Kavli Affiliate: Li Xin Li | First 5 Authors: Yuqian Yuan, Hang Zhang, Wentong Li, Zesen Cheng, Boqiang Zhang | Summary: Video Large Language Models (Video LLMs) have recently exhibited remarkable capabilities in general video understanding. However, they mainly focus on holistic comprehension and struggle with capturing fine-grained spatial and temporal details. Besides, the lack […]
Kavli Affiliate: Jing Wang | First 5 Authors: Zhenpeng Huang, Xinhao Li, Jiaqi Li, Jing Wang, Xiangyu Zeng | Summary: Multimodal Large Language Models (MLLMs) have shown significant progress in offline video understanding. However, applying these models to real-world scenarios, such as autonomous driving and human-computer interaction, presents unique challenges due to the need for […]
Kavli Affiliate: Misao Sasaki | First 5 Authors: Shi Pi, Misao Sasaki, Volodymyr Takhistov, Jianing Wang, | Summary: Primordial Black Holes (PBHs) can form from gravitational collapse of large overdensities in the early Universe, giving rise to rich phenomena in astrophysics and cosmology. We develop a novel, general, and accurate method based on theory of […]
Kavli Affiliate: Misao Sasaki | First 5 Authors: Shi Pi, Misao Sasaki, Volodymyr Takhistov, Jianing Wang, | Summary: Primordial Black Holes (PBHs) can form from gravitational collapse of large overdensities in the early Universe, giving rise to rich phenomena in astrophysics and cosmology. We develop a novel, general, and accurate method based on theory of […]
Kavli Affiliate: Yi Zhou | First 5 Authors: Wei Chen, Yi Zhou, , , | Summary: In the realm of class-incremental learning (CIL), alleviating the catastrophic forgetting problem is a pivotal challenge. This paper discovers a counter-intuitive observation: by incorporating domain shift into CIL tasks, the forgetting rate is significantly reduced. Our comprehensive studies demonstrate […]
Kavli Affiliate: Austin Joyce | First 5 Authors: Daniel Glazer, Austin Joyce, Maria J. Rodriguez, Luca Santoni, Adam R. Solomon | Summary: We study the scalar tidal responses of spinning higher-dimensional black holes, and their effective field theory description. After constructing the effective field theory of a spinning point particle in general dimension, we apply […]
Kavli Affiliate: Bo Gu | First 5 Authors: Songhan Zhao, Shimin Gong, Bo Gu, Lanhua Li, Bin Lyu | Summary: In this paper, we consider an aerial reconfigurable intelligent surface (ARIS)-assisted wireless network, where multiple unmanned aerial vehicles (UAVs) collect data from ground users (GUs) by using the non-orthogonal multiple access (NOMA) method. The ARIS […]
Kavli Affiliate: Feng Wang | First 5 Authors: Zhengyang Lu, Weifan Wang, Tianhao Guo, Feng Wang, | Summary: Reflections often degrade the visual quality of images captured through transparent surfaces, and reflection removal methods suffers from the shortage of paired real-world samples.This paper proposes a hybrid approach that combines cycle-consistency with denoising diffusion probabilistic models […]
Kavli Affiliate: Toshiyuki Kobayashi | First 5 Authors: Toshiyuki Kobayashi, , , , | Summary: This article is a record of the lecture at the centennial conference for Harish-Chandra. The admissibility theorem of Harish-Chandra concerns the restrictions of irreducible representations to maximal compact subgroups. In this article, we begin with a brief explanation of two […]
Kavli Affiliate: Jia Liu | First 5 Authors: Jia Liu, Yue Wang, Zhiqi Lin, Min Chen, Yixue Hao | Summary: Large language model fine-tuning techniques typically depend on extensive labeled data, external guidance, and feedback, such as human alignment, scalar rewards, and demonstration. However, in practical application, the scarcity of specific knowledge poses unprecedented challenges […]