Related papers: ChannelFlow-Tools: A Standardized Dataset Creation…

This paper presents a novel generative model to synthesize fluid simulations from a set of reduced parameters. A convolutional neural network is trained on a collection of discrete, parameterizable fluid simulation velocity fields. Due to…

High-level synthesis (HLS) has enabled the rapid development of custom hardware circuits for many software applications. However, developing high-performance hardware circuits using HLS is still a non-trivial task requiring expertise in…

In this paper, we present our vision of differentiable ML pipelines called DiffML to automate the construction of ML pipelines in an end-to-end fashion. The idea is that DiffML allows to jointly train not just the ML model itself but also…

One dimensional (1D) simulations of the flow and flooding of open channels are known to be inaccurate as the flow is multi-dimensional in nature, especially at the flooded regions. However, multi-dimensional simulations, even in two…

We introduce CADFS, a data-centric framework that enables large vision-language models to generate complex CAD design histories. Existing generative CAD systems are restricted to sketch-extrude operations due to simplified representations…

Driving planning is a critical component of end-to-end (E2E) autonomous driving. However, prevailing Imitative E2E Planners often suffer from multimodal trajectory mode collapse, failing to produce diverse trajectory proposals. Meanwhile,…

We introduce Canonical Consolidation Fields (CanFields). This novel method interpolates arbitrary-length sequences of independently sampled 3D point clouds into a unified, continuous, and coherent deforming shape. Unlike prior methods that…

Optical flow estimation is a crucial subfield of computer vision, serving as a foundation for video tasks. However, the real-world robustness is limited by animated synthetic datasets for training. This introduces domain gaps when applied…

Machine-learning (ML) techniques provide a new and encouraging perspective for constructing turbulence models for Reynolds-averaged Navier--Stokes (RANS) simulations. In this study, an iterative ML-RANS computational framework is proposed…

Obtaining the ground truth labels from a video is challenging since the manual annotation of pixel-wise flow labels is prohibitively expensive and laborious. Besides, existing approaches try to adapt the trained model on synthetic datasets…

Recent efforts have extended the flow-matching framework to discrete generative modeling. One strand of models directly works with the continuous probabilities instead of discrete tokens, which we colloquially refer to as Continuous-State…

Normalizing Flows (NFs) are flexible explicit generative models that have been shown to accurately model complex real-world data distributions. However, their invertibility constraint imposes limitations on data distributions that reside on…

Safety validation for Level 4 autonomous vehicles (AVs) is currently bottlenecked by the inability to scale the detection of rare, high-risk long-tail scenarios using traditional rule-based heuristics. We present Deep-Flow, an unsupervised…

Normalizing flows are deep generative models that enable efficient likelihood estimation and sampling through invertible transformations. A key challenge is to design linear layers that enhance expressiveness while maintaining efficient…

This work explores a new approach for optimization in the field of microfluidics, using the combination of CFD (Computational Fluid Dynamics), and Machine Learning techniques. The objective of this combination is to enable global…

TensorFlow is a popular cloud computing framework that targets machine learning applications. It separates the specification of application logic (in a dataflow graph) from the execution of the logic. TensorFlow's native runtime executes…

Recent advances in generative models have shown promise in generating behavior plans for long-horizon, sparse reward tasks. While these approaches have achieved promising results, they often lack a principled framework for hierarchical…

Training multimodal large language models (MLLMs) for video understanding requires large-scale annotated data spanning diverse tasks such as object counting, question answering, and segmentation. However, collecting and annotating…

Generative models excel at synthesizing high-fidelity samples from complex data distributions, but they often violate hard constraints arising from physical laws or task specifications. A common remedy is to project intermediate samples…

Recent advances in Large Vision-Language Models (LVLMs) have shown strong potential for multi-modal radiological reasoning, particularly in tasks like diagnostic visual question answering (VQA) and radiology report generation. However, most…