图像生成 - arXivDaily 专题

2404.00237 2024-09-05 cs.RO 50%

Joint Pedestrian Trajectory Prediction through Posterior Sampling

Haotian Lin, Yixiao Wang, Mingxiao Huo, Chensheng Peng, Zhiyuan Liu, Masayoshi Tomizuka

专题命中效率与蒸馏：diffusion(abstract)

2312.17293 2024-09-05 eess.IV cs.LG physics.med-ph 50%

$μ$GUIDE: a framework for quantitative imaging via generalized uncertainty-driven inference using deep learning

Maëliss Jallais, Marco Palombo

专题命中效率与蒸馏：diffusion(abstract)

2408.14513 2024-08-28 cs.LG cs.AI 50%

Variational autoencoder-based neural network model compression

Liang Cheng, Peiyuan Guan, Amir Taherkordi, Lei Liu, Dapeng Lan

专题命中效率与蒸馏：image generation(abstract)

2406.03555 2024-08-22 astro-ph.HE 50%

Superbubbles as Galactic PeVatrons: The Potential Role of Rapid Second-Order Fermi Acceleration

Jacco Vink

专题命中效率与蒸馏：diffusion(abstract)

Comments Submitted to A&A letters. This is a revised version, taking into account the comments by the referee. 5 pages, 3 figures

2408.10982 2024-08-21 cs.DC 50%

GreediRIS: Scalable Influence Maximization using Distributed Streaming Maximum Cover

Reet Barik, Wade Cappa, S M Ferdous, Marco Minutoli, Mahantesh Halappanavar, Ananth Kalyanaraman

专题命中效率与蒸馏：diffusion(abstract)

2408.09566 2024-08-20 cond-mat.mtrl-sci cond-mat.mes-hall 50%

Efficient spin to charge conversion and spin memory loss mitigation in oriented $\text{RuO}_2$ films

Abhisek Mishra, Kshitij Singh Rathore, Swayang Priya Mahanta, Subhankar Bedanta

专题命中效率与蒸馏：diffusion(abstract)

2205.14630 2024-08-16 cs.LG 50%

Physical Activation Functions (PAFs): An Approach for More Efficient Induction of Physics into Physics-Informed Neural Networks (PINNs)

Jassem Abbasi, Pål Østebø Andersen

专题命中效率与蒸馏：diffusion(abstract)

Comments 26 pages, 9 figures

2404.17397 2024-08-14 astro-ph.HE 50%

Individual particle approach to the diffusive shock acceleration. Effect of the non-uniform flow velocity downstream of the shock

O. Petruk, T. Kuzyo

专题命中效率与蒸馏：diffusion(abstract)

Comments Accepted by Astronomy & Astrophysics

Journal ref A&A 688, A108 (2024)

2312.07893 2024-07-30 physics.flu-dyn quant-ph 50%

Quantum computing of reacting flows via Hamiltonian simulation

Zhen Lu, Yue Yang

专题命中效率与蒸馏：diffusion(abstract)

Journal ref Proc. Combust. Inst. 40 (2024) 105440

2307.08006 2024-07-30 physics.chem-ph 50%

Lambda-ABF: Simplified, Portable, Accurate and Cost-effective Alchemical Free Energy Computations

Louis Lagardère, Lise Maurin, Olivier Adjoua, Krystel El Hage, Pierre Monmarché, Jean-Philip Piquemal, Jérôme Hénin

专题命中效率与蒸馏：diffusion(abstract)

Journal ref Journal of Chemical Theory and Computation 20 (2024) 4481-4498

2407.18802 2024-07-29 stat.ML cs.IT cs.LG math.IT 50%

Log-Concave Coupling for Sampling Neural Net Posteriors

Curtis McDonald, Andrew R Barron

专题命中效率与蒸馏：diffusion(abstract)

Comments This research was presented at the International Symposium on Information Theory (ISIT). Athens, Greece, July 11, 2024. The material was also presented in the 2024 Shannon Lecture

2407.15238 2024-07-23 cs.LG cs.AI cs.NE 50%

Variational Potential Flow: A Novel Probabilistic Framework for Energy-Based Generative Modelling

Junn Yong Loo, Michelle Adeline, Arghya Pal, Vishnu Monn Baskaran, Chee-Ming Ting, Raphael C. -W. Phan

专题命中效率与蒸馏：image generation(abstract)

