AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
Paper
•
2412.03248
•
Published
•
26
•
2
Yiwu Zhong
YiwuZhong
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene
Understanding
upvoted
a
paper
about 1 month ago
AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and
Pruning
commented
a paper
about 1 month ago
AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and
Pruning
Organizations
YiwuZhong's activity
commented
a
paper
about 1 month ago
Corrupted files
3
#1 opened 4 months ago
by
YiwuZhong
Corrupted files
3
#1 opened 4 months ago
by
YiwuZhong
Corrupted files
3
#1 opened 4 months ago
by
YiwuZhong