Image de couverture de livre

Revisiting MLLM Token Technology through the Lens of Classical Visual Coding

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Jinming, Lin, Junyan, Wei, Yuntao, Shao, Kele, Tao, Keda, Huang, Jianguo, Yang, Xudong, Chen, Zhibo, Wang, Huan, Jin, Xin
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification
par: Jin, Xin, et autres
Publié: (2026)

StreamingTOM: Streaming Token Compression for Efficient Video Understanding
par: Chen, Xueyi, et autres
Publié: (2025)

HoliTom: Holistic Token Merging for Fast Video Large Language Models
par: Shao, Kele, et autres
Publié: (2025)

OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
par: Tao, Keda, et autres
Publié: (2025)

Semantics Disentanglement and Composition for Universal Image Coding with Efficiently LLM Reasoning and Generative Diffusion
par: Liu, Jinming, et autres
Publié: (2024)

Tell Codec What Worth Compressing: Semantically Disentangled Image Coding for Machine with LMMs
par: Liu, Jinming, et autres
Publié: (2024)

A Survey of Token Compression for Efficient Multimodal Large Language Models
par: Shao, Kele, et autres
Publié: (2025)

Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs
par: Zhang, Kejia, et autres
Publié: (2025)

DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
par: Tao, Keda, et autres
Publié: (2024)

Revisiting Visual Understanding in Multimodal Reasoning through a Lens of Image Perturbation
par: Li, Yuting, et autres
Publié: (2025)

Is Oracle Pruning the True Oracle?
par: Feng, Sicheng, et autres
Publié: (2024)

StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding
par: Jin, Xinqi, et autres
Publié: (2025)

TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs
par: Zhang, Kejia, et autres
Publié: (2025)

UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking
par: Wu, Hao, et autres
Publié: (2026)

ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement
par: Huang, Runhui, et autres
Publié: (2025)

Limitations and Implications: Revisiting the Clinical Relevance of Ductal Features in Abiraterone‐Treated Prostate Cancer
par: Wenjing Xie, et autres
Publié: (2026)

Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM
par: Chi, Donghwan, et autres
Publié: (2025)

CodeDance: A Dynamic Tool-integrated MLLM for Executable Visual Reasoning
par: Song, Qi, et autres
Publié: (2025)

Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimization
par: Chen, Zhibo, et autres
Publié: (2024)

TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models
par: Tan, Xudong, et autres
Publié: (2025)

VisualLens: Personalization through Task-Agnostic Visual History
par: Zhu, Wang Bill, et autres
Publié: (2024)

Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models
par: Tao, Keda, et autres
Publié: (2025)

Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
par: Du, Wenjie, et autres
Publié: (2025)

Speak While Watching: Unleashing TRUE Real-Time Video Understanding Capability of Multimodal Large Language Models
par: Lin, Junyan, et autres
Publié: (2026)

AdaCodec: A Predictive Visual Code for Video MLLMs
par: Hou, Haowen, et autres
Publié: (2026)

Visual Position Prompt for MLLM based Visual Grounding
par: Tang, Wei, et autres
Publié: (2025)

Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See
par: Zhang, Zeliang, et autres
Publié: (2024)

LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs
par: Krojer, Benno, et autres
Publié: (2026)

LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs
par: Tao, Keda, et autres
Publié: (2026)

RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs
par: Li, Hongliang, et autres
Publié: (2025)

ECR-Chain: Advancing Generative Language Models to Better Emotion-Cause Reasoners through Reasoning Chains
par: Huang, Zhaopei, et autres
Publié: (2024)

Sequential Token Merging: Revisiting Hidden States
par: Wen, Yan, et autres
Publié: (2025)

Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior
par: Feng, Ruoyu, et autres
Publié: (2025)

Revisiting Multi-Permutation Equivariance through the Lens of Irreducible Representations
par: Sverdlov, Yonatan, et autres
Publié: (2024)

Revisiting Transformers through the Lens of Low Entropy and Dynamic Sparsity
par: Ren, Ruifeng, et autres
Publié: (2025)

Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights
par: Karthika, N J, et autres
Publié: (2025)

EfficientUICoder: Efficient MLLM-based UI Code Generation via Input and Output Token Compression
par: Xiao, Jingyu, et autres
Publié: (2025)

Rethinking MLLM Itself as a Segmenter with a Single Segmentation Token
par: Zhang, Anqi, et autres
Publié: (2026)

Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understanding
par: Shao, Run, et autres
Publié: (2024)

Active Perception Agent for Omnimodal Audio-Video Understanding
par: Tao, Keda, et autres
Publié: (2025)