Zobrazeno 1 - 10
of 386 410
pro vyhledávání: '"Si, A."'
Autor:
Li, Bowen, Li, Zhaoyu, Du, Qiwei, Luo, Jinqi, Wang, Wenshan, Xie, Yaqi, Stepputtis, Simon, Wang, Chen, Sycara, Katia P., Ravikumar, Pradeep Kumar, Gray, Alexander G., Si, Xujie, Scherer, Sebastian
Recent years have witnessed the rapid development of Neuro-Symbolic (NeSy) AI systems, which integrate symbolic reasoning into deep neural networks. However, most of the existing benchmarks for NeSy AI fail to provide long-horizon reasoning tasks wit
Externí odkaz:
http://arxiv.org/abs/2411.00773
Constructing atomic models from cryo-electron microscopy (cryo-EM) maps is a crucial yet intricate task in structural biology. While advancements in deep learning, such as convolutional neural networks (CNNs) and graph neural networks (GNNs), have sp
Externí odkaz:
http://arxiv.org/abs/2410.23321
Exploring the universal structure of the gravitational path integral beyond semi-classical saddles and uncovering a compelling statistical interpretation of black hole thermodynamics have long been significant challenges. We investigate the statistic
Externí odkaz:
http://arxiv.org/abs/2410.23006
The sampling problem under local differential privacy has recently been studied with potential applications to generative models, but a fundamental analysis of its privacy-utility trade-off (PUT) remains incomplete. In this work, we define the fundam
Externí odkaz:
http://arxiv.org/abs/2410.22699
We study the next-to-leading order (NLO) electroweak (EW) corrections to the $\gamma \gamma \to \tau^+ \tau^-$ process in Pb-Pb ultraperipheral collision (UPC). We find that the EW correction $\delta \sigma_{\mathrm{EW}}$ decreases the total cross se
Externí odkaz:
http://arxiv.org/abs/2410.21963
Autor:
Pal, Pratap, Schad, Jonathon L., Vibhakar, Anuradha M., Ojha, Shashank Kumar, Kim, Gi-Yeop, Shenoy, Saurav, Xue, Fei, Rzchowski, Mark S., Bombardi, A., Johnson, Roger D., Choi, Si-Young, Chen, Long-Qing, Ramesh, Ramamoorthy, Radaelli, Paolo G., Eom, Chang-Beom
The single variant spin cycloid and associated antiferromagnetic order in multiferroic BiFeO3 can provide a direct and predictable magnetoelectric coupling to ferroelectric order for deterministic switching, and also a key to fundamental understandin
Externí odkaz:
http://arxiv.org/abs/2410.22447
We analyze the error rates of the Hamiltonian Monte Carlo algorithm with leapfrog integrator for Bayesian neural network inference. We show that due to the non-differentiability of activation functions in the ReLU family, leapfrog HMC for networks wi
Externí odkaz:
http://arxiv.org/abs/2410.22065
Autor:
Ng, Si-Ioi, Xu, Lingfeng, Siegert, Ingo, Cummins, Nicholas, Benway, Nina R., Liss, Julie, Berisha, Visar
There has been a surge of interest in leveraging speech as a marker of health for a wide spectrum of conditions. The underlying premise is that any neurological, mental, or physical deficits that impact speech production can be objectively assessed v
Externí odkaz:
http://arxiv.org/abs/2410.21640
Generative AI tools, particularly those utilizing large language models (LLMs), have become increasingly prevalent in both professional and personal contexts, offering powerful capabilities for text generation and communication support. While these t
Externí odkaz:
http://arxiv.org/abs/2410.21358
Autor:
Yen, Jui-Nan, Si, Si, Meng, Zhao, Yu, Felix, Duvvuri, Sai Surya, Dhillon, Inderjit S., Hsieh, Cho-Jui, Kumar, Sanjiv
Low-rank adaption (LoRA) is a widely used parameter-efficient finetuning method for LLM that reduces memory requirements. However, current LoRA optimizers lack transformation invariance, meaning the actual updates to the weights depends on how the tw
Externí odkaz:
http://arxiv.org/abs/2410.20625