Latest Machine Learning Research Papers

The newest Machine Learning papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Machine Learning so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• Nitric oxide in the occurrence and development of ischemic cerebrovascular disease.
  Tatiana Kh. Bogodvid, Dinara I. Silantyeva, Андрианов Вячеслав Вадимович, Гайнутдинов Халил Латыпович · PubMed Central · Jan 1, 2027

  Since nitric oxide is a chemically highly reactive free radical that can act as both an oxidizing agent and a reducing agent, it is assumed that it has diverse effects on biological tissues. Nitric oxide is fundamentally important for the r…

• Oxygen, carbon dioxide, and nitric oxide: role in the pathophysiology of obstructive sleep apnea.
  Antonio Fabozzi, Pasquale Tondo, Caterina Antonaglia, Alessia Steffanina et al. · PubMed Central · Jan 1, 2027

  Obstructive sleep apnea is a prevalent sleep-related breathing disorder with recurrent episodes of upper airway collapse during sleep, leading to cyclic blood gas fluctuations. Oxygen, carbon dioxide, and nitric oxide play a crucial role in…

• High levels of nitric oxide and peroxynitrite with protein nitration: a new therapeutic target for gliomas.
  Ying Yang, Qi Zhang, Yuchen Ma, Serge Yannick Ouédraogo et al. · PubMed Central · Jan 1, 2027

  The gap junction signaling pathway is a core hub mediating intercellular communication, which plays a vital role in maintaining tissue homeostasis, and its dysfunction is closely related to glioma. Nitroproteomics studies have shown that pr…

• Ambient particulate matter pollution and stroke burden.
  Lu Jiang, Kuangyang Yu, Long Gu, Wenfeng Xiao et al. · PubMed Central · Jan 1, 2027

  As a major component of air pollution, ambient particulate matter pollution has rarely been studied with respect to its global stroke burden. This study aims to evaluate the global stroke incidence, mortality, and health inequalities relate…

• LGAN: An Efficient High-Order Graph Neural Network via the Line Graph Aggregation
  Lin Du, Lu Bai, Jincheng Li, Lixin Cui et al. · AAAI 2026 · Dec 31, 2026

  Graph Neural Networks (GNNs) have emerged as a dominant paradigm for graph classification. Specifically, most existing GNNs mainly rely on the message passing strategy between neighbor nodes, where the expressivity is limited by the 1-dimen…

• Assessment and characterization of back pain and biopsychosocial influences in lower limb amputation: scoping review.
  Kevin Arribart, Maximilian O'Malley, Gerson Cipriano, Marlon L. Wong et al. · PubMed Central · Dec 1, 2026

  Back pain affects over half of individuals with lower limb amputation, yet research findings on associated factors remain fragmented. In view of the evolution of pain science in the general population, this fragmentation likely stems from s…

• Glycated hemoglobin and retinal microvascular changes in type 2 diabetic retinopathy patients treated with metformin and/or insulin: A retrospective study.
  Zhongshu Han, Ping Zhu · PubMed · Dec 1, 2026

  BACKGROUND: Diabetes retinopathy (DR) is the main blinding complication of type 2 diabetes (T2DM). Glycated hemoglobin (HbA1c) can reflect long-term blood glucose control and optical coherence tomography (OCT) can evaluate retinal microvess…

• TO STUDY THE RESPONSE RATE OF HYPO-FRACTIONATED BLADDER PRESERVATION RADIOTHERAPY IN MUSCLE INVASIVE BLADDER CANCER
  DR. SHEIKH TAHIR SIDDIQUE , DR. ZEESHAN BADAR , DR. MUHAMMAD UMAIR , DR SANA NAEEM , DR. SAMINA SIDDIQUE , DR RAB NAWAZ MAKEN (SUPERVISOR) · TPM Testing, psychometrics,... · Nov 5, 2026

  Objective: To determine the response rate of hypofractionated bladder-preservation radiotherapy in patients with muscle-invasive bladder cancer according to RECIST criteria. Study Design: Descriptive case series. Place and Duration of Study…

