图像生成 - arXivDaily 专题

2510.19356 2025-10-23 cs.RO 50%

Imitation Learning Policy based on Multi-Step Consistent Integration Shortcut Model

Yu Fang, Xinyu Wang, Xuehe Zhang, Wanli Xue, Mingwei Zhang, Shengyong Chen, Jie Zhao

机构 * State Key Laboratory of Robotics and Systems, Harbin Institute of Technology（机器人与系统国家重点实验室，哈尔滨工业大学）； School of Computer Science and Engineering, Tianjin University of Technology（计算机科学与工程学院，天津理工大学）

专题命中效率与蒸馏：diffusion(abstract)

2501.12407 2025-10-23 cs.DC cs.LG 50%

The Streaming Batch Model for Efficient and Fault-Tolerant Heterogeneous Execution

Frank Sifei Luan, Ron Yifeng Wang, Yile Gu, Ziming Mao, Charlotte Lin, Amog Kamsetty, Hao Chen, Cheng Su, Balaji Veeramani, Scott Lee, SangBin Cho, Clark Zinzow, Eric Liang, Ion Stoica, Stephanie Wang

机构 * UC Berkeley（加州大学伯克利分校）； University of Washington（华盛顿大学）； Anyscale

专题命中效率与蒸馏：diffusion(abstract)

2509.02106 2025-10-22 cs.DB 50%

GeoLayer: Towards Low-Latency and Cost-Efficient Geo-Distributed Graph Stores with Layered Graph

Feng Yao, Xiaokang Yang, Shufeng Gong, Song Yu, Yanfeng Zhang, Ge Yu

专题命中效率与蒸馏：diffusion(abstract)

2507.15897 2025-10-21 cs.LG cs.AI stat.ML 50%

ReDi: Rectified Discrete Flow

Jaehoon Yoo, Wonjung Kim, Seunghoon Hong

专题命中效率与蒸馏：image generation(abstract)

2505.06535 2025-10-21 cs.AI cs.LG stat.ML 50%

Online Feedback Efficient Active Target Discovery in Partially Observable Environments

Anindya Sarkar, Binglin Ji, Yevgeniy Vorobeychik

专题命中效率与蒸馏：diffusion(abstract)

Comments 31 pages, 28 figures, Accepted to NeurIPS 2025

2510.15628 2025-10-20 quant-ph 50%

Time evolution of the Husimi and Glauber-Sudarshan functions in terms of complementary Hamiltonian symbols

Mritunjay Tyagi, Simon Friederich

专题命中效率与蒸馏：diffusion(abstract)

Comments 14 pages

2510.12842 2025-10-17 q-bio.QM cs.LG 50%

Protenix-Mini+: efficient structure prediction model with scalable pairformer

Bo Qiang, Chengyue Gong, Xinshi Chen, Yuxuan Zhang, Wenzhi Xiao

机构 * University of Washington（华盛顿大学）

专题命中效率与蒸馏：diffusion(abstract)

2507.23675 2025-10-17 cs.LG 50%

One-Step Flow Policy Mirror Descent

Tianyi Chen, Haitong Ma, Na Li, Kai Wang, Bo Dai

机构 * Georgia Institute of Technology（佐治亚理工学院）； Harvard University（哈佛大学）

专题命中效率与蒸馏：diffusion(abstract)

2510.12651 2025-10-15 eess.SP 50%

Moment-based Posterior Sampling for Multi-reference Alignment

Axel Janson, Joakim Andén

专题命中效率与蒸馏：diffusion(abstract)

2510.12562 2025-10-15 astro-ph.HE 50%

Modeling gamma-ray signatures of particle acceleration in stellar clusters from GeV to PeV

A. Inventar, S. Gabici, E. Peretti

专题命中效率与蒸馏：diffusion(abstract)

Comments 8 pages, 3 figures, ICRC proceeding

2510.11988 2025-10-15 astro-ph.HE 50%

Impact of Cosmic Ray Acceleration on the Early Evolution of Bow Shocks around Massive Runaway Stars

