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 250
When LLM Agents See a Conflict but Still Proceed: Cross-Domain Dependencies in Network Slicing
Future AI-native networks are being designed to apply autonomous agents built on large language models (LLMs) in network management through intents.Can Rényi Accountants Beat Lossless Accountants for DP-SGD?
Recent frameworks in differential privacy (DP), such as privacy loss distributions and $f$-DP, provide lossless representations of the privacy leakage of mechanisms.Masked Attention Pooling Is Invariant to Padding and Permutation: A Formal Proof in Lean
Attention-based multiple instance learning (MIL) pools a variable-size bag of instance embeddings into one vector.OpenDGO: Benchmarking Multi-Agent Organizations Across Diverse Application Domains
Large language model (LLM)-based multi-agent systems are increasingly applied across diverse domains, yet different applications require different forms of agent organization.SCOPE Before You Sample: Conformal Scores Guide Posterior Exploration for Fast and Calibrated Bayesian Predictive Inference
Bayesian predictive regions account for parameter uncertainty but can be poorly calibrated under model misspecification, even with expensive full MCMC.Implicit and explicit reparameterizations of the Folded Normal and Rice distributions
Variational inference is a flexible tool for modeling experimental data and has proven useful in crystallography.Neuromorphic Decoding and Dynamical Image Reconstruction from Populations of Spiking Retinal Ganglion Cells
Decoding visual stimuli from the spiking activity of retinal ganglion cells (RGCs) informs both our understanding of the retinal code and the design of visual prostheses.A Generalized McDiarmid Inequality: Sample Reuse and Non-Uniform Unbounded Differences
We develop a novel generalization of McDiarmid's concentration inequality and use it to obtain a uniform law of large numbers result and error bounds on stochastic optimization problems which…Comprehensive Workflow for Uncertainty-Aware Ionic Liquid Solvent Discovery
Designing synthesizable materials with targeted properties remains one of the central objectives in materials sciences.Generative Flow on Symbolic Abstractions for Embodiment Capability Discovery
Achieving complex, long-horizon robot behavior remains challenging because successful execution depends on skills grounded in a robot's physical affordances.FunDM: Cheap & Label-Free Decision Models from Frozen Language Models
Decision models such as Jev score candidate answers or actions.ModRes: A modification of the ResPlan dataset ready for floor plan analysis and graph machine learning
Floor plan datasets underpin computational analysis of building layouts, spatial connectivity and graph machine learning.Soft Teacher Forcing
Soft tokens have so far been used to replace discrete chain-of-thought in latent reasoning methods.CartoVec: General-Purpose Location Embeddings from Open Map Data
Geographic coordinates are common inputs in applied machine learning, but latitude and longitude describe position rather than the surrounding environment.FreeSolo: Linear-time Sparse Attention with Zero-Shot Length Extrapolation
Linear-time sequence models typically store long-context information in a recurrent state.MLAfication: Efficiently Enabling High-Fidelity MLA for Modern LLMs
Multi-Head Latent Attention (MLA) compresses the KV cache into a latent representation, reducing inference memory and bandwidth.Online LLM Personalization from Pairwise Preferences Across Users
Large language models can answer the same question in different styles, but users' preferred styles are hidden and vary across users and questions.Density-Matrix Reinforcement Learning
What information does a reinforcement learning policy omit?Compute-optimal data scaling for neural surrogates via multi-fidelity training
Neural surrogates for Partial Differential Equations (PDEs) are usually trained on synthetic data from numerical simulators.CodeLift: Your Test Suite Is Secretly a Dense SWE Curriculum
The pass-all-test binary reward has become a standard recipe for training software engineering agents, but its sparsity eliminates difference of partially correct patches.