图像生成 - arXivDaily 专题

2407.18304 2024-11-25 astro-ph.GA astro-ph.HE astro-ph.IM physics.plasm-ph physics.space-ph 50%

A novel numerical method for mixed-frame multigroup radiation-hydrodynamics with GPU acceleration implemented in the QUOKKA code

Chong-Chong He, Benjamin D. Wibking, Mark R. Krumholz

专题命中效率与蒸馏：diffusion(abstract)

Comments 18 pages, 8 figures, MNRAS in press. The code described in this article is available at: https://github.com/quokka-astro/quokka

2402.04292 2024-11-25 cs.LG cs.AI 50%

AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies

Xixi Hu, Bo Liu, Xingchao Liu, Qiang Liu

专题命中效率与蒸馏：diffusion(abstract)

Comments NeuRIPS 2024

2111.04470 2024-11-25 cond-mat.stat-mech nlin.AO nlin.PS physics.comp-ph 50%

Self-organized quantization and oscillations on continuous fixed-energy sandpiles

Jakob Niehues, Gorm Gruner Jensen, Jan O. Haerter

专题命中效率与蒸馏：diffusion(abstract)

Comments 13 pages, 7 figures, plus supplement

2410.11104 2024-11-20 astro-ph.SR 50%

Radiative acceleration calculation methods and abundance anomalies in Am stars

Alain Hui-Bon-Hoa

专题命中效率与蒸馏：diffusion(abstract)

Comments 11 pages, 8 figures

Journal ref A&A 691, A266 (2024)

2404.18893 2024-11-20 cs.DS cs.LG stat.ML 50%

Learning general Gaussian mixtures with efficient score matching

Sitan Chen, Vasilis Kontonis, Kulin Shah

专题命中效率与蒸馏：diffusion(abstract)

Comments 57 pages

2411.10911 2024-11-19 cond-mat.mtrl-sci cs.LG physics.chem-ph 50%

Constructing accurate machine-learned potentials and performing highly efficient atomistic simulations to predict structural and thermal properties

Junlan Liu, Qian Yin, Mengshu He, Jun Zhou

专题命中效率与蒸馏：diffusion(abstract)

2411.09356 2024-11-15 cs.AI 50%

Multi-scale Generative Modeling for Fast Sampling

Xiongye Xiao, Shixuan Li, Luzhe Huang, Gengshuo Liu, Trung-Kien Nguyen, Yi Huang, Di Chang, Mykel J. Kochenderfer, Paul Bogdan

专题命中效率与蒸馏：diffusion(abstract)

2411.09117 2024-11-15 cs.LG cs.DS math.PR stat.ML 50%

Efficiently learning and sampling multimodal distributions with data-based initialization

Frederic Koehler, Holden Lee, Thuy-Duong Vuong

专题命中效率与蒸馏：diffusion(abstract)

2406.07555 2024-11-13 stat.CO stat.ME 50%

Sequential Monte Carlo for Cut-Bayesian Posterior Computation

Joseph Mathews, Giri Gopalan, James Gattiker, Sean Smith, Devin Francom

专题命中效率与蒸馏：diffusion(abstract)

Comments Revision accepted for Computational Statistics

2411.04323 2024-11-08 cs.LG cond-mat.mtrl-sci 50%

Efficient Symmetry-Aware Materials Generation via Hierarchical Generative Flow Networks

Tri Minh Nguyen, Sherif Abdulkader Tawfik, Truyen Tran, Sunil Gupta, Santu Rana, Svetha Venkatesh

专题命中效率与蒸馏：diffusion(abstract)

2411.00853 2024-11-05 cs.LG cs.AI cs.CL 50%

Accelerated AI Inference via Dynamic Execution Methods

Haim Barad, Jascha Achterberg, Tien Pei Chou, Jean Yu

专题命中效率与蒸馏：diffusion(abstract)

2411.00040 2024-11-04 math.NA cs.AI cs.LG cs.NA 50%

P$^2$C$^2$Net: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics

Qi Wang, Pu Ren, Hao Zhou, Xin-Yang Liu, Zhiwen Deng, Yi Zhang, Ruizhi Chengze, Hongsheng Liu, Zidong Wang, Jian-Xun Wang, Ji-Rong_Wen, Hao Sun, Yang Liu

专题命中效率与蒸馏：diffusion(abstract)

2406.19437 2024-10-31 astro-ph.CO astro-ph.GA astro-ph.IM 50%

pop-cosmos: Scaleable inference of galaxy properties and redshifts with a data-driven population model

