Sabre
PulseAugur coverage of Sabre — every cluster mentioning Sabre across labs, papers, and developer communities, ranked by signal.
-
New SaBRe framework enhances neural network verification for AI safety
Researchers have developed a new framework called SaBRe that uses a branch-and-bound approach to verify neural networks against relational specifications. This method is crucial for ensuring the safety of AI components …
-
New SABRE framework automates stress testing for vision-language models
Researchers have developed SABRE, a new automated pipeline designed to create stress tests for vision-language models (VLMs). This framework converts task designs into structured specifications, images, and question-ans…
-
New multi-agent system improves out-of-distribution detection for vision-language models
Researchers have introduced SABRE (Selective Agentic Budgeted Reliability Ensemble), a novel multi-agent system designed to improve out-of-distribution (OOD) detection for vision-language models. Unlike traditional meth…
-
Microsoft patches record 622 vulnerabilities with AI-enhanced bug hunt
Microsoft's latest Patch Tuesday release addressed a record 622 security vulnerabilities, indicating success in their AI-enhanced bug hunting efforts. This update aims to improve overall system security by patching nume…
-
New Agentic SABRE framework enhances adaptive ransomware detection
Researchers have developed Agentic SABRE, a novel neuro-symbolic multi-agent framework designed for adaptive ransomware detection. This system integrates semantic and behavioral evidence, using Monte Carlo Dropout to qu…
-
Graph RL router boosts quantum circuit fidelity using calibration data
Researchers have developed a new quantum circuit routing method using graph reinforcement learning that incorporates calibration data from quantum processors. This approach, trained with proximal policy optimization and…
-
Quantum Circuit Routing Enhanced by Calibration-Aware Reinforcement Learning
Researchers have developed a novel routing method for quantum circuits that incorporates calibration data to improve fidelity. This graph reinforcement learning approach uses same-day calibration information from IBM He…