Cover Image

Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Jiazheng, Wu, Chi-Hao, Liu, Yunze, Ding, Kaize, Li, Jundong, Zhang, Chuxu
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

O-MARC: Omni Memory-Augmented Compression Distillation for Efficient Video Understanding
by: Wu, Peiran, et al.
Published: (2026)

MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
by: Wu, Peiran, et al.
Published: (2025)

Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning
by: Wang, Chendong, et al.
Published: (2025)

SpatialMem: Metric-Aligned Long-Horizon Video Memory for Language Grounding and QA
by: Zheng, Xinyi, et al.
Published: (2026)

VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding
by: Yin, Yufei, et al.
Published: (2025)

OmniRetriever: Any-to-Any Audio-Video-Text Retrieval via Fusion-as-Teacher Distillation
by: Liu, Yunze, et al.
Published: (2026)

A Benchmark and Agentic Framework for Omni-Modal Reasoning and Tool Use in Long Videos
by: Kurpath, Mohammed Irfan, et al.
Published: (2025)

ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos
by: Wu, Peiran, et al.
Published: (2025)

Visual Agentic Memory: Enabling Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic Retrieval
by: Li, Aiden Yiliu, et al.
Published: (2026)

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

GaitGS: Temporal Feature Learning in Granularity and Span Dimension for Gait Recognition
by: Xiong, Haijun, et al.
Published: (2023)

CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding
by: Liu, Yunze, et al.
Published: (2024)

PhysReaction: Physically Plausible Real-Time Humanoid Reaction Synthesis via Forward Dynamics Guided 4D Imitation
by: Liu, Yunze, et al.
Published: (2024)

VideoMAP: Toward Scalable Mamba-based Video Autoregressive Pretraining
by: Liu, Yunze, et al.
Published: (2025)

VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding
by: He, Haichen, et al.
Published: (2026)

VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges
by: Wang, Yuxuan, et al.
Published: (2024)

Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning
by: Tian, Shulin, et al.
Published: (2025)

Agentic Very Long Video Understanding
by: Rege, Aniket, et al.
Published: (2026)

UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks
by: Wu, Peiran, et al.
Published: (2025)

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

Video World Models with Long-term Spatial Memory
by: Wu, Tong, et al.
Published: (2025)

RELIC: Interactive Video World Model with Long-Horizon Memory
by: Hong, Yicong, et al.
Published: (2025)

Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams
by: Zhang, Haoji, et al.
Published: (2024)

OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning
by: Liang, Zhijia, et al.
Published: (2026)

Hierarchical Memory for Long Video QA
by: Wang, Yiqin, et al.
Published: (2024)

PointNet4D: A Lightweight 4D Point Cloud Video Backbone for Online and Offline Perception in Robotic Applications
by: Liu, Yunze, et al.
Published: (2025)

SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation
by: Dou, Weijia, et al.
Published: (2026)

CFSum: A Transformer-Based Multi-Modal Video Summarization Framework With Coarse-Fine Fusion
by: Guo, Yaowei, 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)

Point to Span: Zero-Shot Moment Retrieval for Navigating Unseen Hour-Long Videos
by: Jeon, Mingyu, et al.
Published: (2025)

Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation
by: Wu, Mingqiang, et al.
Published: (2026)

LumosFlow: Motion-Guided Long Video Generation
by: Chen, Jiahao, et al.
Published: (2025)

LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation
by: Gao, Jianxiong, et al.
Published: (2025)

X-LeBench: A Benchmark for Extremely Long Egocentric Video Understanding
by: Zhou, Wenqi, et al.
Published: (2025)

Training-Free Spatio-temporal Decoupled Reasoning Video Segmentation with Adaptive Object Memory
by: Zhu, Zhengtong, et al.
Published: (2026)

MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining
by: Liu, Yunze, et al.
Published: (2024)

Spatial-Conditioned Reasoning in Long-Egocentric Videos
by: Tribble, James, et al.
Published: (2026)

Preacher: Paper-to-Video Agentic System
by: Liu, Jingwei, et al.
Published: (2025)

VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning
by: Li, Chenglin, et al.
Published: (2026)

Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning
by: Liu, Xinyu, et al.
Published: (2025)