Boost Peptide Design with Conformal Prediction & RL
Discover how conformal prediction enhances generative design of permeable peptides using reinforcement learning for reliable, efficient molecular optimizat...
Robust Explainability for Safety-Critical ATR Systems
Explore limitations of post-hoc XAI methods in ATR systems and discover paths toward robust, reliable explainability for safety-critical AI applications.
Best Arm Identification in Generalized Linear Bandits Using Hybrid Feedback
Discover advanced methods for best arm identification in generalized linear bandits with hybrid feedback, improving efficiency and decision accuracy.
HyperLens: Measuring Cognitive Effort in Large Language Models
Discover HyperLens, a tool that quantifies cognitive effort in LLMs by tracking fine-grained confidence trajectories during inference.
ReFlect: Boosting Long-Horizon Reasoning in LLMs
Discover ReFlect, a novel system that enhances complex long-horizon reasoning and self-correction in large language models without extra training.