Large Language Models

AKD: Adversarial Knowledge Distillation for Large Language Models Alignment on Coding Tasks

Adversarial knowledge distillation framework that stress-tests and distills Code-LLMs into smaller, more robust and reliable models.

May 5, 2025
LARG, Language-based Automatic Reward and Goal Generation

LLM-based approach that automatically converts text-based task descriptions into reward and goal-generation functions for robotic manipulation.

Jun 19, 2023