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 221
Latent Annealed Posterior Sampling with a Variance-Preserving Bridge for Sparsely Observed Random Fields
Posterior inference for random fields from sparse observations presents two major challenges: accurately characterizing complex spatial uncertainty and preventing conditional sampling costs from…Graph Additive Models disentangling feature, topology, and interactions
Graph Neural Additive Networks (GNANs) have emerged as effective, interpretable-by-design architectures for graph learning.Evaluating Model Capabilities After Benchmark Saturation
Rapid advances in AI capabilities are causing benchmarks to saturate.CascadeLedger: Counterfactual Auditing of Information and Resource Integrity in LLM Cascades
We introduce CascadeLedger, a counterfactual execution-audit framework for budgeted language-model cascades.Value-Informed Schedule Trimming for Accelerated Sequential Monte Carlo Guidance in Discrete Diffusion
Reward-guided discrete diffusion enables test-time alignment with downstream objectives, but applying Sequential Monte Carlo (SMC) guidance at every denoising step is computationally expensive.On the Stability and Convergence of Flow Map Training
Flow maps are a recent method of probabilistic generation that amortize diffusion trajectories into one-step samplers, unlocking efficient generation.AlphaDiana: A Measurement System for Agents in Verifiable Reasoning Tasks
Agents pair reasoning models with harnesses that organize model calls, execute tools, load skill instructions, and retain history in memory.Spectral Indistinguishability and Learning-Curve Identifiability in Quadratic Networks
Motivated by information-organization sculpting, we study spectral summaries and scalar learning curves in centered quadratic networks.Diminishing Returns of Data in Sparse Autoencoders: Functional Behavior does not Guarantee Feature Reproducibility
Sparse autoencoders (SAEs) are typically trained on hundreds of millions to billions of activation tokens, yet little work has tested whether this scale is necessary.TurboMamba: Faster Inference, Faster Training, and Better Prediction with Lexical Memory
We introduce TurboMamba, a language-model architecture for faster inference, faster training, and better token prediction.Causal Syntax Circuits in CodeLMs: Budget and Probe Decide What Looks Localised
Code models write Python when the prompt does not say which language to use.Learning Topology-Aware Representations for Mechanics-Relevant TPMS Metamaterials
Learning informative representations of mechanical Triply Periodic Minimal Surface (TPMS) metamaterials is important for mechanics analysis and structural design, yet existing methods have rarely…RoLaQ: Joint Rotation and Range Calibration for 2-Bit KV Caches in Multi-Head Latent Attention
Multi-head latent attention (MLA) compresses the content of a key-value cache into a shared latent per token, making low-bit storage attractive for long-context inference.On-Policy Residual Learning for Diffusion Language Models
Residual context is key to unlocking the speed-quality Pareto frontier of diffusion language models (DLMs) by carrying forward predictive distributions across denoising steps.Quantile-Guided Diffusion for Probabilistic Time-Series Forecasting
Quantile forecasts summarize uncertainty at each future time step, while diffusion forecasters represent it through sampled future trajectories.Vertical Sliced Wasserstein Distances for Meta-Measures
Many modern learning problems require comparing probability distributions whose individual observations are themselves probability measures, naturally giving rise to meta-measures in…Ergodic topology sampling toward the continuum with Stochastic Normalizing Flows
In this work we provide numerical evidence that topological freezing in $\mathrm{SU}(3)$ Yang-Mills theory can be mitigated with a flow-based approach, as tested at lattice spacings as fine as…Interpreting Language Model Parameters
Mechanistic interpretability aims to uncover how neural networks use their parameters to implement their impressive neural algorithms.Optimal Hydra: Model Heterogeneous Federated Learning for LLMs using Data-Informed Hydra-Nets
Large language models (LLMs) trained on vast amounts of data have demonstrated impressive performance over a range of tasks, but future performance gains will require increasing amounts of data and…Purify Before You Align: Improving Representation Alignment for Diffusion Models
Representation alignment improves and accelerates diffusion training by encouraging intermediate features to match a pretrained visual encoder.