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.
A Self-Supervised Approach on Motion Calibration for Enhancing Physical Plausibility in Text-to-Motion
Artificial Intelligence Graduate School (AIGS), Ulsan National Institute of Science and Technology (UNIST)（人工智能研究生院（AIGS）、乌山国立科学技术研究所（UNIST））；Department of Electrical Engineering (EE), Pohang University of Science and Technology (POSTECH)（电气工程系（EE）、浦项科学技术大学（POSTECH））
GraphAlign: Enhancing Accurate Feature Alignment by Graph matching for Multi-Modal 3D Object Detection
School of Computer and Information Technology, Beijing Jiaotong University（北京交通大学计算机与信息技术学院）；School of Information Science and Engineering, Hebei University of Science and Technology（河北科技大学信息科学与工程学院）；State Key Laboratory of Automotive Safety and Energy, Tsinghua University（清华大学汽车安全与节能国家重点实验室）
Open-Vocabulary HOI Detection with Interaction-aware Prompt and Concept Calibration
Wangxuan Institute of Computer Technology, Peking University（北京大学王璇计算机技术研究所）；National Institute of Health Data Science, Peking University（北京大学国家健康数据科学研究院）
Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration
School of Mechatronic Engineering and Automation, Shanghai University（机械电子工程与自动化学院，上海大学）；Department of Computer Science, City University of Hong Kong（计算机科学系，城市大学）；School of Artificial Intelligence, Xidian University（人工智能学院，西安电子科技大学）；Department of Electronic Engineering, The Chinese University of Hong Kong（电子工程系，香港中文大学）
