DLM: Advanced Language Models for Multi-Agent Decision Making
Discover how DLM leverages large language models for scalable, offline multi-agent sequential decision making with strong zero-shot generalization.
Pref-CTRL: Preference-Based Alignment for Large Language Models
Discover Pref-CTRL, a novel preference-driven framework improving LLM alignment with human values using multi-objective representation editing.
Refining Safety Rules in CPS Using Grammar-Constrained AI
Explore grammar-constrained refinement of safety rules in cyber-physical systems using AI to ensure syntactic and semantic accuracy for safer operations.
Overcoming Spectral Bias in KANs for Time Series Forecasting
Discover how autocorrelation reintroduces spectral bias in KANs and how DCT preprocessing enhances time series forecasting accuracy.
Managing Uncertainty Propagation in LLM Systems
Explore how uncertainty propagates in LLM-based systems and learn strategies to manage risks for reliable AI applications.