AI
Adaptive Probabilistic Shielding by Learning MDPs for Safe Reinforcement Learning
Researchers have developed a method for safe reinforcement learning called adaptive probabilistic sh...
AI
Repo0: Design-Driven Zero-to-All Code Generation
Repo0 is a framework for generating code from natural-language requirements without assuming a prede...
AI
Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners
Researchers have developed a new self-supervised learning framework called Next-Audio-Patch-Embeddin...
AI
A knowledge-guided agentic framework for mitigating patient-context ambiguity in health queries
Researchers have developed a framework to help healthcare chatbots better understand patient queries...
AI
Separating Covariate Shift from Mechanism Change with Two Discriminators: CJSD, a Conditional Discrepancy with an Exact Covariate-Concept Decomposition
Researchers have developed a method called CJSD to help streaming systems decide...
AI
Evidence Before Expansion: Reuse, Spawn, or Defer in Lifelong Expert Pools
Researchers have proposed a decision layer for streaming systems that maintain a...
AI
Interrupting the Loop: Periodic Subject Changes Raise Judged Surprise and Connection in Base Language Models
Researchers have found that injecting new subjects into a language model's strea...
AI
MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection
Researchers have created a comprehensive benchmark for detecting malicious behav...