Cover Image

Small Vision-Language Models are Smart Compressors for Long Video Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fei, Junjie, Chen, Jun, Liu, Zechun, Xiong, Yunyang, Zhou, Chong, Wen, Wei, Han, Junlin, Zhuge, Mingchen, Suri, Saksham, Qian, Qi, Liu, Shuming, Wu, Lemeng, Krishnamoorthi, Raghuraman, Chandra, Vikas, Elhoseiny, Mohamed, Zhu, Chenchen
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Efficient Track Anything
by: Xiong, Yunyang, et al.
Published: (2024)

EdgeTAM: On-Device Track Anything Model
by: Zhou, Chong, et al.
Published: (2025)

PathFusion: Path-consistent Lidar-Camera Deep Feature Fusion
by: Wu, Lemeng, et al.
Published: (2022)

VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
by: Liu, Shuming, et al.
Published: (2026)

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

SqueezeSAM: User friendly mobile interactive segmentation
by: Varadarajan, Balakrishnan, et al.
Published: (2023)

Efficient Universal Perception Encoder
by: Zhu, Chenchen, et al.
Published: (2026)

dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models
by: Zhang, Wenxuan, et al.
Published: (2026)

MobileMoE: Scaling On-Device Mixture of Experts
by: Chen, Yanbei, et al.
Published: (2026)

MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
by: Liu, Zechun, et al.
Published: (2024)

SpinQuant: LLM quantization with learned rotations
by: Liu, Zechun, et al.
Published: (2024)

Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts
by: Jawahar, Ganesh, et al.
Published: (2023)

Agent-as-a-Judge: Evaluate Agents with Agents
by: Zhuge, Mingchen, et al.
Published: (2024)

ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
by: Liu, Zechun, et al.
Published: (2025)

MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes
by: Zhao, Changsheng, et al.
Published: (2025)

Goldfish: Vision-Language Understanding of Arbitrarily Long Videos
by: Ataallah, Kirolos, et al.
Published: (2024)

Communication Efficient Distributed Training with Distributed Lion
by: Liu, Bo, et al.
Published: (2024)

DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
by: Fu, Yonggan, et al.
Published: (2022)

Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images
by: Yu, Zhuoran, et al.
Published: (2023)

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations
by: Fedorov, Igor, et al.
Published: (2024)

Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory
by: Agarwal, Vatsal, et al.
Published: (2026)

VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
by: Li, Xiang, et al.
Published: (2024)

Kestrel: 3D Multimodal LLM for Part-Aware Grounded Description
by: Ahmed, Mahmoud, et al.
Published: (2024)

3DCoMPaT200: Language-Grounded Compositional Understanding of Parts and Materials of 3D Shapes
by: Ahmed, Mahmoud, et al.
Published: (2025)

Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models
by: Xiong, Ruibin, et al.
Published: (2025)

UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders
by: Walmer, Matthew, et al.
Published: (2026)

LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptors
by: Suri, Saksham, et al.
Published: (2024)

StoryGPT-V: Large Language Models as Consistent Story Visualizers
by: Shen, Xiaoqian, et al.
Published: (2023)

Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding
by: Shen, Xiaoqian, et al.
Published: (2025)

TransCompressor: LLM-Powered Multimodal Data Compression for Smart Transportation
by: Yang, Huanqi, et al.
Published: (2024)

The Compressor-Retriever Architecture for Language Model OS
by: Yang, Yuan, et al.
Published: (2024)

EgoAVU: Egocentric Audio-Visual Understanding
by: Seth, Ashish, et al.
Published: (2026)

Neural Computers
by: Zhuge, Mingchen, et al.
Published: (2026)

Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network
by: Ji, Ge-Peng, et al.
Published: (2021)

M-MiniGPT4: Multilingual VLLM Alignment via Translated Data
by: Han, Seung Hun, et al.
Published: (2026)

Exploring Audio Hallucination in Egocentric Video Understanding
by: Seth, Ashish, et al.
Published: (2026)

Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents
by: Chen, Jun, et al.
Published: (2024)

LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior
by: Wang, Hanyu, et al.
Published: (2024)

Target-Aware Language Modeling via Granular Data Sampling
by: Chang, Ernie, et al.
Published: (2024)

XProvence: Zero-Cost Multilingual Context Pruning for Retrieval-Augmented Generation
by: Mohamed, Youssef, et al.
Published: (2026)