Image de couverture de livre

Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Pengxiang, Tsai, Joey, Xue, Hongwei, Shi, Kunyu, Yan, Shilin
Format:	Preprint
Publié:	2026
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

CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms
par: Yan, Shilin, et autres
Publié: (2025)

SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMs
par: Tong, Jintao, et autres
Publié: (2026)

Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models
par: Yan, Shilin, et autres
Publié: (2026)

MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning
par: Shen, Haozhan, et autres
Publié: (2026)

PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation
par: Wang, Ao, et autres
Publié: (2024)

FaceGCD: Generalized Face Discovery via Dynamic Prefix Generation
par: Oh, Yunseok, et autres
Publié: (2025)

MS-CustomNet: Controllable Multi-Subject Customization with Hierarchical Relational Semantics
par: Cai, Pengxiang, et autres
Publié: (2026)

Semantic-Aware Prefix Learning for Token-Efficient Image Generation
par: Li, Qingfeng, et autres
Publié: (2026)

Enhancing Continual Learning of Vision-Language Models via Dynamic Prefix Weighting
par: Jang, Hyeonseo, et autres
Publié: (2026)

RTFDNet: Fusion-Decoupling for Robust RGB-T Segmentation
par: Tan, Kunyu, et autres
Publié: (2026)

VPG: Visual Prefix Guidance for Autoregressive Image and Video Generation
par: Liao, Xinyao, et autres
Publié: (2026)

FastVMT: Eliminating Redundancy in Video Motion Transfer
par: Ma, Yue, et autres
Publié: (2026)

Beyond Reconstruction: Reconstruction-to-Vector Diffusion for Hyperspectral Anomaly Detection
par: Xiang, Jijun, et autres
Publié: (2026)

Visual Perception by Large Language Model's Weights
par: Ma, Feipeng, et autres
Publié: (2024)

Multi-Modal Generative Embedding Model
par: Ma, Feipeng, et autres
Publié: (2024)

Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference
par: Zhao, Han, et autres
Publié: (2024)

Towards more realistic human motion prediction with attention to motion coordination
par: Ding, Pengxiang, et autres
Publié: (2024)

DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Mode
par: Huang, Junjia, et autres
Publié: (2025)

Go Beyond Earth: Understanding Human Actions and Scenes in Microgravity Environments
par: Wen, Di, et autres
Publié: (2025)

PVP: Polar Representation Boost for 3D Semantic Occupancy Prediction
par: Xue, Yujing, et autres
Publié: (2024)

Fast and Stable Diffusion Inverse Solver with History Gradient Update
par: He, Linchao, et autres
Publié: (2023)

Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance
par: Song, Wenxuan, et autres
Publié: (2026)

Hybrid SD: Edge-Cloud Collaborative Inference for Stable Diffusion Models
par: Yan, Chenqian, et autres
Publié: (2024)

VISA: Reasoning Video Object Segmentation via Large Language Models
par: Yan, Cilin, et autres
Publié: (2024)

FIN: Fast Inference Network for Map Segmentation
par: Bispo, Ruan, et autres
Publié: (2025)

Enhancing Adversarial Transferability via Component-Wise Transformation
par: Liu, Hangyu, et autres
Publié: (2025)

User-Aware Prefix-Tuning is a Good Learner for Personalized Image Captioning
par: Wang, Xuan, et autres
Publié: (2023)

Beyond the Textual: Generating Coherent Visual Options for MCQs
par: Wang, Wanqiang, et autres
Publié: (2025)

Proteus-ID: ID-Consistent and Motion-Coherent Video Customization
par: Zhang, Guiyu, et autres
Publié: (2025)

Explainable AI (XAI) in Image Segmentation in Medicine, Industry, and Beyond: A Survey
par: Gipiškis, Rokas, et autres
Publié: (2024)

Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymization
par: Yang, Haoxin, et autres
Publié: (2025)

T-MASK: Temporal Masking for Probing Foundation Models across Camera Views in Driver Monitoring
par: Ponbagavathi, Thinesh Thiyakesan, et autres
Publié: (2025)

Probing Fine-Grained Action Understanding and Cross-View Generalization of Foundation Models
par: Ponbagavathi, Thinesh Thiyakesan, et autres
Publié: (2024)

Cascade-Free Mandarin Visual Speech Recognition via Semantic-Guided Cross-Representation Alignment
par: Yang, Lei, et autres
Publié: (2026)

Beyond Static Frames: Temporal Aggregate-and-Restore Vision Transformer for Human Pose Estimation
par: Fang, Hongwei, et autres
Publié: (2026)

FastUSP: A Multi-Level Collaborative Acceleration Framework for Distributed Diffusion Model Inference
par: Li, Guandong
Publié: (2026)

Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning
par: Shi, Fan, et autres
Publié: (2025)

A Visual Semantic Adaptive Watermark grounded by Prefix-Tuning for Large Vision-Language Model
par: Zheng, Qi, et autres
Publié: (2026)

Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate Gradients
par: Lun, Li, et autres
Publié: (2025)

Consistent text-to-image generation via scene de-contextualization
par: Tang, Song, et autres
Publié: (2025)