conftrace_

hybrid resolution

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

encoder-free architecture (1) spatio-temporal representation (1) large language model (1) token merging (1) video-language understanding (1) video understanding (1) multimodal learning (1) model compression (1)

Papers

Breaking the Encoder Barrier for Seamless Video-Language Understanding ICCV 2025