Cover Image

Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Xuan, Du, Cunxiao, Yu, Sicheng, Wu, Jiawei, Zhang, Fengzhuo, Gao, Wei, Liu, Qian
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation
by: Li, Xingyao, et al.
Published: (2026)

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
by: Yang, Penghui, et al.
Published: (2025)

MMViR: A Multi-Modal and Multi-Granularity Representation for Long-range Video Understanding
by: Li, Zizhong, et al.
Published: (2026)

LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation
by: Zhang, Xuan, et al.
Published: (2024)

Frame-Voyager: Learning to Query Frames for Video Large Language Models
by: Yu, Sicheng, et al.
Published: (2024)

Prompt as Free Lunch: Enhancing Diversity in Source-Free Cross-domain Few-shot Learning through Semantic-Guided Prompting
by: Zhuo, Linhai, et al.
Published: (2024)

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
by: Cheng, Zesen, et al.
Published: (2024)

Are Vision LLMs Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video Understanding
by: Zeng, Tong, et al.
Published: (2025)

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
by: Song, Enxin, et al.
Published: (2023)

LLMs Meet Long Video: Advancing Long Video Question Answering with An Interactive Visual Adapter in LLMs
by: Li, Yunxin, et al.
Published: (2024)

VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI
by: Cheng, Sijie, et al.
Published: (2024)

ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding
by: Ma, David, et al.
Published: (2025)

DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding
by: Zhang, Hongzhi, et al.
Published: (2025)

VideoChat: Chat-Centric Video Understanding
by: Li, KunChang, et al.
Published: (2023)

Unleashing Hour-Scale Video Training for Long Video-Language Understanding
by: Lin, Jingyang, et al.
Published: (2025)

GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents
by: Wang, Yunzhe, et al.
Published: (2026)

FreeInv: Free Lunch for Improving DDIM Inversion
by: Bao, Yuxiang, et al.
Published: (2025)

Understanding Alignment in Multimodal LLMs: A Comprehensive Study
by: Amirloo, Elmira, et al.
Published: (2024)

Video Understanding with Large Language Models: A Survey
by: Tang, Yolo Y., et al.
Published: (2023)

An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs' Sentimental Perception Capability
by: Wu, Daiqing, et al.
Published: (2025)

VideoJudge: Bootstrapping Enables Scalable Supervision of MLLM-as-a-Judge for Video Understanding
by: Waheed, Abdul, et al.
Published: (2025)

Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding
by: Wang, Xiao, et al.
Published: (2024)

Freeplane: Unlocking Free Lunch in Triplane-Based Sparse-View Reconstruction Models
by: Sun, Wenqiang, et al.
Published: (2024)

Draw2Think: Harnessing Geometry Reasoning through Constraint Engine Interaction
by: Hu, Juncheng, et al.
Published: (2026)

VideoExplorer: Think With Videos For Agentic Long-Video Understanding
by: Yuan, Huaying, et al.
Published: (2025)

NeMo: Needle in a Montage for Video-Language Understanding
by: Hu, Zi-Yuan, et al.
Published: (2025)

Free-Lunch Long Video Generation via Layer-Adaptive O.O.D Correction
by: Tian, Jiahao, et al.
Published: (2026)

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

LLaVA-Video: Video Instruction Tuning With Synthetic Data
by: Zhang, Yuanhan, et al.
Published: (2024)

Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities Using Web Instructional Videos
by: Ohkawa, Takehiko, et al.
Published: (2023)

Speak While Watching: Unleashing TRUE Real-Time Video Understanding Capability of Multimodal Large Language Models
by: Lin, Junyan, et al.
Published: (2026)

Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
by: Fu, Chaoyou, et al.
Published: (2024)

Realizing Video Summarization from the Path of Language-based Semantic Understanding
by: Mu, Kuan-Chen, et al.
Published: (2024)

Towards Event-oriented Long Video Understanding
by: Du, Yifan, et al.
Published: (2024)

NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing
by: Pan, Tianlin, et al.
Published: (2026)

How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts
by: Qian, Yusu, et al.
Published: (2024)

FreeCus: Free Lunch Subject-driven Customization in Diffusion Transformers
by: Zhang, Yanbing, et al.
Published: (2025)

Prompt Highlighter: Interactive Control for Multi-Modal LLMs
by: Zhang, Yuechen, et al.
Published: (2023)

RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers
by: Zhao, Min, et al.
Published: (2025)

IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs
by: Ma, David, et al.
Published: (2025)