 16 • 38.9k • 1.5k • 1

updated a model about 1 month ago

chamber111/VPPO-32B

33B • Updated Oct 16 • 19 • 2

New activity in chamber111/VPPO-7B about 1 month ago

Add missing metadata tags

#1 opened about 1 month ago by

nielsr

New activity in chamber111/VPPO-Eval about 1 month ago

Add task category, sample usage, and prominent links

#2 opened about 1 month ago by

nielsr

New activity in chamber111/VPPO_ViRL39K_train about 1 month ago

Add task categories and update paper link

#1 opened about 1 month ago by

nielsr

New activity in chamber111/VPPO_MMK12_validation about 1 month ago

Add task category to dataset card

#2 opened about 1 month ago by

nielsr

upvoted 2 collections about 1 month 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 15 days ago • 4

authored a paper about 1 month ago

Spotlight on Token Perception for Multimodal Reinforcement Learning

Paper • 2510.09285 • Published Oct 10 • 36