Stephen Thorp, Justin Alsing, Hiranya V. Peiris, Sinan Deger, Daniel J. Mortlock, Boris Leistedt, Joel Leja, Arthur Loureiro

专题命中效率与蒸馏：diffusion(abstract)

Comments 24 pages, 15 figures. Accepted for publication in ApJ. Catalog of redshifts and galaxy properties available on Zenodo at https://zenodo.org/doi/10.5281/zenodo.13627488

Journal ref ApJ 975, 145 (2024)

2410.21340 2024-10-30 cs.LG cs.AI cs.DC 50%

Meta-Learning for Speeding Up Large Model Inference in Decentralized Environments

Yuzhe Yang, Yipeng Du, Ahmad Farhan, Claudio Angione, Yue Zhao, Harry Yang, Fielding Johnston, James Buban, Patrick Colangelo

专题命中效率与蒸馏：image generation(abstract)

2405.16321 2024-10-25 cond-mat.stat-mech physics.chem-ph physics.comp-ph 50%

On the Definition of Velocity in Discrete-Time, Stochastic Langevin Simulations

Niels Grønbech-Jensen

专题命中效率与蒸馏：diffusion(abstract)

Comments 25 pages, 21 figures

Journal ref Journal of Statistical Physics Vol.191, 137 (2024)

2404.14700 2024-10-25 eess.AS cs.AI cs.CL cs.LG cs.SD 50%

FlashSpeech: Efficient Zero-Shot Speech Synthesis

Zhen Ye, Zeqian Ju, Haohe Liu, Xu Tan, Jianyi Chen, Yiwen Lu, Peiwen Sun, Jiahao Pan, Weizhen Bian, Shulin He, Wei Xue, Qifeng Liu, Yike Guo

专题命中效率与蒸馏：diffusion(abstract)

Comments Efficient zero-shot speech synthesis

2210.11102 2024-10-22 math.NA cs.NA math.PR 50%

Piecewise linear interpolation of noise in finite element approximations of parabolic SPDEs

Gabriel Lord, Andreas Petersson

专题命中效率与蒸馏：diffusion(abstract)

Comments Extended introduction, added supplementary comparison to spectral method

2410.06544 2024-10-10 cs.SD eess.AS 50%

SRC-gAudio: Sampling-Rate-Controlled Audio Generation

Chenxing Li, Manjie Xu, Dong Yu

专题命中效率与蒸馏：diffusion(abstract)

Comments Accepted by APSIPA2024

2408.10445 2024-10-10 astro-ph.SR astro-ph.HE physics.plasm-ph 50%

Compression Acceleration of Protons and Heavier Ions at the Heliospheric Current Sheet

Giulia Murtas, Xiaocan Li, Fan Guo

专题命中效率与蒸馏：diffusion(abstract)

Comments 15 pages, 6 figures. Accepted by ApJ

2410.01776 2024-10-03 physics.ao-ph cs.LG 50%

Dynamical-generative downscaling of climate model ensembles

Ignacio Lopez-Gomez, Zhong Yi Wan, Leonardo Zepeda-Núñez, Tapio Schneider, John Anderson, Fei Sha

专题命中效率与蒸馏：diffusion(abstract)

2401.08092 2024-09-24 cs.LG cs.AI cs.DC 50%

A Survey of Resource-efficient LLM and Multimodal Foundation Models

Mengwei Xu, Wangsong Yin, Dongqi Cai, Rongjie Yi, Daliang Xu, Qipeng Wang, Bingyang Wu, Yihao Zhao, Chen Yang, Shihe Wang, Qiyang Zhang, Zhenyan Lu, Li Zhang, Shangguang Wang, Yuanchun Li, Yunxin Liu, Xin Jin, Xuanzhe Liu

专题命中效率与蒸馏：diffusion(abstract)

2301.13362 2024-09-23 cs.LG 50%

Optimizing DDPM Sampling with Shortcut Fine-Tuning

Ying Fan, Kangwook Lee

专题命中效率与蒸馏：diffusion(abstract)

Comments ICML 2023

2409.10108 2024-09-17 cond-mat.stat-mech physics.chem-ph 50%

Smart Resetting: An Energy-Efficient Strategy for Stochastic Search Processes

Ofir Tal-Friedman, Tommer D. Keidar, Shlomi Reuveni, Yael Roichman

专题命中效率与蒸馏：diffusion(abstract)

2409.09351 2024-09-17 eess.AS cs.SD 50%

E1 TTS: Simple and Fast Non-Autoregressive TTS

Zhijun Liu, Shuai Wang, Pengcheng Zhu, Mengxiao Bi, Haizhou Li

专题命中效率与蒸馏：diffusion(abstract)

