English
Related papers

Related papers: TADA! Tuning Audio Diffusion Models through Activa…

200 papers

Text-conditioned diffusion models can generate impressive images, but fall short when it comes to fine-grained control. Unlike direct-editing tools like Photoshop, text conditioned models require the artist to perform "prompt engineering,"…

Computer Vision and Pattern Recognition · Computer Science 2024-04-05 Michelle Shu , Charles Herrmann , Richard Strong Bowen , Forrester Cole , Ramin Zabih

Large, text-conditioned generative diffusion models have recently gained a lot of attention for their impressive performance in generating high-fidelity images from text alone. However, achieving high-quality results is almost unfeasible in…

Computer Vision and Pattern Recognition · Computer Science 2023-06-01 Manuel Brack , Patrick Schramowski , Felix Friedrich , Dominik Hintersdorf , Kristian Kersting

Distilled one-step (T=1) or few-step (T$\leq$4) diffusion models enable real-time image generation but often exhibit reduced sample diversity compared to their multi-step counterparts. In multi-step diffusion, diversity can be introduced…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Ankit Yadav , Arpit Garg , Ta Duc Huy , Lingqiao Liu

Recent advances in diffusion-based generative models have enabled high-quality text-to-audio synthesis, but fine-grained acoustic control remains a significant challenge in open-source research. We present Audio Palette, a diffusion…

Sound · Computer Science 2025-12-09 Junnuo Wang

Text-guided diffusion models such as DALLE-2, Imagen, eDiff-I, and Stable Diffusion are able to generate an effectively endless variety of images given only a short text prompt describing the desired image content. In many cases the images…

Computer Vision and Pattern Recognition · Computer Science 2023-09-27 Wan-Duo Kurt Ma , J. P. Lewis , Avisek Lahiri , Thomas Leung , W. Bastiaan Kleijn

Diffusion models have transformed image generation, yet controlling their outputs to reliably erase undesired concepts remains challenging. Existing approaches usually require task-specific training and struggle to generalize across both…

Recent progress in diffusion-based audio generation and restoration has substantially improved performance across heterogeneous conditioning regimes, including text-conditioned audio generation and audio-conditioned super-resolution.…

Sound · Computer Science 2026-05-07 Xuanhao Zhang , Chang Li

Recent guidance methods in diffusion models steer reverse sampling by perturbing the model to construct an implicit weak model and guide generation away from it. Among these approaches, attention perturbation has demonstrated strong…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Donghoon Ahn , Jiwon Kang , Sanghyun Lee , Minjae Kim , Jaewon Min , Wooseok Jang , Sangwu Lee , Sayak Paul , Susung Hong , Seungryong Kim

Diffusion models have become the foundation of modern generative systems, with most research focusing primarily on improving generation efficiency and output quality. The timestep embedding component is a crucial part of the diffusion…

Machine Learning · Computer Science 2026-05-05 An Huang , Junggab Son , Zuobin Xiong

Alignment in LLMs is more brittle than commonly assumed: misalignment can be triggered by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization. Recent evidence suggests that some misalignment behaviors…

Artificial Intelligence · Computer Science 2026-04-10 Niklas Herbster , Martin Zborowski , Alberto Tosato , Gauthier Gidel , Tommaso Tosato

Music editing is an important step in music production, which has broad applications, including game development and film production. Most existing zero-shot text-guided editing methods rely on pretrained diffusion models by involving…

Zero-shot Text-to-Speech (TTS) models can generate speech that captures both the voice timbre and accent of a reference speaker. However, disentangling these attributes remains challenging, as the output often inherits both the accent and…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-09 Mu Yang , John H. L. Hansen

Audio editing is applicable for various purposes, such as adding background sound effects, replacing a musical instrument, and repairing damaged audio. Recently, some diffusion-based methods achieved zero-shot audio editing by using a…

Sound · Computer Science 2023-04-06 Yuancheng Wang , Zeqian Ju , Xu Tan , Lei He , Zhizheng Wu , Jiang Bian , Sheng Zhao

Agent-based models are a natural choice for modeling complex social systems. In such models simple stochastic interaction rules for a large population of individuals can lead to emergent dynamics on the macroscopic scale, for instance a…

Physics and Society · Physics 2023-08-02 Luzie Helfmann , Jobst Heitzig , Péter Koltai , Jürgen Kurths , Christof Schütte

Complex social behaviors, such as empathy and strategic politeness, are widely assumed to resist the directional decomposition that makes activation steering effective for coarse attributes like sentiment or toxicity. We present STAR:…

Computation and Language · Computer Science 2026-03-18 Niranjan Chebrolu , Kokil Jaidka , Gerard Christopher Yeo

Diffusion autoencoders (DAs) are variants of diffusion generative models that use an input-dependent latent variable to capture representations alongside the diffusion process. These representations, to varying extents, can be used for…

Machine Learning · Computer Science 2025-06-03 Magdalena Proszewska , Nikolay Malkin , N. Siddharth

Controlling the behavior of large language models (LLMs) at inference time is essential for aligning outputs with human abilities and safety requirements. \emph{Activation steering} provides a lightweight alternative to prompt engineering…

Artificial Intelligence · Computer Science 2026-01-30 Diaoulé Diallo , Katharina Dworatzyk , Sophie Jentzsch , Peer Schütt , Sabine Theis , Tobias Hecking

Point-based interactive editing serves as an essential tool to complement the controllability of existing generative models. A concurrent work, DragDiffusion, updates the diffusion latent map in response to user inputs, causing global…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Haofeng Liu , Chenshu Xu , Yifei Yang , Lihua Zeng , Shengfeng He

A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time. Activation steering, which modifies internal model activations during inference, offers a potential solution. However, prior…

Machine Learning · Computer Science 2025-03-04 Reza Bayat , Ali Rahimi-Kalahroudi , Mohammad Pezeshki , Sarath Chandar , Pascal Vincent

In recent advancements in audio self-supervised representation learning, the standard Transformer architecture has emerged as the predominant approach, yet its attention mechanism often allocates a portion of attention weights to irrelevant…

Sound · Computer Science 2025-07-04 Junyu Wang , Tianrui Wang , Meng Ge , Longbiao Wang , Jianwu Dang