NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generation

Kavli Affiliate: Matthew Fisher | First 5 Authors: Vikas Thamizharasan, Difan Liu, Matthew Fisher, Nanxuan Zhao, Evangelos Kalogerakis | Summary: The success of denoising diffusion models in representing rich data distributions over 2D raster images has prompted research on extending them to other data representations, such as vector graphics. Unfortunately due to their variable structure […]


Continue.. NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generation

Entanglement-swapping in generalised probabilistic theories, and iterated CHSH games

Kavli Affiliate: David Gross | First 5 Authors: Lionel J. Dmello, Laurens T. Ligthart, David Gross, , | Summary: While there exist theories that have states "more strongly entangled" than quantum theory, in the sense that they show CHSH values above Tsirelson’s bound, all known examples of such theories have a strictly smaller set of […]


Continue.. Entanglement-swapping in generalised probabilistic theories, and iterated CHSH games

Entanglement-swapping in generalised probabilistic theories, and iterated CHSH games

Kavli Affiliate: David Gross | First 5 Authors: Lionel J. Dmello, Laurens T. Ligthart, David Gross, , | Summary: While there exist theories that have states "more strongly entangled" than quantum theory, in the sense that they show CHSH values above Tsirelson’s bound, all known examples of such theories have a strictly smaller set of […]


Continue.. Entanglement-swapping in generalised probabilistic theories, and iterated CHSH games

Personalized Residuals for Concept-Driven Text-to-Image Generation

Kavli Affiliate: Matthew Fisher | First 5 Authors: Cusuh Ham, Matthew Fisher, James Hays, Nicholas Kolkin, Yuchen Liu | Summary: We present personalized residuals and localized attention-guided sampling for efficient concept-driven generation using text-to-image diffusion models. Our method first represents concepts by freezing the weights of a pretrained text-conditioned diffusion model and learning low-rank residuals […]


Continue.. Personalized Residuals for Concept-Driven Text-to-Image Generation

Self-assembling clusters of particles on a shrinking liquid surface

Kavli Affiliate: Mark J. Bowick | First 5 Authors: Xin Li, Shuchen Zhang, Mark J. Bowick, Duanduan Wan, | Summary: After rainfall, pine needles are observed to float on the surface of small puddles. As the water evaporates, these pine needles exhibit spontaneous self-assembly into distinct clusters. Motivated by this natural phenomenon, we conducted experimental […]


Continue.. Self-assembling clusters of particles on a shrinking liquid surface

Self-assembling clusters of particles on a shrinking liquid surface

Kavli Affiliate: Mark J. Bowick | First 5 Authors: Xin Li, Shuchen Zhang, Mark J. Bowick, Duanduan Wan, | Summary: After rainfall, pine needles are observed to float on the surface of small puddles. As the water evaporates, these pine needles exhibit spontaneous self-assembly into distinct clusters. Motivated by this natural phenomenon, we conducted experimental […]


Continue.. Self-assembling clusters of particles on a shrinking liquid surface

Accurate and efficient protein embedding using multi-teacher distillation learning

Kavli Affiliate: Cheng Peng | First 5 Authors: Jiayu Shang, Cheng Peng, Yongxin Ji, Jiaojiao Guan, Dehan Cai | Summary: Motivation: Protein embedding, which represents proteins as numerical vectors, is a crucial step in various learning-based protein annotation/classification problems, including gene ontology prediction, protein-protein interaction prediction, and protein structure prediction. However, existing protein embedding methods […]


Continue.. Accurate and efficient protein embedding using multi-teacher distillation learning

Team Samsung-RAL: Technical Report for 2024 RoboDrive Challenge-Robust Map Segmentation Track

Kavli Affiliate: Yi Zhou | First 5 Authors: Xiaoshuai Hao, Yifan Yang, Hui Zhang, Mengchuan Wei, Yi Zhou | Summary: In this report, we describe the technical details of our submission to the 2024 RoboDrive Challenge Robust Map Segmentation Track. The Robust Map Segmentation track focuses on the segmentation of complex driving scene elements in […]


Continue.. Team Samsung-RAL: Technical Report for 2024 RoboDrive Challenge-Robust Map Segmentation Track

Fluctuations in Spin Dynamics Excited by Pulsed Light

Kavli Affiliate: Mamoru Matsuo | First 5 Authors: Tetsuya Sato, Shinichi Watanabe, Mamoru Matsuo, Takeo Kato, | Summary: We theoretically investigate nonequilibrium spin fluctuations in a ferromagnet induced by a light pulse. Using a Lindblad equation consistent with the Landau-Lifshitz-Gilbert equation, we compute the autocorrelation function of magnetization. Our analysis reveals that this function comprises […]


Continue.. Fluctuations in Spin Dynamics Excited by Pulsed Light

The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition

Kavli Affiliate: Yi Zhou | First 5 Authors: Lingdong Kong, Shaoyuan Xie, Hanjiang Hu, Yaru Niu, Wei Tsang Ooi | Summary: In the realm of autonomous driving, robust perception under out-of-distribution conditions is paramount for the safe deployment of vehicles. Challenges such as adverse weather, sensor malfunctions, and environmental unpredictability can severely impact the performance […]


Continue.. The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition