Manmohan Chandraker

A Minimalist Prompt for Zero-Shot Policy Learning

2024 · arXiv (Cornell University)

Transformer-based methods have exhibited significant generalization ability when prompted with target-domain demonstrations or example solutions during inference. Although demonstrations, as a way of task specification, can capture rich information that may be hard to specify …

Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement

2024

Visual program synthesis is a promising approach to ex-ploit the reasoning abilities of large language models for compositional computer vision tasks. Previous work has used few-shot prompting with frozen LLMs to synthesize visual programs. Training …