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

• 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…

• Exposure with response prevention in virtual reality for obsessive-compulsive disorder: A randomized controlled trial
  L. Rolvien, L. Jelinek, L. Lohse, S. Moritz et al. · MPG.PuRe (Max Planck Society) · Dec 31, 2026
• 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…

• Enhancement of Hydrodynamic Conditions forUltrafiltration Fouling Mitigation Using 3D PrintedElements
  Al-Tayawi Aws Nawfal Ahmed · SZTE Repository of Disserta... · Oct 23, 2026

  This Ph.D. study presents a sustainable strategy to enhance hydrodynamics and mitigate membrane fouling in ultrafiltration (UF) systems through the integration of 3D printed turbulence promoters (dead-end UF) and spacers (cross-flow vibrato…

• Teaching Tip: A Data Preparation and Enrichment Exercise for Location-Aware Analysis of University Innovation
  Andrés Díaz López, Saisrinivas Mamunuru, Joseph Cazier · Journal of the Association ... · Sep 15, 2026

  Prior research highlights the growing importance of location-based data for business decision-making, while also documenting its limited integration into information systems curricula. Although students are routinely exposed to data analyti…

• General Quantification of Covariate and Concept Shifts
  Hongbo Chen, Li Charlie Xia · arXiv · Sep 10, 2026

  Generalization under distribution shift remains a core challenge in modern machine learning, yet existing learning bound theory is limited to narrow, idealized settings and is non-estimable from samples. In this paper, we bridge the gap bet…

• Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated Data
  Atindra Jha, Margaret Li, Jure Leskovec, Percy Liang et al. · arXiv · Sep 10, 2026

  As the supply of human-written text is exhausted, it has become standard practice to repeat language model training data. Prior work has studied data repetition for densely activated Transformers, but the effects of data repetition remains …

• Generative Marketing Mix Modeling: A Causal Inference Framework Linking GEO and GEM to Business Impact
  Masahiro Kato, Daiki Honma, Taka Kato · arXiv · Sep 10, 2026

  Generative artificial intelligence changes how firms reach customers, but standard marketing data do not record how often users see and notice a firm's name in generated answers. We develop Generative Marketing Mix Modeling (GMMM) to estima…

• From Protocols to Evidence: Bounded Claims for AI in Service of the Common Good
  Nitesh V. Chawla, Paulo Benanti · arXiv · Sep 10, 2026

  Artificial Intelligence does more than create a governance problem. It can also reveal where institutions have already failed to provide responsiveness, belonging, care, and accountability. Once deployed, AI becomes an intervention in those…

• TART: A Modular Tool for Technique-Aware Audio-to-Tablature Guitar Transcription
  Akshaj Gupta, Hwi Joo Park, Andrea Guzman, Shamak Gowda et al. · arXiv · Sep 10, 2026

  Automatic Music Transcription (AMT) for guitar remains limited by three challenges: existing systems often fail to capture expressive techniques such as slides, bends, and percussive hits; they often assign notes to incorrect string-fret co…

• CausalArena: Benchmarking Causal Discovery in the Foundation Model Era
  Zi-Rong Li, Si-Yang Liu, Tian-Zuo Wang, Han-Jia Ye · arXiv · Sep 10, 2026

  Causal discovery aims to uncover causal structures from data and is fundamental to scientific reasoning and intervention-based decision making. Its evaluation relies heavily on structural causal models (SCMs), which specify a causal graph t…

• 3D Point Splatting for mmWave Radar Novel View Synthesis
  Adnan Armouti, Yixuan Gao, Rajalakshmi Nandakumar · arXiv · Sep 10, 2026

  Solving novel view synthesis (NVS) for millimeter-wave (mmWave) radar requires a renderer that is physically faithful, complex-valued, and multi-viewpoint-tractable. No prior method achieves these three properties simultaneously. Differenti…

• CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search
  Yifan Yang, Zhaoyan Wang, Zheng Gao, Xiaoyu Li et al. · arXiv · Sep 10, 2026

  Zero-cost proxies rank architectures cheaply, but their reliability varies across search spaces. We introduce CoRA-NAS (COarse Ranking + Anchor-residual), a two-stage framework combining a static ranking prior with low-cost learning-curve r…

• Domain-Specific Hallucination Detection in Large Language Models
  Varun Teja Chundru, Debasmita Biswas · arXiv · Sep 10, 2026

  Large language models generate fluent text that can contain unfaithful claims -- a phenomenon known as hallucination. We present a multi-signal detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo (MC) Dropout unce…

• The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
  Yi Duan, Ying Liu, Zirui Tang, Haodong Chen et al. · arXiv · Sep 10, 2026

  Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement. We first use the Headroom-Closed Index (HCI) to reveal t…

• Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting
  Bowen Zhang, Hsiu-Wen Cheng, Hongyu Yang, Evie L. Shen et al. · arXiv · Sep 10, 2026

  Continuous glucose monitoring (CGM) provides high-frequency measurements of glucose dynamics and enables short-term glucose forecasting for diabetes management. Although time-series foundation models have shown strong general forecasting ab…

• AdamX: Cosine similarity meets gradient descent
  Francisco Caldas, Ruben Belo, Cláudia Soares · arXiv · Sep 10, 2026

