Max Ku

vinesmsuic's activity

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

upvoted a paper about 8 hours ago

StopLoss: Teaching Agents to Predict Failure and Stop Early

Paper • 2610.25525 • Published 3 days ago • 8

upvoted a paper 6 days ago

WorldCast: Distributed Multiplayer World Models

Paper • 2610.12412 • Published 13 days ago • 3

upvoted a paper 7 days ago

PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos

Paper • 2609.38377 • Published 22 days ago • 17

submitted a paper to Daily Papers 7 days ago

PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos

Paper • 2609.38377 • Published 22 days ago • 17

authored a paper 8 days ago

PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos

Paper • 2609.38377 • Published 22 days ago • 17

updated a model 8 days ago

vinesmsuic/PhyProbe

Updated 8 days ago

published a model 8 days ago

vinesmsuic/PhyProbe

Updated 8 days ago

authored a paper 13 days ago

VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations

Paper • 2610.00994 • Published 20 days ago • 35

upvoted a paper 13 days ago

VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations

Paper • 2610.00994 • Published 20 days ago • 35

submitted a paper to Daily Papers 13 days ago

VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations

Paper • 2610.00994 • Published 20 days ago • 35

authored a paper 14 days ago

World Editing: Intervening on Executable Worlds at Increasing Depth

Paper • 2610.02331 • Published 20 days ago • 31

upvoted a paper 14 days ago

World Editing: Intervening on Executable Worlds at Increasing Depth

Paper • 2610.02331 • Published 20 days ago • 31

commented a paper 14 days ago

World Editing: Intervening on Executable Worlds at Increasing Depth

Paper • 2610.02331 • Published 20 days ago • 31 •

3

submitted a paper to Daily Papers 14 days ago

World Editing: Intervening on Executable Worlds at Increasing Depth

Paper • 2610.02331 • Published 20 days ago • 31

upvoted 2 papers 19 days ago

TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining

Paper • 2609.33419 • Published 24 days ago • 19

PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation

Paper • 2609.38597 • Published 22 days ago • 34

New activity in TIGER-Lab/VisPhyWorld-Sub-Generated-Videos 3 months ago

Add paper link and task categories

#2 opened 5 months ago by

nielsr

upvoted 3 papers 3 months ago

From Pixels to States: Rethinking Interactive World Models as Game Engines

Paper • 2607.14076 • Published Jul 15 • 32

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

Paper • 2607.12463 • Published Jul 14 • 305

Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation

Paper • 2607.05382 • Published Jul 9 • 83