Image de couverture de livre

CurveStream: Boosting Streaming Video Understanding in MLLMs via Curvature-Aware Hierarchical Visual Memory Management

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Chao, Tan, Xudong, Cao, Jianjian, Li, Kangcong, Chen, Tao
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding
par: Li, Kangcong, et autres
Publié: (2026)

StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering
par: Xie, Ming, et autres
Publié: (2026)

X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding
par: Sun, Peiwen, et autres
Publié: (2026)

Memory Helps, but Confabulation Misleads: Understanding Streaming Events in Videos with MLLMs
par: Zhang, Gengyuan, et autres
Publié: (2025)

StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding
par: Lin, Junming, et autres
Publié: (2024)

Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding
par: Wu, Hang, et autres
Publié: (2026)

FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding
par: Xie, Yiweng, et autres
Publié: (2026)

VideoScaffold: Elastic-Scale Visual Hierarchies for Streaming Video Understanding in MLLMs
par: Zheng, Naishan, et autres
Publié: (2025)

OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning
par: Liang, Zhijia, et autres
Publié: (2026)

StreamingTOM: Streaming Token Compression for Efficient Video Understanding
par: Chen, Xueyi, et autres
Publié: (2025)

AURA: Always-On Understanding and Real-Time Assistance via Video Streams
par: Lu, Xudong, et autres
Publié: (2026)

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
par: Zhang, Haowei, et autres
Publié: (2026)

StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding
par: Wang, Junxi, et autres
Publié: (2026)

StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding
par: Yang, Yanlai, et autres
Publié: (2025)

Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding
par: Chatterjee, Dibyadip, et autres
Publié: (2025)

Open-ended Hierarchical Streaming Video Understanding with Vision Language Models
par: Kang, Hyolim, et autres
Publié: (2025)

StreamEQA: Towards Streaming Video Understanding for Embodied Scenarios
par: Wang, Yifei, et autres
Publié: (2025)

StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding
par: Yang, Haolin, et autres
Publié: (2025)

StreamForest: Efficient Online Video Understanding with Persistent Event Memory
par: Zeng, Xiangyu, et autres
Publié: (2025)

VideoScan: Enabling Efficient Streaming Video Understanding via Frame-level Semantic Carriers
par: Li, Ruanjun, et autres
Publié: (2025)

CacheFlow: Compressive Streaming Memory for Efficient Long-Form Video Understanding
par: Patel, Shrenik, et autres
Publié: (2025)

Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams
par: Zhang, Haoji, et autres
Publié: (2024)

LongStream: Long-Sequence Streaming Autoregressive Visual Geometry
par: Cheng, Chong, et autres
Publié: (2026)

Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation
par: Huang, Zhe, et autres
Publié: (2025)

VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges
par: Wang, Yuxuan, et autres
Publié: (2024)

Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
par: Wang, Yiyu, et autres
Publié: (2025)

HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming
par: Qiu, Haonan, et autres
Publié: (2025)

TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models
par: Tan, Xudong, et autres
Publié: (2025)

Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory
par: Agarwal, Vatsal, et autres
Publié: (2026)

Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge
par: Xiong, Haomiao, et autres
Publié: (2025)

StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding
par: Jin, Xinqi, et autres
Publié: (2025)

StreamingVLM: Real-Time Understanding for Infinite Video Streams
par: Xu, Ruyi, et autres
Publié: (2025)

StreamChat: Chatting with Streaming Video
par: Liu, Jihao, et autres
Publié: (2024)

Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation
par: Wu, Bin, et autres
Publié: (2026)

video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM
par: Sun, Guangzhi, et autres
Publié: (2025)

StrLoRA: Towards Streaming Continual Visual Instruction Tuning for MLLMs
par: Che, Chang, et autres
Publié: (2026)

IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams
par: Li, Jinzhao, et autres
Publié: (2026)

DeformStream: Deformation-based Adaptive Volumetric Video Streaming
par: Li, Boyan, et autres
Publié: (2024)

Streaming Long Video Understanding with Large Language Models
par: Qian, Rui, et autres
Publié: (2024)

An Efficient Streaming Video Understanding Framework with Agentic Control
par: Liu, Jinming, et autres
Publié: (2026)