-
Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations
Paper • 2512.21004 • Published • 13 -
Spatia: Video Generation with Updatable Spatial Memory
Paper • 2512.15716 • Published • 33 -
NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos
Paper • 2601.00393 • Published • 133 -
Geometry-Aware Rotary Position Embedding for Consistent Video World Model
Paper • 2602.07854 • Published • 10
KeXing
KXingLab
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 hours ago
CutClaw: Agentic Hours-Long Video Editing via Music Synchronization updated a collection about 1 month ago
paper upvoted a paper about 2 months ago
VideoWorld 2: Learning Transferable Knowledge from Real-world VideosOrganizations
-
Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations
Paper • 2512.21004 • Published • 13 -
Spatia: Video Generation with Updatable Spatial Memory
Paper • 2512.15716 • Published • 33 -
NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos
Paper • 2601.00393 • Published • 133 -
Geometry-Aware Rotary Position Embedding for Consistent Video World Model
Paper • 2602.07854 • Published • 10
datasets 0
None public yet