-
Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations
Paper • 2512.21004 • Published • 12 -
Spatia: Video Generation with Updatable Spatial Memory
Paper • 2512.15716 • Published • 30 -
NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos
Paper • 2601.00393 • Published • 106
KeXing
KXingLab
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
3 days ago
LTX-2: Efficient Joint Audio-Visual Foundation Model
updated
a collection
5 days ago
paper
upvoted
a
paper
5 days ago
Pretraining Frame Preservation in Autoregressive Video Memory Compression
Organizations
