paper-with-me

홈 › Papers

UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion Models

2025-03-21 · Fanghua Yu, Jinjin Gu, JinFan Hu, Zheyuan Li, Chao Dong

We introduce UniCon, a novel architecture designed to enhance control and efficiency in training adapters for large-scale diffusion models. Unlike existing methods that rely on bidirectional interaction between the diffusion model and control adapter, UniCon implements a unidirectional flow from the diffusion network to the adapter, allowing the adapter alone to generate the final output. UniCon reduces computational demands by eliminating the need for the diffusion model to compute and store gradients during adapter training. Our results indicate that UniCon reduces GPU memory usage by one-third and increases training speed by 2.3 times, while maintaining the same adapter parameter size. Additionally, without requiring extra computational resources, UniCon enables the training of adapters with double the parameter volume of existing ControlNets. In a series of image conditional generation tasks, UniCon has demonstrated precise responsiveness to control inputs and exceptional generation capabilities.

📄 PDF Abstract BibTeX arXiv:2503.17221

Code (0)

등록된 구현이 없습니다.

Tasks

GPU

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Adapter 설명 없음

Similar Papers 제목 키워드 기반

UniCon: A Unified System for Efficient Robot Learning Transfers

2026-01-21 · Yunfeng Lin, Li Xu, Yong Yu, Jiangmiao Pang 외 arxiv

Deploying learning-based controllers across heterogeneous robots is challenging due to platform differences, inconsistent interfaces, and inefficient middleware. To address these issues, we present UniCon, a lightweight …

UniConFlow: A Unified Constrained Generalization Framework for Certified Motion Planning with Flow Matching Models

2025-06-03 · Zewen Yang, Xiaobing Dai, Dian Yu, Qianru Li 외

Generative models have become increasingly powerful tools for robot motion generation, enabling flexible and multimodal trajectory generation across various tasks. Yet, most existing approaches remain limited in handling…

Collision AvoidanceMotion GenerationMotion Planning

UniCon+: ICTCAS-UCAS Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2022

2022-06-22 · Yuanhang Zhang, Susan Liang, Shuang Yang, Shiguang Shan

This report presents a brief description of our winning solution to the AVA Active Speaker Detection (ASD) task at ActivityNet Challenge 2022. Our underlying model UniCon+ continues to build on our previous work, the Uni…

Active Speaker DetectionAudio-Visual Active Speaker Detection

UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild

2023-05-18 · NeurIPS 2023 11 · Can Qin, Shu Zhang, Ning Yu, Yihao Feng 외

Achieving machine autonomy and human control often represent divergent objectives in the design of interactive AI systems. Visual generative foundation models such as Stable Diffusion show promise in navigating these goa…

Image Generation

UniCon: Universal Neural Controller For Physics-based Character Motion

2020-11-30 · Tingwu Wang, Yunrong Guo, Maria Shugrina, Sanja Fidler

The field of physics-based animation is gaining importance due to the increasing demand for realism in video games and films, and has recently seen wide adoption of data-driven techniques, such as deep reinforcement lear…

Deep Reinforcement LearningReinforcement Learning (RL)