AI & Machine Learning · Computer Science & AI
Machine Learning
The newest papers in Machine Learning that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 12 October 2026 to 5 November 2026: 5,000 arXiv preprints.
Get the few papers worth your time in Machine Learning every morning.
Follow Machine Learning and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 40
Ask, Don't Equip: Question-Driven Coding Agents for Deep Kernel Optimization
LLM agents for GPU kernel optimization sit at two ends of a structure-freedom tradeoff.VIAS: Value-Isolating Activation Steering for Multi-Value Alignment and Compliance for Organisations
Organisations increasingly deploy large language model agents that must follow organisational values.PanoTac: A Dense Three-Axis Tactile Sensor for Robust Touch-Centric Manipulation
Contact-rich manipulation benefits from tactile feedback that captures both detailed contact geometry and interaction forces.DistDebug-Bench: Can LLM Agents Diagnose Bugs in Distributed Systems?
LLM agents show strong potential in software engineering tasks such as competitive programming and code synthesis.Library of Layers (LoL): Adaptively Ordering Transformer Layers at Runtime
Computer programmers chain together the same reusable computational primitives, for example, conditional statements or loops, but in different orders to implement different algorithms.Variational Functional Neural Networks (vfNN)
We present a variational functional neural network (vfNN) algorithm that optimizes physically motivated continuum functionals in integral form (e.g., Lagrangian, Hamiltonian, or free energy) to find…Can LLM Agents Improve Imperfect Earth System Model Parameterizations?
Earth system models (ESMs) rely on parameterizations to represent unresolved processes such as convection, cloud microphysics, and turbulence.Nonparametric Intensity Estimation for Covariate-Driven Poisson Processes Using Deep Learning
We consider nonparametric maximum likelihood estimation of the intensity function of a Poisson process, allowing the intensity to depend on observed covariates.BISECT: Bilevel Spectral Decomposition for Low-Rank Continual Learning
Exemplar-free continual learning on pre-trained Vision Transformers increasingly relies on Low-Rank Adaptation (LoRA), yet prevailing methods govern the low-rank update space through strict subspace…Sonar-MoE: In-Backward Expert Updates for Memory-Efficient Mixture-of-Experts Training
Most parameters of a Mixture-of-Experts (MoE) model belong to its experts, and standard training keeps every expert gradient in GPU memory until the optimizer step.A Scaling Theory of Multi-Epoch Pretraining: Late-Time Overfitting and Ensembling
In the near future language model pretraining will become bound by total data rather than total compute.Evaluating Uncertainty Calibration in Probabilistic Time Series Foundation Models
Time series foundation models (TSFMs) are increasingly used for probabilistic forecasting across diverse domains, yet the reliability of their uncertainty estimates remains poorly understood.DynaSolver: A Neural Operator for Autoregressive 4D Flow Prediction with Dynamic Boundaries
Neural operators provide efficient surrogates for computational fluid dynamics (CFD), but most are designed for static geometries and are not equipped to model unsteady flows induced by continuously…Spacetime Emergence in the Memory of a Learning Agent
We show that the causal structure of spacetime can emerge within the memory of a learning agent performing a quantum information task.Structured Visual Landscape: Generating Preferred Representations in Biological and Artificial Neural Networks
Understanding how neurons respond to visual stimulus is an important question in both deep learning and neuroscience.Should We Combine Our Data? Algorithms and Limits for Privately Assessing Data Sharing
In this paper, we study when two parties should pool their data to train a machine learning model.Efficient Closure Learning in Dynamical Systems: A Comparison of Data-Assimilated and Embedded Approaches
Increased computing power has transformed computational science and improved predictive capabilities for complex systems, but many phenomena still exceed current simulation capabilities or require…Benchmark Prediction with Sparse and Unpaired Cached Responses
Evaluating a generative model on all queries from all available benchmark tasks is prohibitively expensive.D&A: Decoupling Description and Assessment Enables VLMs as Zero-Shot Robotic Reward Models
Vision-Language Models (VLMs) hold promise for zero-shot video task-progress estimation in robot learning, yet existing frameworks frequently suffer from confirmation bias, hallucinating progress in…Thought-deciphering via hierarchical EEG-to-text alignment
Non-invasive brain-to-text interfaces offer alternative communication pathways for people with communication disabilities.