Abhay Yadav — accepted AI-conference papers

2026

WRIVINDER: Towards Spatial Intelligence for Geo-locating Ground Images onto Satellite Imagery

Chandrakanth Gudavalli, Tajuddin Manhar Mohammed, Abhay Yadav, Ananth Vishnu Bhaskar, Hardik Prajapati, Cheng Peng +3

CVPR 2026

Aligning ground-level imagery with geo-registered satellite maps is crucial for mapping, navigation, and situational awareness, yet remains challenging under large viewpoint gaps or when GPS is unreliable. We introduce Wrivinder, a zero-shot, geometry-driven framework that aggregates multiple ground

Cited by 0 Source ↗code ↗Scholar ↗

2020

On the Similarity between the Laplace and Neural Tangent Kernels

Amnon Geifman, Abhay Yadav, Yoni Kasten, Meirav Galun, David Jacobs, Basri Ronen

NeurIPS 2020poster

Recent theoretical work has shown that massively overparameterized neural networks are equivalent to kernel regressors that use Neural Tangent Kernels (NTKs). Experiments show that these kernel methods perform similarly to real neural networks. Here we show that NTK for fully connected networks wi…

Cited by 117 Source ↗PDF ↗Scholar ↗

2018

Stabilizing Adversarial Nets with Prediction Methods

Abhay Yadav, Sohil Shah, Zheng Xu, David Jacobs, Tom Goldstein

ICLR 2018poster

Adversarial neural networks solve many important problems in data science, but are notoriously difficult to train. These difficulties come from the fact that optimal weights for adversarial nets correspond to saddle points, and not minimizers, of the loss function. The alternating stochastic gradien…

Cited by 121 Source ↗PDF ↗code ↗Scholar ↗

2017

Automated Inference with Adaptive Batches

Soham De, Abhay Yadav, David Jacobs, Tom Goldstein

AISTATS 2017poster

Classical stochastic gradient methods for optimization rely on noisy gradient approximations that become progressively less accurate as iterates approach a solution. The large noise and small signal in the resulting gradients makes it difficult to use them for adaptive stepsize selection and automat…

Cited by 112 Source ↗PDF ↗Scholar ↗