Image de couverture de livre

Shifting AI Efficiency From Model-Centric to Data-Centric Compression

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Xuyang, Wen, Zichen, Wang, Shaobo, Chen, Junjie, Tao, Zhishan, Wang, Yubo, Chen, Tailai, Jin, Xiangqi, Zou, Chang, Wang, Yiyu, Liao, Chenfei, Zheng, Xu, Chen, Honggang, Li, Weijia, Hu, Xuming, He, Conghui, Zhang, Linfeng
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence 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

Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
par: Wang, Yiyu, et autres
Publié: (2025)

Variation-aware Vision Token Dropping for Faster Large Vision-Language Models
par: Chen, Junjie, et autres
Publié: (2025)

IPCV: Information-Preserving Compression for MLLM Visual Encoders
par: Chen, Yuan, et autres
Publié: (2025)

Flash-Unified: A Training-Free and Task-Aware Acceleration Framework for Native Unified Models
par: Ke, Junlong, et autres
Publié: (2026)

Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning
par: Wang, Shaobo, et autres
Publié: (2025)

Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods
par: Liao, Chenfei, et autres
Publié: (2025)

VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction
par: Wang, Shaobo, et autres
Publié: (2025)

Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models
par: Liu, Xuyang, et autres
Publié: (2025)

Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More
par: Wen, Zichen, et autres
Publié: (2025)

AI for Service: Proactive Assistance with AI Glasses
par: Wen, Zichen, et autres
Publié: (2025)

Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models
par: Han, Yuhang, et autres
Publié: (2026)

Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?
par: Wen, Zichen, et autres
Publié: (2025)

Efficient Multi-modal Large Language Models via Progressive Consistency Distillation
par: Wen, Zichen, et autres
Publié: (2025)

Can MLLMs Reason Beyond Language? VisReason: A Comprehensive Benchmark for Vision-Centric Reasoning
par: Guo, Longteng, et autres
Publié: (2026)

AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs
par: He, Peize, et autres
Publié: (2025)

EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant
par: Wen, Zichen, et autres
Publié: (2026)

Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers
par: Wang, Shaobo, et autres
Publié: (2024)

Text Data-Centric Image Captioning with Interactive Prompts
par: Wang, Yiyu, et autres
Publié: (2024)

Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models
par: Liu, Xuyang, et autres
Publié: (2025)

Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration
par: Han, Yuhang, et autres
Publié: (2024)

Dataset Distillation with Neural Characteristic Function: A Minmax Perspective
par: Wang, Shaobo, et autres
Publié: (2025)

Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching
par: Zheng, Zhixin, et autres
Publié: (2025)

The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs
par: Wen, Zichen, et autres
Publié: (2025)

LucidDreaming: Controllable Object-Centric 3D Generation
par: Wang, Zhaoning, et autres
Publié: (2023)

dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching
par: Liu, Zhiyuan, et autres
Publié: (2025)

VideoChat: Chat-Centric Video Understanding
par: Li, KunChang, et autres
Publié: (2023)

OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation
par: Zhong, Ding, et autres
Publié: (2025)

Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving
par: Xiong, Minhao, et autres
Publié: (2025)

Trustworthy Medical Question Answering: An Evaluation-Centric Survey
par: Wang, Yinuo, et autres
Publié: (2025)

Towards 3D Object-Centric Feature Learning for Semantic Scene Completion
par: Wang, Weihua, et autres
Publié: (2025)

Thinking Inside the Mask: In-Place Prompting in Diffusion LLMs
par: Jin, Xiangqi, et autres
Publié: (2025)

EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
par: Yang, Yantai, et autres
Publié: (2025)

Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation
par: Liao, Kang, et autres
Publié: (2025)

Data Distribution Matters: A Data-Centric Perspective on Context Compression for Large Language Model
par: Lv, Kangtao, et autres
Publié: (2026)

Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching
par: Zou, Chang, et autres
Publié: (2024)

Diffusion LLM with Native Variable Generation Lengths: Let [EOS] Lead the Way
par: Yang, Yicun, et autres
Publié: (2025)

SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation
par: Dou, Weijia, et autres
Publié: (2026)

VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders
par: Liu, Xuyang, et autres
Publié: (2023)

NestedKV: Nested Memory Routing for Long-Context KV Cache Compression
par: Chen, Hong, et autres
Publié: (2026)

StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding
par: Wang, Junxi, et autres
Publié: (2026)