Reason First, Retrieve What Matters: Hypothesis-Guided Keyframe Selection for Long Video Understanding
cs.CV, cs.AI
Submitted: 2026-11-07
Updated: 2026-11-07
Terminology
Sources
- Qwen2.5-VL Technical Report
- Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation
- MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
- Efficient Frame Selection for Long Videos at Test Time with Attention-Based MLLM Selectors
- Kwai Keye-VL 1.5 Technical Report
- Frame-Voyager: Learning to Query Frames for Video Large Language Models
- LLaVA-Video: Video Instruction Tuning With Synthetic Data
- MLVU: Benchmarking Multi-task Long Video Understanding
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs