Answering visual queries is a complex task that requires both visual processing and
reasoning. End-to-end models, the dominant approach for this task, do not explicitly …

This study focuses on using large language models (LLMs) as a planner for embodied
agents that can follow natural language instructions to complete complex tasks in a visually …

Large language models (LLMs) have recently been applied in software engineering to
perform tasks such as translating code between programming languages, generating code …

Language models (LMs) are becoming the foundation for almost all major language
technologies, but their capabilities, limitations, and risks are not well understood. We present …

Attaining a high degree of user controllability in visual generation often requires intricate,
fine-grained inputs like layouts. However, such inputs impose a substantial burden on users …

With the rapid progress of large language models (LLMs), many downstream NLP tasks can
be well solved given appropriate prompts. Though model developers and researchers work …

The task of generating code from a natural language description, or NL2Code, is considered
a pressing and significant challenge in code intelligence. Thanks to the rapid development …

The advancement of large language models (LLMs) has significantly enhanced the ability to
effectively tackle various downstream NLP tasks and unify these tasks into generative …

What does learning to model relationships between strings teach Large Language Models
(LLMs) about the visual world? We systematically evaluate LLMs' abilities to generate and …

Large language models (LLMs) have exhibited remarkable capabilities in learning from
explanations in prompts, but there has been limited understanding of exactly how these …