Xue-She Wang

Ze Ma, Daquan Zhou, Chun-Hsiao Yeh et al. · berkeley

Creating content with specified identities (ID) has attracted significant interest in the field of generative models. In the field of text-to-image generation (T2I), subject-driven creation has achieved great progress with the identity controlled via reference images. However, its extension to video generation is not well explored. In this work, we propose a simple yet effective subject identity controllable video generation framework, termed Video Custom Diffusion (VCD). With a specified identity defined by a few images, VCD reinforces the identity characteristics and injects frame-wise correlation at the initialization stage for stable video outputs. To achieve this, we propose three novel components that are essential for high-quality identity preservation and stable video generation: 1) a noise initialization method with 3D Gaussian Noise Prior for better inter-frame stability; 2) an ID module based on extended Textual Inversion trained with the cropped identity to disentangle the ID information from the background 3) Face VCD and Tiled VCD modules to reinforce faces and upscale the video to higher resolution while preserving the identity's features. We conducted extensive experiments to verify that VCD is able to generate stable videos with better ID over the baselines. Besides, with the transferability of the encoded identity in the ID module, VCD is also working well with personalized text-to-image models available publicly. The codes are available at https://github.com/Zhen-Dong/Magic-Me.

Xue-She Wang, Brian P. Mann

Recent research efforts demonstrate that the intentional use of nonlinearity enhances the capabilities of energy harvesting systems. One of the primary challenges that arise in nonlinear harvesters is that nonlinearities can often result in multiple attractors with both desirable and undesirable responses that may co-exist. This paper presents a nonlinear energy harvester which is based on translation-to-rotational magnetic transmission and exhibits coexisting attractors with different levels of electric power output. In addition, a control method using deep reinforcement learning was proposed to realize attractor switching between coexisting attractors with constrained actuation.

Xue-She Wang, Samuel A. Moore, James D. Turner et al.

Understanding the basins of attraction (BoA) is often a paramount consideration for nonlinear systems. Most existing approaches to determining a high-resolution BoA require prior knowledge of the system's dynamical model (e.g., differential equation or point mapping for continuous systems, cell mapping for discrete systems, etc.), which allows derivation of approximate analytical solutions or parallel computing on a multi-core computer to find the BoA efficiently. However, these methods are typically impractical when the BoA must be determined experimentally or when the system's model is unknown. This paper introduces a model-free sampling method for BoA. The proposed method is based upon hybrid active learning (HAL) and is designed to find and label the "informative" samples, which efficiently determine the boundary of BoA. It consists of three primary parts: 1) additional sampling on trajectories (AST) to maximize the number of samples obtained from each simulation or experiment; 2) an active learning (AL) algorithm to exploit the local boundary of BoA; and 3) a density-based sampling (DBS) method to explore the global boundary of BoA. An example of estimating the BoA for a bistable nonlinear system is presented to show the high efficiency of our HAL sampling method.

Xue-She Wang, James D. Turner, Brian P. Mann

This paper describes an approach for attractor selection (or multi-stability control) in nonlinear dynamical systems with constrained actuation. Attractor selection is obtained using two different deep reinforcement learning methods: 1) the cross-entropy method (CEM) and 2) the deep deterministic policy gradient (DDPG) method. The framework and algorithms for applying these control methods are presented. Experiments were performed on a Duffing oscillator, as it is a classic nonlinear dynamical system with multiple attractors. Both methods achieve attractor selection under various control constraints. While these methods have nearly identical success rates, the DDPG method has the advantages of a high learning rate, low performance variance, and a smooth control approach. This study demonstrates the ability of two reinforcement learning approaches to achieve constrained attractor selection.