From Shadow to Light: Toward Safe and Efficient Policy Learning Across MPC, DeePC, RL, and LLM Agents
arxiv.orgยท19h
Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning
arxiv.orgยท1d
Feasibility-Aware Decision-Focused Learning for Predicting Parameters in the Constraints
arxiv.orgยท19h
Loading...Loading more...