15 accepted papers
Diffusion models have demonstrated remarkable image generation capabilities, but their performance heavily relies on classifier-free guidance (CFG). While CFG significantly enhances image quality, evaluating both conditional and unconditional models at every denoising step leads to substantial compu…
Large language models (LLMs) have shown remarkable progress in mathematical problem-solving, but evaluation has largely focused on problems that have exact analytical solutions or involve formal proofs, often overlooking approximation-based problems ubiquitous in applied science and engineering. To…
Edge deployment of large Vision-Language Models (VLMs) increasingly relies on flash-based weight offloading, where activation sparsification is used to reduce I/O overhead. However, conventional sparsification remains model-centric, selecting neurons solely by activation magnitude and neglecting how…
Recent guidance methods in diffusion models steer reverse sampling by perturbing the model to construct an implicit weak model and guide generation away from it. Among these approaches, attention perturbation has demonstrated strong empirical performance in unconditional scenarios where classifier-f…
Federated learning is for training a global model without collecting private local data from clients. As they repeatedly need to upload locally-updated weights or gradients instead, clients require both computation and communication resources enough to participate in learning, but in reality their r…
In time-series forecasting, signals such as traffic volume collected in the real world are noisy and irregularly sampled due to sensor malfunctions, so it is difficult to make accurate prediction. To resolve such difficulty, downsampling can be used to reduce noise and allow capturing slow trend of…
Powered lower-limb prosthetic devices may be becoming a promising option for amputation patients. Although various methods have been proposed to produce gait trajectories similar to those of non-disabled individuals, implementing these control methods is still challenging. It remains unclear whether
Surface electromyography contains muscular information representing gestures and corresponding forces. However, conventional sEMG-based motion recognition methods, such as pattern classification and regression, have intrinsic limitations due to the complex characteristics of sEMG signals. In this pa…
The interpretation of surface electromyographic (sEMG) signals facilitates intuitive gesture recognition. However, sEMG signals are highly dependent on measurement conditions. The relationship between sEMG signals and gestures identified from a specific subject cannot be applied to other subjects ow
We propose a novel method for unsupervised image-to-image translation, which incorporates a new attention module and a new learnable normalization function in an end-to-end manner. The attention module guides our model to focus on more important regions distinguishing between source and target domai…
Muscle activation signals are measured from the skin surface as surface electromyography (EMG) signals that contain information on human intentions; therefore, they are widely used in various robotics applications owing to their usability. However, selective muscle activation extraction is difficult…
Skin impedance should be minimized to obtain reliable and precise surface electromyography (sEMG) signals. High skin impedance decreases sensitivity to muscular activation and makes sEMG signals vulnerable to external noise. Microneedle-based electrodes have been proposed to achieve low skin impedan…
The human finger exhibits fine motor skills that are widely used in daily activities. Thus, the motion estimation of a moving finger has several potential applications. Several surface electromyography interfaces have been proposed to estimate finger motion by analyzing finger-related muscles. Howev
The human hand shows complex motor skills and is widely used in activities in daily living. Thus, finger movement recognition has many potential applications in rehabilitation, tele-operation, and prosthetic hands. Several surface electromyography (sEMG) interfaces have been developed to recognize f
Method of moment estimators exhibit appealing statistical properties, such as asymptotic unbiasedness, for nonconvex problems. However, they typically require a large number of samples and are extremely sensitive to model misspecification. In this paper, we apply the framework of M-estimation to dev…