相关论文: Scaling and Distilling Transformer Models for sEMG

Recent diffusion distillation methods have achieved remarkable progress, enabling high-quality ${\sim}4$-step sampling for large-scale text-conditional image and video diffusion models. However, further reducing the number of sampling steps…

This paper presents SANA-1.5, a linear Diffusion Transformer for efficient scaling in text-to-image generation. Building upon SANA-1.0, we introduce three key innovations: (1) Efficient Training Scaling: A depth-growth paradigm that enables…

Free-space trajectory similarity calculation, e.g., DTW, Hausdorff, and Frechet, often incur quadratic time complexity, thus learning-based methods have been proposed to accelerate the computation. The core idea is to train an encoder to…

Distilling large language models (LLMs) typically involves transferring the teacher model's responses through supervised fine-tuning (SFT). However, this approach neglects the potential to distill both data (output content) and reward…

The Distribution Matching Distillation (DMD) has been successfully applied to text-to-image diffusion models such as Stable Diffusion (SD) 1.5. However, vanilla DMD suffers from convergence difficulties on large-scale flow-based…

An important goal of self-supervised learning is to enable model pre-training to benefit from almost unlimited data. However, one method that has recently become popular, namely masked image modeling (MIM), is suspected to be unable to…

In the past few years, transformers have achieved promising performances on various computer vision tasks. Unfortunately, the immense inference overhead of most existing vision transformers withholds their from being deployed on edge…

Human-machine interaction is gaining traction in rehabilitation tasks, such as controlling prosthetic hands or robotic arms. Gesture recognition exploiting surface electromyographic (sEMG) signals is one of the most promising approaches,…

Myoelectric control is one of the leading areas of research in the field of robotic prosthetics. We present our research in surface electromyography (sEMG) signal classification, where our simple and novel attention-based approach now leads…

Language models (LMs) require robust episodic grounding-the capacity to learn from and apply past experiences-to excel at physical planning tasks. Current episodic grounding approaches struggle with scalability and integration, limiting…

Vision transformer (ViT) recently has drawn great attention in computer vision due to its remarkable model capability. However, most prevailing ViT models suffer from huge number of parameters, restricting their applicability on devices…

Deploying medical image segmentation models in routine clinical workflows is often constrained by on-premises infrastructure, where computational resources are fixed and cloud-based inference may be restricted by governance and security…

Diffusion Transformers have emerged as the foundation for vision generative models, but their scalability is limited by the high cost of hyperparameter (HP) tuning at large scales. Recently, Maximal Update Parametrization ($\mu$P) was…

Multimodal large language models (MLLMs) have demonstrated impressive performance in vision-language tasks across a broad spectrum of domains. However, the large model scale and associated high computational costs pose significant…

Recent vision-language (VL) studies have shown remarkable progress by learning generic representations from massive image-text pairs with transformer models and then fine-tuning on downstream VL tasks. While existing research has been…

Efficient transformer variants with linear time complexity have been developed to mitigate the quadratic computational overhead of the vanilla transformer. Among them are low-rank projection methods such as Linformer and kernel-based…

Surface electromyography (sEMG) sensors are widely used in human-computer interaction, yet the failure of a single sensor can compromise system usability. We propose a methodological framework for implementing a fail-safe mechanism in…

The rapid advancement of large language models (LLMs) has led to significant improvements in natural language processing but also poses challenges due to their high computational and energy demands. This paper introduces a series of…

This paper introduces the first generalization and adaptation benchmark using machine learning for evaluating out-of-distribution performance of electromyography (EMG) classification algorithms. The ability of an EMG classifier to handle…

The Segment Anything Model (SAM) is a foundational model for image segmentation tasks, known for its strong generalization across diverse applications. However, its impressive performance comes with significant computational and resource…