• GLP-1 Receptor Agonist and GIP/GLP-1 Receptor Dual Agonist Therapeutics at the Intersection of Alcohol Use Disorder, Obesity, and Cardiometabolic Dysfunction.
  Joshua Reitz, Daniel B. Rosoff, Pál Pacher, Falk W. Lohoff · PubMed · Nov 1, 2026
• Phenotyping Antibody-mediated Rejection Without Detectable Donor-specific Antibodies 8 d After Heart Transplantation: A Case Study.
  Sarah Flint, Aiwen Zhang, Gabriel Kim, Amanda R. Vest et al. · PubMed Central · Nov 1, 2026
• SHAHAR YO'L TARMOQLARI VA AVTOMOBIL TRAFIK TIRBANDLIGI: SABABLARI, BAHOLASH USULI VA INTEGRATSIYALANGAN YENGILLASHTIRISH STRATEGIYALARI
  Davlatov Ikrom Shavxidinovich, Tog'aymurodov Zavqiddin Zayniyevich · InnoRes · Oct 31, 2026

  Rapid urbanization, increasing motorization, and spatial concentration ofemployment and services are putting increasing pressure on urban road networks. Trafficcongestion is not only a transportation problem, but also a multidimensional urb…

• The Relationship Between Axial Length and Age in Patients with Congenital Cataract
  AYUB ZEN, Indri Wahyuni, Risa Etika, Rozalina Loebis · Healthy Tadulako Journal (J... · Oct 31, 2026

  Background: Congenital cataract can impair visual development, while axial length is an important parameter in pediatric ocular assessment. Objectives: This study examined the relationship between axial length and age among patients diagnos…

• THE INFLUENCE OF FINANCIAL TECHNOLOGY, RISK TOLERANCE, FINANCIAL SELF-EFFICACY, COGNITIVE DISSONANCE BIAS, AND LOSS AVERSION ON INVESTMENT DECISIONS
  Muhammad Ramadhan Pamungkas, Fathi Rifqi Mu’afa, Yordan Ifraim Risyafa, Dicky Rizkyadi · Dinamika · Oct 30, 2026

  Investment decisions are shaped by various investor considerations, including financial technology, risk tolerance, financial self-efficacy, cognitive dissonance bias, and loss aversion. Because the findings of previous studies have been in…

• Propose-Filter-Release: Scaling Noise to Typical Sensitivity via Private Filtering
  Moshe Shenfeld, Eliad Tsfadia, Katrina Ligett · arXiv · Oct 29, 2026

  An estimator can be accurate and stable on typical data, yet sensitive to a few possible records. Differentially private mechanisms commonly scale their noise to the worst-case influence of a single record, which lets these records dictate …

• Rethinking Neural Thickets Without Weight Perturbations
  Nicolas Dufour, Elouan Gardès, Amil Dravid, Patrick Pérez et al. · arXiv · Oct 29, 2026

  The Neural Thickets hypothesis posits that pretrained language models lie in dense neighborhoods of task-specific experts in weight space, which random Gaussian perturbations can uncover. We reproduce the reported gains, but show that they …

• Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers
  Jiongfan Yang, Weichen Fan, Haiwen Diao, Zhongang Cai et al. · arXiv · Oct 29, 2026

  Pixel-space generative Transformers typically use one token per image patch, so capturing finer detail requires more tokens and makes global attention increasingly expensive. We observe that finer detail does not necessarily require more gl…

• Adaptive Scenario Generation for KL-DRO Around a Learned Density Model
  Aron Brenner, Saurabh Amin · arXiv · Oct 29, 2026

  Distributionally robust optimization (DRO) hedges data-driven two-stage stochastic programs against error in the distribution estimated from a finite record, and standard ambiguity sets differ in how they treat realizations absent from that…

• world2vec: Mechanistic world models through latent dynamics learning
  Tobias Schmidt, Rodrigo Gonzalez Laiz, Krisztián Szuppinger, Steffen Schneider · arXiv · Oct 29, 2026

  World models can achieve strong control performance without faithfully capturing the dynamics of their environment, limiting their potential for mechanistic interpretability and scientific discovery. Here, we introduce world2vec to learn me…

• An ODE-based Sampler for Discrete Diffusion Models
  Samson Gourevitch, Yazid Janati, Eric Moulines, Eric P. Xing et al. · arXiv · Oct 29, 2026

  The marginals of a continuous diffusion model can be reproduced by a deterministic ordinary differential equation (ODE), known as the probability flow ODE, which provides a foundation for accelerated sampling and consistency distillation. I…

