arXiv:2608.20638v1 Announce Type: cross Abstract: The edge-of-stability (EoS) phenomenon of Adam has been widely observed, while its underlying dynamical…
Author: script
One Hierarchy, Two Systems: Semantic Product IDs for Discovery-Surface Ranking and Search-Page Query Reformulation
arXiv:2608.20640v1 Announce Type: cross Abstract: Multi-merchant e-commerce catalogs contain equivalent and related products under different…
Amplifying the imaging power of digital sky surveys with space telescopes data and generative AI
arXiv:2608.20666v1 Announce Type: cross Abstract: While Digital sky surveys provide excellent throughput of image data and can cover a large footprint,…
C-Score: Beyond Accuracy for Robustness Assessment in Semi-Supervised Learning under Open-World Unlabeled Contamination
arXiv:2608.20667v1 Announce Type: cross Abstract: Pseudo-label-based semi-supervised learning has achieved strong performance due to its simplicity and…
RiskTraf: Risk-Extrapolated Residual Learning for Multi-Variate Traffic Flow Prediction
arXiv:2608.20656v1 Announce Type: cross Abstract: Traffic sensors commonly record flow, speed, and occupancy, but standard traffic flow forecasting…
ARQ: Agentic CodeQL Query Refinement for C/C++ Vulnerability Detection
arXiv:2608.20637v1 Announce Type: cross Abstract: Static analyzers have been widely adopted for vulnerability detection in C/C++ programs. Query-based…
Self-Driving Cars Could Someday Take Requests
This article is part of our exclusive IEEE Journal Watch series in partnership with IEEE Xplore. The idea of letting a machine do the driving for you may…
Testing and Evaluation of Agentic AI Systems In Military Command and Control
arXiv:2608.20597v1 Announce Type: cross Abstract: Agentic AI systems are being procured for military command and control (C2) under public commitments to…
Lancium and NVIDIA Partner to Deploy Gigawatt-Scale AI Factories
Lancium, the Texas energy-infrastructure company behind the Abilene campus that anchors the Stargate buildout, has signed a strategic collaboration with…
JuryProbe: An Empirical Consensus-Risk Diagnostic for Routing Reference-Free Factuality Judge Panels to Grounded Verification
arXiv:2608.20607v1 Announce Type: cross Abstract: Panels of inexpensive LLM judges increasingly make accept-or-escalate decisions. In factuality settings,…