Latest in AI and developer tools

Today's trail

updated 12m ago

Pulse · helpnetsecurity.com

helpnetsecurity.com · Nov 2

People Inc. is building custom APIs to make its journalism easier for AI agents to use

The group behind Aur0ra ransomware gave AI agents stolen credentials and let them move through victim networks toward domain admin access.

Pulse

Top picks this weekarXiv

arXiv

Oct 30

GazeRIB: Systematic Evaluation of Multi-Reader Gaze-Guided Chest X-ray Learning

Radiologists' visual attention can supervise medical image learning, but how reader panel composition affects its value remains untested. We evaluated GazeRIB (Gaze-guided Radiologist-Informed Blackout), which masks unviewed regions during training and uses unmasked images at inference. Eight experts repeatedly read the same 80 chest X-rays (CXRs). We compared individual readers with three-, five- and eight-reader panels across seven architectures and 10 seeds, evaluating 910 models on a separate 2,897-CXR cohort for four-class severity prediction. Every panel improved macro F1 over the no-gaze baseline by 5.33-7.47 percentage points (pp; Bonferroni-adjusted p < 0.007); no individual reader reached significance on this endpoint. Three readers captured 73-80% of the eight-reader gain in macro F1, the area under the receiver-operating-characteristic curve (ROC-AUC) and the area under the precision-recall curve (AU-PRC). On external validation without retraining, all four panels improved ROC-AUC on SIIM-FISABIO-RSNA by +1.93 to +4.24 pp (p <= 0.004); on MIMIC-Eye no panel differed significantly from baseline, whereas the single-reader average declined (-1.40 pp, p = 0.008). Reader…

Top picks

All arXiv Hugging Face GitHub Hacker News

Latest Top this week

arXiv

Oct 1

Range-GRPO: Policy Optimization via Pairwise Relations among Reward Intervals

As the use of large language models (LLMs) expands, post-training has become increasingly important for adapting them to downstream tasks. However, obtaining reliable supervision remains costly, especially in domains without reference answers or executable verifiers.…

arXiv

Oct 1

Reinforcement Learning to Accelerate Primal-Dual Hybrid Gradient for Linear Programming

Primal-dual hybrid gradient (PDHG) methods solve large-scale linear programs (LPs) using GPU-friendly matrix-vector products and projections, but their practical performance depends on coordinating algorithm parameters, acceleration, and restarts. We introduce GALLOP, which…

arXiv

Oct 1

Revisiting Cross-Reconstruction for Generalizable Deepfake Detection

Existing image forgery detectors often suffer from generalization to unseen manipulation methods due to the limited ability to capture transferable forensic cues. Recent cross-reconstruction based methods attempt to improve generalization through semantic-artifact…

arXiv

Oct 1

Synthetic training for long-tail haemorrhagic lesion segmentation in data-scarce settings

Cerebral microbleeds (CMBs) and cortical superficial siderosis (cSS) are imaging markers of cerebral small vessel disease, but their automated segmentation is limited by the scarcity of positive cases and voxel-level annotations. We propose a synthetic training framework for…

This week in Multimodal

This week

Get the morning digest

Today's trail

Pulse

Top picks

Today's trail

This week in Multimodal

Most active this week

Rising tools