-
Emu3.5: Native Multimodal Models are World Learners
Paper • 2510.26583 • Published • 112 -
Cambrian-S: Towards Spatial Supersensing in Video
Paper • 2511.04670 • Published • 38 -
MagicWorld: Interactive Geometry-driven Video World Exploration
Paper • 2511.18886 • Published • 19 -
WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
Paper • 2512.14614 • Published • 71
Oğuzhan Ercan
oguzhanercan
AI & ML interests
deep representation learning
Recent Activity
updated
a collection
about 3 hours ago
Video Generation Control-Style Transfer updated
a collection
about 3 hours ago
Image-Video MultiModal Understanding updated
a collection
about 6 hours ago
RAG Organizations
None yet