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 106
Learning Force-Reactive Humanoid Loco-Manipulation
Many everyday tasks require controlling contact force as well as motion.Auto-Research Arena: Benchmarking and Advancing Auto-Research in Language Modeling
As autonomous research systems become more capable, benchmarks must both evaluate their performance and support meaningful research progress.Multiple Leak Localization in Water Distribution Networks through Graph Neural Networks
Leak localization in water distribution networks is challenging when multiple leaks occur simultaneously, particularly under sparse monitoring.A Graph-informed Kriging model for sample-efficient Bayesian optimization of wind farm layouts
Wind farm layout optimization becomes increasingly difficult as turbine count grows, especially when high-fidelity aerodynamic models are used.UnityBench-Mini3D: Evaluating LLM Agents for 3D Game Development in Unity
Game development stresses coding agents in ways general software engineering does not: correctness depends on how engine APIs, serialized scene state, and runtime behavior interact, not on source…Let the Gate Decide: Per-Lookup Precision for Quantized Conditional Memory in LLMs
Conditional memory layers, such as DeepSeek's Engram, attach large hashed n-gram tables to a language model, and removing them from DeepSeek-V4.1-Flash costs 36.8 PopQA points.PROBE: Frontier Coding Agents Find Different Bugs Than Maintainers Fix
Proactive bug discovery is an important software-engineering problem.Layerwise Repacking: Variable-Length Hybrid-Attention Training without an Extra Redistribution Pass
Variable-length training creates conflicting parallelism requirements across the layers of a hybrid-attention model.MedJev: Evaluating Zero-Shot System-One Decision Making in Medicine
System One decision models such as Jev answer structured questions in a single forward pass without generating text, offering fast and computationally efficient clinical decision support.DuplexTune: Coupled-State Replay for Memory-Efficient Mixture-of-Experts Adaptation
Sparse expert execution does not remove the stored states needed to adapt a mixture-of-experts language model.Anchored Stein Variational Gradient Descent Algorithm for Non-smooth Sampling
We introduce a Stein variational framework for sampling from a target density $p\propto e^{-U}$ when the target potential $U$ is possibly non-smooth.Causal DAG-Guided Reinforcement Learning for Long-Term Physical Activity Maintenance: Using Prior Data to Inform Future Deployment
Digital health interventions can provide scalable, personalized support for physical activity (PA), yet sustaining PA over the long-term remains difficult.Exploratory creative pre-ranking: Hierarchical empirical-Bayes Thompson sampling for real-time creative optimization
Dynamic creative optimization decides which creative of an ad to render for each request.The proton structure one mode at a time: a Neural Tangent Kernel analysis of a DIS fit
We study the training dynamics of a feed-forward neural network (NN) through the analysis of the neural tangent kernel (NTK) in a phenomenologically relevant fit of parton distribution functions…Rollback: Experience Backtracking in World Models for Policy Improvement
Action-conditioned world models offer a scalable alternative to costly real-world interaction for improving robot policies.Jaxnasium: Embracing PyTrees For Any-Agent, Cross-Suite Reinforcement Learning
Hardware-accelerated reinforcement learning in JAX has gained rapid popularity in recent years and has proven to be a successful method of scaling online reinforcement learning.Learning on-the-fly quasi-stationarity diagnostics from low-dimensional surrogates
Accelerated dynamics methods, such as parallel replica dynamics, require estimates of the decorrelation time, after which a process trapped in one of its metastable states is distributed according…Closed-Loop Aware Planning via Imitation-Free Speed Scoring for End-to-End Autonomous Driving
End-to-end autonomous driving has predominantly relied on open-loop imitation learning for training, which presents two limitations.How Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning
Financial institutions operating under data-residency constraints are restricted to open-weight models small enough to locally host, which trail frontier systems on multi-step quantitative reasoning.FinLLM-KG: Knowledge Graph-Enhanced LLMs for Financial Sentiment Analysis in Algorithmic Trading
Recent advances in Generative AI have substantially improved financial sentiment analysis through post-trained financial large language models (LLMs).