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 57
Do Earnings Calls Help Predict Financial Restatements? Evaluating Text Beyond Public Firm Information
Financial restatements correct errors in previously published financial reports.What Does a Safety Label Measure? Auditing Situational-Safety Benchmarks for Multimodal LLMs
Situational-safety benchmarks label each scene SAFE or UNSAFE and score a multimodal large language model (MLLM) against that label, usually by judging its free-form answer, and these scores guide…World Models Need Not Be Right to Rank Policies Right: Relative Bounds and Audit Limits
Selecting a reinforcement-learning (RL) policy usually requires additional environment interaction, while learned world models offer cheap but potentially biased evaluations.Lower Bounds on Inference Complexity for Polyak-Ruppert Averaged Stochastic Gradient Descent
In this paper, we establish sharp lower bounds for Gaussian approximation of Polyak-Ruppert averaged stochastic gradient descent with polynomially decreasing step sizes.Lightweight Representation Learning for Low Tucker Rank Tensors
Low Tucker rank tensors provide compact representations of multidimensional dependencies, but standard learning pipelines can incur substantial computational and memory overhead from redundant…TRIAGE: Reliability- and Load-Conditioned Escalation for Two-Tier LLM Serving with a Semantic Evidence Judge
Two-tier LLM serving escalates selected requests from a small model to a large one, but prompt-based routers cannot see whether retrieved evidence supports an answer, and they treat the GPU cost of…Fast and Exact Relative-Position Attention via Structure-Aware Kernels
Relative-position attention mechanisms offer compelling alternatives to RoPE across various transformer architectures, delivering superior performance in domains such as audio.Satisfied, Not Solving: Wireheading of Bounded Homeostatic Rewards in Reinforcement Learning
Bounded intrinsic rewards are often assumed to be safe from exploitation: if a signal can yield at most a fixed amount, gaming it should not pay.Zeroth-Order Policy Optimization for Scheduling in Queueing Networks
Reinforcement learning in queueing network scheduling presents significant challenges because of the countably infinite state space and the high stochasticity in transitions.ArSciKids: Arabic Curriculum-Aligned Datasets for Scientific Experiment and Multiple-Choice Question Generation in Primary Education
Despite growing interest in Arabic natural language processing, curriculum-aligned educational resources remain scarce compared with English, and few public datasets for Arabic curriculum content…Online Autotuning of Algebraic Multigrid via Contextual Bandits and Reinforcement Learning
Algebraic multigrid (AMG) methods are widely used for solving large sparse linear systems, but their efficiency depends strongly on interacting setup and solve parameters.GraCo: A Unified Toolkit of Graph Coarsening Algorithms and Metrics
Graph coarsening aims to reduce a graph to a smaller one that preserves chosen properties of the original.A Batched Hartigan's $k$-Means Clustering
Hartigan's $k$-means algorithm has theoretical advantages over the standard Lloyd's variant, which has become synonymous with "$k$-means".Adaptive Optimizers Can Get a Policy Ranking Wrong: Momentum, Dependent Data, and a Two-Run Remedy
Operators choosing among decision rules, such as when a battery charges or where an idle taxi goes, rank them by estimated long-run value.Reproducing INP-Former: Reconstructing Intrinsic Normal Prototypes for Industrial Anomaly Detection
We reproduce the central claims of INP-Former, a reconstruction-based method for multi-class industrial anomaly detection.Mathematical Formulation and Comparative Performance Evaluation of Machine Learning Algorithms for Maize Land Suitability Prediction
Addressing the food needs of a growing population is one of the major challenges of developing countries like Ethiopia.Learning What to Ask and What to Believe: Distilling a Variational Bayesian Agent into Language Models
Interactive tasks such as eliciting a user's preferences or diagnosing a hidden mechanism require an agent to track its uncertainty over a latent state, ask informative questions and act on the…LoRAForge: Co-Designing Post-Hoc Compression and Execution for Efficient Multi-LoRA Serving
Multi-LoRA serving allows many task-specific adapters to share a common base model, but scaling to large adapter fleets introduces substantial storage, loading, and execution overheads.Does Random Search Discover Task Experts? Revisiting Neural Thickets
Pretrained models are typically viewed as generalists, requiring bespoke post-training to achieve task-specific expertise.Learning momenta for Hamiltonian-based models
There has been increasing interest in methodologies that incorporate physics priors into neural network architectures to enhance their modeling capabilities.