Zobrazeno 1 - 10
of 55 115
pro vyhledávání: '"P, Agrawal"'
Medical image segmentation is crucial in robotic surgeries, disease diagnosis, and treatment plans. This research presents an innovative methodology that combines Kolmogorov-Arnold Networks (KAN) with an adapted Mamba layer for medical image segmenta
Externí odkaz:
http://arxiv.org/abs/2411.11926
Autor:
Shanmugam, Divya, Agrawal, Monica, Movva, Rajiv, Chen, Irene Y., Ghassemi, Marzyeh, Pierson, Emma
The increased capabilities of generative AI have dramatically expanded its possible use cases in medicine. We provide a comprehensive overview of generative AI use cases for clinicians, patients, clinical trial organizers, researchers, and trainees.
Externí odkaz:
http://arxiv.org/abs/2412.10337
Autor:
Miao, Kevin, Agrawal, Harsh, Zhang, Qihang, Semeraro, Federico, Cavallo, Marco, Gu, Jiatao, Toshev, Alexander
Generating high-quality 3D content requires models capable of learning robust distributions of complex scenes and the real-world objects within them. Recent Gaussian-based 3D reconstruction techniques have achieved impressive results in recovering hi
Externí odkaz:
http://arxiv.org/abs/2412.09648
Autor:
Agrawal, Abhinav, Domke, Justin
Normalizing flow-based variational inference (flow VI) is a promising approximate inference approach, but its performance remains inconsistent across studies. Numerous algorithmic choices influence flow VI's performance. We conduct a step-by-step ana
Externí odkaz:
http://arxiv.org/abs/2412.08824
Autor:
Szot, Andrew, Mazoure, Bogdan, Attia, Omar, Timofeev, Aleksei, Agrawal, Harsh, Hjelm, Devon, Gan, Zhe, Kira, Zsolt, Toshev, Alexander
We examine the capability of Multimodal Large Language Models (MLLMs) to tackle diverse domains that extend beyond the traditional language and vision tasks these models are typically trained on. Specifically, our focus lies in areas such as Embodied
Externí odkaz:
http://arxiv.org/abs/2412.08442
How well are unimodal vision and language models aligned? Although prior work have approached answering this question, their assessment methods do not directly translate to how these models are used in practical vision-language tasks. In this paper,
Externí odkaz:
http://arxiv.org/abs/2412.04616
Autor:
Finnerty, Luke, Xin, Yinzi, Xuan, Jerry W., Inglis, Julie, Fitzgerald, Michael P, Agrawal, Shubh, Baker, Ashley, Blake, Geoffrey A., Calvin, Benjamin, Cetre, Sylvain, Delorme, Jacques-Robert, Doppman, Greg, Echeverri, Daniel, Horstman, Katelyn, Hsu, Chih-Chun, Jovanovic, Nemanja, Liberman, Joshua, López, Ronald A., Martin, Emily C., Mawet, Dimitri, Morris, Evan, Pezzato-Rovner, Jacklyn, Ruffio, Jean-Baptiste, Sappey, Ben, Schofield, Tobias, Skemer, Andrew, Venenciano, Taylor, Wallace, J. Kent, Wallack, Nicole L., Wang, Jason J., Wang, Ji
We present Keck/KPIC phase II $K$-band observations of the non-transiting hot Jupiter HD 143105 b. Using a cross-correlation approach, we make the first detection of the planetary atmosphere at $K_p = 185^{+11}_{-13}\rm km\ s^{-1}$ and an inferior co
Externí odkaz:
http://arxiv.org/abs/2412.04552
Effective communication is fundamental to any interaction, yet challenges arise when participants do not share a common language. Automatic translation systems offer a powerful solution to bridge language barriers in such scenarios, but they introduc
Externí odkaz:
http://arxiv.org/abs/2412.04205
The goal of mechanistic interpretability is discovering simpler, low-rank algorithms implemented by models. While we can compress activations into features, compressing nonlinear feature-maps -- like MLP layers -- is an open problem. In this work, we
Externí odkaz:
http://arxiv.org/abs/2412.03773
Autor:
Torne, Marcel, Jain, Arhan, Yuan, Jiayi, Macha, Vidaaranya, Ankile, Lars, Simeonov, Anthony, Agrawal, Pulkit, Gupta, Abhishek
Scaling robot learning requires data collection pipelines that scale favorably with human effort. In this work, we propose Crowdsourcing and Amortizing Human Effort for Real-to-Sim-to-Real(CASHER), a pipeline for scaling up data collection and learni
Externí odkaz:
http://arxiv.org/abs/2412.01770