Related papers: Contextualized Data-Wrangling Code Generation in C…
Vision Language Models (VLMs) often struggle with chart understanding tasks, particularly in accurate chart description and complex reasoning. Synthetic data generation is a promising solution, while usually facing the challenge of noise…
How can we better organize code in computational notebooks? Notebooks have become a popular tool among data scientists, as they seamlessly weave text and code together, supporting users to rapidly iterate and document code experiments.…
Multimodal large-scale models have significantly advanced the development of web agents, enabling perception and interaction with digital environments akin to human cognition. In this paper, we argue that web agents must first acquire…
Extracting informative arguments of events from news articles is a challenging problem in information extraction, which requires a global contextual understanding of each document. While recent work on document-level extraction has gone…
Software developers maintain extensive mental models of code they produce and its context, often relying on memory to retrieve or reconstruct design decisions, edge cases, and debugging experiences. These missing links and data obstruct…
Transformer architectures have achieved remarkable success across language, vision, and multimodal tasks, and there is growing demand for them to address in-context compositional learning tasks. In these tasks, models solve the target…
Academic research is an exploratory activity to discover new solutions to problems. By this nature, academic research works perform literature reviews to distinguish their novelties from prior work. In natural language processing, this…
Many analysis and prediction tasks require the extraction of structured data from unstructured texts. However, an annotation scheme and a training dataset have not been available for training machine learning models to mine structured data…
Process mining has emerged as a way to analyze the behavior of an organization by extracting knowledge from event logs and by offering techniques to discover, monitor and enhance real processes. In the discovery of process models,…
Prior natural language datasets for data visualization have focused on tasks such as visualization literacy assessment, insight generation, and visualization generation from natural language instructions. These studies often rely on…
Evaluating creative text such as human-written stories using language models has always been a challenging task -- owing to the subjectivity of multi-annotator ratings. To mimic the thinking process of humans, chain of thought (CoT)…
The size and complexity of software applications is increasing at an accelerating pace. Source code repositories (along with their dependencies) require vast amounts of labor to keep them tested, maintained, and up to date. As the…
Evaluating code generation models for 3D spatial reasoning requires executing generated code in realistic environments and assessing outputs beyond surface-level correctness. We introduce a platform VoxelCode, for analyzing code generation…
We present Common Inpainted Objects In-N-Out of Context (COinCO), a novel dataset addressing the scarcity of out-of-context examples in existing vision datasets. By systematically replacing objects in COCO images through diffusion-based…
Predicting program behavior and reasoning about code execution remain significant challenges in software engineering, particularly for large language models (LLMs) designed for code analysis. While these models excel at understanding static…
Unstructured text has long been difficult to automatically analyze at scale. Large language models (LLMs) now offer a way forward by enabling {\em semantic data processing}, where familiar data processing operators (e.g., map, reduce,…
LLM-powered coding agents spend the majority of their token budget reading repository files, yet much of the retrieved code is irrelevant to the task at hand. Existing learned pruners compress this context with a single-objective sequence…
We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies. It builds on recently proposed plan-based neural…
Machine learning algorithms such as linear regression, SVM and neural network have played an increasingly important role in the process of scientific discovery. However, none of them is both interpretable and accurate on nonlinear datasets.…
We consider the task of text generation in language models with constraints specified in natural language. To this end, we first create a challenging benchmark Cognac that provides as input to the model a topic with example text, along with…