An implicit neural representation (INR) is a neural network that approximates a spatiotemporal function. Many memory-intensive visualization tasks, including mo...
We introduce the first principled framework, Lumos, for specifying and formally certifying Language Model System (LMS) behaviors. Lumos is an imperative probabi...
In low-light environments like nighttime driving, image degradation severely challenges in-vehicle camera safety. Since existing enhancement algorithms are ofte...
This chapter investigates the evolutionary ecology of software, focusing on the symbiotic relationship between software and innovation. An interplay between con...
We present Layout Anything, a transformer-based framework for indoor layout estimation that adapts the OneFormer's universal segmentation architecture to geomet...
While machine learning has enabled the rapid prediction of inorganic materials with novel properties, the challenge of determining how to synthesize these mater...
The next frontier for video generation lies in developing models capable of zero-shot reasoning, where understanding real-world scientific laws is crucial for a...
Novel view synthesis (NVS) is crucial in computer vision and graphics, with wide applications in AR, VR, and autonomous driving. While 3D Gaussian Splatting (3D...
This paper is concerned with the problem of how to speed up computation for Gaussian process models trained on autocorrelated data. The Gaussian process model i...
While Neural Processing Units (NPUs) offer high theoretical efficiency for edge AI, state-of-the-art Vision--Language Models (VLMs) tailored for GPUs often falt...
Move is a research-oriented programming language design for secure and verifiable smart contract development and has been widely used in managing billions of di...
Recent advances in reasoning techniques have substantially improved the performance of large language models (LLMs), raising expectations for their ability to p...
Debugging is one of the most time-consuming and expensive tasks in software development and circuit design. Several formula-based fault localisation (FBFL) meth...
Diffusion large language models (dLLMs) offer a promising alternative to autoregressive models, but their practical utility is severely hampered by slow, iterat...
Test-time policy optimization enables large language models (LLMs) to adapt to distribution shifts by leveraging feedback from self-generated rollouts. However,...
Majority voting has proven effective for close-ended question answering by aggregating parallel reasoning traces. However, it is not directly applicable to open...
Hate speech recognition in low-resource languages remains a difficult problem due to insufficient datasets, orthographic heterogeneity, and linguistic variety. ...
High Performance Computing (HPC) centers provide advanced infrastructure that enables scientific research at extreme scale. These centers operate with hardware ...
Code-generating LLMs are trained largely on static artifacts (source, comments, specifications) and rarely on materializations of run-time behavior. As a result...
Digital sound synthesis presents the opportunity to explore vast parameter spaces containing millions of configurations. Quality diversity (QD) evolutionary alg...
Emerging alongside generative AI and the broader trend of AI-assisted coding, the term 'vibe coding' refers to creating software via natural language prompts ra...
Data science initiatives frequently exhibit high failure rates, driven by technical constraints, organizational limitations and insufficient risk management pra...
Migrating a set of software variants into a software product line (SPL) is an expensive and potentially challenging endeavor. Indeed, SPL engineering can signif...
The most common strategy for enabling a process in a distributed system to broadcast a message is one-to-all communication. However, this approach is not scalab...
