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 112
Controlled Block Proximal Linearized Method for Nonconvex and Nonsmooth Optimization
We consider multiblock nonconvex and nonsmooth optimization without assuming bounded iterates or coercivity of the original objective.Dynamic Multi-Step Decoding for Time-Series Foundation Models
Time-series forecasting models typically use a fixed decoding strategy at inference time: either one-shot prediction of the full horizon or autoregressive rollout over atomic chunks.From GPU to TPU with Coding Agents: What Works, What Fails, and What It Costs?
A coding agent can migrate a machine learning workload, report success, and still change how the model trains.ScaleRLT: Exact Log-Probabilities and Fast Deferred Rollouts for Reinforcement Learning on Looped Transformers
Looped language models such as Ouro reuse one block of layers several times per token.Non-Ergodic Markovian Mirror Descent with Unbounded Noise
We analyze stochastic mirror descent for minimizing a convex objective expressed as an expectation under the stationary distribution of a Markov chain, using noisy subgradient observations along a…Speculative Decoding for Mixture-of-Experts Models: Expert Bytes, Kernel Bandwidth and the Best Draft Length
Speculative decoding checks several drafted tokens in one verification pass.From Explaining to Enabling: Actionable Transparency in Algorithmic Insurance Pricing
Machine learning (ML) systems increasingly make consequential decisions about individuals, including credit, hiring, and insurance.End-to-End Neural Modeling of EM Response and Design Performance for Free-Form RFIC Passives
Passive matching networks are critical components in radio-frequency integrated circuits (RFICs), but their design is bottlenecked by expensive finite-difference-based electromagnetic (EM) simulation.IntNet: A Communication-Driven Multi-Agent Reinforcement Learning Framework for Cooperative Autonomous Driving
Achieving safety in autonomous driving through Multi-Agent Reinforcement Learning (MARL) is a critical yet challenging task due to non-stationarity, partial observability, and the need for effective…Extrapolating learned dynamics across bifurcations based on generalized synchronization
Predicting dynamics across bifurcations by extrapolating trained models is crucial in diverse fields of physics.Finite-Sample Sensitivity of Kernel Metrics for Generative Evaluation
Kernel distances such as the Kernel Inception Distance (KID) and the Kernel Audio Distance (KAD) compare generated and reference samples in an embedding space, and model comparisons rest on their…Intrinsic Gradient Barriers in Pushforward Deep Generative Models
Broad classes of deep generative models (DGMs) operate by learning to map a simple source distribution, such as a standard Gaussian, to a complex high-dimensional target distribution.Models Verify Sufficiency, Not Validity: Usable Falsehoods Evade the Checks that Gaps Trigger
Ask a model "how many settlements did the Normans control?" and it answers that the passage does not say.Efficient Proof Generation for Lean Statements with Multiple Candidate Answers
In formal systems such as Lean 4, efficiently finding answers to mathematical problems and generating verifiable proofs is an important task in automated mathematical reasoning.Wave Is All You Need: A Quantum Language Model Based on Fully Connected Quantum Boltzmann Machine
This work proposes a self-attention mechanism based on the fully connected quantum Boltzmann machine (FC-QBM), and further constructs a fully connected quantum Boltzmann machine language model…Certifying Distributionally Robust Decisions from Projection Observations
A scalar measurement can determine a robust decision without identifying the latent covariance or every decision risk.Approximate Unlearning in Prototype-based-classifiers
The recent data and AI regulations and governance needs have highlighted the need for removing specific data even from models trained on or with them.Best Policy Tracking in Reinforcement Learning
Reinforcement learning commonly exhibits non-monotonic performance dynamics in single-task settings.Ambiguous Fits: The Rashomon Effect and Challenges in Scaling Law Estimation
Estimating neural scaling laws involves an end-to-end pipeline: designing a scaling recipe, training models across scales, evaluating models on a target metric, and deploying an algorithm to fit a…TRIAGE: Efficient Vision-Language-Action Inference Needs Both Reuse and Pruning
Vision-language-action (VLA) models are increasingly used for robot manipulation because they map camera images and a language instruction directly to actions.