2405.02845 2024-07-17 cs.LG q-bio.MN 50%

Data-Efficient Molecular Generation with Hierarchical Textual Inversion

Seojin Kim, Jaehyun Nam, Sihyun Yu, Younghoon Shin, Jinwoo Shin

专题命中效率与蒸馏：image generation(abstract)

Comments ICML 2024

2310.01103 2024-07-15 physics.comp-ph cs.CE 50%

An efficient computational model of the in-flow capturing of magnetic nanoparticles by a cylindrical magnet for cancer nanomedicine

Barbara Wirthl, Vitaly Wirthl, Wolfgang A. Wall

专题命中效率与蒸馏：diffusion(abstract)

Journal ref Physical Review E, 109 (2024), 065309

2407.07873 2024-07-11 cs.LG math.DS math.OC math.PR stat.ML 50%

Dynamical Measure Transport and Neural PDE Solvers for Sampling

Jingtong Sun, Julius Berner, Lorenz Richter, Marius Zeinhofer, Johannes Müller, Kamyar Azizzadenesheli, Anima Anandkumar

专题命中效率与蒸馏：diffusion(abstract)

2407.06294 2024-07-10 physics.comp-ph cond-mat.mtrl-sci physics.chem-ph 50%

Beyond theory driven discovery: hot random search and datum derived structures

Chris J. Pickard

专题命中效率与蒸馏：diffusion(abstract)

Comments 13 pages, 9 figures, contributed to Data-driven discovery in the chemical sciences Faraday Discussion

2406.15122 2024-07-08 cs.IT math.IT 50%

Convolutional dynamical sampling and some new results

Longxiu Huang, A. Martina Neuman, Sui Tang, Yuying Xie

专题命中效率与蒸馏：diffusion(abstract)

2407.01286 2024-07-02 physics.bio-ph physics.chem-ph 50%

Learning data efficient coarse-grained molecular dynamics from forces and noise

Aleksander E. P. Durumeric, Yaoyi Chen, Frank Noé, Cecilia Clementi

专题命中效率与蒸馏：diffusion(abstract)

Comments 25 pages, 8 figures

2406.17672 2024-06-27 cs.SD eess.AS 50%

SpecMaskGIT: Masked Generative Modeling of Audio Spectrograms for Efficient Audio Synthesis and Beyond

Marco Comunità, Zhi Zhong, Akira Takahashi, Shiqi Yang, Mengjie Zhao, Koichi Saito, Yukara Ikemiya, Takashi Shibuya, Shusuke Takahashi, Yuki Mitsufuji

专题命中效率与蒸馏：diffusion(abstract)

Comments 6 pages, 8 figures, 8 tables. Audio samples: https://zzaudio.github.io/SpecMaskGIT/index.html

2406.14306 2024-06-21 cond-mat.mtrl-sci 50%

Efficient parameterization of transferable Atomic Cluster Expansion for water

Eslam Ibrahim, Yury Lysogorskiy, Ralf Drautz

专题命中效率与蒸馏：diffusion(abstract)

2310.07551 2024-06-18 math.NA cs.NA 50%

Efficient third order tensor-oriented directional splitting for exponential integrators

Fabio Cassini

专题命中效率与蒸馏：diffusion(abstract)

2310.06036 2024-06-11 quant-ph cond-mat.stat-mech cond-mat.str-el 50%

Efficient Large-Scale Many-Body Quantum Dynamics via Local-Information Time Evolution

Claudia Artiaco, Christoph Fleckenstein, David Aceituno Chávez, Thomas Klein Kvorning, Jens H. Bardarson

专题命中效率与蒸馏：diffusion(abstract)

Comments 29 pages, 17 figures

Journal ref PRX Quantum 5, 020352 (2024)

2402.10488 2024-06-05 math.NA cs.NA 50%

Reduced Order Model Enhanced Source Iteration with Synthetic Acceleration for Parametric Radiative Transfer Equation

Zhichao Peng

专题命中效率与蒸馏：diffusion(abstract)

Comments 25 pages, 8 figures

2402.03008 2024-05-30 stat.ML cs.LG stat.CO 50%

Diffusive Gibbs Sampling

Wenlin Chen, Mingtian Zhang, Brooks Paige, José Miguel Hernández-Lobato, David Barber

专题命中效率与蒸馏：diffusion(abstract)

Comments Accepted for publication at ICML 2024. Code available: https://github.com/Wenlin-Chen/DiGS