Keito Watanabe, Stefanie Walch, Tim-Eric Rathjen, Jonathan Mackey, Pierre Nürnberger, Philipp Girichidis

专题命中效率与蒸馏：diffusion(abstract)

Comments 25 pages, 26 figures (7 figures in Appendix). Submitted to A&A

2510.09309 2025-10-13 cs.CL 50%

Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference

Jianuo Huang, Yaojie Zhang, Yicun Yang, Benhao Huang, Biqing Qi, Dongrui Liu, Linfeng Zhang

机构 * School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院）； Huazhong University of Science and Technology（华中科技大学）； University of Electronic Science and Technology of China（电子科技大学）； Carnegie Mellon University（卡内基梅隆大学）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）

专题命中效率与蒸馏：diffusion(abstract)

Comments 17 pages, 8 figures

2510.08462 2025-10-10 quant-ph cs.LG stat.ML 50%

Wavefunction Flows: Efficient Quantum Simulation of Continuous Flow Models

David Layden, Ryan Sweke, Vojtěch Havlíček, Anirban Chowdhury, Kirill Neklyudov

机构 * IBM Research（IBM研究院）； MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）； African Institute for Mathematical Sciences (AIMS), South Africa（非洲数学科学研究所（AIMS））； Department of Mathematical Sciences, Stellenbosch University, Stellenbosch 7600, South Africa（斯泰伦博斯大学数学科学系）； National Institute for Theoretical and Computational Sciences (NITheCS), South Africa（国家理论与计算科学研究所）； Mila - Quebec AI Institute（魁北克人工智能研究所）

专题命中效率与蒸馏：diffusion(abstract)

2510.08330 2025-10-10 physics.app-ph 50%

A Simultaneous Synergistic Protection Mechanism in Hybrid Perovskite-Organic Multi-junctions Enables Long-Term Stable and Efficient Tandem Solar Cells

Chao Liu, Kaicheng Zhang, Xin Zhou, Mingjian Wu, Paul Weitz, Shudi Qiu, Andrej Vincze, Yuchen Bai, Michael A. Anderson, Johannes Frisch, Regan G. Wilks, Marcus Bar, Zijian Peng, Chaohui Li, Jingjing Tian, Jiyun Zhang, Jianchang Wu, Jonas Englhard, Thomas Heumuller, Jens Hauch, Yixing Huang, Ning Li, Julien Bachmann, Erdmann Spiecker, Christoph J. Brabec

专题命中效率与蒸馏：diffusion(abstract)

2510.08218 2025-10-10 cs.LG cs.AI 50%

Expressive Value Learning for Scalable Offline Reinforcement Learning

Nicolas Espinosa-Dice, Kiante Brantley, Wen Sun

机构 * Department of Computer Science（计算机科学系）； Cornell University（康奈尔大学）； Kempner Institute（凯普纳研究所）； Harvard University（哈佛大学）

专题命中效率与蒸馏：diffusion(abstract)

Comments 24 pages, 5 figures

2510.07865 2025-10-10 cs.RO cs.AI 50%

DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulation

Guowei Zou, Haitao Wang, Hejun Wu, Yukun Qian, Yuhang Wang, Weibing Li

机构 * School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）； Guangdong Key Laboratory of Big Data Analysis and Processing（广东大数据分析与处理重点实验室）

专题命中效率与蒸馏：diffusion(abstract)

Comments Website with code: https://guowei-zou.github.io/dm1/

2510.07667 2025-10-10 eess.IV 50%

An Energy-Efficient Edge Coprocessor for Neural Rendering with Explicit Data Reuse Strategies

Binzhe Yuan, Xiangyu Zhang, Zeyu Zheng, Yuefeng Zhang, Haochuan Wan, Zhechen Yuan, Junsheng Chen, Yunxiang He, Junran Ding, Xiaoming Zhang, Chaolin Rao, Wenyan Su, Pingqiang Zhou, Jingyi Yu, Xin Lou

专题命中效率与蒸馏：image synthesis(abstract)

