Related papers: LARD: Large-scale Artificial Disfluency Generation

Recent progress in generative AI, primarily through diffusion models, presents significant challenges for real-world deepfake detection. The increased realism in image details, diverse content, and widespread accessibility to the general…

It is common to reject undesired outputs of Large Language Models (LLMs); however, current methods to do so require an excessive amount of computation to re-sample after a rejection, or distort the distribution of outputs by constraining…

Diffusion models have shown promise in text generation, but often struggle with generating long, coherent, and contextually accurate text. Token-level diffusion doesn't model word-order dependencies explicitly and operates on short, fixed…

Using unlabeled wild data containing both in-distribution (ID) and out-of-distribution (OOD) data to improve the safety and reliability of models has recently received increasing attention. Existing methods either design customized losses…

Recent advancements in 3D content generation from text or a single image struggle with limited high-quality 3D datasets and inconsistency from 2D multi-view generation. We introduce DiffSplat, a novel 3D generative framework that natively…

Learning graph generative models over latent spaces has received less attention compared to models that operate on the original data space and has so far demonstrated lacklustre performance. We present GLAD a latent space graph generative…

Generative models have been very popular in the recent years for their image generation capabilities. GAN-based models are highly regarded for their disentangled latent space, which is a key feature contributing to their success in…

Previous stance detection studies typically concentrate on evaluating stances within individual instances, thereby exhibiting limitations in effectively modeling multi-party discussions concerning the same specific topic, as naturally…

Sampling from generative models has become a crucial tool for applications like data synthesis and augmentation. Diffusion, Flow Matching and Continuous Normalising Flows have shown effectiveness across various modalities, and rely on…

Spoken language understanding (SLU) system usually consists of various pipeline components, where each component heavily relies on the results of its upstream ones. For example, Intent detection (ID), and slot filling (SF) require its…

Training large AI models typically requires large-scale datasets in the machine learning process, making training and parameter-tuning process both time-consuming and costly. Some researchers address this problem by carefully synthesizing a…

The task of identifying out-of-domain (OOD) input examples directly at test-time has seen renewed interest recently due to increased real world deployment of models. In this work, we focus on OOD detection for natural language sentence…

We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that efficiently samples large-scale foundational image diffusion models in just 1-4 steps while maintaining high image quality. We use score distillation to…

Fault detection and isolation in water distribution networks is an active topic due to its model's mathematical complexity and increased data availability through sensor placement. Here we simplify the model by offering a data driven…

Frontier commercial generative models face a growing threat from distillation, whereby a distiller harvests generated responses and trains a competing model of its own at drastically lower cost. Existing defenses either rely on modifying…

The detection of manufacturing errors is crucial in fabrication processes to ensure product quality and safety standards. Since many defects occur very rarely and their characteristics are mostly unknown a priori, their detection is still…

The modeling of turbulent flows is critical to scientific and engineering problems ranging from aircraft design to weather forecasting and climate prediction. Over the last sixty years numerous turbulence models have been proposed, largely…

Retrieval-Augmented Generation (RAG) merges retrieval methods with deep learning advancements to address the static limitations of large language models (LLMs) by enabling the dynamic integration of up-to-date external information. This…

Generative deep learning systems offer powerful tools for artefact generation, given their ability to model distributions of data and generate high-fidelity results. In the context of computational creativity, however, a major shortcoming…

Model extraction attacks (MEAs) on large language models (LLMs) have received increasing attention in recent research. However, existing attack methods typically adapt the extraction strategies originally developed for deep neural networks…