Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers proposed FLoKD, an adaptive knowledge-distillation framework for federated LoRA fine-tuning of large language models over wireless networks that transmits intermediate LoRA activations instead of logits or fu…
A new paper on arXiv (2609.13648v1) introduces Solar Intelligence, a hybrid retrieval-augmented framework that unifies structured solar analytics, evidence-grounded scientific question answering, and machine learning for…
The FedV-KGQA poster paper reports that federated fusion across vertically partitioned knowledge graphs recovers most of the accuracy of a centralized system, while a single silo recovers little. The work, presented as a…
Researchers proposed a Position Encoding-Based Deformable Spatial Aggregation Module (PEBDSAM) that addresses over-smoothing, over-compression, fixed receptive fields, and topological noise in graph neural networks, acco…
Researchers introduced JaxAHT, described as the first open-source, JAX-based library for the Ad Hoc Teamwork research lifecycle, achieving approximately 95x wall-clock speedup over PyTorch counterparts. JaxAHT provides a…
A physiology-guided hybrid framework combining a convolutional neural network branch with a morphology-prior branch estimated blood pressure from photoplethysmography (PPG) with mean absolute errors of 3.77 mmHg for syst…
Researchers introduced Counterfactual Search for Grounding Regions (CSGR), a scalable pipeline that labels answer-critical image regions in visual question answering (VQA) data by perturbing candidate regions and measuri…
A three-stage pipeline built from Stable Diffusion 1.5 components generated synthetic leprosy lesion images whose internal perceptual diversity (0.662) was statistically indistinguishable from that of the real leprosy se…
Researchers introduced Abstract-LoRA, a single-image style transfer method that trains lightweight LoRA adapters on specific U-Net blocks in diffusion models, according to an arXiv paper (arXiv:2609.13239v1). Building on…
Researchers Alpay Ozkan and colleagues introduced a pixel-wise planarity prediction framework for monocular plane segmentation from a single RGB image, published as arXiv:2609.13246v1. The method adds a dedicated planari…
A new arXiv survey (arXiv:2609.13255v1) reviews multimodal facial state analysis, covering core tasks, representative methods, and datasets for facial expression recognition, action unit (AU) detection, and face-based so…
Researchers introduced TryOnReward, a fine-grained reward model for virtual try-on (VTON) built on a vision-language backbone that uses a foveation calibration objective and jointly optimizes pairwise preferences and per…
Researchers introduced Fraglingo, an autoregressive fragment-based molecular generator that jointly models fragment identity and attachment in a continuous latent space, according to an arXiv paper (arXiv:2609.13519v1). …
A study posted to arXiv (2609.13566v1) empirically compared planning and reinforcement learning for multi-asset bearing maintenance using run-to-failure data, finding that planning enforces reliability as a hard constrai…
A new arXiv paper (arXiv:2609.13805v1) proposes an LLM-enhanced multi-agent reinforcement learning framework that simultaneously optimizes the grid, electric vehicles, and charging stations within a unified loop for publ…
A reinforcement learning system called ViperQ, built on Auction Market Theory primitives, achieved +163.6% ROI on TSLA with a -27.5% max drawdown across 27,019 trades and +116.5% ROI on NVDA with a -47.8% max drawdown ac…
A new arXiv paper (arXiv:2609.13879v1) proposes a five-part attribution table for specifying how acquired representations enlarge a system's cognitive repertoire without transferring the capacities used to produce them. …
Researchers introduced UniCAR-RL, an annotation-free reinforcement learning framework that decouples perception and reasoning optimization in Multimodal Large Language Models (MLLMs) to improve complex mathematical visua…
Programmer Michał Żarnecki published the first part of a three-part series on time series analysis and forecasting, covering fundamentals, use cases, and a Parkinson's disease case study detecting Freezing of Gait episod…
Researchers submitted a paper to arXiv on 14 Sep 2026 introducing Discrete Beckmann Transport Models (DBTM), a time-independent flow whose autonomous transport map provably carries any point in the ambient space to a fix…