conftrace_

encoder-free architecture

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

multimodal learning (2) hybrid resolution (1) spatio-temporal alignment (1) decoder architecture (1) computational overhead (1) spatio-temporal representation (1) large language model (1) decoder-only architecture (1) token merging (1) video-language model (1)

Papers

Breaking the Encoder Barrier for Seamless Video-Language Understanding ICCV 2025 Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models CVPR 2025 Unveiling Encoder-Free Vision-Language Models NeurIPS 2024