conftrace_

video token

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

video understanding (3) multimodal large language model (2) video token compression (1) instruction injection (1) conditional pre-training (1) information pre-filtering (1) cross-modal query (1) gaussian attention blocks (1) registers (1) semantic registers (1)

Papers

Imagine Before Concentration: Diffusion-Guided Registers Enhance Partially Relevant Video Retrieval CVPR 2026 Adaptive Keyframe Sampling for Long Video Understanding CVPR 2025 Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models CVPR 2025 LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding ICML 2025 SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning EMNLP 2025