AI
CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment
Researchers propose a new framework called CLEAR to improve the safety of large language models (LLM...
AI
AUSO: Action-Level Unified Skill Optimization from Internalization to Utilization
Researchers have developed AUSO (Action-Level Unified Skill Optimization), a method for learning and...
AI
From Regulation to Implementation: A Critical Evaluation of LLM-Assisted Regulatory Compliance in Industry
The European Union's regulations on sustainability and privacy require companies to create documenta...
AI
Unified Branch-and-Bound Search for the Steiner Traveling Salesman Problem on Graphs of Convex Sets
Researchers have proposed a new approach to solving the Steiner Traveling Salesman Problem (Steiner-...
AI
Anatomy-Informed Neural Networks: Encoding Anatomic Priors in Loss and Architecture, with an SE(3) Formulation of Guidewire-Induced Aortoiliac Deformation
Researchers have developed a new type of neural network called Anatomy-Informed ...
AI
VIALS: A Benchmark for Visual Interpretation of Artifacts in the Life Sciences
Researchers have created a benchmark called VIALS for evaluating AI's ability to...
AI
When Vocabulary Comprehension Fails Clinical Reasoning: Evaluating Therapy Bots' Safety Risks for Generation Alpha
Researchers have evaluated the safety of conversational AI systems used by Gener...
AI
Who Do Language Models Think Is Competent? A Mechanistic Analysis of Occupational Bias
Researchers analyzed language models to see if they still hold biases towards ce...