Adversarial knowledge distillation framework that stress-tests and distills Code-LLMs into smaller, more robust and reliable models.
May 5, 2025
LLM-based approach that automatically converts text-based task descriptions into reward and goal-generation functions for robotic manipulation.
Jun 19, 2023
Novel approach for learning visual representations using caption annotations for improved visual understanding.
Jan 1, 2020
Novel end-to-end memory access regulation mechanism for Memory Networks that achieves state-of-the-art performance on bAbI and Dialog bAbI tasks.
Jan 1, 2017
Memory Network approach to dialog state tracking framed as machine reading comprehension.
Jan 1, 2017