11 accepted papers
Beyond general recognition tasks, specialized domains and fine-grained settings often encounter data scarcity, especially for tail classes. To obtain less biased and more reliable models under such scarcity, practitioners leverage diffusion models to supplement underrepresented regions of real data.
Federated Learning (FL) offers a privacy-preserving pathway for aligning Large Language Models (LLMs); however, existing frameworks typically enforce a monolithic reward model, inevitably averaging out inherently conflicting user preferences (e.g., helpfulness vs. harmlessness). While Variational Pr…
The rise of model hubs has made it easier to access reusable model components, making model merging a practical tool for combining capabilities. Yet, this modularity also creates a *governance gap*: downstream users can recompose released weights into unauthorized mixtures that bypass safety alignme…
Scaling test-time computation, generating and analyzing multiple or sequential outputs for a single input, has become a promising strategy for improving the reliability and quality of large language models (LLMs), as evidenced by advances in uncertainty quantification and multi-step reasoning. A key
Training and validating models for semantic segmentation require datasets with pixel-wise annotations, which are notoriously labor-intensive. Although useful priors such as foundation models or crowdsourced datasets are available, they are error-prone. We hence propose an effective framework of acti…
The cable-driven redundant manipulator (CDRM) has significant potential for applications in narrow and hazardous spaces. However, traditional CDRMs have limited stiffness and load capacity due to their cable routing method. To address these limitations, several scholars have proposed new mechanisms…
This paper proposes a new active learning method for semantic segmentation. The core of our method lies in a new annotation query design. It samples informative local image regions ($\textit{e.g.}$, superpixels), and for each of such regions, asks an oracle for a multi-hot vector indicating all clas…
Learning semantic segmentation requires pixel-wise annotations, which can be time-consuming and expensive. To reduce the annotation cost, we propose a superpixel-based active learning (AL) framework, which collects a dominant label per superpixel instead. To be specific, it consists of adaptive supe…
Cable driven redundant manipulator (CDRM) can provide complex movements with high dexterity and singularity reduction. However, traditional CDRMs with universal joints have the disadvantages of requiring a high number of motors and having a narrow joint workspace. Furthermore, there is a limitation…
For immersive interaction in a virtual reality (VR) environment, an omnidirectional treadmill (ODT) can support performance of various locomotive motions (curved walk, side walk, moving with shooting stance) in any direction. When a user performs lateral locomotive motions on an ODT, a control schem…
Crowdsourcing systems enable us to collect large-scale dataset, but inherently suffer from noisy labels of low-paid workers. We address the inference and learning problems using such a crowdsourced dataset with noise. Due to the nature of sparsity in crowdsourcing, it is critical to exploit both pro…