Front-end developers author UI components to be broadly reusable by parameterizing visual and behavioral properties. While flexible, this makes instantiation harder, as developers must reason about numerous property values and interactions. In practice, they must explore the component’s large design space and provide realistic and natural values to properties. To address this, we introduce distinguishing variations: variations that are both mimetic and distinct. We frame distinguishing variation generation as design-space sampling, combining symbolic inference to identify visually important properties with an LLM-driven mimetic sampler to produce realistic instantiations from its world knowledge.

Despite being trained on vast amounts of data, most LLMs are unable to reliably generate well-designed UIs. Designer feedback is essential to improving performance on UI generation; however, we find that existing RLHF methods based on ratings or rankings are not well-aligned with with designers' workflows and ignore the rich rationale used to critique and improve UI designs. In this paper, we investigate several approaches for designers to give feedback to UI generation models, using familiar interactions such as commenting, sketching and direct manipulation. We first perform an evaluation with 21 designers where they gave feedback using these interactions, which resulted in 1500 design annotations. We then use this data to finetune a series of LLMs to generate higher quality UIs. Finally, we evaluate these models with human judges, and we find that our designer-aligned approaches outperform models trained with traditional ranking feedback and all tested baselines, including GPT-5.

UI prototyping often involves iterating and blending elements from examples such as screenshots and sketches, but current tools offer limited support for incorporating these examples.Inspired by the cognitive process of conceptual blending, we introduce a novel UI workflow that allows developers to rapidly incorporate diverse aspects from design examples into work-in-progress UIs.We prototyped this workflow as Misty.Through a exploratory first-use study with 14 frontend developers, we assessed Misty's effectiveness and gathered feedback on this workflow.Our findings suggest

Jason Wu, Eldon Schoop, Alan Leung, Titus Barik, Jeffrey Bigham, Jeffrey Nichols. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Programmers frequently engage with machine learning tutorials in computational notebooks and have been adopting code generation technologies based on large language models (LLMs). However, they encounter difficulties in understanding and working with code produced by LLMs. To mitigate these challenges, we introduce a novel workflow into computational notebooks that augments LLM-based code generation with an additional ephemeral UI step, offering users UI scaffolds as an intermediate stage between user prompts and code generation. We present this workflow in Biscuit, an extension for JupyterLab that provides users with ephemeral UIs generated by LLMs based on the context of their code and intentions, scaffolding users to understand, guide, and explore with LLMgenerated code. Through a user study where 10 novices used Biscuit for machine learning tutorials, we found that Biscuit offers users representations of code to aid their understanding, reduces the complexity of prompt engineering, and creates a playground for users to explore different variables and iterate on their ideas.

While editing code, it is common for developers to make multiple related repeated edits that are all instances of a more general program transformation. Since this process can be tedious and error-prone, we study the problem of automatically learning program transformations from past edits, which can then be used to predict future edits. We take a novel view of the problem as a semi-supervised learning problem: apart from the concrete edits that are instances of the general transformation, the learning procedure also exploits access to additional inputs (program subtrees) that are marked as positive or negative depending on whether the transformation applies on those inputs. We present a procedure to solve the semi-supervised transformation learning problem using anti-unification and programming-by-example synthesis technology. To eliminate reliance on access to marked additional inputs, we generalize the semi-supervised learning procedure to a feedback-driven procedure that also generates the marked additional inputs in an iterative loop. We apply these ideas to build and evaluate three applications that use different mechanisms for generating feedback. Compared to existing tools that learn program transformations from edits, our feedback-driven semi-supervised approach is vastly more effective in successfully predicting edits with significantly lesser amounts of past edit data.

