Related papers: Object Capabilities and Lightweight Affinity in Sc…
Voice cloning is the task of learning to synthesize the voice of an unseen speaker from a few samples. While current voice cloning methods achieve promising results in Text-to-Speech (TTS) synthesis for a new voice, these approaches lack…
Cultural awareness in language models is the capacity to understand and adapt to diverse cultural contexts. However, most existing approaches treat culture as static background knowledge, overlooking its dynamic and evolving nature. This…
In this study, we aim to explore efficient tuning methods for speech self-supervised learning. Recent studies show that self-supervised learning (SSL) can learn powerful representations for different speech tasks. However, fine-tuning…
Linearizability is a widely accepted notion of correctness for concurrent objects. Recent research has investigated redefining linearizability for particular hardware weak memory models, in particular for TSO. In this paper, we provide an…
The C Object System (Cos) is a small C library which implements high-level concepts available in Clos, Objc and other object-oriented programming languages: uniform object model (class, meta-class and property-metaclass), generic functions,…
Typestate-oriented programming is an extension of the OO paradigm in which objects are modeled not just in terms of interfaces but also in terms of their usage protocols, describing legal sequences of method calls, possibly depending on the…
Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger…
In this paper, we present a neural spoken language diarization model that supports an unconstrained span of languages within a single framework. Our approach integrates a learnable query-based architecture grounded in multilingual…
Type-level programming is an increasingly popular way to obtain additional type safety. Unfortunately, it remains a second-class citizen in the majority of industrially-used programming languages. We propose a new dependently-typed system…
Topological mapping offers a compact and robust representation for navigation, but progress in the field is hindered by the lack of standardized evaluation metrics, datasets, and protocols. Existing systems are assessed using different…
Paisley is an extensible lightweight embedded domain-specific language for nondeterministic pattern matching in Java. Using simple APIs and programming idioms, it brings the power of functional-logic processing of arbitrary data objects to…
A major challenge to deploying cyber-physical systems with learning-enabled controllers is to ensure their safety, especially in the face of changing environments that necessitate runtime knowledge acquisition. Model-checking and automated…
Vision-Language-Action Models (VLAs) have shown remarkable progress towards embodied intelligence. While their architecture partially resembles that of Large Language Models (LLMs), VLAs exhibit higher complexity due to their multi-modal…
Language-based information flow security aims to decide whether an action-observable program can unintentionally leak confidential information if it has the authority to access confidential data. Recent concerns about declassification…
Speaker anonymization aims to conceal a speaker's identity without degrading speech quality and intelligibility. Most speaker anonymization systems disentangle the speaker representation from the original speech and achieve anonymization by…
Language-oriented modularity (LOM) is a methodology that complements language-oriented programming (LOP) in providing on-demand language abstraction solutions during software development. It involves the implementation and immediate…
This work provides a study to demonstrate the potential of using off-the-shelf programming languages and their theories to build sound language-based-security tools. Our study focuses on information flow security encompassing…
Foundational models with billions of parameters which have been trained on large corpora of data have demonstrated non-trivial skills in a variety of domains. However, due to their monolithic structure, it is challenging and expensive to…
While there has been much recent progress using deep learning techniques to separate speech and music audio signals, these systems typically require large collections of isolated sources during the training process. When extending audio…
Learning classifier systems (LCSs) originated from cognitive-science research but migrated such that LCS became powerful classification techniques. Modern LCSs can be used to extract building blocks of knowledge to solve more difficult…