AI
BioMed-Agent-RL: A Meta Learning, All You Need for Biomedical Applications
Researchers have developed BioMed-Agent-RL, a unified medical agent that uses reinforcement learning...
AI
GuardPaint:SpeculativeSafetyDecodingforText-to-ImageGeneration
Researchers have proposed a new framework called GuardPaint to address the safety concerns in text-t...
AI
Pruned Traffic Trees: Native Semantic Compression with a Protocol-Structured Model Family for Encrypted Traffic Classification
Researchers have developed a method to compress deep learning models used in encrypted traffic class...
AI
A Scalable Vector Graphics Latent Space
Researchers have developed a new method for representing Scalable Vector Graphics (SVG) in a continu...
AI
Breaking the Assumptions: Auditing Input-Side Jailbreak Defenses Against Semantic Attacks
Researchers have audited several defenses against 'jailbreak attacks' on locally...
AI
Bi-EZP: LLM-Guided Bilevel Program Evolution for Ensemble Zero-Cost Proxy Discovery
Researchers have developed a new method for discovering ensemble zero-cost proxi...
AI
EDGE: Experience-Distillation for Guided Exploration in Agentic Reinforcement Learning
A new framework called EDGE is proposed to improve reinforcement learning in com...
AI
Bulbul: A Dataset for Dialectal Arabic Speech Recognition
A new dataset called Bulbul has been created to help improve speech recognition ...