Cover Image

AdaFocus: Adaptive Relevance-Diversity Sampling with Zero-Cache Look-back for Efficient Long Video Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Xiao, Ma, Yingzhe, Yu, Haoxuan, Li, Zixin, Qin, Ning
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Uni-AdaFocus: Spatial-temporal Dynamic Computation for Video Recognition
by: Wang, Yulin, et al.
Published: (2024)

AdaRD-key: Adaptive Relevance-Diversity Keyframe Sampling for Long-form Video understanding
by: Zhang, Xian, et al.
Published: (2025)

AdaSpark: Adaptive Sparsity for Efficient Long-Video Understanding
by: Li, Handong, et al.
Published: (2026)

AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding
by: Xue, Zhucun, et al.
Published: (2025)

AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers
by: Liu, Dong, et al.
Published: (2026)

Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models
by: Tao, Keda, et al.
Published: (2025)

AdaFlow: Efficient Long Video Editing via Adaptive Attention Slimming And Keyframe Selection
by: Zhang, Shuheng, et al.
Published: (2025)

Adaptive Keyframe Sampling for Long Video Understanding
by: Tang, Xi, et al.
Published: (2025)

CacheFlow: Compressive Streaming Memory for Efficient Long-Form Video Understanding
by: Patel, Shrenik, et al.
Published: (2025)

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction
by: Man, Yuanbin, et al.
Published: (2024)

Think, Then Verify: A Hypothesis-Verification Multi-Agent Framework for Long Video Understanding
by: Wang, Zheng, et al.
Published: (2026)

AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding
by: Wang, Xiao, et al.
Published: (2025)

REEF: Relevance-Aware and Efficient LLM Adapter for Video Understanding
by: Reza, Sakib, et al.
Published: (2025)

Adaptive Hybrid Caching for Efficient Text-to-Video Diffusion Model Acceleration
by: Wei, Yuanxin, et al.
Published: (2025)

LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval
by: Ning, Zhenyu, et al.
Published: (2025)

VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding
by: Yang, Ruoliu, et al.
Published: (2026)

VideoRouter: Query-Adaptive Dual Routing for Efficient Long-Video Understanding
by: Lin, Kuanwei, et al.
Published: (2026)

AdaVid: Adaptive Video-Language Pretraining
by: Patel, Chaitanya, et al.
Published: (2025)

Dual-Signal Adaptive KV-Cache Optimization for Long-Form Video Understanding in Vision-Language Models
by: Sai, Vishnu, et al.
Published: (2026)

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
by: Zhang, Haowei, et al.
Published: (2026)

Zero-Shot Long-Form Video Understanding through Screenplay
by: Wu, Yongliang, et al.
Published: (2024)

Mitigating Long-Tail Bias in HOI Detection via Adaptive Diversity Cache
by: Jiang, Yuqiu, et al.
Published: (2025)

AccKV: Towards Efficient Audio-Video LLMs Inference via Adaptive-Focusing and Cross-Calibration KV Cache Optimization
by: Jiang, Zhonghua, et al.
Published: (2025)

Decouple and Cache: KV Cache Construction for Streaming Video Understanding
by: Pang, Zhanzhong, et al.
Published: (2026)

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
by: Shen, Xiaoqian, et al.
Published: (2024)

LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference
by: Wan, Zhongwei, et al.
Published: (2024)

LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation
by: Xiao, Yang, et al.
Published: (2025)

FlexSelect: Flexible Token Selection for Efficient Long Video Understanding
by: Zhang, Yunzhu, et al.
Published: (2025)

AdaTooler-V: Adaptive Tool-Use for Images and Videos
by: Wang, Chaoyang, et al.
Published: (2025)

VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs
by: Liao, Ruotong, et al.
Published: (2024)

VideoPro: Adaptive Program Reasoning for Long Video Understanding
by: Li, Chenglin, et al.
Published: (2025)

VideoMem: Enhancing Ultra-Long Video Understanding via Adaptive Memory Management
by: Jin, Hongbo, et al.
Published: (2025)

FOCUS: Efficient Keyframe Selection for Long Video Understanding
by: Zhu, Zirui, et al.
Published: (2025)

Anatomy-Slot: Unsupervised Anatomical Factorization for Homologous Bilateral Reasoning in Retinal Diagnosis
by: Ma, Yingzhe, et al.
Published: (2026)

Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models
by: Ji, Yicheng, et al.
Published: (2026)

AdaDocVQA: Adaptive Framework for Long Document Visual Question Answering in Low-Resource Settings
by: Li, Haoxuan, et al.
Published: (2025)

QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation
by: Wu, Junyi, et al.
Published: (2025)

Where to Focus: Query-Modulated Multimodal Keyframe Selection for Long Video Understanding
by: Wang, Shaoguang, et al.
Published: (2026)

Video-Zero: Self-Evolution Video Understanding
by: Zhang, Ruixu, et al.
Published: (2026)

UniCP: A Unified Caching and Pruning Framework for Efficient Video Generation
by: Sun, Wenzhang, et al.
Published: (2025)