Fanziyang's picture

8

Fanziyang

BugKiller-399

·

Fanziyang-v

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging

authored a paper 2 days ago

FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging

updated a Space 6 days ago

MovieBench/MovieBench2

View all activity

Organizations

Papers 1

arxiv:2602.08024

models 0

None public yet

datasets 2

BugKiller-399/moviebench-results2

Updated 19 days ago • 13

BugKiller-399/moviebench-data

Updated 23 days ago • 3k