Cover Image

Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Zhihang, Xie, Chen-Wei, Li, Pandeng, Zhao, Liming, Tang, Longxiang, Zheng, Yun, Liu, Chuanbin, Xie, Hongtao
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Rethinking Video Tokenization: A Conditioned Diffusion-based Approach
by: Yang, Nianzu, et al.
Published: (2025)

Hallucination Mitigation Prompts Long-term Video Understanding
by: Sun, Yiwei, et al.
Published: (2024)

From Evaluation to Defense: Advancing Safety in Video Large Language Models
by: Sun, Yiwei, et al.
Published: (2025)

RegionRAG: Region-level Retrieval-Augmented Generation for Visual Document Understanding
by: Li, Yinglu, et al.
Published: (2025)

ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement
by: Liu, Zhihang, et al.
Published: (2025)

InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models
by: Liu, Xinxin, et al.
Published: (2026)

CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness
by: Liu, Zhihang, et al.
Published: (2025)

SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability
by: Wang, Jiankang, et al.
Published: (2025)

GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning
by: Jiang, Kaixun, et al.
Published: (2026)

OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models
by: Ding, Yue, et al.
Published: (2026)

PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering
by: Gao, Yifan, et al.
Published: (2025)

Decoupling Perception from Reasoning for Hallucination-Resistant Video Understanding
by: Pu, Bowei, et al.
Published: (2025)

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

AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation
by: Ge, Jiannan, et al.
Published: (2024)

Universal Video Temporal Grounding with Generative Multi-modal Large Language Models
by: Li, Zeqian, et al.
Published: (2025)

Structure-aware Domain Knowledge Injection for Large Language Models
by: Liu, Kai, et al.
Published: (2024)

UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface
by: Tang, Hao, et al.
Published: (2025)

Vision-centric Token Compression in Large Language Model
by: Xing, Ling, et al.
Published: (2025)

FCoT-VL:Advancing Text-oriented Large Vision-Language Models with Efficient Visual Token Compression
by: Li, Jianjian, et al.
Published: (2025)

Understanding the Multi-modal Prompts of the Pre-trained Vision-Language Model
by: Ma, Shuailei, et al.
Published: (2023)

UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing
by: Tang, Hao, et al.
Published: (2025)

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

Efficient Multi-modal Large Language Models via Visual Token Grouping
by: Huang, Minbin, et al.
Published: (2024)

InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models
by: Wei, Cong, et al.
Published: (2024)

InstructCoder: Instruction Tuning Large Language Models for Code Editing
by: Li, Kaixin, et al.
Published: (2023)

Rethinking Personalization in Large Language Models at the Token Level
by: Zhang, Chenheng, et al.
Published: (2026)

Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
by: Yan, Jun, et al.
Published: (2023)

TEAL: Tokenize and Embed ALL for Multi-modal Large Language Models
by: Yang, Zhen, et al.
Published: (2023)

HybridToken-VLM: Hybrid Token Compression for Vision-Language Models
by: Zhang, Jusheng, et al.
Published: (2025)

VIMI: Grounding Video Generation through Multi-modal Instruction
by: Fang, Yuwei, et al.
Published: (2024)

VII: Visual Instruction Injection for Jailbreaking Image-to-Video Generation Models
by: Zheng, Bowen, et al.
Published: (2026)

Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language Models
by: Cui, Xiao, et al.
Published: (2024)

VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models
by: Wang, Yuxuan, et al.
Published: (2024)

Large Multi-modal Models Can Interpret Features in Large Multi-modal Models
by: Zhang, Kaichen, et al.
Published: (2024)

Scaffolding Language Learning via Multi-modal Tutoring Systems with Pedagogical Instructions
by: Liu, Zhengyuan, et al.
Published: (2024)

OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models
by: Yang, Morunliu, et al.
Published: (2026)

TiFRe: Text-guided Video Frame Reduction for Efficient Video Multi-modal Large Language Models
by: Zheng, Xiangtian, et al.
Published: (2026)

AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation
by: Liao, Zhaohe, et al.
Published: (2026)

From Token to Token Pair: Efficient Prompt Compression for Large Language Models in Clinical Prediction
by: Zhu, Mingcheng, et al.
Published: (2026)

Language-Guided Token Compression with Reinforcement Learning in Large Vision-Language Models
by: Cao, Sihan, et al.
Published: (2026)