Vikas Singh

papers

444

total citations

papers (18)

MobileDets: Searching for Object Detection Architectures for Mobile Accelerators

CVPR 2021arXiv

150

citations

Deep Unlearning via Randomized Conditionally Independent Hessians

CVPR 2022arXiv

111

citations

On the Versatile Uses of Partial Distance Correlation in Deep Learning

ECCV 2022arXiv

citations

FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret

ECCV 2020arXiv

citations

Connecting What To Say With Where To Look by Modeling Human Attention Traces

CVPR 2021arXiv

citations

Generating Accurate Pseudo-Labels in Semi-Supervised Learning and Avoiding Overconfident Predictions via Hermite Polynomial Activations

CVPR 2020arXiv

citations

FrameQuant: Flexible Low-Bit Quantization for Transformers

ICML 2024arXiv

citations

An Online Riemannian PCA for Stochastic Canonical Correlation Analysis

NEURIPS 2021arXiv

citations

VCC: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens

NEURIPS 2023arXiv

citations

Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets

CVPR 2022arXiv

citations

Differentiable Optimization of Generalized Nondecomposable Functions using Linear Programs

NEURIPS 2021

citations

Implicit Representations via Operator Learning

ICML 2024

citations

FoGE: Fock Space inspired encoding for graph prompting

NEURIPS 2025arXiv

citations

Vikas Singh

papers (18)

MobileDets: Searching for Object Detection Architectures for Mobile Accelerators

Deep Unlearning via Randomized Conditionally Independent Hessians

On the Versatile Uses of Partial Distance Correlation in Deep Learning

FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret

Connecting What To Say With Where To Look by Modeling Human Attention Traces

Generating Accurate Pseudo-Labels in Semi-Supervised Learning and Avoiding Overconfident Predictions via Hermite Polynomial Activations

FrameQuant: Flexible Low-Bit Quantization for Transformers

An Online Riemannian PCA for Stochastic Canonical Correlation Analysis

VCC: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens

Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets

Simpler Certified Radius Maximization by Propagating Covariances

Pooling Image Datasets with Multiple Covariate Shift and Imbalance

IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers

Neural TMDlayer: Modeling Instantaneous Flow of Features via SDE Generators

Understanding Uncertainty Maps in Vision With Statistical Testing

Differentiable Optimization of Generalized Nondecomposable Functions using Linear Programs

Implicit Representations via Operator Learning

FoGE: Fock Space inspired encoding for graph prompting

papers (18)

MobileDets: Searching for Object Detection Architectures for Mobile Accelerators

Deep Unlearning via Randomized Conditionally Independent Hessians

On the Versatile Uses of Partial Distance Correlation in Deep Learning

FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret

Connecting What To Say With Where To Look by Modeling Human Attention Traces

Generating Accurate Pseudo-Labels in Semi-Supervised Learning and Avoiding Overconfident Predictions via Hermite Polynomial Activations

FrameQuant: Flexible Low-Bit Quantization for Transformers

An Online Riemannian PCA for Stochastic Canonical Correlation Analysis

VCC: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens

Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets

Simpler Certified Radius Maximization by Propagating Covariances

Pooling Image Datasets with Multiple Covariate Shift and Imbalance

IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers

Neural TMDlayer: Modeling Instantaneous Flow of Features via SDE Generators

Understanding Uncertainty Maps in Vision With Statistical Testing

Differentiable Optimization of Generalized Nondecomposable Functions using Linear Programs

Implicit Representations via Operator Learning

FoGE: Fock Space inspired encoding for graph prompting