Related papers: ALMA: Automata Learner using Modulo 2 Multiplicity…
When used as verifiers in Arthur-Merlin systems, two-way quantum finite automata can verify membership in all languages with bounded error with double-exponential expected running time, which cannot be achieved by their classical…
When aligning large language models (LLMs), their performance on various tasks (such as being helpful, harmless, and honest) depends heavily on the composition of their training data. However, selecting a data mixture that achieves strong…
In this work we study a non-linear generalization based on affine transformations of probabilistic and quantum automata proposed recently by D\'iaz-Caro and Yakary{\i}lmaz \cite{DCY16A} referred as affine automata. First, we present…
We are motivated by the following question: which data languages admit an active learning algorithm? This question was left open in previous work by the authors, and is particularly challenging for languages recognised by nondeterministic…
This paper presents LOLA, a massively multilingual large language model trained on more than 160 languages using a sparse Mixture-of-Experts Transformer architecture. Our architectural and implementation choices address the challenge of…
The Atacama Large Millimeter/Submillimeter Array (ALMA) is an international effort to construct an instrument capable of matching the exquisite imaging properties of optical space telescopes at millimeter and submillimeter wavelengths. ALMA…
Formal reasoning and automated theorem proving constitute a challenging subfield of machine learning, in which machines are tasked with proving mathematical theorems using formal languages like Lean. A formal verification system can check…
Humans learn compositional and causal abstraction, \ie, knowledge, in response to the structure of naturalistic tasks. When presented with a problem-solving task involving some objects, toddlers would first interact with these objects to…
Multilingual automatic speech recognition (ASR) remains a challenging task, especially when balancing performance across high- and low-resource languages. Recent advances in sequence modeling suggest that architectures beyond Transformers…
We introduce Symbolic Alternating Finite Automata (s-AFA) as an expressive, succinct, and decidable model for describing sets of finite sequences over arbitrary alphabets. Boolean operations over s-AFAs have linear complexity, which is in…
Automata learning has been successfully applied in the verification of hardware and software. The size of the automaton model learned is a bottleneck for scalability, and hence optimizations that enable learning of compact representations…
ALMA is estimated to generate TB scale data during only one observation; astronomers manage to identify which part of the data they are really interested in. Now we have been developing new GUI software for this purpose utilizing the VO…
ALAMO is a computational methodology for leaning algebraic functions from data. Given a data set, the approach begins by building a low-complexity, linear model composed of explicit non-linear transformations of the independent variables.…
We study the influence of the dimension of cellular automata (CA) for real time language recognition of one-dimensional languages with parallel input. Specifically, we focus on the question of determining whether every language that can be…
Perceiving and understanding non-speech sounds and non-verbal speech is essential to making decisions that help us interact with our surroundings. In this paper, we propose GAMA, a novel General-purpose Large Audio-Language Model (LALM)…
We present a Deep-Learning (DL) pipeline developed for the detection and characterization of astronomical sources within simulated Atacama Large Millimeter/submillimeter Array (ALMA) data cubes. The pipeline is composed of six DL models: a…
This article introduces an innovative architecture designed to declaratively combine Large Language Models (LLMs) with shared histories, and triggers to identify the most appropriate LLM for a given task. Our approach is general and…
State-of-the-art multilingual systems rely on shared vocabularies that sufficiently cover all considered languages. To this end, a simple and frequently used approach makes use of subword vocabularies constructed jointly over several…
In this paper we present product-form solutions from the point of view of stochastic process algebra. In previous work we have shown how to derive product-form solutions for a formalism called Labelled Markov Automata (LMA). LMA are very…
The rapid evolution of large language models (LLMs) has opened new possibilities for automating various tasks in software development. This paper evaluates the capabilities of the Llama 2-70B model in automating these tasks for scientific…