2404.00845 2024-09-17 cond-mat.mtrl-sci 50%

Harnessing Interlayer Magnetic Coupling for Efficient, Field-Free Current-Induced Magnetization Switching in a Magnetic Insulator

Leran Wang, Alejandro O. Leon, Wenqing He, Zhongyu Liang, Xiaohan Li, Xiaoxiao Fang, Wenyun Yang, Licong Peng, Jinbo Yang, Caihua Wan, Gerrit E. W. Bauer, Zhaochu Luo

专题命中效率与蒸馏：diffusion(abstract)

2409.07912 2024-09-13 cs.CE 50%

Multi-granularity Score-based Generative Framework Enables Efficient Inverse Design of Complex Organics

Zijun Chen, Yu Wang, Liuzhenghao Lv, Hao Li, Zongying Lin, Li Yuan, Yonghong Tian

专题命中效率与蒸馏：diffusion(abstract)

2409.07323 2024-09-12 cs.LG stat.ML 50%

Efficient and Unbiased Sampling of Boltzmann Distributions via Consistency Models

Fengzhe Zhang, Jiajun He, Laurence I. Midgley, Javier Antorán, José Miguel Hernández-Lobato

专题命中效率与蒸馏：diffusion(abstract)

Comments 10 pages, 4 figures

2409.07032 2024-09-12 stat.ML cs.LG 50%

From optimal score matching to optimal sampling

Zehao Dou, Subhodh Kotekal, Zhehao Xu, Harrison H. Zhou

专题命中效率与蒸馏：diffusion(abstract)

Comments 71 pages

2312.14810 2024-09-10 cs.CE math.OC stat.ME 50%

Accurate, scalable, and efficient Bayesian optimal experimental design with derivative-informed neural operators

Jinwoo Go, Peng Chen

专题命中效率与蒸馏：diffusion(abstract)

2408.17257 2024-09-06 stat.ME 50%

Likelihood estimation for stochastic differential equations with mixed effects

Fernando Baltazar-Larios, Mogens Bladt, Michael Sørensen

专题命中效率与蒸馏：diffusion(abstract)

1. 效率与蒸馏 2557 篇

A novel numerical method for mixed-frame multigroup radiation-hydrodynamics with GPU acceleration implemented in the QUOKKA code

AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies

Self-organized quantization and oscillations on continuous fixed-energy sandpiles

Radiative acceleration calculation methods and abundance anomalies in Am stars

Learning general Gaussian mixtures with efficient score matching

Constructing accurate machine-learned potentials and performing highly efficient atomistic simulations to predict structural and thermal properties

Multi-scale Generative Modeling for Fast Sampling

Efficiently learning and sampling multimodal distributions with data-based initialization

Sequential Monte Carlo for Cut-Bayesian Posterior Computation

Efficient Symmetry-Aware Materials Generation via Hierarchical Generative Flow Networks

Accelerated AI Inference via Dynamic Execution Methods

P$^2$C$^2$Net: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics

pop-cosmos: Scaleable inference of galaxy properties and redshifts with a data-driven population model

Meta-Learning for Speeding Up Large Model Inference in Decentralized Environments

On the Definition of Velocity in Discrete-Time, Stochastic Langevin Simulations

FlashSpeech: Efficient Zero-Shot Speech Synthesis

Piecewise linear interpolation of noise in finite element approximations of parabolic SPDEs

SRC-gAudio: Sampling-Rate-Controlled Audio Generation

Compression Acceleration of Protons and Heavier Ions at the Heliospheric Current Sheet

Dynamical-generative downscaling of climate model ensembles

A Survey of Resource-efficient LLM and Multimodal Foundation Models

Optimizing DDPM Sampling with Shortcut Fine-Tuning

Smart Resetting: An Energy-Efficient Strategy for Stochastic Search Processes

E1 TTS: Simple and Fast Non-Autoregressive TTS

Harnessing Interlayer Magnetic Coupling for Efficient, Field-Free Current-Induced Magnetization Switching in a Magnetic Insulator

Multi-granularity Score-based Generative Framework Enables Efficient Inverse Design of Complex Organics

Efficient and Unbiased Sampling of Boltzmann Distributions via Consistency Models

From optimal score matching to optimal sampling

Accurate, scalable, and efficient Bayesian optimal experimental design with derivative-informed neural operators

Likelihood estimation for stochastic differential equations with mixed effects