Pu Fanyi

pufanyi's activity

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

upvoted a paper 7 days ago

MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification

Paper • 2603.15726 • Published 10 days ago • 179

authored a paper 7 days ago

Demystifing Video Reasoning

Paper • 2603.16870 • Published 9 days ago • 358

upvoted a paper 9 days ago

Demystifing Video Reasoning

Paper • 2603.16870 • Published 9 days ago • 358

upvoted a paper 10 days ago

HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions

Paper • 2603.15612 • Published 10 days ago • 149

liked a Space 16 days ago

Running

4

Video Frame Extractor

🎬

4

Extract frames from video files

updated a Space 16 days ago

Running

4

Video Frame Extractor

🎬

4

Extract frames from video files

published a Space 16 days ago

Running

4

Video Frame Extractor

🎬

4

Extract frames from video files

upvoted an article 18 days ago

view article

Article

NEO-unify: Building Native Multimodal Unified Models End to End

• 

21 days ago

•

103

upvoted a paper 21 days ago

ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors

Paper • 2603.04338 • Published 22 days ago • 24

liked a dataset 23 days ago

Video-Reason/VBVR-Bench-Data

Viewer • Updated about 1 month ago • 500 • 3.36k • 8

upvoted 2 papers 23 days ago

A Very Big Video Reasoning Suite

Paper • 2602.20159 • Published Feb 23 • 517

UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?

Paper • 2603.03241 • Published 23 days ago • 86

updated a dataset 27 days ago

LMMs-Lab-Speedrun/Data_NanoVLM

Viewer • Updated 27 days ago • 1.62M • 34

upvoted 2 papers about 1 month ago

UniT: Unified Multimodal Chain-of-Thought Test-time Scaling

Paper • 2602.12279 • Published Feb 12 • 20

OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence

Paper • 2602.08683 • Published Feb 9 • 52

upvoted a collection 2 months ago

NEO1_0

Collection

From Pixels to Words -- Towards Native Vision-Language Primitives at Scale • 7 items • Updated Jan 27 • 9

upvoted a paper 3 months ago

Fewer Truncations Improve Language Modeling

Paper • 2404.10830 • Published Apr 16, 2024 • 5

liked a Space 3 months ago

Running

79

Chinese Open Source Heatmap

🔥

79

Explore open source AI projects and their release activity over time

liked 2 models 3 months ago

Qwen/Qwen3-VL-8B-Thinking

Image-Text-to-Text • 9B • Updated Nov 26, 2025 • 125k • 195

Qwen/Qwen3-VL-235B-A22B-Thinking

Image-Text-to-Text • 236B • Updated Nov 26, 2025 • 319k • • 385