UMD Tech+Research 23

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

vatsalag authored a paper 18 days ago

Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory

vatsalag authored a paper 18 days ago

MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos

vatsalag authored a paper 9 months ago

Do text-free diffusion models learn discriminative visual representations?

View all activity

models 0

None public yet

datasets 0

None public yet