Penghao Wu

craigwu's activity

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

upvoted 2 papers about 1 month ago

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

Paper • 2511.20785 • Published Nov 25, 2025 • 181

PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image

Paper • 2511.13648 • Published Nov 17, 2025 • 52

upvoted 3 papers 3 months ago

From Pixels to Words -- Towards Native Vision-Language Primitives at Scale

Paper • 2510.14979 • Published Oct 16, 2025 • 66

RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark

Paper • 2509.24897 • Published Sep 29, 2025 • 46

Visual Jigsaw Post-Training Improves MLLMs

Paper • 2509.25190 • Published Sep 29, 2025 • 35

updated a collection 3 months ago

Visual Jigsaw

Collection

6 items • Updated Sep 30, 2025 • 1

commented a paper 3 months ago

Visual Jigsaw Post-Training Improves MLLMs

Paper • 2509.25190 • Published Sep 29, 2025 • 35 •

2

published a dataset 3 months ago

craigwu/visual_jigsaw_training_data

Viewer • Updated Sep 28, 2025 • 519k • 47 • 3

published 3 models 3 months ago

craigwu/visual_jigsaw_3D_7B

8B • Updated Sep 27, 2025 • 8 • 1

craigwu/visual_jigsaw_video_7B

8B • Updated Sep 27, 2025 • 10 • 1

craigwu/visual_jigsaw_image_7B

8B • Updated Sep 27, 2025 • 128 • 1

updated a collection 3 months ago

Visual Jigsaw

Collection

6 items • Updated Sep 30, 2025 • 1

updated a dataset 3 months ago

craigwu/visual_jigsaw_eval_data

Preview • Updated Sep 28, 2025 • 8

published a dataset 3 months ago

craigwu/visual_jigsaw_eval_data

Preview • Updated Sep 28, 2025 • 8

updated a dataset 3 months ago

craigwu/visual_jigsaw_training_data

Viewer • Updated Sep 28, 2025 • 519k • 47 • 3

updated 2 models 3 months ago

craigwu/visual_jigsaw_3D_7B

8B • Updated Sep 27, 2025 • 8 • 1

craigwu/visual_jigsaw_video_7B

8B • Updated Sep 27, 2025 • 10 • 1