paper-with-me

홈 › Papers

Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration

2026-03-25 · Danil Tokhchukov, Aysel Mirzoeva, Andrey Kuznetsov, Konstantin Sobolev arxiv

In this paper, we uncover the hidden potential of Diffusion Transformers (DiTs) to significantly enhance generative tasks. Through an in-depth analysis of the denoising process, we demonstrate that introducing a single learned scaling parameter can significantly improve the performance of DiT blocks. Building on this insight, we propose Calibri, a parameter-efficient approach that optimally calibrates DiT components to elevate generative quality. Calibri frames DiT calibration as a black-box reward optimization problem, which is efficiently solved using an evolutionary algorithm and modifies just ~100 parameters. Experimental results reveal that despite its lightweight design, Calibri consistently improves performance across various text-to-image models. Notably, Calibri also reduces the inference steps required for image generation, all while maintaining high-quality outputs.

📄 PDF Abstract BibTeX arXiv:2603.24800

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Diffusion-Inspired Reconfiguration of Transformers for Uncertainty Calibration

2026-02-09 · Manh Cuong Dao, Quang Hung Pham, Phi Le Nguyen, Thao Nguyen Truong 외 arxiv

Uncertainty calibration in pre-trained transformers is critical for their reliable deployment in risk-sensitive applications. Yet, most existing pre-trained transformers do not have a principled mechanism for uncertainty…

Enhancing path-integral approximation for non-linear diffusion with neural network

2024-04-13 · Anna Knezevic

Enhancing the existing solution for pricing of fixed income instruments within Black-Karasinski model structure, with neural network at various parameterisation points to demonstrate that the method is able to achieve su…

Diffscaler: Enhancing the Generative Prowess of Diffusion Transformers

2024-04-15 · Nithin Gopalakrishnan Nair, Jeya Maria Jose Valanarasu, Vishal M. Patel

Recently, diffusion transformers have gained wide attention with its excellent performance in text-to-image and text-to-vidoe models, emphasizing the need for transformers as backbone for diffusion models. Transformer-ba…

Image GenerationUnconditional Image Generation

An Analysis on Quantizing Diffusion Transformers

2024-06-16 · Yuewei Yang, Jialiang Wang, Xiaoliang Dai, Peizhao Zhang 외

Diffusion Models (DMs) utilize an iterative denoising process to transform random noise into synthetic data. Initally proposed with a UNet structure, DMs excel at producing images that are virtually indistinguishable wit…

Conditional Image GenerationDenoisingImage GenerationQuantization

S$^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation

2025-08-06 · Weilun Feng, Haotong Qin, Chuanguang Yang, Xiangqi Li 외 arxiv

Diffusion transformers have emerged as the mainstream paradigm for video generation models. However, the use of up to billions of parameters incurs significant computational costs. Quantization offers a promising solutio…

Model CompressionVideo Generation