Socrates Loss: Enhancing Confidence Calibration & Classification
Discover Socrates Loss, a unified approach improving confidence calibration and classification stability in deep neural networks for reliable AI.
Continuous Knowledge Metabolism for Dynamic Hypothesis Generation
Discover how Continuous Knowledge Metabolism updates scientific knowledge to generate timely hypotheses from evolving research literature efficiently.
MolMem: Efficient Molecular Optimization with Memory RL
Discover MolMem, a memory-augmented reinforcement learning framework that boosts sample efficiency in molecular optimization for drug discovery.
TEMPLATEFUZZ: Advanced Chat Template Fuzzing for LLM Security
Discover TEMPLATEFUZZ, a fine-grained fuzzing tool that boosts LLM security by detecting jailbreak vulnerabilities in chat templates with 98% success.
LLM-Guided Semantic Bootstrapping for Interpretable NLP
Discover how LLM-guided semantic bootstrapping enhances interpretable text classification using Tsetlin Machines, combining accuracy and transparency.