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 94
Scaling Laws for Tool-Use Agents via Controllable Environment Synthesis
We explore how to build performant large language model (LLM) tool-use agents that complete complex, multi-step tasks.Dexterous In-Hand Object Pose Reaching with Learned Safety Filters
Dexterous manipulation with multi-fingered hands is the next frontier of robotics, yet learned hand skills remain limited to simple grasps or basic repeated motions, such as rotating an object.Attention as Lattice Gauge Theory: Relations Interact Only Through Wilson Loops
Relations compose through the entity they share - Alice is Bob's mother and Bob is Carol's father, so Alice is Carol's grandmother - and the order matters, since a father's mother is not a mother's…Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness
We introduce Heads of Security (HoS), a prompt injection defense that enforces instruction-data separation via a small set of learned per-head attention gates.When Should We Intervene at Test Time?
Test-time adaptation helps a deployed model respond to changing inputs, but the same intervention can rescue one batch and damage the next.Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction
Novel view synthesis and 3D reconstruction have advanced rapidly with radiance fields and splatting, yet their memory and computational demands limit their use in resource-constrained settings.Moment-Guided Optimizers for Noisy Deep Learning: MGO-SC as a Simple Consistency Gate for Adam-Style Updates
Adaptive optimizers are widely used in deep learning, yet their behavior can degrade under heavy stochasticity and label noise where the sign and magnitude of gradients can be unstable.Generation, Not Selection: LLM Proposals for Certified Access-Control Policy Mining
Attribute-Based Access Control (ABAC) policy mining---recovering a compact, auditable policy from an access log---is posed as minimum set cover and solved greedily, which enjoys an $s^{*}(1+\ln m)$…Learning Graph Beliefs for Active Radio Mapping With Decision-Certified Multi-Step Sensing
Radio maps provide essential wireless propagation knowledge for network optimization and autonomous platforms.What a Weight Update Buys: Leverage Across Training Stages
Post-training moves a language model's weights by about a thousandth of their norm and changes its behavior sharply; pretraining moves them by a third and buys a slow drift.LRMoE: Demand-Side Load Re-Calibration for Efficient MoE Training on Memory-Constrained Nodes
Sparse Mixture-of-Experts (MoE) models offer scalable capacity for Web applications, but uneven routing creates computation and communication bottlenecks.Threshold Compatibility and Support-Selection Diagnostics in Neural Discovery of Partial Differential Equations
Accurate regression need not yield the correct equation after support selection.Predicate Neuron: Differentiable Quantization of Predicate Relations in Gradient-based Learning
In machine learning, symbolic reasoning approaches often rely on static architectures that hinder integration into deep neural networks and gradient-based optimization.Beyond Similarity Search: Knowledge Graph Metadata Enrichment for Enterprise Retrieval-Augmented Generation
A key challenge of RAG systems is retrieving information from enterprise documents created by multiple teams over time, where it is not possible to enrich the information using the latest…Amortized Localized Posterior Inference for Model Calibration with Application to an Ocean Turbulence Closure
Model discrepancy may prevent a single calibration parameter from reproducing a physical response across the context domain.ThinkJev: One Thought, Every Budget for Calibrated Typed Decisions
Many uses of language models end in a typed decision: a choice among a closed set of options, whose probabilities code can act on.Selective Transfer Learning for Groundwater Level Anomaly Forecasting: Accuracy-Risk Trade-offs
This work studies context-aware selective transfer learning for multi-well groundwater anomaly forecasting in the Netherlands.Anisotropic Trust Region Warping for Prior-Data Fitted Networks in Bayesian Optimisation
Prior-Data Fitted Networks (PFNs) replace the hyperparameter refitting of Gaussian Process (GP) surrogates in Bayesian optimisation with a single forward pass, at the cost of a prior that is fixed…OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery
Large language models (LLMs) have shown increasing promise in research-level problem solving, yet a comprehensive collection of such problems is still missing, and evaluating them on research-level…Agentic Backdoors via Pretraining Poisoning
Large language models are pretrained on vast, uncurated corpora scraped from the public web.