Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
A new graph-based framework from arXiv research (2607.11894v1) detects disinformation narratives in Telegram ecosystems by combining weak supervision with propagation graph analysis, enabling identification of coordinate…
A new architecture called Cost-Governed RAG, integrating a codebook-oblivious vector index (TurboVec) with a multi-tenant LLM governance gateway, achieves 99.96% end-to-end cost attribution accuracy across 100 simulated …
Researchers propose SpikeDS, a spiking neural network that uses dual sparsity to predict perineural invasion from 3D MRI in cholangiocarcinoma patients. In a clinical cohort of 139 patients, SpikeDS achieves an AUC of 0.…
Researchers introduced a multi-feature fusion framework for non-invasive semantic reconstruction from brain recordings, achieving state-of-the-art performance by combining static lexical representations (W2V) with dynami…
A new paper on arXiv (2607.11937v1) introduces viable path entropy (VPE), a finite-budget measure of verified continuation capacity for intelligent systems under repeated reflection. In language-model reasoning experimen…
Researchers have developed a self-evolving in-context learning (ICL) framework for pilot-to-beamformer design in multi-user multiple-input single-output (MU-MISO) systems that outperforms existing methods including the W…
A new calibration-first reward audit framework for reinforcement learning control in smart greenhouses, proposed in arXiv:2607.11959v1, decomposes scalar rewards into conditional temperature, CO2, humidity, vapor-pressur…
Researchers propose GenDiff, a diffusion-based framework for low-dose CT reconstruction that jointly models continuous radiation dose and anatomical information, outperforming state-of-the-art methods across multiple cli…
A new arXiv preprint (2607.11958v1) from researchers studying the free energy principle demonstrates that a predictive system's default behavior can decouple from its representational accuracy, a phenomenon called ontolo…
A study on arXiv (2607.11967v1) found that donor-specific functional fingerprints remain detectable in neural networks after Neural Collapse, with all 20 ordered donor-recipient pairs correctly identified (p=0.0083) usin…
A systematic review of 19 machine learning studies on early Chronic Kidney Disease (CKD) prediction found that high data leakage inflates reported accuracy to an average of 95.48%, compared to 80.2% for leakage-free stud…
A new anatomy-privileged teacher-student framework for predicting perineural invasion from T2-weighted MRI achieved the highest mean AUROC of 0.750 among matched MRI-only baselines in a study of 155 patients, according t…
A new framework for designing agent-ready websites improved AI web agent success rates from 49.3% to 89.3% in a controlled experiment, according to a preprint on arXiv. The study, involving 300 runs across three browser-…
OmniPM-Net, a Convolutional Conditional Neural Process-based fusion model, reconciles discrete station forecasts with gridded fields for PM10 forecasting, matching the accuracy of graph neural networks (mean absolute err…
Researchers propose CARE-LoRA, a compressed activation reconstruction framework that reduces memory usage during LoRA fine-tuning of large pre-trained models by replacing full input activations with low-rank compressed a…
Researchers propose BattVAE-GP, a hybrid physics-probabilistic learning framework that uses a Variational Autoencoder and sparse multitask Gaussian process to model long-horizon lithium-ion battery degradation trajectori…
Researchers propose SymbOmni, an agentic omni-model that uses Symbolic Concept Learning to overcome the 'perpetual novice' problem in visual generation, enabling cumulative evolution and autonomous self-improvement. The …
Researchers propose Self-Consistent Flow (SC-Flow), a new method that unifies velocity and endpoint prediction in rectified-flow generative models, achieving improved generation quality and training stability. The method…
A new survey from arXiv examines in-context reinforcement learning (ICRL) under non-stationarity, defining the problem as adapting through context while deployed policy parameters remain fixed. The authors organize the l…
A zero-setup framework for multi-phase segmentation of synchrotron X-ray tomography data generates interpretable masks for unseen datasets without user input or retraining, combining a material-agnostic mask preparation …