Kavli Affiliate: Feng Wang | First 5 Authors: Zilong Chen, Yikai Wang, Feng Wang, Zhengyi Wang, Huaping Liu | Summary: Automatic 3D generation has recently attracted widespread attention. Recent methods have greatly accelerated the generation speed, but usually produce less-detailed objects due to limited model capacity or 3D data. Motivated by recent advancements in video […]
Kavli Affiliate: Felix Fischer | First 5 Authors: Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai | Summary: In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, […]
Kavli Affiliate: Felix Fischer | First 5 Authors: Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai | Summary: In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, […]
Kavli Affiliate: Felix Fischer | First 5 Authors: Moonkwang Jeong, Xiangzhou Tan, Felix Fischer, Tian Qiu, | Summary: Small-scale robots hold great potential for targeted cargo delivery in minimally-inv asive medicine. However, current robots often face challenges to locomote efficiently on slip pery biological tissue surfaces, especially when loaded with heavy cargos. Here, we report […]
Kavli Affiliate: Feng Wang | First 5 Authors: Jun-Yi Shan, Nathaniel Morrison, Su-Di Chen, Feng Wang, Eric Y. Ma | Summary: Microwave impedance microscopy (MIM) is an emerging scanning probe technique for nanoscale complex permittivity mapping and has made significant impacts in diverse fields from semiconductors to quantum materials. To date, the most significant hurdles […]
Kavli Affiliate: Feng Wang | First 5 Authors: Ruoqi Wang, Haitao Wang, Qiong Luo, Feng Wang, Hejun Wu | Summary: Radio telescopes produce visibility data about celestial objects, but these data are sparse and noisy. As a result, images created on raw visibility data are of low quality. Recent studies have used deep learning models […]
Kavli Affiliate: Ting Xu | First 5 Authors: Yanghao Su, Jie Zhang, Ting Xu, Tianwei Zhang, Weiming Zhang | Summary: Deep neural networks (DNNs) have revolutionized various industries, leading to the rise of Machine Learning as a Service (MLaaS). In this paradigm, well-trained models are typically deployed through APIs. However, DNNs are susceptible to backdoor […]
Kavli Affiliate: Ting Xu | First 5 Authors: Yanghao Su, Jie Zhang, Ting Xu, Tianwei Zhang, Weiming Zhang | Summary: Backdoor attacks pose a significant security vulnerability for deep neural networks (DNNs), enabling them to operate normally on clean inputs but manipulate predictions when specific trigger patterns occur. Currently, post-training backdoor detection approaches often operate […]
Kavli Affiliate: Feng Wang | First 5 Authors: Isabelle Mohr, Markus Krimmel, Saba Sturua, Mohammad Kalim Akram, Andreas Koukounas | Summary: We introduce a novel suite of state-of-the-art bilingual text embedding models that are designed to support English and another target language. These models are capable of processing lengthy text inputs with up to 8192 […]
Kavli Affiliate: Feng Wang | First 5 Authors: Yiding Sun, Feng Wang, Yutao Zhu, Wayne Xin Zhao, Jiaxin Mao | Summary: The ability of the foundation models heavily relies on large-scale, diverse, and high-quality pretraining data. In order to improve data quality, researchers and practitioners often have to manually curate datasets from difference sources and […]