Researchers propose Disease Continuum Positioning (DCP), a longitudinal Bayesian Learning framework that estimates Alzheimer's disease severity continuously from diffusion tensor imaging, outperformin…
A new arXiv preprint (2608.19497v1) characterizes the learning dynamics of a compact hybrid quantum forecasting model against a classical baseline, finding that both achieve similar held-out performan…
Researchers propose 4MAS (4 Module Awake/Sleep), a novel macroarchitecture that models asymmetric brain hemispheres with separate long- and short-term memory mechanisms and a sleep phase between tasks…
Researchers introduced DeltaML-Bench, a benchmark of 48 tasks from research papers that tests AI agents' ability to improve published baselines in real-world repositories. In evaluations, the ARG scaf…
Researchers introduced RecPFN, a prior-fitted network that brings in-context learning to sequential recommendation, achieving state-of-the-art zero-shot performance across eight public benchmarks. Rec…
FleetSieve, a new profiling method for LLM serving fleets, reaches the oracle aggregate decision using 22,200 GPU-seconds, 6.9% less than uniform random profiling on a fixed H100 grid for a 31B-parame…
Researchers propose SAGE-XGBoost, a machine learning framework combining noise-based data augmentation with graph embeddings, achieving AUC values of approximately 0.97 for landslide and 0.95 for wild…
Researchers propose TUP (Truncate-bad, Upweight-good Policy), a distillation method that removes low-ranked completions from the support and reweights only the retained upper tail with tunable sharpne…
A new arXiv study (2608.19760v1) auditing step-level credit assignment in LLM agents against causal ground truth from executed replay in ALFWorld found that none of the credit signals used to train LL…
Researchers at an undisclosed institution introduced Reliable Neural Collapse approximation (ReNC), a method for Open-World Test-Time Adaptation (OWTTA) that uses neural collapse as a structural prior…
A new arXiv preprint (2608.19801v1) finds that the choice of anomaly scoring function is critical for flow-matching-based unsupervised anomaly detection on tabular financial data, with trajectory-base…
Researchers propose MileGPO, a method for credit assignment in long-horizon agentic reinforcement learning that derives process-level credit from grouped on-policy rollouts via Milestone Discovery, Re…
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-tu…
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 ambigu…
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, classi…
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 a…
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…
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 PROTE…
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-chanc…
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 …