Comments 11 pages, 17 figures, 2 tables

2306.02708 2025-10-10 q-fin.MF math.PR 50%

Efficient simulation of a new class of Volterra-type SDEs

Ofelia Bonesini, Giorgia Callegaro, Martino Grasselli, Gilles Pagès

专题命中效率与蒸馏：diffusion(abstract)

Comments Previously appearing as "From elephant to goldfish (and back): memory in stochastic Volterra processes"

2510.05984 2025-10-08 cs.SD cs.AI eess.AS 50%

ECTSpeech: Enhancing Efficient Speech Synthesis via Easy Consistency Tuning

Tao Zhu, Yinfeng Yu, Liejun Wang, Fuchun Sun, Wendong Zheng

机构 * School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院）； Joint International Research Laboratory of Silk Road Multilingual Cognitive Computing（丝绸之路多语种认知计算联合国际实验室）； Tsinghua University（清华大学）； Tianjin University of Technology（天津工业大学）

专题命中效率与蒸馏：diffusion(abstract)

Comments Accepted for publication by Proceedings of the 2025 ACM Multimedia Asia Conference(MMAsia '25)

2509.03091 2025-10-08 astro-ph.HE 50%

Diffusive shock acceleration: non-classical model of cosmic ray transport

A. A. Lagutin

专题命中效率与蒸馏：diffusion(abstract)

Comments 17 pages, the 5th International Symposium on Cosmic Rays and Astrophysics (ISCRA-2025)

2510.04635 2025-10-07 astro-ph.HE hep-ph 50%

The Role of Acoustic Instability in Cosmic-Ray Self-Confinement

Antonio Capanema, Pasquale Blasi, Emanuele Sobacchi

专题命中效率与蒸馏：diffusion(abstract)

Comments Presented at the 39th International Cosmic Ray Conference (ICRC 2025). 8 pages, 5 figures

2506.11893 2025-10-07 cs.LG 50%

Measurement-Aligned Sampling for Inverse Problem

Shaorong Zhang, Rob Brekelmans, Yunshu Wu, Greg Ver Steeg

机构 * University of California Riverside（加州大学河滨分校）； Vector Institute（向量研究所）

专题命中效率与蒸馏：diffusion(abstract)

2510.01790 2025-10-03 math.NA cs.NA math.AP math.DG 50%

Efficient manifold evolution algorithm using adaptive B-Spline interpolation

Muhammad Ammad, Leevan Ling

专题命中效率与蒸馏：diffusion(abstract)

2508.01622 2025-10-03 cs.RO cs.LG 50%

VFP: Variational Flow-Matching Policy for Multi-Modal Robot Manipulation

Xuanran Zhai, Qianyou Zhao, Qiaojun Yu, Ce Hao

机构 * National University of Singapore（新加坡国立大学）； Shanghai Jiao Tong University（上海交通大学）； Shanghai AI Lab（上海人工智能实验室）

专题命中效率与蒸馏：diffusion(abstract)

2410.02367 2025-10-02 cs.LG 50%

SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration

Jintao Zhang, Jia Wei, Haofeng Huang, Pengle Zhang, Jun Zhu, Jianfei Chen

机构 * Dept. of Comp. Sci. & Tech.（计算机科学与技术系）； Institute for AI（人工智能研究院）； BNRist Center（BNRist中心）； Tsinghua-Bosch Joint ML Center（清华大学-博世联合机器学习中心）； THBI Lab（THBI实验室）； Tsinghua University（清华大学）

专题命中效率与蒸馏：image generation(abstract)

Comments @inproceedings{zhang2025sageattention, title={SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration}, author={Zhang, Jintao and Wei, Jia and Zhang, Pengle and Zhu, Jun and Chen, Jianfei}, booktitle={International Conference on Learning Representations (ICLR)}, year={2025} }

Journal ref The Thirteenth International Conference on Learning Representations (ICLR 2025)

2510.00722 2025-10-02 math.NA cs.NA 50%

Carleman Linearization of Parabolic PDEs: Well-posedness, convergence, and efficient numerical methods

Bernhard Heinzelreiter, John W. Pearson

专题命中效率与蒸馏：diffusion(abstract)

