相关论文: Cornfigurator: Automated Planning for Any-to-Any M…

We introduce OmniFlow, a novel generative model designed for any-to-any generation tasks such as text-to-image, text-to-audio, and audio-to-image synthesis. OmniFlow advances the rectified flow (RF) framework used in text-to-image models to…

The feasibility of collecting a large amount of expert demonstrations has inspired growing research interests in learning-to-drive settings, where models learn by imitating the driving behaviour from experts. However, exclusively relying on…

Conventional wisdom holds that model-based planning is a powerful approach to sequential decision-making. It is often very challenging in practice, however, because while a model can be used to evaluate a plan, it does not prescribe how to…

Multimodal learning is a framework for building models that make predictions based on different types of modalities. Important challenges in multimodal learning are the inference of shared representations from arbitrary modalities and…

Unified image understanding and generation has emerged as a promising paradigm in multimodal artificial intelligence. Despite recent progress, the optimal architectural design for such unified models remains an open challenge. In this work,…

Voxel-wise dose prediction is a critical yet challenging task in practical radiotherapy (RT) planning, as bespoke models trained from scratch often struggle to generalize across diverse clinical settings. Meanwhile, generative models…

The emergence of large-scale Mixture of Experts (MoE) models represents a significant advancement in artificial intelligence, offering enhanced model capacity and computational efficiency through conditional computation. However, deploying…

In-network machine learning enables real-time classification directly on network hardware, offering consistently low inference latency. However, current solutions are limited by strict hardware constraints, scarce on-device resources, and…

Reliable uncertainty quantification is critical in multivariate time series forecasting problems arising in domains such as energy systems and transportation networks, among many others. Although Transformer-based architectures have…

While image-based virtual try-on has made significant strides, emerging approaches still fall short of delivering high-fidelity and robust fitting images across various scenarios, as their models suffer from issues of ill-fitted garment…

We introduce AnyEnhance, a unified generative model for voice enhancement that processes both speech and singing voices. Based on a masked generative model, AnyEnhance is capable of handling both speech and singing voices, supporting a wide…

Accurate and timely prediction of tool conditions is critical for intelligent manufacturing systems, where unplanned tool failures can lead to quality degradation and production downtime. In modern industrial environments, predictive…

Recent works in the robot learning community have successfully introduced generalist models capable of controlling various robot embodiments across a wide range of tasks, such as navigation and locomotion. However, achieving agile control,…

Explaining how to get from A to B can be challenging. It requires mentally simulating what the listener will do based on what they are told. To capture this process, we propose a computational model that converts utterances into action…

Trajectory prediction and planning are fundamental yet disconnected components in autonomous driving. Prediction models forecast surrounding agent motion under unknown intentions, producing multimodal distributions, while planning assumes…

State-of-the-art systems neuroscience experiments yield large-scale multimodal data, and these data sets require new tools for analysis. Inspired by the success of large pretrained models in vision and language domains, we reframe the…

Image reconstruction and image synthesis are important for handling incomplete multimodal imaging data, but existing methods require various task-specific models, complicating training and deployment workflows. We introduce Any2all, a…

While recently Multimodal Large Language Models (MM-LLMs) have made exciting strides, they mostly fall prey to the limitation of only input-side multimodal understanding, without the ability to produce content in multiple modalities. As we…

Efficient planning in high-dimensional spaces, such as those involving deformable objects, requires computationally tractable yet sufficiently expressive dynamics models. This paper introduces a method that automatically generates…

The surge in generative AI workloads has created a need for scalable inference systems that can flexibly harness both GPUs and specialized accelerators while containing operational costs. This paper proposes a hardware-agnostic control loop…