Machine Learning News

A new arXiv paper (2609.10830v1) reports that language models' apparent memory of training data is largely confounded, using exact duplication counts from the published pretraining corpora of OLMo-2 and Pythia. Across fi…

Researchers introduced a completeness estimation approach for multimodal sentiment analysis that quantifies how much sentiment-relevant information survives in incomplete data and uses that estimate to guide reconstructi…

Researchers introduced CityPlanner, a sandbox-agent framework for executable urban planning, detailed in arXiv paper 2609.09578v1. CityPlanner uses UrbanSandbox, a unified file-based environment where agents inspect task…

A new arXiv paper (2609.09448v1) introduces two methods, Latent Trajectory Dynamics (LTD) and the Action Representation Probe (ARP), that use a model's internal representations to predict task success in multi-turn agent…

A paper posted to arXiv (2609.09306v1) introduces "Gradland," an idealized world of neural networks whose physics are known and functions mostly differentiable, to test whether the first-order structure of physical inter…

A new arXiv paper (2609.09589v1) develops a statistical-mechanical description of deep neural network learning directly in function space, treating parameter configurations as microscopic realizations and functions with …

A new arXiv paper (2609.09627v1) identifies seven non-exclusive sources of Physical AI capability formation: Recorded-Experience, Predictive-Modeling, Evaluative-Interaction, Surrogate-Environment, Mechanism-Grounded, Em…

A paper posted to arXiv (2609.10589v1) introduces Halo, a modification that reuses an existing deep forecaster's architecture to add a second output estimating the scale of its implied distribution and trains it under th…

A new arXiv paper (arXiv:2609.10776v1) presents preliminary work showing that a Bellman optimality equation exists for optimizing plasticity within Markov decision processes, building on Abel et al. (2025), which defined…

A systematic literature mapping published on arXiv reviewed 96 articles from 2015 onward on AI and deep learning for lung cancer detection in radiology, finding convolutional neural networks with transfer learning and da…

Researchers introduced GeoSteer, an optimization-based method for norm-preserving activation steering in large language models that formulates steering as a Riemannian optimization problem and updates activations through…

Researchers proposed the Adaptive Margin Ordinal Loss (AMOL), a multiplicative per-class weighting scheme that suppresses "center-class hedging" in ordinal classification, according to an arXiv paper (arXiv:2609.10752v1)…

Researchers designed and implemented DR-LabStack, a React-Flask web system that integrates four externally developed pretrained diabetic retinopathy prediction models: RuleFit, Pruned RuleFit, Elaborative XGBoost, and Tw…

Researchers proposed counterfactual (CF) marginalisation, a test-time evaluation procedure for assessing how robust classification models are to nuisance variables such as age or sex, according to a paper published as ar…

Researchers introduced Graph-Guided Quasimetric Dense Reward (G2QDR), a framework that predicts pairwise state connectivity strength in asymmetric environments and converts those strengths into scalar auxiliary dense rew…

A new arXiv paper (arXiv:2609.10866v1) extends certification methods for reinforcement learning to risk-sensitive objectives, establishing lower bounds on the exponential utility of cumulative rewards under l_p-norm-boun…

Researchers introduced TrajFusionNet+, a transformer-based model that predicts pedestrian crossing intention for autonomous vehicles by fusing sequential trajectory data, visual bounding-box overlays, and pedestrian-cent…

A new arXiv paper (2609.10863v1) identifies a duality between continuous and discrete flow matching, showing that projecting continuous convex-interpolant paths with one-hot targets through a position-wise argmax yields …

Researchers introduced MHE-Former, a Transformer-based multi-hypothesis framework that uses entropy maximization to generate diverse 3D hand and body mesh recovery predictions from monocular input, according to a paper p…

A few-shot regression framework combining Vision Transformer (ViT) feature embeddings, fuzzy c-means clustering-based task construction, and gradient-based meta-learning enables reliable plant growth estimation under sev…