AdaAlloc: Adaptive Visual Token Allocation for Long-Video Question Answering
cs.CV, cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Project page: https://vision.cs.utexas.edu/projects/adaalloc
Terminology
Sources
- UniversalVTG: A Universal and Lightweight Foundation Model for Video Temporal Grounding
- Qwen3-VL Technical Report
- TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability
- Event-Anchored Frame Selection for Effective Long-Video Understanding
- LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning
- Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
- FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding
- GPT-4o System Card
- VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
- Zoom-Zero: Reinforced Coarse-to-Fine Video Understanding via Temporal Zoom-in
- From Frames to Clips: Training-free Adaptive Key Clip Selection for Long-Form Video Understanding
- Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding
- SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding
- VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding
- Memory-enhanced Retrieval Augmentation for Long Video Understanding
- VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
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