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 137
Aligning Large Language Models with Human Feedback: Mathematical Foundations and Algorithm Design
This article provides an introduction to the mathematical foundations and algorithmic frameworks used to align Large Language Models (LLMs) with human intentions, preferences, and values.Rewriting Scaling Laws for Synthetic Data with Compute and Data Constraints
Synthetic rewrites, where a language model rewrites a natural document e.g. into a target style, are now a standard ingredient of pretraining corpora.Forecasting Associations, Not Interventions: A Preregistered Causal Audit of Covariate-Aware Time Series Foundation Models
Covariate-aware time series foundation models (TSFMs) accept a future path for a control variable and return a forecast, inviting what-if queries.Effectiveness of Curriculum Learning Depends on Reward Sparsity and Competing Optima
While animals and people tend to learn a task more quickly and reliably when they first train on simpler versions of it, curriculum learning's effectiveness in artificial settings varies, and…Scaling Transformer Energy-based Models For High Quality Image Synthesis
Energy-Based Models (EBMs) are a flexible class of generative models that decouple probabilistic modeling from the generation process.Combinatorial Characterizations of the Learnability of Conditional Distributions
We study the PAC-learnability of function classes that map inputs to probability distributions over a finite space.Learning Structured Sparsity for Large Models: Bridging Model Compressibility and Efficient Inference
Scaling laws continue to reward increases in model scale, while the resulting computational and memory demands drive greater reliance on cloud infrastructure for inference.Real-to-Sim Calibration of Bosch Etching Simulators with Few-Shot XSEM Data and Hybrid Search
The Bosch process is widely used in MEMS and TSV fabrication, but accurate prediction of etching outcomes remains difficult without calibration against real measurements, which are sparse and costly…Topological Equivalence of Spectral and Density Cluster Hierarchies
We compare two canonical ways to recover hierarchical clustering from an underlying density $f$: the \emph{density cluster tree} given by connected components of superlevel sets $\{f\geλ\}$, and a…Decode Late, Multiply Once: Rethinking the Dot Product for Quantized Weights
Large neural networks are increasingly deployed with 1-4 bit weights and 16- or 32-bit activations, yet their dot products still use one multiplier per element.Input Bias Correction in Gaussian Process Regression
In traditional Gaussian process (GP) regression, the inputs are typically assumed to be known, and uncertainty enters only through the measurements.ENCL: Enabling Efficient Neuromorphic Continual Learning with Local Learning Rule and Sub-Network Freezing Strategy
Continual learning (CL) in neural networks is a promising learning approach for updating the knowledge of deployed systems based on new data encountered at run time, that have not been learned…Every Weight Is a Path of Shared Discrete Decisions
We introduce TWIG (Tree-structured Weights with Inherited Gates), a representation in which every weight of a neural network is the end of a path of small discrete decisions: a sign, a shift by a…Beyond Local Accuracy: Benchmarking the Rollout Reliability of PDE Foundation Models
PDE foundation models enable data-efficient adaptation but are deployed autoregressively, so short-horizon accuracy need not imply reliable simulation.Agreement rather than normalisation keeps depth reusable in looped language models
Looped language models apply one block of layers repeatedly, and the design pays off only if depth is reusable: loop steps beyond the trained budget must remain usable at inference.Towards Trustworthy AI-Enabled Emergency Medical Dispatch: Uncertainty-Aware Ambulance Travel Time Estimation
Emergency medical dispatch increasingly relies on AI-enabled decision support systems when making ambulance dispatch decisions.Kolibri: A Sovereign European Model on the Pareto Frontier
This report introduces Kolibri, an English-German mixture-of-experts transformer with 78.1B total parameters and 3.46B active parameters per token, released as open weights under the Apache 2.0…Sharp Bounds on the Winner's Bias under Independent and Nonnegatively Correlated Noise
Reporting the best of $M$ noisy, unbiased scores overstates the winner's value by up to $c\sqrt{V}$, where $V$ is the total noise variance and the sharp constant $c$ depends on how the noise is…RobustNCL: Robustifying Neuromorphic Continual Learning under Transient Faults with Lightweight Detect-and-Cure Strategy
In neural networks, continual learning (CL) is a prominent approach for enabling deployed systems to adapt to dynamic operational environments by effectively learning from new unseen data at runtime.A Mathematical Theory of the Jacobian Lens
Recent work from Anthropic introduced a new interpretability tool, called the Jacobian lens (J-lens, Gurnee et al., 2026).