Zobrazeno 1 - 10
of 941
pro vyhledávání: '"HUANG, SIYUAN"'
Neural networks have achieved remarkable performance across a wide range of tasks, yet they remain susceptible to adversarial perturbations, which pose significant risks in safety-critical applications. With the rise of multimodality, diffusion model
Externí odkaz:
http://arxiv.org/abs/2410.14089
In the realm of graph learning, there is a category of methods that conceptualize graphs as hierarchical structures, utilizing node clustering to capture broader structural information. While generally effective, these methods often rely on a fixed g
Externí odkaz:
http://arxiv.org/abs/2410.06746
Self-Consistency, a widely-used decoding strategy, significantly boosts the reasoning capabilities of Large Language Models (LLMs). However, it depends on the plurality voting rule, which focuses on the most frequent answer while overlooking all othe
Externí odkaz:
http://arxiv.org/abs/2410.10857
Synthesizing human motions in 3D environments, particularly those with complex activities such as locomotion, hand-reaching, and human-object interaction, presents substantial demands for user-defined waypoints and stage transitions. These requiremen
Externí odkaz:
http://arxiv.org/abs/2410.03187
Autor:
Zhang, Wenbo, Li, Yang, Qiao, Yanyuan, Huang, Siyuan, Liu, Jiajun, Dayoub, Feras, Ma, Xiao, Liu, Lingqiao
Generalist robot manipulation policies (GMPs) have the potential to generalize across a wide range of tasks, devices, and environments. However, existing policies continue to struggle with out-of-distribution scenarios due to the inherent difficulty
Externí odkaz:
http://arxiv.org/abs/2410.01220
Autor:
Yu, Qiaojun, Huang, Siyuan, Yuan, Xibin, Jiang, Zhengkai, Hao, Ce, Li, Xin, Chang, Haonan, Wang, Junbo, Liu, Liu, Li, Hongsheng, Gao, Peng, Lu, Cewu
Previous studies on robotic manipulation are based on a limited understanding of the underlying 3D motion constraints and affordances. To address these challenges, we propose a comprehensive paradigm, termed UniAff, that integrates 3D object-centric
Externí odkaz:
http://arxiv.org/abs/2409.20551
Autor:
Li, Xin, Huang, Siyuan, Yu, Qiaojun, Jiang, Zhengkai, Hao, Ce, Zhu, Yimeng, Li, Hongsheng, Gao, Peng, Lu, Cewu
Automating garment manipulation poses a significant challenge for assistive robotics due to the diverse and deformable nature of garments. Traditional approaches typically require separate models for each garment type, which limits scalability and ad
Externí odkaz:
http://arxiv.org/abs/2409.18082
Autor:
Lin, Weifeng, Wei, Xinyu, Zhang, Renrui, Zhuo, Le, Zhao, Shitian, Huang, Siyuan, Xie, Junlin, Qiao, Yu, Gao, Peng, Li, Hongsheng
This paper presents a versatile image-to-image visual assistant, PixWizard, designed for image generation, manipulation, and translation based on free-from language instructions. To this end, we tackle a variety of vision tasks into a unified image-t
Externí odkaz:
http://arxiv.org/abs/2409.15278
Autor:
Chen, Yixin, Zhang, Guoxi, Zhang, Yaowei, Xu, Hongming, Zhi, Peiyuan, Li, Qing, Huang, Siyuan
Recently, large language models (LLMs) have shown strong potential in facilitating human-robotic interaction and collaboration. However, existing LLM-based systems often overlook the misalignment between human and robot perceptions, which hinders the
Externí odkaz:
http://arxiv.org/abs/2409.15684
Situation awareness is essential for understanding and reasoning about 3D scenes in embodied AI agents. However, existing datasets and benchmarks for situated understanding are limited in data modality, diversity, scale, and task scope. To address th
Externí odkaz:
http://arxiv.org/abs/2409.02389