Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration
Paper
•
2412.13180
•
Published
•
13
•
2
Mark Endo
markendo
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
16 days ago
MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based
Scientific Research
upvoted
a
paper
22 days ago
Video Action Differencing
upvoted
a
paper
2 months ago
Temporal Preference Optimization for Long-Form Video Understanding
Organizations
None yet
markendo's activity
commented
a
paper
4 months ago