AI
Conformal Policy Control
Researchers have developed a method for controlling AI policies in high-stakes environments. The app...
AI
SkillNet: Create, Evaluate, and Connect AI Skills
Researchers have introduced SkillNet, an open infrastructure for creating, evaluating, and organizin...
AI
From Multi-Agent to Single-Agent: When Is Skill Distillation Beneficial?
Researchers from China have proposed a new method for distilling complex workflows into single-agent...
AI
Interval POMDP Shielding for Imperfect-Perception Agents
Researchers have developed an algorithm to improve the safety of autonomous systems with imperfect p...
AI
When Audio-Language Models Fail to Leverage Multimodal Context for Dysarthric Speech Recognition
Researchers have found that current audio-language models are not effectively us...
AI
Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios
Researchers have developed a new AI framework called Event-Causal RAG that impro...
AI
MBABench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in Finance
Researchers have developed a benchmark to evaluate the performance of large lang...
AI
RULER: Representation-Level Verification of Machine Unlearning
Researchers have introduced RULER, a set of metrics to verify machine unlearning...