Tabular Few-Shot Generalization Across Heterogeneous Feature Spaces Paper • 2311.10051 • Published Nov 16, 2023
Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes Paper • 2412.13998 • Published Dec 18, 2024
Towards Automated Knowledge Integration From Human-Interpretable Representations Paper • 2402.16105 • Published Feb 5, 2025
The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data Paper • 2412.06877 • Published Jun 6, 2025
Eliciting Numerical Predictive Distributions of LLMs Without Autoregression Paper • 2603.02913 • Published Mar 3 • 1
Preference Learning for AI Alignment: a Causal Perspective Paper • 2506.05967 • Published Jun 6, 2025