Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models
Paper
•
2503.16036
•
Published
•
1
Zhihang Liu
lntzm
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
Routing Matters in MoE: Scaling Diffusion Transformers with Explicit
Routing Guidance
upvoted
a
paper
5 months ago
Test-Time Scaling with Reflective Generative Model
updated
a dataset
7 months ago
lntzm/CAPability
Organizations
None yet
authored
a
paper
9 months ago