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 152
Engram Memory Network: Brain-Inspired Prototype Explanations
Artificial intelligence systems are increasingly deployed in high-stakes decision-making.How Much Do $\ell_1$ Attacks Need Concentrated Perturbations?
A global $\ell_1$ budget limits how much an adversary may change an image, not how that change is distributed.Foundations of the Scaling Law
Empirical scaling laws relate loss to parameters $N$, training tokens $D$ and compute $C$.TerraNostra-Bench: Benchmarking Spatial Downscaling and Temporal Rollout for Global 1-km Land-Use Reconstruction
Uncertainty in the terrestrial carbon cycle remains a major constraint in climate projections, partly due to imperfect land surface representations in Earth system models.Certified Adaptive List Decoding for Error-Correcting Codes
Maximum-likelihood (ML) decoding of linear block codes is NP-hard, so neural decoders are evaluated by how closely they approach it.SliMOO: Interpretable Multi-Objective Evolutionary Search for LLM Depth Pruning
As large language models (LLMs) grow more powerful, their scale makes them costly to serve.ProVe: Proposer-Verifier Decoding
Speculative decoding accelerates autoregressive (AR) language models by letting a small model draft tokens serially and a large model verify them in parallel.From Generic to Dedicated: A Novel Optimizer for Online Continual Learning
Online Continual Learning (OCL) requires models to learn from non-stationary data streams under a strict single-pass constraint, making them highly susceptible to catastrophic forgetting.SAPD: Learning from Agent Experience without Environment Interaction
Scaling the training of Large Language Model (LLM) agents typically requires a large collection of executable environments, whose construction, maintenance, and operation constrain the expansion of…LaLa-World: Scaling Latent World Models with Natural Language Actions
This paper shows that JEPA-style latent world models (LWMs) can learn across diverse domains and data sources by adopting the language-conditioned interface of video generation models.From Tokens to Files: Multi-Granularity Detection and Localization of AI-Involved Code
The increasing use of large language models for code generation calls for methods that distinguish purely human-written code from AI-involved code: files in which any part, however small, was…Enumeration-Guided Training of Neural Hamilton-Jacobi Safety Certificates
Hamilton-Jacobi (HJ) reachability analysis offers formal safety guarantees for control systems, but training accurate neural certificates remains difficult, particularly when unsafe regions are hard…Elicitation or Expansion? Demystifying Gains from Agent Harness Optimization
Recent studies in harness optimization have shown substantial performance gains in language model agents without updating model weights.Physical-Variable-Informed Deep Learning for Robust Diagnosis in Industrial Fluid Transport Systems
Industrial fluid transport systems are monitored through heterogeneous sensing streams, but robust fault diagnosis remains difficult because response signals vary with operating conditions and…The Shape of the DPO Hyperparameter Landscape: What to Measure, How It Moves with Scale, and When Not to Transfer It
Direct preference optimisation (DPO) is widely used for language model post-training, but its performance depends strongly on the choice of its hyperparameters, such as the learning rate and the…Near-Duplicate Image Selection Transfers Preferences in Vision-Language Models
Subliminal learning is the phenomenon in which a model transmits its preferences to another model through data that do not explicitly express them.Unsupervised Head Network Personalization for Split Computing via Federated Learning
Split Computing (SC) is a distributed inference method designed for balancing computational load and reducing latency by partitioning a neural network into head and tail networks and deploying them…Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay
Recent advances in large (vision) language models have enabled computer-use agents that automate digital workflows via fine-grained keyboard and mouse operations.Neural Closed-Loop Identification of Nonlinear Systems with Stability and Generalization Guarantees
Neural networks are expressive models of nonlinear dynamics, but identifying such systems from closed-loop data raises two difficulties: the feedback loop correlates inputs with measurement noise…Annealed correlation and quenched noise sensitivity in biased deep neural networks
In earlier work by Jonasson, Steif and Zetterqvist (2023), fully connected deep neural networks with layers of width $n$, i.i.d.\ standard Gaussian weights, sign activations and no bias terms were…