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 2
When Scores Conflict with Preferences: Pre-Alignment Diagnosis and Adaptive Correction of Constraint Drift in DPO
Direct Preference Optimization (DPO) is increasingly used in settings where pairwise preferences coexist with pointwise criteria such as response length, answer correctness, or safety scores.Adversarial Multiplicity: Cherry-Picked Models and the Limits of Disclosure
Predictive multiplicity -- where similarly accurate models disagree on individual predictions -- can be leveraged to optimize secondary metrics (e.g., fairness) without loss in predictive performance.CacheGraft: Enhancing Retrieval-Augmented Generation via Latent-Space Document Enrichment
Recent work in machine learning has demonstrated that transformer-based language model agents can communicate state not only through text, but also directly in latent space via key-value (KV) caches.Rigorously Certified Neural-Network Computation of Nonlinear Water Waves at Near-Machine Precision
We present a computational framework that combines machine-learning-based discovery with rigorous computer-assisted numerical certification and formal verification for strongly nonlinear partial…Spectral symmetry fingerprints in equivariant representations
Symmetry governs the organization of physical structures, while symmetry breaking reveals their transformations.Truncated backpropagation through time induces a two-sided gradient turnpike property
Truncated backpropagation through time reduces the computational burden of training recurrent models by restricting gradient computations to shorter temporal contexts.IMUDINO: Self-distilled Foundation Model for Inertial Sensing
We present IMUDINO, the first foundation model (FM) for inertial sensing to achieve competitive performance across diverse sensing tasks including human activity recognition (HAR), health, motion…Two-stage residual learning for calibrated uncertainty in solar irradiance forecasts
Accurate forecasting of renewable generation requires not only point predictions but also reliable estimates of the uncertainty attached to them, particularly at extended horizons.Latency-Aware Adaptive Best-of-$N$
Test-time compute (TTC) improves language model responses by spending additional computation at inference time, and the right amount of compute depends on the prompt.The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks
How can an agent handle a real-world task end to end?Echoes of Error: Residual-Directional Local Rollout Consistency for Timeseries Forecasting
In time-series forecasting, rollout errors are not merely one-step fitting discrepancies: once fed back into the evolving state, they can perturb future predictions.Adversarial Robustness of Kernel Machines: A Comprehensive Analysis
Kernel machines are an important class of models in machine learning.KOSMOS: Self-scheduling Persistent Kernels for Communication-Compute Overlap
Tensor and sequence parallelism (TP+SP) and expert parallelism (EP) put collectives on the critical path of transformer layers.Localization Does Not Imply Steerability: A Mechanistic Study of Sign Errors in LLM Mathematics
When large language models do multi-step mathematics, a characteristic failure recurs: the model writes one wrong sign token mid-computation -- a cofactor sign, the minus of a recursive…OPRD-Imp: a dataset of experimentally observed impurities and side products in multi-step pharmaceutical syntheses
Predicting reaction impurities is a critical yet persistently data-limited challenge in pharmaceutical process chemistry.Statistical and Privacy Guarantees for Deep M-Regression via Stochastic Gradient Langevin Dynamics
In this article, we study deep nonparametric regression trained via stochastic gradient Langevin dynamics (SGLD), a variant of stochastic gradient descent that injects carefully calibrated Gaussian…Learning Multi-Agent Orchestration:Higher-Order Interactions in Policy Improvement
Learned orchestration has emerged as a promising paradigm for large language model (LLM)-based multi-agent systems, in which a central orchestrator selects agents and controls the information they…ZYFA: Speed and Accuracy of FP8 FlashAttention on AMD CDNA4
Attention is a core building block of frontier models and often dominates compute-bound prefill at long context.Coverage Hides Churn: Auditing and Preserving Conformal Decisions as VLM Label Registries Grow
Vision-language classifiers can learn new labels from text alone, so the label lists they serve keep growing.RLGPA: A Reinforcement Learning-Guided Granularity Planning Attack for Decision-Based Sparse Adversarial Examples
Decision-based sparse attacks must reduce perturbation support using only the victim's predicted label.