English
Related papers

Related papers: Trust-Region Noise Search for Black-Box Alignment …

200 papers

The efficient Test-Time Scaling (TTS) paradigm offers a promising perspective for enhancing the generation performance of diffusion models. However, current solutions are limited to a static, pre-defined noise pool and suffer from…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Gang Dai , Yining Huang , Yiming Xia , Guohao Chen , Shuaicheng Niu

Adapting a pretrained diffusion model to new objectives at inference time remains an open problem in generative modeling. Existing steering methods suffer from inaccurate value estimation, especially at high noise levels, which biases…

Machine Learning · Computer Science 2025-06-27 Vineet Jain , Kusha Sareen , Mohammad Pedramfar , Siamak Ravanbakhsh

Diffusion models have shown promising generative capabilities across diverse domains, yet aligning their outputs with desired reward functions remains a challenge, particularly in cases where reward functions are non-differentiable. Some…

Machine Learning · Computer Science 2025-06-04 Xiner Li , Masatoshi Uehara , Xingyu Su , Gabriele Scalia , Tommaso Biancalani , Aviv Regev , Sergey Levine , Shuiwang Ji

This tutorial provides an in-depth guide on inference-time guidance and alignment methods for optimizing downstream reward functions in diffusion models. While diffusion models are renowned for their generative modeling capabilities,…

Artificial Intelligence · Computer Science 2025-01-22 Masatoshi Uehara , Yulai Zhao , Chenyu Wang , Xiner Li , Aviv Regev , Sergey Levine , Tommaso Biancalani

Diffusion models are state-of-the-art generative models, yet their samples often fail to satisfy application objectives such as safety constraints or domain-specific validity. Existing techniques for alignment require gradients, internal…

The new paradigm of test-time scaling has yielded remarkable breakthroughs in Large Language Models (LLMs) (e.g. reasoning models) and in generative vision models, allowing models to allocate additional computation during inference to…

Machine Learning · Computer Science 2025-08-14 Luca Eyring , Shyamgopal Karthik , Alexey Dosovitskiy , Nataniel Ruiz , Zeynep Akata

Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model. Although existing methods are derived from different perspectives, we show…

Machine Learning · Computer Science 2026-05-08 Jeongjae Lee , Jinho Chang , Jeongsol Kim , Jong Chul Ye

In this work, we focus on the alignment problem of diffusion models with a continuous reward function, which represents specific objectives for downstream tasks, such as increasing darkness or improving the aesthetics of images. The central…

Machine Learning · Computer Science 2024-10-03 Zhiwei Tang , Jiangweizhi Peng , Jiasheng Tang , Mingyi Hong , Fan Wang , Tsung-Hui Chang

Reinforcement learning with stochastic optimal control offers a promising framework for diffusion fine-tuning, where a pre-trained diffusion model is optimized to generate paths that lead to a reward-tilted distribution. While these…

Machine Learning · Computer Science 2025-09-30 Sophia Tang , Yuchen Zhu , Molei Tao , Pranam Chatterjee

The performance of text-to-image diffusion models may be improved at test-time by scaling computation to search for a generated image that maximizes a given reward function. While existing trajectory level exploration methods improve the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Qingtao Yu , Changlin Song , Minghao Sun , Zhengyang Yu , Vinay Kumar Verma , Soumya Roy , Sumit Negi , Hongdong Li , Dylan Campbell

Existing audio-text retrieval (ATR) methods are essentially discriminative models that aim to maximize the conditional likelihood, represented as p(candidates|query). Nevertheless, this methodology fails to consider the intrinsic data…

Sound · Computer Science 2024-10-18 Yifei Xin , Xuxin Cheng , Zhihong Zhu , Xusheng Yang , Yuexian Zou

Reinforcement learning (RL) algorithms have been used recently to align diffusion models with downstream objectives such as aesthetic quality and text-image consistency by fine-tuning them to maximize a single reward function under a fixed…

Artificial Intelligence · Computer Science 2026-03-13 Min Cheng , Fatemeh Doudi , Dileep Kalathil , Mohammad Ghavamzadeh , Panganamala R. Kumar

The iterative and stochastic nature of diffusion models enables test-time scaling, whereby spending additional compute during denoising generates higher-fidelity samples. Increasing the number of denoising steps is the primary scaling axis,…

Machine Learning · Computer Science 2025-09-09 Vignav Ramesh , Morteza Mardani

Generative AI has redefined artificial intelligence, enabling the creation of innovative content and customized solutions that drive business practices into a new era of efficiency and creativity. In this paper, we focus on diffusion…

Machine Learning · Computer Science 2024-03-21 Zihao Li , Hui Yuan , Kaixuan Huang , Chengzhuo Ni , Yinyu Ye , Minshuo Chen , Mengdi Wang

Diffusion models have become the de-facto approach for generating visual data, which are trained to match the distribution of the training dataset. In addition, we also want to control generation to fulfill desired properties such as…

Machine Learning · Computer Science 2024-12-30 Dinghuai Zhang , Yizhe Zhang , Jiatao Gu , Ruixiang Zhang , Josh Susskind , Navdeep Jaitly , Shuangfei Zhai

Diffusion models and flow matching have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on fine-tuning pre-trained generative models to maximize a given reward function,…

Machine Learning · Statistics 2026-02-03 Yidong Ouyang , Liyan Xie , Hongyuan Zha , Guang Cheng

Gray-box optimization, where parts of optimization problems are represented by algebraic models while others are treated as black-box models lacking analytic derivatives, remains a challenge. Trust-region (TR) methods provide a robust…

Optimization and Control · Mathematics 2026-04-15 Gul Hameed , Tao Chen , Antonio del Rio Chanona , Lorenz T. Biegler , Michael Short

This paper introduces new perspectives on analog design space search. To minimize the time-to-market, this endeavor better cast as constraint satisfaction problem than global optimization defined in prior arts. We incorporate model-based…

In this paper, we propose and analyze a trust-region model-based algorithm for solving unconstrained stochastic optimization problems. Our framework utilizes random models of an objective function $f(x)$, obtained from stochastic…

Optimization and Control · Mathematics 2016-09-26 Ruobing Chen , Matt Menickelly , Katya Scheinberg

Generating human motion that satisfies customized zero-shot goal functions, enabling applications such as controllable character animation and behavior synthesis for virtual agents, is a critical capability. While current approaches handle…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Hanchao Liu , Fang-Lue Zhang , Shining Zhang , Tai-Jiang Mu , Shi-Min Hu
‹ Prev 1 2 3 10 Next ›