Cover Image

WeaveTime: Stream from Earlier Frames into Emergent Memory in VideoLLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yulin, Shi, Cheng, Yang, Sibei
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video
by: Zhang, Yulin, et al.
Published: (2025)

Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding
by: Chatterjee, Dibyadip, et al.
Published: (2025)

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously
by: Guan, Yiran, et al.
Published: (2026)

Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs
by: Chung, Hyungjin, et al.
Published: (2025)

Lost in Time: A New Temporal Benchmark for VideoLLMs
by: Cores, Daniel, et al.
Published: (2024)

Sharp Eyes and Memory for VideoLLMs: Information-Aware Visual Token Pruning for Efficient and Reliable VideoLLM Reasoning
by: Qin, Jialong, et al.
Published: (2025)

VideoLLM-online: Online Video Large Language Model for Streaming Video
by: Chen, Joya, et al.
Published: (2024)

Vision Function Layer in Multimodal LLMs
by: Shi, Cheng, et al.
Published: (2025)

Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering
by: Cai, Jianfeng, et al.
Published: (2025)

Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs
by: Kim, Minji, et al.
Published: (2025)

VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation
by: Wu, Shiwei, et al.
Published: (2024)

EchoPrune: Interpreting Redundancy as Temporal Echoes for Efficient VideoLLMs
by: Li, Jiameng, et al.
Published: (2026)

Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency
by: Li, Hongyu, et al.
Published: (2025)

Geometry-Guided Camera Motion Understanding in VideoLLMs
by: Feng, Haoan, et al.
Published: (2026)

The devil is in the object boundary: towards annotation-free instance segmentation using Foundation Models
by: Shi, Cheng, et al.
Published: (2024)

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

Part2Object: Hierarchical Unsupervised 3D Instance Segmentation
by: Shi, Cheng, et al.
Published: (2024)

Proact-VL: A Proactive VideoLLM for Real-Time AI Companions
by: Yan, Weicai, et al.
Published: (2026)

Vision Transformers Need More Than Registers
by: Shi, Cheng, et al.
Published: (2026)

Plain-Det: A Plain Multi-Dataset Object Detector
by: Shi, Cheng, et al.
Published: (2024)

No More Sibling Rivalry: Debiasing Human-Object Interaction Detection
by: Yang, Bin, et al.
Published: (2025)

VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format
by: Wang, Yueqian, et al.
Published: (2024)

VideoLLM Benchmarks and Evaluation: A Survey
by: Kumar, Yogesh
Published: (2025)

Free on the Fly: Enhancing Flexibility in Test-Time Adaptation with Online EM
by: Dai, Qiyuan, et al.
Published: (2025)

Language-Guided Temporal Token Pruning for Efficient VideoLLM Processing
by: Kumar, Yogesh
Published: (2025)

Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM
by: Wang, Han, et al.
Published: (2024)

FrameVGGT: Geometry-Aligned Frame-Level Memory for Bounded Streaming VGGT
by: Xu, Zhisong, et al.
Published: (2026)

VideoScan: Enabling Efficient Streaming Video Understanding via Frame-level Semantic Carriers
by: Li, Ruanjun, et al.
Published: (2025)

When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding
by: Fang, Pengcheng, et al.
Published: (2025)

Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs
by: Zhang, Shaojie, et al.
Published: (2025)

Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models
by: Wang, Haibo, et al.
Published: (2024)

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

LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs
by: Kim, Jihwan, et al.
Published: (2026)

AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
by: Wang, Zun, et al.
Published: (2026)

"I Can See Forever!": Evaluating Real-time VideoLLMs for Assisting Individuals with Visual Impairments
by: Zhang, Ziyi, et al.
Published: (2025)

IPFormer-VideoLLM: Enhancing Multi-modal Video Understanding for Multi-shot Scenes
by: Liang, Yujia, et al.
Published: (2025)

Making Every Frame Matter: Continuous Activity Recognition in Streaming Video via Adaptive Video Context Modeling
by: Wu, Hao, et al.
Published: (2024)

Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentation
by: Dai, Qiyuan, et al.
Published: (2024)

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

Memory Helps, but Confabulation Misleads: Understanding Streaming Events in Videos with MLLMs
by: Zhang, Gengyuan, et al.
Published: (2025)