Related papers: Finite Sentence-Interface Control for Learning Bou…

Background: Federated Learning (FL) has emerged as a promising paradigm for training machine learning models while preserving data privacy. However, applying FL to Natural Language Processing (NLP) tasks presents unique challenges due to…

This paper presents a restricted form of linear indexed grammars, called even linear indexed grammars, which yield the even linear indexed languages. These languages properly contain the context-free languages and are contained in the set…

A linear parameter must be consumed exactly once in the body of its function. When declaring resources such as file handles and manually managed memory as linear arguments, a linear type system can verify that these resources are used…

Conversational Speech Synthesis (CSS) aims to generate speech with natural prosody by understanding the multimodal dialogue history (MDH). The latest work predicts the accurate prosody expression of the target utterance by modeling the…

A variety of contextualised language models have been proposed in the NLP community, which are trained on diverse corpora to produce numerous Neural Language Models (NLMs). However, different NLMs have reported different levels of…

Long-context large language models remain computationally expensive to run and often fail to reliably process very long inputs, which makes context compression an important component of many systems. Existing compression approaches…

Tree-controlled grammars are context-free grammars where the derivation process is controlled in such a way that every word on a level of the derivation tree must belong to a certain control language. We investigate the generative capacity…

Classifier-Free Guidance (CFG) is a widely used mechanism for controlling diffusion-based generative models, yet its guidance scale is typically treated as a fixed hyperparameter throughout generation. This static design yields a suboptimal…

A type theory is presented that combines (intuitionistic) linear types with type dependency, thus properly generalising both intuitionistic dependent type theory and full linear logic. A syntax and complete categorical semantics are…

This paper introduces a generalized federated prompt-tuning framework for practical scenarios where local datasets are multi-modal and exhibit different distributional patterns of missing features at the input level. The proposed framework…

Current efficient fine-tuning methods (e.g., adapters, prefix-tuning, etc.) have optimized conditional text generation via training a small set of extra parameters of the neural language model, while freezing the rest for efficiency. While…

We propose FC, a new logic on words that combines finite model theory with the theory of concatenation - a first-order logic that is based on word equations. Like the theory of concatenation, FC is built around word equations; in contrast…

Federated learning has emerged as a promising approach for training machine learning models on decentralized data sources while preserving data privacy. However, challenges such as communication bottlenecks, heterogeneity of client devices,…

We study the problem of fitting ontologies and constraints to positive and negative examples that take the form of a finite relational structure. As ontology and constraint languages, we consider the description logics $\mathcal{E\mkern-2mu…

Multilingual transformer-based models demonstrate remarkable zero and few-shot transfer across languages by learning and reusing language-agnostic features. However, as a fixed-size model acquires more languages, its performance across all…

We systematically investigate the complexity of model checking the existential positive fragment of first-order logic. In particular, for a set of existential positive sentences, we consider model checking where the sentence is restricted…

Masked diffusion models have emerged as a powerful framework for text and multimodal generation. However, their sampling procedure updates multiple tokens simultaneously and treats generated tokens as immutable, which may lead to error…

Existing work on controlled text generation (CTG) assumes a control interface of categorical attributes. In this work, we propose a natural language (NL) interface, where we craft a PCFG to embed the control attributes into natural language…

Classifier-free guidance (CFG) is a core technique powering state-of-the-art image generation systems, yet its underlying mechanisms remain poorly understood. In this work, we begin by analyzing CFG in a simplified linear diffusion model,…

Aligning language models (LMs) with user intent is becoming increasingly relevant to enhance user experience. This calls for designing methods that can allow users to control the properties of the language that LMs generate, for example,…