Cover Image

LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Boyuan, Zhao, Jiaxing, Wei, Xihan, Hou, Qibin
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction Multimedia
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding
by: Sun, Boyuan, et al.
Published: (2025)

See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding
by: Sun, Boyuan, et al.
Published: (2026)

SVFAP: Self-supervised Video Facial Affect Perceiver
by: Sun, Licai, et al.
Published: (2023)

MindCine: Multimodal EEG-to-Video Reconstruction with Large-Scale Pretrained Models
by: Zhou, Tian-Yi, 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)

VideoMap: Supporting Video Editing Exploration, Brainstorming, and Prototyping in the Latent Space
by: Lin, David Chuan-En, et al.
Published: (2022)

MindCross: Fast New Subject Adaptation with Limited Data for Cross-subject Video Reconstruction from Brain Signals
by: Liu, Xuan-Hao, et al.
Published: (2025)

G3R: Generating Rich and Fine-grained mmWave Radar Data from 2D Videos for Generalized Gesture Recognition
by: Deng, Kaikai, et al.
Published: (2024)

Editing Physiological Signals in Videos Using Latent Representations
by: Zhou, Tianwen, et al.
Published: (2025)

Videogenic: Identifying Highlight Moments in Videos with Professional Photographs as a Prior
by: Lin, David Chuan-En, et al.
Published: (2022)

Seeing, Hearing, and Knowing Together: Multimodal Strategies in Deepfake Videos Detection
by: Chen, Chen, et al.
Published: (2026)

Panonut360: A Head and Eye Tracking Dataset for Panoramic Video
by: Xu, Yutong, et al.
Published: (2024)

Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model
by: He, Xu, et al.
Published: (2024)

AttentionBender: Manipulating Cross-Attention in Video Diffusion Transformers as a Creative Probe
by: Cole, Adam, et al.
Published: (2026)

BATON: A Multimodal Benchmark for Bidirectional Automation Transition Observation in Naturalistic Driving
by: Wang, Yuhang, et al.
Published: (2026)

Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs
by: Caffagni, Davide, et al.
Published: (2024)

Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning
by: Chaubey, Ashutosh, et al.
Published: (2025)

Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation
by: Yang, Sicheng, et al.
Published: (2025)

FastPerson: Enhancing Video Learning through Effective Video Summarization that Preserves Linguistic and Visual Contexts
by: Kawamura, Kazuki, et al.
Published: (2024)

Social-LLaVA: Enhancing Robot Navigation through Human-Language Reasoning in Social Spaces
by: Payandeh, Amirreza, et al.
Published: (2024)

Color When It Counts: Grayscale-Guided Online Triggering for Always-On Streaming Video Sensing
by: Cai, Weitong, et al.
Published: (2026)

ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model
by: Cheng, Luo, et al.
Published: (2025)

SentiAvatar: Towards Expressive and Interactive Digital Humans
by: Jin, Chuhao, et al.
Published: (2026)

ReactFace: Online Multiple Appropriate Facial Reaction Generation in Dyadic Interactions
by: Luo, Cheng, et al.
Published: (2023)

Across-Game Engagement Modelling via Few-Shot Learning
by: Pinitas, Kosmas, et al.
Published: (2024)

Emotion Based Prediction in the Context of Optimized Trajectory Planning for Immersive Learning
by: Sungheetha, Akey, et al.
Published: (2023)

MS2Mesh-XR: Multi-modal Sketch-to-Mesh Generation in XR Environments
by: Tong, Yuqi, et al.
Published: (2024)

Generative Timelines for Instructed Visual Assembly
by: Pardo, Alejandro, et al.
Published: (2024)

Shu Dao: A Calligraphy Score Framework Linking Calligraphy, Music, and Performance
by: Huang, Lican
Published: (2026)

Secure & Personalized Music-to-Video Generation via CHARCHA
by: Agarwal, Mehul, et al.
Published: (2025)

EyeNavGS: A 6-DoF Navigation Dataset and Record-n-Replay Software for Real-World 3DGS Scenes in VR
by: Ding, Zihao, et al.
Published: (2025)

DiffMesh: A Motion-aware Diffusion Framework for Human Mesh Recovery from Videos
by: Zheng, Ce, et al.
Published: (2023)

Code2Video: A Code-centric Paradigm for Educational Video Generation
by: Chen, Yanzhe, et al.
Published: (2025)

WebXR, A-Frame and Networked-Aframe as a Basis for an Open Metaverse: A Conceptual Architecture
by: Macario, Giuseppe
Published: (2024)

LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning
by: Cocchi, Federico, et al.
Published: (2025)

SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation
by: Yin, Wanqi, et al.
Published: (2025)

adder-viz: Real-Time Visualization Software for Transcoding Event Video
by: Freeman, Andrew C., et al.
Published: (2025)

SkinGEN: an Explainable Dermatology Diagnosis-to-Generation Framework with Interactive Vision-Language Models
by: Lin, Bo, et al.
Published: (2024)

Learning High-Quality Navigation and Zooming on Omnidirectional Images in Virtual Reality
by: Cao, Zidong, et al.
Published: (2024)

Towards Aligning Multimodal LLMs with Human Experts: A Focus on Parent-Child Interaction
by: Shi, Weiyan, et al.
Published: (2025)