  We introduce AdamX, a first-order optimizer that incorporates cosine similarity as an adaptive mechanism for controlling update magnitudes. The proposed method is scalable, model-agnostic, and straightforward to integrate into existing trai…

• Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption Models
  Rodion Krjutškov, Eduard Barbu, Nikos Sakkas, Sofia Yfanti · arXiv · Sep 10, 2026

  Energy consumption forecasting relies on increasingly complex machine learning (ML) models, such as Genetic Programming-based symbolic regressors, whose predictions can be difficult for facility managers and building operators to interpret.…

• Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport
  Luyi Jia, Boyan Zhang, Yilun Liu, Steffen Rulands · arXiv · Sep 10, 2026

  Diffusion and flow-matching schedules control the signal and noise coefficients that mix data and noise along affine probability paths. Minimizing a kinetic action defined on coefficient paths, motivated by optimal transport, helps explain …

• Near-Optimal Reinforcement Learning with Multi-Step Transition Lookahead
  Corentin Pla, Hugo Richard, Marc Abeille, Vianney Perchet · arXiv · Sep 10, 2026

  We study reinforcement learning (RL) with transition look-ahead, where the agent may observe which states would be visited upon playing any sequence of $\ell$ actions before deciding its course of action. Although look-ahead can substantial…

• Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling
  Meimingwei Li, Stefan Andreas Baumann, Felix Krause, Björn Ommer · arXiv · Sep 10, 2026

  Visual Autoregressive Models (VAR) generate images through next-scale prediction, producing all tokens within each scale in parallel. We show that this parallel decoding constitutes a mean-field-style approximation that discards spatial dep…

• Thinking with Looped Flows
  Ayhan Suleymanzade, Chanhyuk Lee, Floor Eijkelboom, Nicholas M. Boffi et al. · arXiv · Sep 10, 2026

  Humans and machines often solve harder problems by spending more time on computation. In deep learning, looped models implement this idea during inference by recurrently updating a hidden state. In practice, however, their training backprop…

• Dynamic language model representations for multi-objective reaction optimisation
  Joshua W. Sin, David Ming Segura, Bojana Ranković, Siu Lun Chau et al. · arXiv · Sep 10, 2026

  Optimising chemical reactions across multiple objectives, such as yield, selectivity, and safety, is central to chemical synthesis, and model-driven approaches depend critically on how reaction components are represented. Established featur…

• Predicting Privacy Leakage from Weight Spectral Density
  Richard J. Preen, Jim Smith · arXiv · Sep 10, 2026

  Membership inference attacks (MIAs) are widely used to audit the privacy disclosure risk of machine learning models, however current state-of-the-art attacks require training computationally expensive shadow models, making large-scale priva…

• Differentially Private EEG Feature Anonymization: A Privacy-Utility Case Study in Clinical Neurophysiology
  Noman Sadiq, Mohsen Toorani · arXiv · Sep 10, 2026

  Clinical electroencephalography (EEG) data are valuable for healthcare research and for developing artificial intelligence (AI)-based clinical decision-support systems, but EEG recordings and derived features may contain sensitive patient-s…

• A Unified Per-Token Gating Family for On-Policy Distillation: FKL/RKL Mixing with Multi-Channel and Bias Coefficients
  Suwan Wu, Yumeng Lin, Pengcheng Yuan, Xiaolong Jiang · arXiv · Sep 10, 2026

  Per-token gating of forward/reverse KL losses has become a standard technique for on-policy knowledge distillation (OPD), but existing methods such as EOPD (Jin et al., 2026) and ToDi (Jung et al., 2025) each fix a single gating signal and …

• Biocompatible Microscale DNA Hydrogels with Programmable Swelling and Sequence-Specific Dissolution
  Corinna Torabi, Takayuki Suzuki, Emily Helm, Harrison Khoo et al. · ACS Applied Bio Materials · Sep 10, 2026

  Stimulus-responsive DNA hydrogels with swelling capabilities are a promising class of materials for biomedical applications such as drug delivery and biosensing. However, translation of these systems to microscale applications requires fabr…

• Fermentation Quality Divergence of Alfalfa Silage within the Same Batch: Insights from 16S rRNA Sequencing and Untargeted Metabolomics
  Jialu Li, Lichao He, Yiwei Liu, Gentu Ge et al. · ACS Omega · Sep 10, 2026

  Abstract Alfalfa silage produced from the same batch of raw material frequently exhibits divergent fermentation quality, yet the microbial and metabolic basis of this divergence remains poorly understood. This study aimed to characterize th…

• The land belongs to men: hegemonic masculinity and women's exclusion in Gayo coffee farming communities, Aceh, Indonesia
  Vellayati Hajad, Sarini Vita Dewi, Irma Permata Sari, Ikhsan Ikhsan et al. · Social Sciences & Humanitie... · Sep 10, 2026

  This study examines how hegemonic masculinity is constructed and reproduced through land ownership and patriarchal discourses, shaping women's exclusion from land ownership and agricultural decision-making in Gayo coffee farming communities…

• Likelihood-free inference with nuisance parameters through normalizing flows
  Phil Assheton · arXiv · Sep 9, 2026

  We present a simple decomposition of a neural-network-based normalizing flow that naturally uncovers a pivotal statistic (or something close) in the presence of nuisance parameters, based only on a sample generator from the distribution of …