图像生成 - arXivDaily 专题

2412.15073 2025-04-01 physics.comp-ph physics.chem-ph 50%

Velocity Jumps for Molecular Dynamics

Nicolaï Gouraud, Louis Lagardère, Olivier Adjoua, Thomas Plé, Pierre Monmarché, Jean-Philip Piquemal

专题命中效率与蒸馏：diffusion(abstract)

Journal ref Journal of Chemical Theory and Computation, 2025, 21 (6), 2854-2866

2503.18078 2025-03-25 eess.SP 50%

GenMetaLoc: Learning to Learn Environment-Aware Fingerprint Generation for Sample Efficient Wireless Localization

Jun Gao, Feng Yin, Wenzhong Yan, Qinglei Kong, Lexi Xu, Shuguang Cui

专题命中效率与蒸馏：diffusion(abstract)

2312.17406 2025-03-25 math.PR q-bio.PE 50%

Sampling probabilities, diffusions, ancestral graphs, and duality under strong selection

Martina Favero, Paul A. Jenkins

专题命中效率与蒸馏：diffusion(abstract)

Comments 44 pages

Journal ref Electronic Journal of Probability 30: 1-43 (2025)

2503.16562 2025-03-24 cs.LG 50%

Bezier Distillation

Ling Feng, SK Yang

专题命中效率与蒸馏：diffusion(abstract)

2407.10763 2025-03-18 math.ST stat.TH 50%

Sampling from the Random Linear Model via Stochastic Localization Up to the AMP Threshold

Han Cui, Zhiyuan Yu, Jingbo Liu

专题命中效率与蒸馏：diffusion(abstract)

2410.11826 2025-03-14 stat.ML cs.LG 50%

Bayesian Experimental Design via Contrastive Diffusions

Jacopo Iollo, Christophe Heinkelé, Pierre Alliez, Florence Forbes

专题命中效率与蒸馏：diffusion(abstract)

2410.18403 2025-03-14 q-bio.BM cs.LG 50%

Structure Language Models for Protein Conformation Generation

Jiarui Lu, Xiaoyin Chen, Stephen Zhewen Lu, Chence Shi, Hongyu Guo, Yoshua Bengio, Jian Tang

专题命中效率与蒸馏：diffusion(abstract)

Comments Published as a conference paper at ICLR 2025, see https://openreview.net/forum?id=OzUNDnpQyd

2502.12371 2025-03-12 cs.RO cs.AI cs.LG 50%

IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimation

Krishan Rana, Robert Lee, David Pershouse, Niko Suenderhauf

专题命中效率与蒸馏：diffusion(abstract)

Comments Videos and code are available at https://imle-policy.github.io/

2503.04357 2025-03-07 cs.LG cs.AI 50%

scDD: Latent Codes Based scRNA-seq Dataset Distillation with Foundation Model Knowledge

Zhen Yu, Jianan Han, Yang Liu, Qingchao Chen

专题命中效率与蒸馏：diffusion(abstract)

2503.02047 2025-03-05 cs.DB 50%

Quantifying Point Contributions: A Lightweight Framework for Efficient and Effective Query-Driven Trajectory Simplification

Yumeng Song, Yu Gu, Tianyi Li, Yushuai Li, Christian S. Jensen, Ge Yu

专题命中效率与蒸馏：diffusion(abstract)

Comments Accepted by VLDB2025

2503.00317 2025-03-04 cs.LG cs.NA math.NA physics.comp-ph 50%

DeepONet Augmented by Randomized Neural Networks for Efficient Operator Learning in PDEs

Zhaoxi Jiang, Fei Wang

专题命中效率与蒸馏：diffusion(abstract)

2503.00461 2025-03-04 cs.AR cs.AI 50%

Leveraging Compute-in-Memory for Efficient Generative Model Inference in TPUs

Zhantong Zhu, Hongou Li, Wenjie Ren, Meng Wu, Le Ye, Ru Huang, Tianyu Jia

专题命中效率与蒸馏：diffusion(abstract)

Comments Accepted to appear at DATE 2025

2412.04318 2025-02-27 cs.CL cs.AI 50%

The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation

Fredrik Carlsson, Fangyu Liu, Daniel Ward, Murathan Kurfali, Joakim Nivre

专题命中效率与蒸馏：image generation(abstract)

