Image de couverture de livre

MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Yucheng, Jiang, Huiqiang, Zhang, Chengruidong, Wu, Qianhui, Luo, Xufang, Ahn, Surin, Abdi, Amir H., Li, Dongsheng, Gao, Jianfeng, Yang, Yuqing, Qiu, Lili
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
par: Jiang, Huiqiang, et autres
Publié: (2024)

SCBench: A KV Cache-Centric Analysis of Long-Context Methods
par: Li, Yucheng, et autres
Publié: (2024)

MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training
par: Li, Wenxuan, et autres
Publié: (2025)

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression
par: Li, Yucheng, et autres
Publié: (2025)

LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
par: Jiang, Huiqiang, et autres
Publié: (2023)

SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling
par: Zhang, Yiqi, et autres
Publié: (2026)

Accelerating Prefilling via Decoding-time Contribution Sparsity
par: He, Zhiyuan, et autres
Publié: (2025)

Mitigate Position Bias in Large Language Models via Scaling a Single Dimension
par: Yu, Yijiong, et autres
Publié: (2024)

On Memory Construction and Retrieval for Personalized Conversational Agents
par: Pan, Zhuoshi, et autres
Publié: (2025)

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
par: Liu, Di, et autres
Publié: (2024)

LeanK: Learnable K Cache Channel Pruning for Efficient Decoding
par: Zhang, Yike, et autres
Publié: (2025)

VecAttention: Vector-wise Sparse Attention for Accelerating Long Context Inference
par: Liu, Anmin, et autres
Publié: (2026)

Unified Medical Image Pre-training in Language-Guided Common Semantic Space
par: He, Xiaoxuan, et autres
Publié: (2023)

LLM-RadJudge: Achieving Radiologist-Level Evaluation for X-Ray Report Generation
par: Wang, Zilong, et autres
Publié: (2024)

Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
par: Liu, Zeyuan, et autres
Publié: (2026)

VL Norm: Rethink Loss Aggregation in RLVR
par: He, Zhiyuan, et autres
Publié: (2025)

Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
par: Yang, Shuo, et autres
Publié: (2025)

pMoE: Prompting Diverse Experts Together Wins More in Visual Adaptation
par: Mo, Shentong, et autres
Publié: (2026)

VisRL: Intention-Driven Visual Perception via Reinforced Reasoning
par: Chen, Zhangquan, et autres
Publié: (2025)

Position Engineering: Boosting Large Language Models through Positional Information Manipulation
par: He, Zhiyuan, et autres
Publié: (2024)

Parrot: Efficient Serving of LLM-based Applications with Semantic Variable
par: Lin, Chaofan, et autres
Publié: (2024)

Region-Adaptive Sampling for Diffusion Transformers
par: Liu, Ziming, et autres
Publié: (2025)

LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
par: Pan, Zhuoshi, et autres
Publié: (2024)

Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty
par: Kim, Jeonghye, et autres
Publié: (2026)

Sparser Block-Sparse Attention via Token Permutation
par: Wang, Xinghao, et autres
Publié: (2025)

Chain-of-Model Learning for Language Model
par: Song, Kaitao, et autres
Publié: (2025)

LSPT: Long-term Spatial Prompt Tuning for Visual Representation Learning
par: Mo, Shentong, et autres
Publié: (2024)

A Large-scale Medical Visual Task Adaptation Benchmark
par: Mo, Shentong, et autres
Publié: (2024)

Agent Lightning: Train ANY AI Agents with Reinforcement Learning
par: Luo, Xufang, et autres
Publié: (2025)

Designing Network Algorithms via Large Language Models
par: He, Zhiyuan, et autres
Publié: (2024)

Babel: A Scalable Pre-trained Model for Multi-Modal Sensing via Expandable Modality Alignment
par: Dai, Shenghong, et autres
Publié: (2024)

Rates of convergence in long time asymptotics of an alignment model with symmetry breaking
par: Surin, Alexandre
Publié: (2025)

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
par: Kim, Jeonghye, et autres
Publié: (2026)

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key
par: Yang, Zhihe, et autres
Publié: (2025)

Improving Sparse Autoencoder with Dynamic Attention
par: Wang, Dongsheng, et autres
Publié: (2026)

Lag-Relative Sparse Attention In Long Context Training
par: Liang, Manlai, et autres
Publié: (2025)

Rectified Sparse Attention
par: Sun, Yutao, et autres
Publié: (2025)

P‐3.9: The Influence of Parallax and Shape Type Factors on the Perception of AR Equipment in Dark Environment
par: Huiqiang Xia, et autres
Publié: (2024)

S2O: Early Stopping for Sparse Attention via Online Permutation
par: Zhang, Yu, et autres
Publié: (2026)

FAST-Prefill: FPGA Accelerated Sparse Attention for Long Context LLM Prefill
par: Jayanth, Rakshith, et autres
Publié: (2026)