JPShi

JPShi's activity

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

upvoted 2 papers 23 days ago

FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance

Paper • 2603.12146 • Published 27 days ago • 5

Can Vision-Language Models Solve the Shell Game?

Paper • 2603.08436 • Published about 1 month ago • 39

upvoted a paper 24 days ago

WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing

Paper • 2603.11593 • Published 28 days ago • 25

upvoted a paper 28 days ago

CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization

Paper • 2603.06449 • Published Mar 6 • 6

liked a dataset about 1 month ago

mxxxxxxxxxxxxxxxxx/ChronusAV

Updated Feb 17 • 44 • 1

liked a dataset 2 months ago

CinematicT2vData/raw_videos_batched

Viewer • Updated Aug 17, 2025 • 9.26k • 367 • 1

submitted a paper to Daily Papers 3 months ago

VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding

Paper • 2601.07290 • Published Jan 12 • 7

authored a paper 3 months ago

VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding

Paper • 2601.07290 • Published Jan 12 • 7

updated a model 3 months ago

JPShi/VideoLoom-8B

8B • Updated Jan 13 • 2

upvoted a paper 3 months ago

VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding

Paper • 2601.07290 • Published Jan 12 • 7

published 2 models 3 months ago

JPShi/VideoLoom-8B

8B • Updated Jan 13 • 2

JPShi/VideoLoom-4B

4B • Updated Jan 13 • 3

updated a collection 3 months ago

VideoLoom

Collection

Model Zoo for VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding • 3 items • Updated Jan 13 • 1

updated a model 3 months ago

JPShi/VideoLoom-4B

4B • Updated Jan 13 • 3

updated a collection 3 months ago

VideoLoom

Collection

Model Zoo for VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding • 3 items • Updated Jan 13 • 1

upvoted a collection 3 months ago

VideoLoom

Collection

Model Zoo for VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding • 3 items • Updated Jan 13 • 1

liked a dataset 6 months ago

tomg-group-umd/cinepile

Viewer • Updated Oct 23, 2024 • 608k • 314 • 91