AI
EnvHarness: Awakening Static Worlds for Agent Learning
Researchers have proposed a new system called EnvHarness to create dynamic environments for AI agent...
AI
TESTNAV: Pareto-Guided Search for Compositional Robustness Testing
Researchers have developed a new testing framework called TESTNAV to identify vulnerabilities in dee...
AI
Write Once, Run Everywhere: The Axon DSL for Shape-Safe and Framework-Agnostic LLM Architectures
Researchers have developed a new domain-specific language called Axon that allows for the creation o...
AI
EXIMO: VLM Guided Exploration of VLA Policies
Researchers from the University of Freiburg and the Max Planck Institute for Intelligent Systems hav...
AI
Bringing analytic rigor to agentic AI for science: The Brain Researcher platform for neuroimaging data analysis
A new platform called Brain Researcher has been developed to improve the rigor o...
AI
Spike-based Belief Propagation in Nonlinear Dynamical Systems
Researchers have developed a brain-like control algorithm that uses spike-based ...
AI
A Strong Linear Baseline for Whole-Heart Cardiac Shape Completion on CT, with an Open Eleven-Structure Statistical Shape Model
Researchers have developed a statistical shape model for the heart that can be u...
AI
Learning Early-to-Final Solution Consistency for MILP Acceleration
Researchers have proposed a new approach to accelerate Mixed-Integer Linear Prog...