Comments Under review at ICLR

2410.08735 2025-02-25 math.NA cs.NA 50%

A Flexible GMRES Solver with Reduced Order Model Enhanced Synthetic Acceleration Preconditioenr for Parametric Radiative Transfer Equation

Zhichao Peng

专题命中效率与蒸馏：diffusion(abstract)

2311.01497 2025-02-25 astro-ph.HE physics.plasm-ph 50%

Efficient micromirror confinement of sub-TeV cosmic rays in galaxy clusters

Patrick Reichherzer, Archie F. A. Bott, Robert J. Ewart, Gianluca Gregori, Philipp Kempski, Matthew W. Kunz, Alexander A. Schekochihin

专题命中效率与蒸馏：diffusion(abstract)

Comments Accepted manuscript for Nature Astronomy, post-peer review, prior to final editorial changes

Journal ref Nature Astronomy, 2025

2403.16883 2025-02-18 cs.LG stat.ML 50%

GLAD: Improving Latent Graph Generative Modeling with Simple Quantization

Van Khoa Nguyen, Yoann Boget, Frantzeska Lavda, Alexandros Kalousis

专题命中效率与蒸馏：diffusion(abstract)

Comments AAAI 2025 (Previously accepted at SPIGM ICML 2024 workshop)

2502.09624 2025-02-17 cs.AI cs.CR 50%

Efficient and Trustworthy Block Propagation for Blockchain-enabled Mobile Embodied AI Networks: A Graph Resfusion Approach

Jiawen Kang, Jiana Liao, Runquan Gao, Jinbo Wen, Huawei Huang, Maomao Zhang, Changyan Yi, Tao Zhang, Dusit Niyato, Zibin Zheng

专题命中效率与蒸馏：diffusion(abstract)

Comments 15 pages, 11 figures

2501.19082 2025-02-14 cs.LG cs.DC math.OC stat.ML 50%

A Bias-Correction Decentralized Stochastic Gradient Algorithm with Momentum Acceleration

Yuchen Hu, Xi Chen, Weidong Liu, Xiaojun Mao

专题命中效率与蒸馏：diffusion(abstract)

2502.04849 2025-02-10 stat.ML cs.LG math.PR 50%

Advancing Wasserstein Convergence Analysis of Score-Based Models: Insights from Discretization and Second-Order Acceleration

Yifeng Yu, Lu Yu

专题命中效率与蒸馏：diffusion(abstract)

2502.01337 2025-02-10 cs.CE 50%

Neural Preconditioning Operator for Efficient PDE Solves

Zhihao Li, Di Xiao, Zhilu Lai, Wei Wang

专题命中效率与蒸馏：diffusion(abstract)

2410.21035 2025-02-10 cs.LG cs.CL 50%

Beyond Autoregression: Fast LLMs via Self-Distillation Through Time

Justin Deschenaux, Caglar Gulcehre

专题命中效率与蒸馏：diffusion(abstract)

2410.08001 2025-02-07 cs.RO cs.AI 50%

Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation

Qingwen Bu, Hongyang Li, Li Chen, Jisong Cai, Jia Zeng, Heming Cui, Maoqing Yao, Yu Qiao

专题命中效率与蒸馏：diffusion(abstract)

Comments Project page: https://opendrivelab.com/RoboDual/

2502.03322 2025-02-06 math.NA cs.CE cs.NA q-bio.TO 50%

An efficient end-to-end computational framework for the generation of ECG calibrated volumetric models of human atrial electrophysiology

Elena Zappon, Luca Azzolin, Matthias A. F. Gsell, Franz Thaler, Anton J. Prassl, Robert Arnold, Karli Gillette, Mohammadreza Kariman, Martin Manninger-Wünscher, Daniel Scherr, Aurel Neic, Martin Urschler, Christoph M. Augustin, Edward J. Vigmond, Gernot Plank

专题命中效率与蒸馏：diffusion(abstract)

Comments 39 pages, 13 figures, 11 tables

2502.00355 2025-02-04 cs.LG stat.ML 50%

Sampling in High-Dimensions using Stochastic Interpolants and Forward-Backward Stochastic Differential Equations

Anand Jerry George, Nicolas Macris

专题命中效率与蒸馏：diffusion(abstract)

Comments 8 pages

2501.17827 2025-01-30 cs.LG 50%

Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning

Haque Ishfaq, Guangyuan Wang, Sami Nur Islam, Doina Precup

专题命中效率与蒸馏：diffusion(abstract)

