Related papers: Mitigating data replication in text-to-audio gener…

Can a text-to-image diffusion model be used as a training objective for adapting a GAN generator to another domain? In this paper, we show that the classifier-free guidance can be leveraged as a critic and enable generators to distill…

One common approach for question answering over speech data is to first transcribe speech using automatic speech recognition (ASR) and then employ text-based retrieval-augmented generation (RAG) on the transcriptions. While this cascaded…

Training-free high-resolution (HR) image generation has garnered significant attention due to the high costs of training large diffusion models. Most existing methods begin by reconstructing the overall structure and then proceed to refine…

This research focuses on the development and enhancement of text-to-image denoising diffusion models, addressing key challenges such as limited sample diversity and training instability. By incorporating Classifier-Free Guidance (CFG) and…

A major obstacle to developing artificial intelligence applications capable of true lifelong learning is that artificial neural networks quickly or catastrophically forget previously learned tasks when trained on a new one. Numerous methods…

The ability to learn sequentially from different data sites is crucial for a deep network in solving practical medical image diagnosis problems due to privacy restrictions and storage limitations. However, adapting on incoming site leads to…

Generative models such as Generative Adversarial Networks (GANs) and Variational Auto-Encoders (VAEs) are widely utilized to model the generative process of user interactions. However, these generative models suffer from intrinsic…

Diffusion and flow-based generative models dominate visual synthesis, with guidance aligning samples to user input and improving perceptual quality. However, Classifier-Free Guidance (CFG) and extrapolation-based methods are heuristic…

Recent advancements in large language models (LLMs) have revolutionized natural language processing through their remarkable capabilities in understanding and executing diverse tasks. While supervised fine-tuning, particularly in…

Recent works have shown that diffusion models are able to memorize training images and emit them at generation time. However, the metrics used to evaluate memorization and its mitigation techniques suffer from dataset-dependent biases and…

Humans can retain old knowledge while learning new information, but Large Language Models (LLMs) often suffer from catastrophic forgetting when post-pretrained or supervised fine-tuned (SFT) on domain-specific data. Moreover, for Multimodal…

Regularization-based methods are beneficial to alleviate the catastrophic forgetting problem in class-incremental learning. With the absence of old task images, they often assume that old knowledge is well preserved if the classifier…

Memorization in large-scale text-to-image diffusion models poses significant security and intellectual property risks, enabling adversarial attribute extraction and the unauthorized reproduction of sensitive or proprietary features. While…

This paper proposes a framework for modeling sound change that combines deep learning and iterative learning. Acquisition and transmission of speech is modeled by training generations of Generative Adversarial Networks (GANs) on unannotated…

Diffusion models generate high-quality samples but can also memorize training data, raising serious privacy concerns. Understanding the mechanisms governing when memorization versus generalization occurs remains an active area of research.…

Large language models (LLMs) are proven to benefit a lot from retrieval-augmented generation (RAG) in alleviating hallucinations confronted with knowledge-intensive questions. RAG adopts information retrieval techniques to inject external…

Real-world datasets collected from sensors or human inputs are prone to noise and errors, posing significant challenges for applying offline reinforcement learning (RL). While existing methods have made progress in addressing corrupted…

Recently, the application of diffusion models has facilitated the significant development of speech and audio generation. Nevertheless, the quality of samples generated by diffusion models still needs improvement. And the effectiveness of…

Diffusion models have emerged as powerful deep generative techniques, producing high-quality and diverse samples in applications in various domains including audio. While existing reviews provide overviews, there remains limited in-depth…

Accurately interpreting cardiac auscultation signals plays a crucial role in diagnosing and managing cardiovascular diseases. However, the paucity of labelled data inhibits classification models' training. Researchers have turned to…