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 215
Neural Wasserstein Splines: Representation-Invariant Second-Order Priors for Trajectory Inference
Population dynamics are often observed only as unpaired snapshots, which leave the evolution between measurements underdetermined.Occupancy Modeling via Drifting: One-Step Generation Enables Direct Policy Extraction
The growing interest in behavior foundation models, combined with recent advancements in generative modeling, has led to an appealing recipe for reinforcement learning from unlabeled data: pre-train…On the Limits of Representation-Based Test-Time Adaptation for Multimodal LLMs
Vision-language models suffer significant accuracy drops under common corruptions.Few-Shot Adaptation for Anomalous Sound Detection at Low False-Positive Rate
Reliable fault detection is crucial for industrial machinery in large-scale facilities, where unexpected failures can cause costly downtime and production interruptions.Universal Sample-Based Embeddings of Higher-Order Objects
Neural networks operate naturally on finite-dimensional vectors, yet many problems require reasoning about higher-order objects such as distributions, functions, and graphs.Multimodal Medical Image Parsing with Task-Specific Low-Rank Adapters
Adapting a single vision-language model to medical image parsing requires training choices that reflect the demands of each task.When Non-Adversarial Noise Hurts Learning: Benchmarking Skill Self-Evolution in Agents
Large language model agents increasingly improve by distilling experience into reusable skills, but errors in that experience can persist in learned rules and affect later tasks.CARD: Closing the Teacher-Student Loop for Adversarial Robustness Distillation
Adversarial robustness distillation typically treats a robust teacher as a fixed knowledge source and transfers robustness to a compact student in a one-way manner.Beyond DFT electronic band structures via dual-space orbital learning
Accurate electronic band structures are essential for predicting material properties, but high-fidelity calculations are computationally demanding.MolHop: Scaffold-Hopping Molecular Design with Agentic Reinforcement Learning
Molecular design is often formulated as an optimization problem over existing molecular spaces.Convergence Rates of Gaussian Process Thompson Sampling for Efficient Global Optimization
Efficient global optimization aims to identify a global optimum of an expensive black-box function within a limited evaluation budget $N$.SAM3RL: Memory Control via Reinforcement Learning for Visual Object Tracking
Segment Anything Model 3 (SAM 3) is a foundation model for image and video segmentation that sets the state of the art in visual object tracking.MorphingNet: Symbolic Regression Where the Network Is the Formula
We introduce MorphingNet, a network for symbolic regression (SR) whose units change their function continuously.Learning Graph Energies for Finite-Time Generation
Energy-based models can represent distributions over discrete structures such as molecular graphs, but an energy that is accurate at equilibrium need not yield accurate samples when the sampler…AtomSearch: Evidence-Grounded Tree Search for Agent Skill Optimization
Agent skills adapt frozen models through editable external instructions.Choosing the Number of Attention Heads from Intrinsic Dimension: A Small-Scale Study
The number of attention heads in a transformer is usually set by convention or grid search.Safe-FCL: Continual Risk Awareness and Fine-Grained Safety Aggregation for Federated Continual Learning of LLMs
Federated fine-tuning enables large language models (LLMs) to learn collaboratively from distributed client data, but malicious client updates can compromise global model safety.LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation
Looped Mixture-of-Experts (MoE) models combine parameter reuse with sparse computation to improve performance under matched budgets.Empirical Boundaries of Reservoir Computing for Few-Shot Sequence Pattern Tasks
Efficient sequence modeling remains a fundamental challenge in machine learning.Provable Transformer Context Compression for In-Context Reinforcement Learning
Transformers can perform in-context reinforcement learning without parameter updates.