Comments 32 pages

2506.05526 2025-10-01 cs.LG stat.ML 50%

On Fitting Flow Models with Large Sinkhorn Couplings

Stephen Zhang, Alireza Mousavi-Hosseini, Michal Klein, Marco Cuturi

机构 * Apple（苹果公司）； University of Toronto（多伦多大学）； University of Melbourne（墨尔本大学）

专题命中效率与蒸馏：image generation(abstract)

Comments 23 pages, 14 figures

2509.26488 2025-10-01 cs.CL 50%

dParallel: Learnable Parallel Decoding for dLLMs

Zigeng Chen, Gongfan Fang, Xinyin Ma, Ruonan Yu, Xinchao Wang

机构 * National University of Singapore（新加坡国立大学）

专题命中效率与蒸馏：diffusion(abstract)

Comments Working in progress, code base: https://github.com/czg1225/dParallel

2509.23299 2025-10-01 cs.SD eess.AS 50%

MeanFlowSE: One-Step Generative Speech Enhancement via MeanFlow

Yike Zhu, Boyi Kang, Ziqian Wang, Xingchen Li, Zihan Zhang, Wenjie Li, Longshuai Xiao, Wei Xue, Lei Xie

机构 * The Hong Kong University of Science and Technology, Hong Kong, China（香港科学与技术大学，香港，中国）； Huawei Technologies, China（华为技术有限公司，中国）

专题命中效率与蒸馏：diffusion(abstract)

Comments Submitted to ICASSP 2026

2504.10188 2025-09-30 cs.LG cs.AI 50%

Efficient Generative Model Training via Embedded Representation Warmup

Deyuan Liu, Peng Sun, Xufeng Li, Tao Lin

机构 * Westlake University（西湖大学）； Zhejiang University（浙江大学）； Nanjing University（南京大学）

专题命中效率与蒸馏：diffusion(abstract)

1. 效率与蒸馏 2544 篇

Imitation Learning Policy based on Multi-Step Consistent Integration Shortcut Model

The Streaming Batch Model for Efficient and Fault-Tolerant Heterogeneous Execution

GeoLayer: Towards Low-Latency and Cost-Efficient Geo-Distributed Graph Stores with Layered Graph

ReDi: Rectified Discrete Flow

Online Feedback Efficient Active Target Discovery in Partially Observable Environments

Time evolution of the Husimi and Glauber-Sudarshan functions in terms of complementary Hamiltonian symbols

Protenix-Mini+: efficient structure prediction model with scalable pairformer

One-Step Flow Policy Mirror Descent

Moment-based Posterior Sampling for Multi-reference Alignment

Modeling gamma-ray signatures of particle acceleration in stellar clusters from GeV to PeV

Impact of Cosmic Ray Acceleration on the Early Evolution of Bow Shocks around Massive Runaway Stars

Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference

Wavefunction Flows: Efficient Quantum Simulation of Continuous Flow Models

A Simultaneous Synergistic Protection Mechanism in Hybrid Perovskite-Organic Multi-junctions Enables Long-Term Stable and Efficient Tandem Solar Cells

Expressive Value Learning for Scalable Offline Reinforcement Learning

DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulation

An Energy-Efficient Edge Coprocessor for Neural Rendering with Explicit Data Reuse Strategies

Efficient simulation of a new class of Volterra-type SDEs

ECTSpeech: Enhancing Efficient Speech Synthesis via Easy Consistency Tuning

Diffusive shock acceleration: non-classical model of cosmic ray transport

The Role of Acoustic Instability in Cosmic-Ray Self-Confinement

Measurement-Aligned Sampling for Inverse Problem

Efficient manifold evolution algorithm using adaptive B-Spline interpolation

VFP: Variational Flow-Matching Policy for Multi-Modal Robot Manipulation

SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration

Carleman Linearization of Parabolic PDEs: Well-posedness, convergence, and efficient numerical methods

On Fitting Flow Models with Large Sinkhorn Couplings

dParallel: Learnable Parallel Decoding for dLLMs

MeanFlowSE: One-Step Generative Speech Enhancement via MeanFlow

Efficient Generative Model Training via Embedded Representation Warmup