Related papers: flowengineR: A Modular and Extensible Framework fo…

Developing machine learning (ML) models requires a deep understanding of real-world problems, which are inherently multi-objective. In this paper, we present VirnyFlow, the first design space for responsible model development, designed to…

Reasoning language models (RLMs), also known as Large Reasoning Models (LRMs), such as OpenAI's o1 and o3, DeepSeek-R1, and Alibaba's QwQ, have redefined AI's problem-solving capabilities by extending LLMs with advanced reasoning…

Computational workflows represent major investments of effort and expertise. As first-class, publishable research objects of their own, they are key to sharing methodological know-how for reuse, reproducibility, and transparency. Thus, the…

Generative flow networks (GFlowNets) are a family of algorithms that learn a generative policy to sample discrete objects $x$ with non-negative reward $R(x)$. Learning objectives guarantee the GFlowNet samples $x$ from the target…

Assessing the quality of outputs generated by generative models, such as large language models and vision language models, presents notable challenges. Traditional methods for evaluation typically rely on either human assessments, which are…

With the advent of large language models (LLMs) and multimodal large language models (MLLMs), the potential of retrieval-augmented generation (RAG) has attracted considerable research attention. Various novel algorithms and models have been…

Robotic instruction following tasks require seamless integration of visual perception, task planning, target localization, and motion execution. However, existing task planning methods for instruction following are either data-driven or…

Conducting data analysis typically involves authoring code to transform, visualize, analyze, and interpret data. Large language models (LLMs) are now capable of generating such code for simple, routine analyses. LLMs promise to democratize…

Workflow management systems allow the users to develop complex applications at a higher level, by orchestrating functional components without handling the implementation details. Although a wide range of workflow engines are developed in…

Pipeline parallelism is an essential distributed parallelism method. Increasingly complex and diverse DNN models necessitate meticulously customized pipeline schedules for performance. However, existing practices typically rely on…

Just like the scientific data they generate, simulation workflows for research should be findable, accessible, interoperable, and reusable (FAIR). However, while significant progress has been made towards FAIR data, the majority of science…

Benchmarking involves designing, running and disseminating rigorous performance assessments of methods, most often for data analysis and software tools, but the process can also be applied to experimental systems. Ideally, a benchmarking…

We introduce OpenTinker, an infrastructure for reinforcement learning (RL) of large language model (LLM) agents built around a separation of concerns across algorithm design, execution, and agent-environment interaction. Rather than relying…

Reasoning has emerged as the next major frontier for language models (LMs), with rapid advances from both academic and industrial labs. However, this progress often outpaces methodological rigor, with many evaluations relying on…

Recent advancements in neural rendering technologies and their supporting devices have paved the way for immersive 3D experiences, significantly transforming human interaction with intelligent devices across diverse applications. However,…

Translating neural networks from theory to clinical practice has unique challenges, specifically in the field of neuroimaging. In this paper, we present DeepNeuro, a deep learning framework that is best-suited to putting deep learning…

Computational Workflows are widely used in data analysis, enabling innovation and decision-making. In many domains (bioinformatics, image analysis, & radio astronomy) the analysis components are numerous and written in multiple different…

Large Language Models (LLMs) have demonstrated remarkable general capabilities, but enhancing skills such as reasoning often demands substantial computational resources and may compromise generalization. While Parameter-Efficient…

World models are central to building agents that can reason, plan, and generalize beyond their training data. However, research on world models is currently fragmented, with disparate codebases, data pipelines, and evaluation protocols…

Learning-based planners are sensitive to the long-tailed distribution of driving data. Common maneuvers dominate datasets, while dangerous or rare scenarios are sparse. This imbalance can bias models toward the frequent cases and degrade…