AI
Low-Power, Neuromorphic, Acoustic Anomaly Detection for Persistent Machine Monitoring
Researchers have developed a low-power acoustic anomaly detection system for persistent machine moni...
AI
Coupled-cluster molecular properties across the main group that extrapolate beyond training size
Researchers have developed a new AI model called MEHnet-MG that can predict molecular properties wit...
AI
Task-Conditioned Least-Privilege Learning for Executable Terminal and MCP Agents
Researchers have developed a method to teach AI models to use the minimum amount of authority requir...
AI
One Gate Is Not Enough: Composing Stateful Pre-Action Controls for Agentic AI
Researchers have identified a problem in agentic AI systems that can lead to unintended consequences...
AI
Selection, Recombination, or a Fresh Solve? A Candidate-Free Control for Single-Pass Test-Time Aggregation
Researchers have proposed a new approach to test-time reasoning in AI systems. T...
AI
TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs
Researchers have developed a new framework called Test-Time Self-Distillation wi...
AI
LEDGER: Claim-to-Evidence Trace Graphs for Auditing LLM Agents
Researchers have developed a system called LEDGER to help review and audit the o...
AI
Vector Symbolic Policy Gradient
Researchers have developed a new method for training AI agents called Vector Sym...