English
Related papers

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

200 papers

Language models (LMs) can "memorize" information, i.e., encode training data in their weights in such a way that inference-time queries can lead to verbatim regurgitation of that data. This ability to extract training data can be…

Multimodal contrastive models have achieved strong performance in text-audio retrieval and zero-shot settings, but improving joint embedding spaces remains an active research area. Less attention has been given to making these systems…

Sound · Computer Science 2025-06-25 Julien Guinot , Elio Quinton , György Fazekas

While diffusion models demonstrate a remarkable capability for generating high-quality images, their tendency to `replicate' training data raises privacy concerns. Although recent research suggests that this replication may stem from the…

Computer Vision and Pattern Recognition · Computer Science 2024-01-25 Chenghao Li , Dake Chen , Yuke Zhang , Peter A. Beerel

Diffusion models excel at generating high-quality, diverse samples, yet they risk memorizing training data when overfit to the training objective. We analyze the distinctions between memorization and generalization in diffusion models…

Machine Learning · Computer Science 2026-02-12 Zekai Zhang , Xiao Li , Xiang Li , Lianghe Shi , Meng Wu , Molei Tao , Qing Qu

Text-to-image (T2I) generation has been actively studied using Diffusion Models and Autoregressive Models. Recently, Masked Generative Transformers have gained attention as an alternative to Autoregressive Models to overcome the inherent…

Computer Vision and Pattern Recognition · Computer Science 2025-08-08 Wonjun Kang , Byeongkeun Ahn , Minjae Lee , Kevin Galim , Seunghyuk Oh , Hyung Il Koo , Nam Ik Cho

Diffusion models are prone to exactly reproduce images from the training data. This exact reproduction of the training data is concerning as it can lead to copyright infringement and/or leakage of privacy-sensitive information. In this…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Anubhav Jain , Yuya Kobayashi , Takashi Shibuya , Yuhta Takida , Nasir Memon , Julian Togelius , Yuki Mitsufuji

Text-to-image diffusion models have achieved state-of-the-art results in synthesis tasks; however, there is a growing concern about their potential misuse in creating harmful content. To mitigate these risks, post-hoc model intervention…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Feifei Li , Mi Zhang , Yiming Sun , Min Yang

Diffusion generative models transform noise into data by inverting a process that progressively adds noise to data samples. Inspired by concepts from the renormalization group in physics, which analyzes systems across different scales, we…

Machine Learning · Computer Science 2024-10-04 Mathis Gerdes , Max Welling , Miranda C. N. Cheng

Diffusion models have demonstrated remarkable potential in generating high-quality images. However, their tendency to replicate training data raises serious privacy concerns, particularly when the training datasets contain sensitive or…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Jingqi Xu , Chenghao Li , Yuke Zhang , Peter A. Beerel

Diffusion models have become emerging generative models. Their sampling process involves multiple steps, and in each step the models predict the noise from a noisy sample. When the models make prediction, the output deviates from the ground…

Machine Learning · Computer Science 2025-10-28 Shifeng Xu , Yanzhu Liu , Adams Wai-Kin Kong

Negation is a fundamental linguistic operator, yet it remains inadequately modeled in diffusion-based generative systems. In this work, we present a formal treatment of linguistic negation in diffusion-based generative models by modeling it…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Taewon Kang , Ming C. Lin

Diffusion models can unintentionally reproduce training examples, raising privacy and copyright concerns as these systems are increasingly deployed at scale. Existing inference-time mitigation methods typically manipulate classifier-free…

Artificial Intelligence · Computer Science 2025-12-12 Tong Zhang , Carlos Hinojosa , Bernard Ghanem

This study aims to construct an audio-video generative model with minimal computational cost by leveraging pre-trained single-modal generative models for audio and video. To achieve this, we propose a novel method that guides single-modal…

Computer Vision and Pattern Recognition · Computer Science 2025-02-26 Akio Hayakawa , Masato Ishii , Takashi Shibuya , Yuki Mitsufuji

In this paper we propose a novel generative approach, DiffRoll, to tackle automatic music transcription (AMT). Instead of treating AMT as a discriminative task in which the model is trained to convert spectrograms into piano rolls, we think…

We tackle the problem of generating audio samples conditioned on descriptive text captions. In this work, we propose AaudioGen, an auto-regressive generative model that generates audio samples conditioned on text inputs. AudioGen operates…

The recent proliferation of large-scale text-to-image models has led to growing concerns that such models may be misused to generate harmful, misleading, and inappropriate content. Motivated by this issue, we derive a technique inspired by…

Machine Learning · Computer Science 2023-10-18 Alvin Heng , Harold Soh

Diffusion models have demonstrated significant potential in achieving state-of-the-art performance across various text generation tasks. In this systematic study, we investigate their application to the table-to-text problem by adapting the…

Computation and Language · Computer Science 2024-09-24 Aleksei S. Krylov , Oleg D. Somov

Concept erasure helps stop diffusion models (DMs) from generating harmful content; but current methods face robustness retention trade off. Robustness means the model fine-tuned by concept erasure methods resists reactivation of erased…

Machine Learning · Computer Science 2026-02-16 Fengpeng Li , Kemou Li , Qizhou Wang , Bo Han , Jiantao Zhou

Pre-trained diffusion models have emerged as powerful generative priors for both unconditional and conditional sample generation, yet their outputs often deviate from the characteristics of user-specific target data. Such mismatches are…

Machine Learning · Computer Science 2026-01-14 Matina Mahdizadeh Sani , Nima Jamali , Mohammad Jalali , Farzan Farnia

Classifier-free guidance (CFG) has become an essential component of modern diffusion models to enhance both generation quality and alignment with input conditions. However, CFG requires specific training procedures and is limited to…

Graphics · Computer Science 2025-11-06 Javad Rajabi , Soroush Mehraban , Seyedmorteza Sadat , Babak Taati
‹ Prev 1 3 4 5 6 7 10 Next ›