Token-Efficient Long Video Understanding for Multimodal LLMs
Paper
•
2503.04130
•
Published
•
70
LOVEU-TGVE
AI & ML interests
None defined yet.
Recent Activity
View all activity
loveu-tgve's activity
xiuyulÂ
authored
a
paper
3 days ago
jaywÂ
authored
2
papers
6 days ago
xiuyulÂ
authored
a
paper
17 days ago
BryanWÂ
authored
a
paper
3 months ago
BryanWÂ
authored
a
paper
4 months ago
BryanWÂ
authored
4
papers
5 months ago
MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models
Paper
•
2410.13370
•
Published
•
37
LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval
Paper
•
2207.04858
•
Published
Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
Paper
•
2410.08261
•
Published
•
50
Integrating View Conditions for Image Synthesis
Paper
•
2310.16002
•
Published
•
3
BryanWÂ
authored
3
papers
9 months ago
Translating Natural Language to Planning Goals with Large-Language Models
Paper
•
2302.05128
•
Published
An Item is Worth a Prompt: Versatile Image Editing with Disentangled Control
Paper
•
2403.04880
•
Published
•
6
Taming Diffusion Models for Music-driven Conducting Motion Generation
Paper
•
2306.10065
•
Published
xiuyulÂ
authored
2
papers
11 months ago
xiuyulÂ
authored
a
paper
about 1 year ago
jaywÂ
authored
a
paper
about 1 year ago
jaywÂ
authored
3
papers
over 1 year ago
DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing
Paper
•
2310.10624
•
Published
MotionDirector: Motion Customization of Text-to-Video Diffusion Models
Paper
•
2310.08465
•
Published
•
16
VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence
Paper
•
2312.02087
•
Published
•
23