相关论文: Refining StreamBED Through Expert Interviews, Desi…

We present Submerse, an end-to-end framework for visualizing flooding scenarios on large and immersive display ecologies. Specifically, we reconstruct a surface mesh from input flood simulation data and generate a to-scale 3D virtual scene…

Although deep learning algorithms have proven their efficiency in automatic sleep staging, the widespread skepticism about their "black-box" nature has limited its clinical acceptance. In this study, we propose WaveSleepNet, an…

We present Swim2Real, a pipeline that calibrates a 16-parameter robotic fish simulator from swimming videos using vision-language model (VLM) feedback, requiring no hand-designed search stages. Calibrating soft aquatic robots is…

Diffusion models (DMs) have become the new trend of generative models and have demonstrated a powerful ability of conditional synthesis. Among those, text-to-image diffusion models pre-trained on large-scale image-text pairs are highly…

Subjective self-reports in VR user studies is a burdening and often tedious task for the participants. To minimize the disruption with the ongoing experience VR research has started to administer the surveying directly inside the virtual…

Online continual learning aims to get closer to a live learning experience by learning directly on a stream of data with temporally shifting distribution and by storing a minimum amount of data from that stream. In this empirical…

RDF streaming has been explored by the Semantic Web community from many angles, resulting in multiple task formulations and streaming methods. However, for many existing formulations of the problem, reliably benchmarking streaming solutions…

In many applications, it is important to reconstruct a fluid flow field, or some other high-dimensional state, from limited measurements and limited data. In this work, we propose a shallow neural network-based learning methodology for such…

Recent language model (LM) advancements have showcased impressive zero-shot voice conversion (VC) performance. However, existing LM-based VC models usually apply offline conversion from source semantics to acoustic features, demanding the…

Large-batch Contrastive Learning (CL), the foundation of modern representation learning, is fundamentally incompatible with the volatile resource constraints of edge devices. This conflict creates a dilemma: small on-device batches degrade…

Supervised learning classifiers inevitably make mistakes in production, perhaps mis-labeling an email, or flagging an otherwise routine transaction as fraudulent. It is vital that the end users of such a system are provided with a means of…

Understanding whether deep neural networks are effectively optimized remains challenging, as training occurs in highly nonconvex landscapes and standard metrics provide limited visibility into layer-wise learning quality. This challenge is…

Streaming video understanding requires models to robustly encode, store, and retrieve information from a continuous video stream to support accurate video question answering (VQA). Existing state-of-the-art approaches rely on key-value…

Online crowdsourcing provides a scalable and inexpensive means to collect knowledge (e.g. labels) about various types of data items (e.g. text, audio, video). However, it is also known to result in large variance in the quality of recorded…

We present EmbodiedHead, a speech-driven talking-head framework that equips LLMs with real-time visual avatars for conversation. A practical embodied avatar must achieve real-time generation, unified listening-speaking behavior, and high…

Network operators need to continuosly upgrade their infrastructures in order to keep their customer satisfaction levels high. Crowdsourcing-based approaches are generally adopted, where customers are directly asked to answer surveys about…

The VirtualCube system is a 3D video conference system that attempts to overcome some limitations of conventional technologies. The key ingredient is VirtualCube, an abstract representation of a real-world cubicle instrumented with RGBD…

Virtual Learning Environments (VLEs) are spaces designed to educate students remotely via online platforms. Although traditional VLEs such as iSocial have shown promise in educating students, they offer limited immersion that diminishes…

Vibe Coding (VC) is a form of software development assisted by generative AI, in which developers describe the intended functionality or logic via natural language prompts, and the AI system generates the corresponding source code. VC can…

Audience feedback is crucial for refining video content, yet it typically comes after publication, limiting creators' ability to make timely adjustments. To bridge this gap, we introduce SimTube, a generative AI system designed to simulate…