Comments Published in The Thirteenth International Conference on Learning Representations (ICLR) 2025. The first two authors contributed equally

2310.09200 2025-01-30 astro-ph.IM 50%

BIPP: An efficient HPC implementation of the Bluebild algorithm for radio astronomy

Emma Tolley, Simon Frasch, Etienne Orliac, Shreyam Krishna, Michele Bianco, Sepand Kashani, Paul Hurley, Matthieu Simeoni, Jean-Paul Kneib

专题命中效率与蒸馏：image synthesis(abstract)

Comments 21 pages, 13 figures

2501.13828 2025-01-24 cs.AR cs.LG 50%

PhotoGAN: Generative Adversarial Neural Network Acceleration with Silicon Photonics

Tharini Suresh, Salma Afifi, Sudeep Pasricha

专题命中效率与蒸馏：image synthesis(abstract)

2306.17737 2025-01-23 stat.CO cs.NA math.NA 50%

Proximal Langevin Sampling With Inexact Proximal Mapping

Matthias J. Ehrhardt, Lorenz Kuger, Carola-Bibiane Schönlieb

专题命中效率与蒸馏：diffusion(abstract)

Comments 29 pages, 11 figures

Journal ref SIAM Journal on Imaging Sciences 2024 17:3, 1729-1760

2404.02819 2025-01-22 quant-ph 50%

Efficient Quantum Circuits for Non-Unitary and Unitary Diagonal Operators with Space-Time-Accuracy trade-offs

Julien Zylberman, Ugo Nzongani, Andrea Simonetto, Fabrice Debbasch

专题命中效率与蒸馏：diffusion(abstract)

2501.09747 2025-01-17 cs.RO cs.LG 50%

FAST: Efficient Action Tokenization for Vision-Language-Action Models

Karl Pertsch, Kyle Stachowicz, Brian Ichter, Danny Driess, Suraj Nair, Quan Vuong, Oier Mees, Chelsea Finn, Sergey Levine

专题命中效率与蒸馏：diffusion(abstract)

Comments Website: https://www.pi.website/research/fast

1. 效率与蒸馏 2544 篇

Velocity Jumps for Molecular Dynamics

GenMetaLoc: Learning to Learn Environment-Aware Fingerprint Generation for Sample Efficient Wireless Localization

Sampling probabilities, diffusions, ancestral graphs, and duality under strong selection

Bezier Distillation

Sampling from the Random Linear Model via Stochastic Localization Up to the AMP Threshold

Bayesian Experimental Design via Contrastive Diffusions

Structure Language Models for Protein Conformation Generation

IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimation

scDD: Latent Codes Based scRNA-seq Dataset Distillation with Foundation Model Knowledge

Quantifying Point Contributions: A Lightweight Framework for Efficient and Effective Query-Driven Trajectory Simplification

DeepONet Augmented by Randomized Neural Networks for Efficient Operator Learning in PDEs

Leveraging Compute-in-Memory for Efficient Generative Model Inference in TPUs

The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation

A Flexible GMRES Solver with Reduced Order Model Enhanced Synthetic Acceleration Preconditioenr for Parametric Radiative Transfer Equation

Efficient micromirror confinement of sub-TeV cosmic rays in galaxy clusters

GLAD: Improving Latent Graph Generative Modeling with Simple Quantization

Efficient and Trustworthy Block Propagation for Blockchain-enabled Mobile Embodied AI Networks: A Graph Resfusion Approach

A Bias-Correction Decentralized Stochastic Gradient Algorithm with Momentum Acceleration

Advancing Wasserstein Convergence Analysis of Score-Based Models: Insights from Discretization and Second-Order Acceleration

Neural Preconditioning Operator for Efficient PDE Solves

Beyond Autoregression: Fast LLMs via Self-Distillation Through Time

Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation

An efficient end-to-end computational framework for the generation of ECG calibrated volumetric models of human atrial electrophysiology

Sampling in High-Dimensions using Stochastic Interpolants and Forward-Backward Stochastic Differential Equations

Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning

BIPP: An efficient HPC implementation of the Bluebild algorithm for radio astronomy

PhotoGAN: Generative Adversarial Neural Network Acceleration with Silicon Photonics

Proximal Langevin Sampling With Inexact Proximal Mapping

Efficient Quantum Circuits for Non-Unitary and Unitary Diagonal Operators with Space-Time-Accuracy trade-offs

FAST: Efficient Action Tokenization for Vision-Language-Action Models