-
ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition
Paper • 2402.15220 • Published • 19 -
Jamba: A Hybrid Transformer-Mamba Language Model
Paper • 2403.19887 • Published • 104 -
MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection
Paper • 2403.19888 • Published • 10 -
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Paper • 2404.02258 • Published • 104
GEON ZH
GEONTT
AI & ML interests
None yet
Organizations
None yet
Collections
7
-
Seamless Human Motion Composition with Blended Positional Encodings
Paper • 2402.15509 • Published • 14 -
TripoSR: Fast 3D Object Reconstruction from a Single Image
Paper • 2403.02151 • Published • 12 -
3D-VLA: A 3D Vision-Language-Action Generative World Model
Paper • 2403.09631 • Published • 7 -
Controllable Text-to-3D Generation via Surface-Aligned Gaussian Splatting
Paper • 2403.09981 • Published • 6
models
None public yet
datasets
None public yet