• Difficulty Calibration Across Time for Membership Inference in Diffusion Models
  Michael Joseph, Yedid Hoshen · arXiv · Oct 29, 2026

  Modern diffusion models are trained on massive datasets that often include copyrighted or private images. Membership inference attacks (MIAs) address this by testing whether a given image was in a model's training set. The standard approach…

• Multistatic ISAC with Deep Learning-Based Clutter Suppression for 5G and Beyond
  Yalin E. Sagduyu, Tugba Erpek, Sastry Kompella · arXiv · Oct 29, 2026

  Integrated sensing and communications (ISAC) systems using 5G and beyond signals of opportunity enable joint wireless sensing and communication using shared infrastructure and spectrum resources. While multistatic ISAC can increase sensing …

• Gym-Anything for Robotics: Scaling physical simulations with digital agents
  Pranjal Aggarwal, Sean Welleck · arXiv · Oct 29, 2026

  Realistic, fast robotics simulations could enable large-scale training of embodied AI models that transfer to the real world. However, despite decades of progress, available simulations cover only a narrow range of real-world tasks and phys…

• Training Foundation Models with a Single Algorithm
  Yuda Song, Alvin Zhang, Fahim Tajwar, Daman Arora et al. · arXiv · Oct 29, 2026

  Foundation models are typically trained in stages: pretraining, midtraining, supervised fine-tuning (SFT), and reinforcement learning (RL), with changes in both data and learning algorithms. We show that this algorithmic separation is not f…

• Machine Learning-Based Detection of Mobile Money Scan Messages in Ghana: A Comparative Evaluation of Naive Bayes, Support Vector Machine, and Randon Forest Classifiers
  Ibrahim Salifu, Muhaisin Tiyumba Nantogmah · arXiv · Oct 29, 2026

  Mobile money (MoMo) is Ghana's preferred retail payment channel, recording GHC518.4 billion in transactions in December 2025 and over 26.7 million active accounts (Graphic Online, 2026). This growth has coincided with increased social-engin…

• TRACER, a time-to-event EHR foundation model for disease detection across health systems
  Mara Pleasure, Ekaterina Redekop, Vedrana Ivezic, Rushikesh Kulkarni et al. · arXiv · Oct 29, 2026

  Foundation models trained on longitudinal electronic health records (EHRs) can predict clinical diagnoses years in the future, making them a potential tool for disease screening. We developed TRACER (Temporal Risk Assessment with Clinical E…

• Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for Portuguese
  Pedro Carvalho Brom · arXiv · Oct 29, 2026

  Building a language model of one's own no longer requires a data centre. This tutorial trains one from scratch, tokenizer included, on one consumer GPU, and shows how to tell whether it is good for the tasks of a specialist domain. It propo…

• NEOPIC: A Neural Operator Framework for Particle-based Kinetic Plasma Simulations
  Sriramkrishnan Muralikrishnan, Chelsea Maria John, Jeffrey Kelling, Michael Bussmann et al. · arXiv · Oct 29, 2026

  We introduce NEOPIC, a framework for learning the field operator in particle-based methods applied to kinetic plasma simulations. Its key novelty is a neural operator that acts directly on the empirical measure of the particles, rather than…

• How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates
  Max Neuwinger, Hanna Yukhymenko, Imanol Schlag · arXiv · Oct 29, 2026

  Safety alignment for Large Language Models is heavily focused on English with limited multilingual representation, particularly damaging low-resource language performance. Related open training datasets are often limited in size or do not f…

• Discovering Interpretable Acoustic Features in Autoregressive Voice-Cloning TTS Models
  Anuj Diwan, David Harwath, Eunsol Choi · arXiv · Oct 29, 2026

  Voice-cloning TTS models synthesize an unseen speaker's voice from brief speech prompts, but it remains unclear which acoustic properties they represent and use. We introduce a feature-based interpretability framework for autoregressive voi…

• Numerical Integration on Bounded Domains via Learned Reflected Diffusions
  Kirill Korolev, Artur Goldman, Timofei Gritsaev, Tigran Ramazyan et al. · arXiv · Oct 29, 2026

  We study high-dimensional integration on bounded convex domains. Given a non-negative integrand $r$, the goal is to estimate $Z=\int_{D}r(x)\,\mathrm dx$ on $D\subset\mathbb R^d$. Standard Quasi-Monte Carlo does not adapt its evaluation poi…