Related papers: CFlow: Supporting Semantic Flow Analysis of Studen…

We study the problem of self-supervised 3D scene flow estimation from real large-scale raw point cloud sequences, which is crucial to various tasks like trajectory prediction or instance segmentation. In the absence of ground truth scene…

Spoken Language Understanding (SLU) consists of two sub-tasks: intent detection (ID) and slot filling (SF). Given its broad range of real-world applications, enhancing SLU for practical deployment is increasingly critical. Profile-based SLU…

Strong semantic representations improve the convergence and generation quality of diffusion and flow models. Existing approaches largely rely on external models, which require separate training, operate on misaligned objectives, and exhibit…

Managing data and code in open scientific research is complicated by two key problems: large datasets often cannot be stored alongside code in repository platforms like GitHub, and iterative analysis can lead to unnoticed changes to data,…

Many recent machine learning models rely on fine-grained dynamic control flow for training and inference. In particular, models based on recurrent neural networks and on reinforcement learning depend on recurrence relations, data-dependent…

More often than not, there is a need to understand the structure of complex computer code: what functions and in what order they are called, how information travels around static, input, and output variables, what depends on what. As a…

Flow matching has emerged as a powerful generative framework, with recent few-step methods achieving remarkable inference acceleration. However, we identify a critical yet overlooked limitation: these models suffer from severe diversity…

Providing personalized assistance at scale is a long-standing challenge for computing educators, but a new generation of tools powered by large language models (LLMs) offers immense promise. Such tools can, in theory, provide on-demand help…

Scientific document representation learning provides powerful embeddings for various tasks, while current methods face challenges across three approaches. 1) Contrastive training with citation-structural signals underutilizes citation…

Human-in-the-loop data analysis applications necessitate greater transparency in machine learning models for experts to understand and trust their decisions. To this end, we propose a visual analytics workflow to help data scientists and…

LLM API calls are becoming a ubiquitous program construct, yet they create a boundary that no existing program analysis can cross: runtime values enter a natural-language prompt, undergo opaque processing inside the LLM, and re-emerge as…

Predicting contextualised engagement in videos is a long-standing problem that has been popularly attempted by exploiting the number of views or the associated likes using different computational methods. The recent decade has seen a boom…

Novice programmers often struggle to understand how code executes and to form the abstract mental models necessary for effective problem-solving, challenges that are amplified in large, diverse introductory courses where students'…

FastFlow is a structured parallel programming framework targeting shared memory multicores. Its layered design and the optimized implementation of the communication mechanisms used to implement the FastFlow streaming networks provided to…

As Machine Learning (ML) gains adoption across industries and new use cases, practitioners increasingly realize the challenges around effectively developing and iterating on ML systems: reproducibility, debugging, scalability, and…

In recent years, there have been numerous developments towards solving multimodal tasks, aiming to learn a stronger representation than through a single modality. Certain aspects of the data can be particularly useful in this case - for…

In-context learning (ICL) can significantly enhance the complex reasoning capabilities of large language models (LLMs), with the key lying in the selection and ordering of demonstration examples. Previous methods typically relied on simple…

Machine-learning models, which are known to accurately predict patterns from large datasets, are crucial in decision making. Consequently, counterfactual explanations-methods explaining predictions by introducing input perturbations-have…

Large Language Models (LLMs) have upended decades of pedagogy in computing education. Students previously learned to code through \textit{writing} many small problems with less emphasis on code reading and comprehension. Recent research has…

Providing timely and personalized guidance for students' programming assignments, offers significant practical value for helping students complete assignments and enhance their learning. In recent years, various automated Fault Localization…