2305.10157 2024-05-30 cs.LG math-ph math.MP 50%

Efficient Error Certification for Physics-Informed Neural Networks

Francisco Eiras, Adel Bibi, Rudy Bunel, Krishnamurthy Dj Dvijotham, Philip Torr, M. Pawan Kumar

专题命中效率与蒸馏：diffusion(abstract)

Comments Accepted to ICML'24

2405.15346 2024-05-27 cs.CL cs.AI cs.LG 50%

BiSup: Bidirectional Quantization Error Suppression for Large Language Models

Minghui Zou, Ronghui Guo, Sai Zhang, Xiaowang Zhang, Zhiyong Feng

专题命中效率与蒸馏：diffusion(abstract)

2307.01198 2024-05-24 cs.LG math.OC math.PR stat.ML 50%

Improved sampling via learned diffusions

Lorenz Richter, Julius Berner

专题命中效率与蒸馏：diffusion(abstract)

Comments Accepted at ICLR 2024

Journal ref International Conference on Learning Representations, 2024

2405.12453 2024-05-22 stat.CO 50%

One-step data-driven generative model via Schrödinger Bridge

Hanwen Huang

专题命中效率与蒸馏：diffusion(abstract)

Comments 22 pages, 5 figures

2312.11529 2024-05-15 cs.SI cs.LG 50%

Efficient and Scalable Graph Generation through Iterative Local Expansion

Andreas Bergmeister, Karolis Martinkus, Nathanaël Perraudin, Roger Wattenhofer

专题命中效率与蒸馏：diffusion(abstract)

Comments Published as a conference paper at ICLR 2024

2308.05045 2024-05-13 math.OC 50%

Boosting Data-Driven Mirror Descent with Randomization, Equivariance, and Acceleration

Hong Ye Tan, Subhadip Mukherjee, Junqi Tang, Carola-Bibiane Schönlieb

专题命中效率与蒸馏：inpainting(abstract)

1. 效率与蒸馏 2557 篇

Joint Pedestrian Trajectory Prediction through Posterior Sampling

$μ$GUIDE: a framework for quantitative imaging via generalized uncertainty-driven inference using deep learning

Variational autoencoder-based neural network model compression

Superbubbles as Galactic PeVatrons: The Potential Role of Rapid Second-Order Fermi Acceleration

GreediRIS: Scalable Influence Maximization using Distributed Streaming Maximum Cover

Efficient spin to charge conversion and spin memory loss mitigation in oriented $\text{RuO}_2$ films

Physical Activation Functions (PAFs): An Approach for More Efficient Induction of Physics into Physics-Informed Neural Networks (PINNs)

Individual particle approach to the diffusive shock acceleration. Effect of the non-uniform flow velocity downstream of the shock

Quantum computing of reacting flows via Hamiltonian simulation

Lambda-ABF: Simplified, Portable, Accurate and Cost-effective Alchemical Free Energy Computations

Log-Concave Coupling for Sampling Neural Net Posteriors

Variational Potential Flow: A Novel Probabilistic Framework for Energy-Based Generative Modelling

Data-Efficient Molecular Generation with Hierarchical Textual Inversion

An efficient computational model of the in-flow capturing of magnetic nanoparticles by a cylindrical magnet for cancer nanomedicine

Dynamical Measure Transport and Neural PDE Solvers for Sampling

Beyond theory driven discovery: hot random search and datum derived structures

Convolutional dynamical sampling and some new results

Learning data efficient coarse-grained molecular dynamics from forces and noise

SpecMaskGIT: Masked Generative Modeling of Audio Spectrograms for Efficient Audio Synthesis and Beyond

Efficient parameterization of transferable Atomic Cluster Expansion for water

Efficient third order tensor-oriented directional splitting for exponential integrators

Efficient Large-Scale Many-Body Quantum Dynamics via Local-Information Time Evolution

Reduced Order Model Enhanced Source Iteration with Synthetic Acceleration for Parametric Radiative Transfer Equation

Diffusive Gibbs Sampling

Efficient Error Certification for Physics-Informed Neural Networks

BiSup: Bidirectional Quantization Error Suppression for Large Language Models

Improved sampling via learned diffusions

One-step data-driven generative model via Schrödinger Bridge

Efficient and Scalable Graph Generation through Iterative Local Expansion

Boosting Data-Driven Mirror Descent with Randomization, Equivariance, and Acceleration