Pu Fanyi

pufanyi's activity

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

liked a model 3 days ago

google/umt5-xxl

Updated Jul 3, 2023 • 83.1k • 60

upvoted a paper 8 days ago

FileGram: Grounding Agent Personalization in File-System Behavioral Traces

Paper • 2604.04901 • Published 9 days ago • 40

upvoted a paper 10 days ago

HippoCamp: Benchmarking Contextual Agents on Personal Computers

Paper • 2604.01221 • Published 13 days ago • 28

liked a model 11 days ago

google/gemma-4-31B-it

Image-Text-to-Text • 33B • Updated 4 days ago • 2.64M • • 1.89k

liked 7 models 13 days ago

sensenova/SenseNova-SI-1.1-InternVL3-8B-800K

Image-Text-to-Text • 8B • Updated Dec 23, 2025 • 13 • 3

sensenova/SenseNova-SI-1.3-InternVL3-8B

Image-Text-to-Text • 8B • Updated Jan 9 • 1.18k • 9

sensenova/ConsistCompose-BAGEL-7B-MoT

Updated 15 days ago • 3 • 6

sensenova/SenseNova-SI-1.1-BAGEL-7B-MoT

Image-Text-to-Text • Updated Jan 13 • 423 • 4

sensenova/SenseNova-MARS-8B

Image-Text-to-Text • 9B • Updated Jan 29 • 195 • 7

sensenova/SenseNova-MARS-32B

Image-Text-to-Text • 33B • Updated Jan 29 • 71 • 5

sensenova/SenseNova-SI-1.4-InternVL3-8B

Image-Text-to-Text • 8B • Updated 19 days ago • 1.7k • 3

liked a dataset 14 days ago

osunlp/Mind2Web

Viewer • Updated Oct 19, 2025 • 253 • 5.19k • 124

liked a dataset 15 days ago

Video-Reason/VBVR-Dataset

Viewer • Updated 13 days ago • 1M • 1.61k • 50

liked a model 15 days ago

Wan-AI/Wan2.2-I2V-A14B

Image-to-Video • Updated Aug 7, 2025 • 8.66k • • 679

liked a model 16 days ago

Wan-AI/Wan2.2-TI2V-5B-Diffusers

Text-to-Video • Updated Aug 9, 2025 • 76.5k • 119

upvoted a paper 26 days ago

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

Paper • 2603.15726 • Published 29 days ago • 185

authored a paper 26 days ago

Demystifing Video Reasoning

Paper • 2603.16870 • Published 28 days ago • 368

upvoted a paper 28 days ago

Demystifing Video Reasoning

Paper • 2603.16870 • Published 28 days ago • 368

upvoted a paper 29 days ago

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

Paper • 2603.15612 • Published 29 days ago • 152

liked a Space about 1 month ago

Running

4

Video Frame Extractor

🎬

4

Extract frames from video files