LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture
Paper
•
2409.02889
•
Published
•
55
Captioning
-
-
MVLLaVA: An Intelligent Agent for Unified and Flexible Novel View Synthesis
Paper • 2409.07129 • Published • 6 -
LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness
Paper • 2409.18125 • Published • 33 -
FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity
Paper • 2411.15411 • Published • 7