Vikas Singh

Learning from Biased and Costly Data Sources: Minimax-optimal Data Collection under a Budget (extended abstract) COLT 2026 SimpleTM: A Simple Baseline for Multivariate Time Series Forecasting ICLR 2025 FrameQuant: Flexible Low-Bit Quantization for Transformers ICML 2024 Implicit Representations via Operator Learning ICML 2024 IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers ICML 2024 Pooling Image Datasets with Multiple Covariate Shift and Imbalance ICLR 2024 Understanding Multi-compositional learning in Vision and Language models via Category Theory ECCV 2024 Controlled Differential Equations on Long Sequences via Non-standard Wavelets ICML 2023 Efficient Discrete Multi Marginal Optimal Transport Regularization ICLR 2023 LookupFFN: Making Transformers Compute-lite for CPU inference ICML 2023 VCC: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens NeurIPS 2023 Deep Unlearning via Randomized Conditionally Independent Hessians CVPR 2022 Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets CVPR 2022 Forward Operator Estimation in Generative Models with Kernel Transfer Operators ICML 2022 Multi Resolution Analysis (MRA) for Approximate Self-Attention ICML 2022 On the Versatile Uses of Partial Distance Correlation in Deep Learning ECCV 2022 Understanding Uncertainty Maps in Vision With Statistical Testing CVPR 2022 An Online Riemannian PCA for Stochastic Canonical Correlation Analysis NeurIPS 2021 A variational approximation for analyzing the dynamics of panel data UAI 2021 Connecting What To Say With Where To Look by Modeling Human Attention Traces CVPR 2021 Differentiable Optimization of Generalized Nondecomposable Functions using Linear Programs NeurIPS 2021 Flow-based Generative Models for Learning Manifold to Manifold Mappings AAAI 2021 Graph reparameterizations for enabling 1000+ Monte Carlo iterations in Bayesian deep neural networks UAI 2021 Learning Invariant Representations using Inverse Contrastive Loss AAAI 2021 MobileDets: Searching for Object Detection Architectures for Mobile Accelerators CVPR 2021 Neural TMDlayer: Modeling Instantaneous Flow of Features via SDE Generators ICCV 2021 Nyströmformer: A Nyström-based Algorithm for Approximating Self-Attention AAAI 2021 Physarum Powered Differentiable Linear Programming Layers and Applications AAAI 2021 Simpler Certified Radius Maximization by Propagating Covariances CVPR 2021 You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling ICML 2021 FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret ECCV 2020 Generating Accurate Pseudo-Labels in Semi-Supervised Learning and Avoiding Overconfident Predictions via Hermite Polynomial Activations CVPR 2020 Optimizing Nondecomposable Data Dependent Regularizers via Lagrangian Reparameterization Offers Significant Performance and Efficiency Gains AAAI 2020 Adaptive Activation Thresholding: Dynamic Routing Type Behavior for Interpretability in Convolutional Neural Networks ICCV 2019 Conditional Recurrent Flow: Conditional Generation of Longitudinal Samples With Applications to Neuroimaging ICCV 2019 Dilated Convolutional Neural Networks for Sequential Manifold-Valued Data ICCV 2019 DUAL-GLOW: Conditional Flow-Based Generative Model for Modality Transfer ICCV 2019 Explicitly Imposing Constraints in Deep Networks via Conditional Gradients Gives Improved Generalization and Faster Convergence AAAI 2019 Mixed Effects Neural Networks (MeNets) With Applications to Gaze Estimation CVPR 2019 Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help? ICCV 2019 Sampling-free Uncertainty Estimation in Gated Recurrent Units with Applications to Normative Modeling in Neuroimaging UAI 2019 Scaling Recurrent Models via Orthogonal Approximations in Tensor Trains ICCV 2019 A Biresolution Spectral Framework for Product Quantization CVPR 2018 A Statistical Recurrent Model on the Manifold of Symmetric Positive Definite Matrices NeurIPS 2018 Efficient Relative Attribute Learning using Graph Neural Networks ECCV 2018 Tensorize, Factorize and Regularize: Robust Visual Relationship Learning CVPR 2018 A Geometric Framework for Statistical Analysis of Trajectories With Distinct Temporal Spans ICCV 2017 Filter Flow Made Practical: Massively Parallel and Lock-Free CVPR 2017 Online Graph Completion: Multivariate Signal Recovery in Computer Vision CVPR 2017 Riemannian Nonlinear Mixed Effects Models: Analyzing Longitudinal Deformations in Neuroimaging CVPR 2017 The Incremental Multiresolution Matrix Factorization Algorithm CVPR 2017 When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests, ℓ_2-consistency and Neuroscience Applications ICML 2017 Coupled Harmonic Bases for Longitudinal Characterization of Brain Networks CVPR 2016 Experimental Design on a Budget for Sparse Linear Models and Applications ICML 2016 Hypothesis Testing in Unsupervised Domain Adaptation with Applications in Alzheimer's Disease NeurIPS 2016 Latent Variable Graphical Model Selection Using Harmonic Analysis: Applications to the Human Connectome Project (HCP) CVPR 2016 An NMF Perspective on Binary Hashing ICCV 2015 A Projection Free Method for Generalized Eigenvalue Problem With a Nonsmooth Regularizer ICCV 2015 Gaze-Enabled Egocentric Video Summarization via Constrained Submodular Maximization CVPR 2015 Interpolation on the Manifold of K Component GMMs ICCV 2015 Manifold-valued Dirichlet Processes ICML 2015 On Statistical Analysis of Neuroimages With Imperfect Registration ICCV 2015 SnFFT: A Julia Toolkit for Fourier Analysis of Functions over Permutations JMLR 2015 Statistical Inference Models for Image Datasets With Systematic Variations CVPR 2015 Multivariate General Linear Models (MGLM) on Riemannian Manifolds with Applications to Statistical Analysis of Diffusion Weighted Images CVPR 2014 Permutation Diffusion Maps (PDM) with Application to the Image Association Problem in Computer Vision NeurIPS 2014 GOSUS: Grassmannian Online Subspace Updates with Structured-Sparsity ICCV 2013 Incorporating User Interaction and Topological Constraints within Contour Completion via Discrete Calculus CVPR 2013 Multi-resolution Shape Analysis via Non-Euclidean Wavelets: Applications to Mesh Segmentation and Surface Alignment Problems CVPR 2013 Solving the multi-way matching problem by permutation synchronization NeurIPS 2013 Speeding up Permutation Testing in Neuroimaging NeurIPS 2013 Q-MKL: Matrix-induced Regularization in Multi-Kernel Learning with Applications to Neuroimaging NeurIPS 2012 Wavelet based multi-scale shape features on arbitrary surfaces for cortical thickness discrimination NeurIPS 2012 Epitome driven 3-D Diffusion Tensor image segmentation: on extracting specific structures NeurIPS 2010 Ensemble Clustering using Semidefinite Programming NeurIPS 2007