Related papers: FreeST: Context-free Session Types in a Functional…

Given the great success of large language models (LLMs) across various tasks, in this paper, we introduce LLM-ST, a novel and effective speech translation model constructed upon a pre-trained LLM. By integrating the large language model…

Soft Prompt Tuning (SPT) is a parameter-efficient method for adapting pre-trained language models (PLMs) to specific tasks by inserting learnable embeddings, or soft prompts, at the input layer of the PLM, without modifying its parameters.…

Scene Text Editing (STE) is a challenging research problem, that primarily aims towards modifying existing texts in an image while preserving the background and the font style of the original text. Despite its utility in numerous real-world…

Sessions are a fundamental notion in message-passing systems. A session is an abstract notion of communication between parties where each one owns an endpoint. Session types are types that are assigned to the endpoints and that are used to…

Language-based testing combines context-free grammar definitions with semantic constraints over grammar elements to generate test inputs. By pairing context-free grammars with constraints, users have the expressiveness of unrestricted…

Computing students increasingly rely on generative AI tools for programming assistance, often without formal instruction or guidance. This highlights a need to teach students how to effectively interact with AI models, particularly through…

Information flow control type systems statically restrict the propagation of sensitive data to ensure end-to-end confidentiality. The property to be shown is noninterference, asserting that an attacker cannot infer any secrets from made…

Compositional speech-to-speech translation (S2ST) systems built upon speech large language models (SpeechLLMs) have recently shown promising performance. However, existing S2ST systems often either neglect source-language information or…

We present a novel parsing algorithm for all context-free languages, based on computing the relation between configurations and reaching transitions in a recursive transition network. Parsing complexity w.r.t. input length matches the state…

Sparse tensor networks are commonly used to represent contractions over sparse tensors. Tensor contractions are higher-order analogs of matrix multiplication. Tensor networks arise commonly in many domains of scientific computing and data…

The AMIDST Toolbox is a software for scalable probabilistic machine learning with a spe- cial focus on (massive) streaming data. The toolbox supports a flexible modeling language based on probabilistic graphical models with latent variables…

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…

Vision-Language-Action (VLA) models have recently shown strong generalization, with some approaches seeking to explicitly generate linguistic reasoning traces or predict future observations prior to execution. However, explicit reasoning…

Compositional text-to-video generation, which requires synthesizing dynamic scenes with multiple interacting entities and precise spatial-temporal relationships, remains a critical challenge for diffusion-based models. Existing methods…

We present a novel communication-free algorithm for individual-based probabilistic neutral biodiversity simulations. The algorithm transforms a neutral Moran ecosystem model into an embarrassingly parallel problem by trading off…

Inspired by Kobayashi's type system for lock freedom, we define a behavioral type system for ensuring progress in a language of binary sessions. The key idea is to annotate actions in session types with priorities representing the urgency…

Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods suboptimally capture steering signals from…

We show how systems of session types can enforce interactions to be bounded for all typable processes. The type system we propose is based on Lafont's soft linear logic and is strongly inspired by recent works about session types as…

Recent work in speech-to-speech translation (S2ST) has focused primarily on offline settings, where the full input utterance is available before any output is given. This, however, is not reasonable in many real-world scenarios. In…

Often, when analyzing the behaviour of systems modelled as context-free languages, we wish to know if two languages overlap. To this end, we present an effective semi-decision procedure for regular separability of context-free languages,…