Zobrazeno 1 - 10
of 5 657
pro vyhledávání: '"A. Vahdat"'
Input aggregation is a simple technique used by state-of-the-art LiDAR 3D object detectors to improve detection. However, increasing aggregation is known to have diminishing returns and even performance degradation, due to objects responding differen
Externí odkaz:
http://arxiv.org/abs/2411.13186
Autor:
Lee, Seul, Kreis, Karsten, Veccham, Srimukh Prasad, Liu, Meng, Reidenbach, Danny, Paliwal, Saee, Vahdat, Arash, Nie, Weili
Fragment-based drug discovery, in which molecular fragments are assembled into new molecules with desirable biochemical properties, has achieved great success. However, many fragment-based molecule generation methods show limited exploration beyond t
Externí odkaz:
http://arxiv.org/abs/2411.12078
Autor:
Xu, Minkai, Geffner, Tomas, Kreis, Karsten, Nie, Weili, Xu, Yilun, Leskovec, Jure, Ermon, Stefano, Vahdat, Arash
Despite remarkable progress in autoregressive language models, alternative generative paradigms beyond left-to-right generation are still being actively explored. Discrete diffusion models, with the capacity for parallel generation, have recently eme
Externí odkaz:
http://arxiv.org/abs/2410.21357
In recent years, the integration of advanced imaging techniques and deep learning methods has significantly advanced computer-aided diagnosis (CAD) systems for breast cancer detection and classification. Transformers, which have shown great promise i
Externí odkaz:
http://arxiv.org/abs/2410.19166
Autor:
Daras, Giannis, Nie, Weili, Kreis, Karsten, Dimakis, Alex, Mardani, Morteza, Kovachki, Nikola Borislavov, Vahdat, Arash
Using image models naively for solving inverse video problems often suffers from flickering, texture-sticking, and temporal inconsistency in generated videos. To tackle these problems, in this paper, we view frames as continuous functions in the 2D s
Externí odkaz:
http://arxiv.org/abs/2410.16152
Autor:
Lee, Sangyun, Xu, Yilun, Geffner, Tomas, Fanti, Giulia, Kreis, Karsten, Vahdat, Arash, Nie, Weili
Consistency models have recently been introduced to accelerate sampling from diffusion models by directly predicting the solution (i.e., data) of the probability flow ODE (PF ODE) from initial noise. However, the training of consistency models requir
Externí odkaz:
http://arxiv.org/abs/2410.14895
Autor:
Pandey, Kushagra, Pathak, Jaideep, Xu, Yilun, Mandt, Stephan, Pritchard, Michael, Vahdat, Arash, Mardani, Morteza
Diffusion models achieve state-of-the-art generation quality across many applications, but their ability to capture rare or extreme events in heavy-tailed distributions remains unclear. In this work, we show that traditional diffusion and flow-matchi
Externí odkaz:
http://arxiv.org/abs/2410.14171
Autor:
Fotiadis, Stathi, Brenowitz, Noah, Geffner, Tomas, Cohen, Yair, Pritchard, Michael, Vahdat, Arash, Mardani, Morteza
Conditioning diffusion and flow models have proven effective for super-resolving small-scale details in natural images.However, in physical sciences such as weather, super-resolving small-scale details poses significant challenges due to: (i) misalig
Externí odkaz:
http://arxiv.org/abs/2410.19814
Text-to-image (T2I) diffusion models have become prominent tools for generating high-fidelity images from text prompts. However, when trained on unfiltered internet data, these models can produce unsafe, incorrect, or stylistically undesirable images
Externí odkaz:
http://arxiv.org/abs/2409.06493
Autor:
Pathak, Jaideep, Cohen, Yair, Garg, Piyush, Harrington, Peter, Brenowitz, Noah, Durran, Dale, Mardani, Morteza, Vahdat, Arash, Xu, Shaoming, Kashinath, Karthik, Pritchard, Michael
Storm-scale convection-allowing models (CAMs) are an important tool for predicting the evolution of thunderstorms and mesoscale convective systems that result in damaging extreme weather. By explicitly resolving convective dynamics within the atmosph
Externí odkaz:
http://arxiv.org/abs/2408.10958