Cover Image

State-Space Hierarchical Compression with Gated Attention and Learnable Sampling for Hour-Long Video Understanding in Large Multimodal Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Geewook, Seo, Minjoon
Format:	Preprint
Published:	2025
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

On Efficient Language and Vision Assistants for Visually-Situated Natural Language Understanding: What Matters in Reading and Reasoning
by: Kim, Geewook, et al.
Published: (2024)

Do Modern Video-LLMs Need to Listen? A Benchmark Audit and Scalable Remedy
by: Kim, Geewook, et al.
Published: (2025)

How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?
by: Lee, Seongyun, et al.
Published: (2024)

MMRefine: Unveiling the Obstacles to Robust Refinement in Multimodal Large Language Models
by: Paik, Gio, et al.
Published: (2025)

Long Video Understanding with Learnable Retrieval in Video-Language Models
by: Xu, Jiaqi, et al.
Published: (2023)

Evaluating Multimodal Generative AI with Korean Educational Standards
by: Park, Sanghee, et al.
Published: (2025)

Understanding Long Videos with Multimodal Language Models
by: Ranasinghe, Kanchana, et al.
Published: (2024)

On the Consistency of Video Large Language Models in Temporal Comprehension
by: Jung, Minjoon, et al.
Published: (2024)

Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models
by: Chen, Yuxiao, et al.
Published: (2026)

Learnable Gated Temporal Shift Module for Deep Video Inpainting
by: Chang, Ya-Liang, et al.
Published: (2019)

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

ReWind: Understanding Long Videos with Instructed Learnable Memory
by: Diko, Anxhelo, et al.
Published: (2024)

CASP: Compression of Large Multimodal Models Based on Attention Sparsity
by: Gholami, Mohsen, et al.
Published: (2025)

MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
by: He, Bo, et al.
Published: (2024)

VideoMamba: State Space Model for Efficient Video Understanding
by: Li, Kunchang, et al.
Published: (2024)

Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision
by: Lee, Seongyun, et al.
Published: (2023)

VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling
by: Li, Xinhao, et al.
Published: (2024)

Long-Context State-Space Video World Models
by: Po, Ryan, et al.
Published: (2025)

Vidi: Large Multimodal Models for Video Understanding and Editing
by: Vidi Team, et al.
Published: (2025)

Beyond Raw Videos: Understanding Edited Videos with Large Multimodal Model
by: Xu, Lu, et al.
Published: (2024)

Streaming Long Video Understanding with Large Language Models
by: Qian, Rui, et al.
Published: (2024)

Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval
by: Jeong, Boseung, et al.
Published: (2025)

Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
by: Wang, Yiyu, et al.
Published: (2025)

RSGMamba: Reliability-Aware Self-Gated State Space Model for Multimodal Semantic Segmentation
by: Xu, Guoan, et al.
Published: (2026)

Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding
by: Liu, Xiangrui, et al.
Published: (2025)

Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding
by: Shu, Yan, et al.
Published: (2024)

HAVEN: Hierarchically Aligned Multimodal Benchmark for Unified Video Understanding
by: Shi, Mengqi, et al.
Published: (2026)

EgoExo-Con: Exploring View-Invariant Video Temporal Understanding
by: Jung, Minjoon, et al.
Published: (2025)

LongVLM: Efficient Long Video Understanding via Large Language Models
by: Weng, Yuetian, et al.
Published: (2024)

Towards Effective Long Video Understanding of Multimodal Large Language Models via One-shot Clip Retrieval
by: Chen, Tao, et al.
Published: (2025)

ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understanding
by: Yashima, Daichi, et al.
Published: (2026)

FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding
by: Guo, Yanan, et al.
Published: (2025)

VidCompress: Memory-Enhanced Temporal Compression for Video Understanding in Large Language Models
by: Lan, Xiaohan, et al.
Published: (2024)

EvoGround: Self-Evolving Video Agents for Video Temporal Grounding
by: Jung, Minjoon, et al.
Published: (2026)

Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding
by: Chen, Guo, et al.
Published: (2024)

VideoMamba: Spatio-Temporal Selective State Space Model
by: Park, Jinyoung, et al.
Published: (2024)

Open-ended Hierarchical Streaming Video Understanding with Vision Language Models
by: Kang, Hyolim, et al.
Published: (2025)

STORM: Token-Efficient Long Video Understanding for Multimodal LLMs
by: Jiang, Jindong, et al.
Published: (2025)

VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs
by: Zhu, Jiaying, et al.
Published: (2025)

Vidi2.5: Large Multimodal Models for Video Understanding and Creation
by: Vidi Team, et al.
Published: (2025)