When working with a document, users often perform context-specific repetitive edits – changes to the document that are similar but specific to the contexts at their locations. Programming by demonstration/examples (PBD/PBE) systems automate these tasks by learning programs to perform the repetitive edits from demonstration or examples. However, PBD/PBE systems are not widely adopted, mainly because they require modal UIs – users must enter a special mode to give the demonstration/examples. This paper presents Blue-Pencil, a modeless system for synthesizing edit suggestions on the fly. Blue-Pencil observes users as they make changes to the document, silently identifies repetitive changes, and automatically suggests transformations that can apply at other locations. Blue-Pencil is parameterized – it allows the ”plug-and-play” of different PBE engines to support different document types and different kinds of transformations. We demonstrate this parameterization by instantiating Blue-Pencil to several domains – C# and SQL code, markdown documents, and spreadsheets – using various existing PBE engines. Our evaluation on 37 code editing sessions shows that Blue-Pencil synthesized edit suggestions with a precision of 0.89 and a recall of 1.0, and took 199 ms to return suggestions on average. Finally, we report on several improvements based on feedback gleaned from a field study with professional programmers to investigate the use of Blue-Pencil during long code editing sessions. Blue-Pencil has been integrated with Visual Studio IntelliCode to power the IntelliCode refactorings feature.

We present Parsimony, a programming-by-example development environment for synthesizing lexers and parsers by example. Parsimony provides a graphical interface in which the user presents examples simply by selecting and labeling sample text in a text editor. An underlying synthesis engine then constructs syntactic rules to solve the system of constraints induced by the supplied examples. Parsimony is more expressive and usable than prior programming-by-example systems for parsers in several ways: Parsimony can (1) synthesize lexer rules in addition to productions, (2) solve for much larger constraint systems over multiple examples, rather than handling examples one-at-a-time, and (3) infer much more complex sets of productions, such as entire algebraic expression grammars, by detecting instances of well-known grammar design patterns. The results of a controlled user study across 18 participants show that users are able to perform lexing and parsing tasks faster and with fewer mistakes when using Parsimony as compared to a traditional parsing workflow.

To offset the high engineering cost of digital circuit design, hardware engineers are looking increasingly toward high-level languages such as C and C++ to implement their designs. To do this, they employ High-Level Synthesis (HLS) tools that translate their high-level specifications down to a hardware description language such as Verilog. Unfortunately, HLS tools themselves employ sophisticated optimization passes that may have bugs that silently introduce errors in realized hardware. The cost of such errors is high, as hardware is costly or impossible to repair if software patching is not an option. In this work, we present a translation validation approach for verifying the correctness of the HLS translation process. Given an initial C program and the generated Verilog code, our approach establishes their equivalence without relying on any intermediate results or representations produced by the HLS tool. We implemented our approach in a tool called VTV that is able to validate a body of programs compiled by the Xilinx Vivado HLS compiler.

Despite decades of research on parsing, the construction of parsers remains a painstaking, manual process prone to subtle bugs and pitfalls. We present a programming-by-example framework called Parsify that is able to synthesize a parser from input/output examples. The user does not write a single line of code. To achieve this, Parsify provides: (a) an iterative algorithm for synthesizing and refining a grammar one example at a time, (b) an interface that provides immediate visual feedback in response to changes in the grammar being refined, and (c) a graphical mechanism for specifying example parse trees using only textual selections. We empirically demonstrate the viability of our approach by using Parsify to construct parsers for source code drawn from Verilog, SQL, Apache, and Tiger.

We present a novel technique for verifying properties of data parallel GPU programs via test amplification. The key insight behind our work is that we can use the technique of static information flow to amplify the result of a single test execution over the set of all inputs and interleavings that affect the property being verified. We empirically demonstrate the effectiveness of test amplification for verifying race-freedom and determinism over a large number of standard GPU kernels, by showing that the result of verifying a single dynamic execution can be amplified over the massive space of possible data inputs and thread interleavings.

Wildcards have become an important part of Java's type system since their introduction 7 years ago. Yet there are still many open problems with Java's wildcards. For example, there are no known sound and complete algorithms for subtyping (and consequently type checking) Java wildcards, and in fact subtyping is suspected to be undecidable because wildcards are a form of bounded existential types. Furthermore, some Java types with wildcards have no joins, making inference of type arguments for generic methods particularly difficult. Although there has been progress on these fronts, we have identified significant shortcomings of the current state of the art, along with new problems that have not been addressed.