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 184
Global Convergence in Deep Networks via the Second Law of Thermodynamics
Existing convergence analyses of finite-width overparameterized deep neural networks under standard parameterization often rely on parameters remaining close to their initialization and typically…Process-Aware Event Log Augmentation for Process Prediction under Labeled Data Scarcity
Predictive Process Monitoring (PPM) forecasts future events of ongoing business processes based on event logs.Martingale Posterior Cox Processes
Cox processes provide a principled Bayesian nonparametric framework for modeling event-based data through an underlying intensity function.Who Gets Unmasked? Sampler-Induced Bias in Diffusion Language Models
Diffusion language models (dLLMs) generate by gradually unmasking a canvas, so their samplers decide not only which token to write but also when to commit it.Is User Calibration Still Necessary for Continuous Myoelectric Control? A Closed-Loop Comparison of Calibration-Free Controllers
The need for user-specific calibration remains an often-cited barrier to widespread adoption of myoelectric control.Tilted Mondrian: Triage and Mitigation of Fine-grained Disparities in Conformal Prediction
Fairness in conformal prediction is often pursued through Mondrian calibration, which provides finite-sample coverage guarantees separately across groups.First-Order LoRA Training with Phone NPUs
On-device fine-tuning lets a large language model (LLM) learn from its user's private data without uploading it.Efficiency Measured in English: Tokeniser Coverage Bounds Small Language Models on Indic Scripts
Small Language Models with quantisation and parameter-efficient adaptation are widely offered as the route to multilingual AI under compute constraints, and their efficiency is almost always…Pair-Aware Optimization: Coordinating Exploration and Refinement for Jailbreaking LLM Agents
Large Language Model (LLM) agents are vulnerable to adversarial inputs that induce attacker-specified malicious behaviors, commonly referred to as jailbreaking.Compose the Horizon: Parameter-Shared Blockwise Forecasting under a Sequential-Compute Trade-off
Most long-horizon forecasters emit the complete future in one pass.Recurrent Temporal Restricted Boltzmann Machines as Unsupervised Encoders for Biomechanical Movement Sequences
Biomechanical movement recordings are continuous, high-dimensional time series, and analyzing them without manually labeling them requires representations that capture how movements evolve over time.A Statistical Viewpoint on Adam, Shampoo and Muon
We provide new statistical insights into designing stochastic optimization methods.An Impossibility Result for ETF Target Geometry, and an Equinorm Remedy for Imbalanced Analytic Continual Learning
Analytic continual learning (ACL) methods such as ACIL and GACL fit a ridge-regression classifier head on frozen features via the Sherman-Morrison-Woodbury identity, achieving exemplar-free, exact…LLM-Based Evaluation Planning for Heterogeneous Optimization
Heterogeneous optimization problems require an optimizer to decide not only which candidate solutions to evaluate, but also which objectives and constraints should be evaluated under different costs…FlowMaker: From Tasks to Cost-Efficient Generative AI Workflow Deployments
Generative AI workflows execute user tasks by composing sequences of LLM calls, where each call performs a sub-task (e.g., summarization or translation), forming a workflow.Bellman Language Models: Solving the Recurring Decisions of LLM Agents
A general observation in agentic workflows, especially bounded ones, is that the decision space of the LLM, when we separate a decision from generation, starts approaching saturation: the agent…The Missing Compliance Class: LLM Graders That Collapse Jailbreak Success, and a Free Check
Jailbreak papers report an attack success rate, the share of responses that deliver the harmful request, and read it as a property of the target model.RAFT: Redundancy-Aware Input Filtering for Temporal Graph Neural Network Training
Temporal graph neural networks (TGNNs) have shown strong performance on dynamic graph learning tasks by continuously updating node memories from evolving interactions (i.e., events) and leveraging…Sample-Efficient Reinforcement Learning with General Utilities via Neural Dual Critics
Reinforcement learning with general utilities optimizes nonlinear functionals of policy-induced occupancy measures.Measuring Data Diversity with Embeddings: A Taxonomy and Benchmark for Diversity Measures
Diversity is a critical property of text corpora, with direct implications for training data curation, test set design, and model generalization.