Related papers: Interactive Program Synthesis
Exploiting the recent advancements in artificial intelligence, showcased by ChatGPT and DALL-E, in real-world applications necessitates vast, domain-specific, and publicly accessible datasets. Unfortunately, the scarcity of such datasets…
Program synthesis is the task of automatically generating a program consistent with a specification. Recent years have seen proposal of a number of neural approaches for program synthesis, many of which adopt a sequence generation paradigm…
Creating and understanding art has long been a hallmark of human ability. When presented with finished digital artwork, professional graphic artists can intuitively deconstruct and replicate it using various drawing tools, such as the line…
Text-to-speech and co-speech gesture synthesis have until now been treated as separate areas by two different research communities, and applications merely stack the two technologies using a simple system-level pipeline. This can lead to…
Recent advances in facial expression synthesis have shown promising results using diverse expression representations including facial action units. Facial action units for an elaborate facial expression synthesis need to be intuitively…
In recent years, researchers have explored component-based synthesis, which aims to automatically construct programs that operate by composing calls to existing APIs. However, prior work has not considered efficient synthesis of methods…
Can we make virtual characters in a scene interact with their surrounding objects through simple instructions? Is it possible to synthesize such motion plausibly with a diverse set of objects and instructions? Inspired by these questions,…
The synthesis of infinite-state reactive systems from temporal logic specifications or infinite-state games has attracted significant attention in recent years, leading to the emergence of novel solving techniques. Most approaches are…
The success of AI models relies on the availability of large, diverse, and high-quality datasets, which can be challenging to obtain due to data scarcity, privacy concerns, and high costs. Synthetic data has emerged as a promising solution…
Recent advances in visual generative models have enabled high-fidelity image editing guided by human instructions. However, these models often struggle with complex instructions involving combinatorial editing operations or inter-step…
Large language models (LLMs) are increasingly deployed as agents, expected to decompose goals, invoke tools, and verify results in dynamic environments. Realizing these capabilities requires access to agentic data-structured interaction…
Our goal is to build systems which write code automatically from the kinds of specifications humans can most easily provide, such as examples and natural language instruction. The key idea of this work is that a flexible combination of…
We ran a study on engagement and achievement for a first year undergraduate programming module which used an online learning environment containing tasks which generate automated feedback. Students could also access human feedback from…
Computational models of human language often involve combinatorial problems. For instance, a probabilistic parser may marginalize over exponentially many trees to make predictions. Algorithms for such problems often employ dynamic…
Software systems are increasingly making decisions on behalf of humans, raising concerns about the fairness of such decisions. Such concerns are usually attributed to flaws in algorithmic design or biased data, but we argue that they are…
Early stages of system development involve outlining desired features such as functionality, availability, or usability. Specifications are derived from these features that concretize vague ideas presented in natural languages. The…
Testing plays an important role in securing the success of a software development project. Prior studies have demonstrated beneficial effects of applying acceptance testing within a Behavioural-Driven Development method. In this research,…
Generative AI is transforming computing education by enabling the automatic generation of personalized content and feedback. We investigate its capabilities in providing high-quality programming tasks to students. Despite promising…
Evaluating retrieval performance without editorial relevance judgments is challenging, but instead, user interactions can be used as relevance signals. Living labs offer a way for small-scale platforms to validate information retrieval…
Computational reproducibility of scientific results, that is, the execution of a computational experiment (e.g., a script) using its original settings (data, code, etc.), should always be possible. However, reproducibility has become a…