arXiv Machine Learning

Optimization as a Dynamical System: Generative Schedules from Latent ODEs

arXiv:2509. 23052v2 Announce Type: replace Abstract: We present a new meta-learning method to determine the optimal learning rate schedule for gradient descent.

arXiv Machine Learning

Jul 3

ZENITH: Automated Gradient Norm Informed Stochastic Optimization

arXiv:2601. 15212v2 Announce Type: replace Abstract: Training deep computer vision models requires manual oversight or hyperparameter tuning of the learning rate (LR) schedule.

By Dhrubo Saha

computer-vision benchmarks

arXiv Machine Learning

Jul 9

Efficient Long-Horizon Learning for Learned Optimization

arXiv:2607. 06772v1 Announce Type: new Abstract: Learned optimization aims to improve upon hand-designed optimizers (e.

By Xiaolong Huang, Benjamin Th\'erien, James Harrison, Eugene Belilovsky

llms computer-vision

arXiv Machine Learning

Jun 11

CaReTS: A Multi-Task Framework Unifying Classification and Regression for Time Series Forecasting

arXiv:2511. 09789v2 Announce Type: replace Abstract: Recent advances in deep forecasting models have achieved remarkable performance, yet most approaches still struggle to provide both accurate predictions and interpretable insights into temporal dynamics.

By Fulong Yao, Wanqing Zhao, Chao Zheng, Xiaofei Han

llms benchmarks

arXiv Machine Learning

Jul 8

Drift Happens: An Empirical Study of Neural Architecture Robustness to Temporal Distribution Shift

arXiv:2607. 05908v1 Announce Type: new Abstract: Real-world data distributions evolve over time, inducing temporal distribution shift that can substantially degrade the reliability of deployed machine learning systems.

By Robin Holzinger (Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA), Riccardo Colletti (Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA)

llms computer-vision nlp

Hugging Face Trending Papers

Jul 9

Systematic Evaluation of Learning Rate Scheduling Strategies Across Heterogeneous Architectures

Choosing a learning rate scheduling strategy is critical to neural network training, but manual selection is costly and rarely exhaustive. While classical AutoML approaches often treat the scheduler as a secondary hyperparameter, we systematically investigate its impact on classification accuracy across a diverse pool of architectures.

llms

arXiv AI

Jul 29

CIFNet: An Analytic Neural Learning Framework for Efficient and Calibrated Class-Incremental Learning

arXiv:2509. 11285v2 Announce Type: replace-cross Abstract: Class-Incremental Learning (CIL) in deep neural networks is conventionally framed as an iterative gradient-based optimization problem, incurring high computational cost, hyperparameter sensitivity, and risk of catastrophic forgetting.

By Alejandro Dopico-Castro, Oscar Fontenla-Romero, Bertha Guijarro-Berdi\~nas, Amparo Alonso-Betanzos

rag diffusion safety

arXiv Machine Learning

2d ago

Adversarial Learning of Classifier-Free Guidance Schedules

arXiv:2608. 14038v1 Announce Type: new Abstract: Modern text-to-image diffusion models rely on classifier-free guidance (CFG) to achieve high image fidelity and text alignment.

By Ashwini Pokle, Alexandre Galashov, Arnaud Doucet, Mauricio Delbracio, Valentin De Bortoli

diffusion benchmarks safety

Hugging Face Trending Papers

Jul 7

Efficient Long-Horizon Learning for Learned Optimization

Learned optimization aims to improve upon hand-designed optimizers (e. g.

llms computer-vision

arXiv Machine Learning

Jul 20

Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training

arXiv:2607. 15745v1 Announce Type: new Abstract: Common practice when training Convolutional Neural Networks (CNNs) is to use randomly shuffled mini-batches.

By Anxhelo Shehu, Enes Stastoli, Arben Cela

benchmarks

arXiv AI

Jun 4

MesaNet: Sequence Modeling by Locally Optimal Test-Time Training

arXiv:2506. 05233v2 Announce Type: replace-cross Abstract: Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention.

By Johannes von Oswald, Nino Scherrer, Seijin Kobayashi, Luca Versari, Songlin Yang, Sarthak Mittal, Maximilian Schlegel, Kaitlin Maile, Yanick Schimpf, Oliver Sieberling, Alexander Meulemans, Rif A. Saurous, Guillaume Lajoie, Charlotte Frenkel, Razvan Pascanu, Blaise Ag\"uera y Arcas, Jo\~ao Sacramento

llms benchmarks

arXiv Machine Learning

Jul 10

Systematic Evaluation of Learning Rate Scheduling Strategies Across Heterogeneous Architectures

arXiv:2607. 08511v1 Announce Type: new Abstract: Choosing a learning rate scheduling strategy is critical to neural network training, but manual selection is costly and rarely exhaustive.

By Hafsa Mateen, Radu Timofte, Dmitry Ignatov

llms

arXiv AI

Jun 4

Can VLMs Predict Future States? Bootstrapping World Models from Inverse Dynamics

arXiv:2506. 06006v3 Announce Type: replace-cross Abstract: Can unified vision-language models (VLMs) perform forward dynamics prediction (FDP), i.

By Yifu Qiu, Yftah Ziser, Anna Korhonen, Shay B. Cohen, Edoardo M. Ponti

llms fine-tuning multimodal benchmarks

Related stories