10 accepted papers
Diffusion models have recently become the dominant paradigm for image generation, yet existing systems struggle to interpret and follow numeric instructions for adjusting semantic attributes. In real-world creative scenarios, especially when precise control over aesthetic attributes is required, cu…
Visual servoing provides the flexibility of robot control in dynamic environments, but three-dimensional (3-D) robot visual servoing is challenging due to the 2-D nature of the image space. Adaptive homography-based visual servoing (HBVS) is effective for 3-D robot pose control under various paramet
Inference-time scaling offers a versatile paradigm for aligning visual generative models with downstream objectives without parameter updates. However, existing approaches that optimize the high-dimensional initial noise suffer from severe inefficiency, as many search directions exert negligible inf…
Controlling articulated soft robots (ASRs) driven by variable stiffness actuators (VSAs) is challenging because they are highly nonlinear and difficult to model accurately. This paper proposes an efficient neural network (NN) learning control solution for ASRs driven by agonistic-antagonistic (AA)-V
Articulated soft robots (ASRs) driven by variable stiffness actuators (VSAs) are challenging to control well due to their highly nonlinear dynamics and difficulties in accurate modeling. The paper proposes a locally weighted learning (LWL)-based robust composite learning control (RCLC) solution for
Text-to-image diffusion models have gained widespread application across various domains, demonstrating remarkable creative potential. However, the strong generalization capabilities of diffusion models can inadvertently lead to the generation of not-safe-for-work (NSFW) content, posing significant…
Despite their remarkable image generation capabilities, text-to-image diffusion models inadvertently learn inappropriate concepts from vast and unfiltered training data, which leads to various ethical and business risks. Specifically, model-generated images may exhibit not safe for work (NSFW) conte…
The ability to handle contact makes robots qualified for many complicated tasks, such as welding, hammering, and wiping. Robot cameras facilitate position planning and control without the geometric knowledge of contact surfaces since they can project contact surfaces onto a 2-dimensional image plane…
Variable impedance control (VIC) is paramount for robots to improve safety and effectiveness in physical human-robot interaction. However, achieving variable target impedance with guaranteed stability is not trivial, particularly under parametric uncertainty in the robot dynamics. This letter propos
We present XFormer, a novel human mesh and motion capture method that achieves real-time performance on consumer CPUs given only monocular images as input. The proposed network architecture contains two branches: a keypoint branch that estimates 3D human mesh vertices given 2D keypoints, and an imag…