Machine Learning News

A new arXiv study (2608.19644v1) finds that analog compute-in-memory (CIM) nonidealities disproportionately attenuate and rotate the classifier-free guidance (CFG) residual in Diffusion Transformers (DiTs), and proposes …

Researchers introduced MUST-PET, a multimodal self-supervised learning framework for whole-body PET-CT lesion segmentation, which uses context-aware masked reconstruction across FDG and PSMA tracers. In tests on multi-in…

Researchers propose Answer-Level Trust Selection (ATS), a post-hoc framework that accepts or rejects individual vision-language model (VLM) predictions for physical quantity estimation without fine-tuning or internal log…

Researchers propose MS-WDRO, a multi-source Wasserstein distributionally robust graph learning framework that fuses heterogeneous source-domain data via a weighted Wasserstein barycenter and an ambiguity ball, yielding a…

A new study from arXiv introduces DQeND, a reinforcement learning-based architecture for early classification of time series in non-stationary environments, which jointly learns representation, classification, and trigge…

A new study systematically evaluates TabPFN-TS, a zero-shot time-series foundation model trained on synthetic data, for probabilistic heat load forecasting in district heating networks, finding that an hourly 24-hour for…

A new study from arXiv (2608.20149v1) evaluates neural-based hillshading against analytical methods in downtown Calgary using high-resolution DEM and DSM data, finding that the machine-learning system Eduard, trained on …

A new arXiv paper (2608.20181v1) proposes a standardized framework for evaluating machine-learning-based power system protection, defining seven required study dimensions. In a case study on the PROTECT-90 benchmark with…

Researchers from an unnamed institution report that a contrastive decoder can extract open-vocabulary word-level information from non-invasive EEG during silent reading, achieving reliable above-chance word-grouped top-1…

A controlled comparison of ceiling-mounted FMCW, IR-UWB, and Wi-Fi radar for in-bedroom human activity monitoring found that IR-UWB achieved the highest cross-subject activity recognition performance (89.0% macro F1), wh…

Researchers introduced BERT-LER, a BERT-style model for coded electronic health records (EHRs) that encodes laboratory test results as discrete tokens via percentile-based binning and integrates Integrated Gradients for …

A new framework called VQC-ZTI, developed by researchers and described in an arXiv paper, uses a split-plane Variational Quantum Classifier to protect Tactile Internet services from cyber threats while preserving control…

SplatRAG 3, a retrieval system using local Gaussian-splat memory, achieved a SciFact (BEIR test, 300 claims, k=10) recall@10 of 0.8804 and nDCG@10 of 0.7624 on a store that also contains 5,000 Urban Dictionary rows, surp…

Moonshot AI detailed how it trained its Kimi K3 model, moving from architecture to a unified system through pretraining, SFT, reinforcement learning, and MOPD. The company trained the MoonViT-V2 vision encoder from scrat…

In the seventh part of a series on classic machine learning from an SRE perspective, an engineer explains that PCA can delete quiet but critical signals, such as a client health metric stuck at 2/10, because it prioritiz…

Australian start-up Cropify will commercially grade pulses such as lentils and chickpeas using artificial intelligence for the first time this harvest, a world-first that promises efficiency gains for the nation's $22bn …

Cosine similarity, the default metric in most RAG pipelines and vector databases, discards vector magnitude, which can carry critical semantic information such as confidence, specificity, or negation, leading to failures…

Waymo LLC, the autonomous driving unit of Alphabet Inc., revealed its custom 5nm application-specific integrated circuit (ASIC) and detailed its compute architecture, which has scaled 20x in eight years, in a blog post. …

Experiments on a Google Colab T4 with a 16 GB GPU show that SDXL's low-VRAM performance depends more on the granularity of runtime offloading than on the nominal memory budget, with finer-grained policies (group, leaf, s…

Researchers introduced HAWKEYE, an open-source framework that uses only 10 expert-written unit tests per GPU architecture to enable AI coding agents to generate hardware-aware kernels, approaching or surpassing expert-wr…