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 81
HotPOT: Operator Transformer with Heterogeneous Physics Experts for Large-Scale PDE Pre-training
Large-scale PDE pre-training trains a single model on the data from multiple partial differential equations (PDEs).The Endgame of FSDP Communication: Layout-Aware Collectives on Copy Engines, RDMA, and NVSwitch
Fully Sharded Data Parallelism (FSDP2) maintains parameters and gradients as per-parameter tensors, whereas its collective path operates on flat, rank-major buffers.Variational Consequence-Driven Offline Reinforcement Learning
Offline reinforcement learning (RL) typically mitigates distribution shift by imposing divergence constraints on the action distributions of the learned and behavior policies.Nearly Minimax Optimal Regret for Adversarial Linear Bandits with Strong Corruptions
We study adversarial linear bandits with strong corruption, in which an adaptive adversary chooses the reward vectors and a strong adversary corrupts each observed reward after seeing the learner's…Transportable Offline Reinforcement Learning in Presence of Unmeasured Confounding
Offline reinforcement learning seeks to learn decision policies from previously collected data, but deployment environments may differ from the domains in which the data were collected, and logged…ParaTTT: Parallelizing Test-Time Training Layers with Deep Memories
Test-time training (TTT) layers replace the linear fast-weight memory of modern recurrent architectures with a small neural network trained online by gradient descent.A Hybrid Physics-informed holomorphic neural networks Method
Physics-informed holomorphic neural networks (PIHNNs) exploit complex-analytic representations to satisfy homogeneous PDEs by construction, but their extension to nonhomogeneous problems is…NAGO: Noise-Aware Generative Operator via Flow Matching
We introduce NAGO, a noise-aware generative operator for efficient sampling from invariant measures of stochastic partial differential equations (SPDEs) in function space.The Role of Quantization in Loss Spikes
Loss spikes in language model pretraining can waste substantial compute and derail otherwise healthy training runs.A Witnessing Duality for ReLU Network Depth
A depth lower bound for ReLU networks asserts that every sufficiently shallow network fails on some input.Does 3D Pose Improve Action Valuation in Football? An Empirical Study of Pose Representations and Learning Objectives
Football action valuation estimates players' contributions to future scoring.Game-Theoretic Foundations for Undiscounted Bisimulation Metrics
Bisimulation metrics offer a principled notion of task-relevant state similarity in reinforcement learning, but existing constructions and methods are largely confined to discounted MDPs, where…A Case Study of a Multi-Agent Kernel-Optimization Loop That Learns a New AI Accelerator
Frontier large language models write correct CUDA kernels for most single-operator benchmark tasks, yet their accuracy collapses on accelerators whose architecture and programming language they have…Multi-Token Prediction Done Right
Multi-Token Prediction (MTP) is now a common ingredient in language-model pre-training, as it improves downstream performance and enables faster inference through speculative decoding.MUSE: Multi-Level Memory with Selective Runtime Injection for Scientific Coding Agents
Historical experience can guide scientific coding at multiple levels, but task-level retrieval may miss implementation lessons that become relevant during execution.Optimal Regret for Communication-Efficient Decentralized Online Learning
In this paper, we investigate decentralized online convex optimization with compressed communication, where $n$ learners over a network jointly minimize a sequence of global loss functions based…Learning a Prior-Data Fitted Network for Graph Foundation Models via Structural Causal Model Priors
Graph Foundation Models (GFMs) have recently emerged as a promising paradigm for learning transferable representations across different graphs and domains.CSO: Refining Robotic Policies via Skill Distribution Alignment and Skill-Grained Optimization
Discretizing continuous actions into discrete skills using methods like VQ-VAE has emerged as a powerful paradigm for robotic manipulation.Towards Reliable, Scalable, and Value-Aligned Generative Recommendation for Large-Scale Advertising
Generative recommendation (GR) reformulates item retrieval as autoregressive generation of discrete semantic identifiers (SIDs), offering a unified paradigm for personalized recommendation.How Much Do Teacher Bridges Matter in Interleaved On-Policy Distillation?
On-policy distillation (OPD) trains a student using teacher predictions on student-generated responses.