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 83
Logical Guidance of Stochastic Interpolants
Guidance and composition of generative models have applications in visual design, chemistry, and biology.Explore Where It Matters: Targeted Exploration for Efficient Rover Adaptation
Future planetary rovers will traverse steep, deformable terrain where slip, sinkage, and terrain deformation can threaten mobility.ExplainCC: Explaining Correlated Clusters by Node Labels
An increasingly important requirement for clustering algorithms is that decisions and outcomes need to be clearly understandable for human users.Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models
Self-distillation offers a way to improve reasoning models when a suitable external teacher is unavailable.On the Generalization Gap of Streaming Federated Learning with Markovian Data
Streaming federated learning (SFL) allows clients to train a shared model from continuously arriving data without retaining large local datasets.Deogen: Automatic Benchmark Generation for Reasoning over Policies
Language models are increasingly being deployed in regulated settings, where a model must apply given rules to the facts of a situation to determine a verdict.Geometry Matters in Packed 3D Attention
Packing a 3D volume into a token sequence is not merely long-sequence modeling.SatOps-Decision: Low-Latency Discriminative Decisions for Onboard Satellite Communication Operations
We propose SatOps-Decision, a method for low-latency decisions in satellite communication operations.Latent Decision Flow Rewards for Clinical Guideline Reasoning
Clinical practice guidelines encode evidence-based recommendations as conditional decision flows, which makes them a natural source of process supervision for training reasoning models.Adversarial Self-Distillation
Even though current safety-aligned language models are able to refuse harmful requests, their guard can still be bypassed by adversarial perturbations.Streaming Speech Recognition on a Microcontroller: a 65.7M-Parameter Transducer in 2 and 4 Bits on the ESP32-P4
We run Kroko, a 65.7M-parameter streaming Zipformer2 transducer for English, on the ESP32-P4, a microcontroller with two 400 MHz RISC-V cores, a 128-bit SIMD extension (PIE) and 32 MB of PSRAM, but…Alpha-TCM: A Nine-Layer Framework for TCM-Guided Multimodal Inference and Structured-Prior Auditing
Alpha-TCM makes two contributions under a central thesis: auditable systems should separate domain knowledge, case evidence, probabilistic inference, and downstream authority.Rennala NSGD: Asynchronous Stochastic Optimization Beyond Euclidean Geometry
The empirical success of matrix-aware optimizers, such as Muon (Jordan et al., 2024) and Shampoo (arXiv:1802.09568), highlights the potential of non-Euclidean geometry for deep learning, including…Auditable Hierarchical Inference with Multimodal Evidence and Bayesian Active Inquiry
Most multimodal classifiers assume that all useful evidence is available upfront, whereas clinical inquiry is sequential.Skillful and realistic precipitation forecasting with reinforced diffusion
Accurate precipitation forecasting remains elusive as physics-based models struggle to resolve mesoscale convection and machine learning often yields physically inconsistent, blurred results that…Loss is Not Behavior: A Unified Output-Space Analysis of Gradient-Based Machine Unlearning
Gradient-based machine unlearning methods typically ``unlearn'' by optimizing forget and retain losses, but similar losses do not necessarily imply similar output-space behavior.Trustworthy Distributed Machine Learning in Cloud-Edge-IoT Systems: A Heterogeneity-Aware Survey of Security, Privacy, and Robustness
Distributed machine learning (DML), including conventional distributed training and federated learning (FL), enables collaborative model development across cloud-edge-IoT systems without fully…Routed Continual Learning
Agents deployed at scale repeatedly encounter related problems, and it is natural to let them learn from each other's experience rather than starting over each time.Pinpointing Pivot Points: The DECIDE Framework for Data Analysis Decision Importances
Human judgment calls made throughout the data science life cycle can change the conclusions drawn from data.Causal Attention on CPU: A Cache-Aware and Load-Balanced Scheduling Kernel for Prefill
Agentic AI drives significant productivity gains across diverse domains, but concurrent long-context prefills from multiple agents can saturate GPU compute resources.