Related papers: Demo2Code: From Summarizing Demonstrations to Synt…

When comprehending code, a helping hand may come from the natural language comments documenting it that, unfortunately, are not always there. To support developers in such a scenario, several techniques have been presented to automatically…

Many advanced Learning from Demonstration (LfD) methods consider the decomposition of complex, real-world tasks into simpler sub-tasks. By reusing the corresponding sub-policies within and between tasks, they provide training data for each…

Large Language Models (LLMs) have shown potential to enhance software development through automated code generation and refactoring, reducing development time and improving code quality. This study empirically evaluates StarCoder2, an LLM…

Source code summarization -- creating natural language descriptions of source code behavior -- is a rapidly-growing research topic with applications to automatic documentation generation, program comprehension, and software maintenance.…

While Vision Language Models (VLMs) have shown promise in Design-to-Code generation, they suffer from a "holistic bottleneck-failing to reconcile high-level structural hierarchy with fine-grained visual details, often resulting in layout…

We present Text2MBL, a text-to-code generation framework that generates executable Building Information Modeling (BIM) code directly from textual descriptions of modular building layout (MBL) design. Unlike conventional layout generation…

In models to generate program source code from natural language, representing this code in a tree structure has been a common approach. However, existing methods often fail to generate complex code correctly due to a lack of ability to…

Training LLMs for code-related tasks typically depends on high-quality code-documentation pairs, which are costly to curate and often scarce for niche programming languages. We introduce BatCoder, a self-supervised reinforcement learning…

We introduce KodCode, a synthetic dataset that addresses the persistent challenge of acquiring high-quality, verifiable training data across diverse difficulties and domains for training Large Language Models for coding. Existing…

Large language models (LLMs) such as Llama 2 perform very well on tasks that involve both natural language and source code, particularly code summarization and code generation. We show that for the task of code summarization, the…

Learning from Demonstration (LfD) seeks to democratize robotics by enabling diverse end-users to teach robots to perform a task by providing demonstrations. However, most LfD techniques assume users provide optimal demonstrations. This is…

We present a framework that, given a set of skills a robot can perform, abstracts sensor data into symbols that we use to automatically encode the robot's capabilities in Linear Temporal Logic. We specify reactive high-level tasks based on…

We introduce Behavior from Language and Demonstration (BLADE), a framework for long-horizon robotic manipulation by integrating imitation learning and model-based planning. BLADE leverages language-annotated demonstrations, extracts…

Code summarization is the task of generating readable summaries that are semantically meaningful and can accurately describe the presumed task of a software. Program comprehension has become one of the most tedious tasks for knowledge…

The challenge in learning abstract concepts from images in an unsupervised fashion lies in the required integration of visual perception and generalizable relational reasoning. Moreover, the unsupervised nature of this task makes it…

Designing robotic hand morphologies for diverse manipulation tasks requires balancing dexterity, manufacturability, and task-specific functionality. While open-source frameworks and parametric tools support reproducible design, they still…

We propose a novel framework, Meta Chain-of-Thought (Meta-CoT), which extends traditional Chain-of-Thought (CoT) by explicitly modeling the underlying reasoning required to arrive at a particular CoT. We present empirical evidence from…

As large language models (LLMs) advance their mathematical capabilities toward the IMO level, the scarcity of challenging, high-quality problems for training and evaluation has become a significant bottleneck. Simultaneously, recent code…

An early stage of developing user-facing applications is creating a wireframe to layout the interface. Once a wireframe has been created it is given to a developer to implement in code. Developing boiler plate user interface code is time…

Large language models (LLMs) can perform complex reasoning by generating intermediate reasoning steps. Providing these steps for prompting demonstrations is called chain-of-thought (CoT) prompting. CoT prompting has two major paradigms. One…