ThunderSyncRL: Lossless Acceleration of Agentic Reinforcement Learning
Research
Research News
New papers, breakthroughs and academic AI research
Runaway Reaction: When Benign Skills Compose into Malicious Behavior
Research
AgentSpy: Making AI Agent Behavior Observable
Research
Non-invasive Seizure Detection Using Wearable Wrist-worn Accelerometry and Deep Learning
Research
RepICL: Reusable In-Context Prediction Across Heterogeneous Representation Spaces
Research
Physics-Informed but Not Physics-Consistent: Error Geometry and Subspace Projection for Neural AC Power Flow
Research
Transfer-Stratified On-Policy Distillation for RL-Improved Reasoning Teachers
Research
Adaptive Expert Guidance for Efficient On-Policy Reinforcement Learning
Research
Incentive Alignment in Online Experimentation
Research
The Blind Spot Paradox: When Adaptive Classifiers Defeat Drift Detectors
Research
A Comprehensive Objective Evaluation of Modern Text-to-Speech for Turkish Using Speech Quality Assessment Models
Research
NCO: A Versatile Plug-in for Handling Negative Constraints in Decoding
Research