Industry
E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings
Yue Wang, Ziyu Jiang, Xiaohan Chen, Pengfei Xu, Yang Zhao, Yingyan Lin, Zhangyang Wang
Hence, manyefforts havebeen made towards efficient CNNinference inresource-constrained platforms. The increasing penetration of intelligent sensors has revolutionized how Internet of Things (IoT) works.
factor of 1000, opening the road for gigapixel image generation at no additional cost. Our cascading method uses the image generated at the lowest resolution as a
In this work, we introduce Pixelsmith, a zero-shot text-to-image generative framework to sample images at higher-resolutions with a single GPU.
Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift
We compare the algorithms on a wide range of large, convolutional and transformer-based neural network architectures.
Mixture Matrix Completion
Neural Information Processing Systems http://nips.cc/
Are sample means in multi-armed bandits positively or negatively biased?
Jaehyeok Shin, Aaditya Ramdas, Alessandro Rinaldo
Neural Information Processing Systems http://nips.cc/
Battle of the Backbones
Diffusion backbone, across a diverse set of computer vision tasks ranging from classification to object detection to OOD generalization and more.
Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Suffices
Santosh Vempala, Andre Wibisono
See Theorem 2 in Section 3.1 formoredetail.
Border on the brink as cartel drones force US to act after years of paralysis
FAA closes El Paso airspace citing cartel drone incursions near military facilities, revealing over 60,000 cartel drone flights along the border in 2024.