Vishnu Naresh Boddeti

Affiliations

Michigan State University

papers

542

total citations

papers (16)

NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search

ECCV 2020arXiv

164

citations

Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing With Non-Learnable Primitives

CVPR 2023arXiv

citations

Utility-Fairness Trade-Offs and How to Find Them

CVPR 2024arXiv

citations

Generating Diverse 3D Reconstructions From a Single Occluded Face Image

CVPR 2022arXiv

citations

Do Learned Representations Respect Causal Relationships?

CVPR 2022arXiv

citations

Generative Zero-Shot Composed Image Retrieval

CVPR 2025

citations

SEAL: Semantic Attention Learning for Long Video Representation

CVPR 2025arXiv

citations

DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flows

CVPR 2025arXiv

citations

CoInD: Enabling Logical Compositions in Diffusion Models

ICLR 2025arXiv

citations

CryptoFace: End-to-End Encrypted Face Recognition

CVPR 2025arXiv

citations

PolyJuice Makes It Real: Black-Box, Universal Red Teaming for Synthetic Image Detectors

NEURIPS 2025arXiv

citations

ProTeGe: Untrimmed Pretraining for Video Temporal Grounding by Video Temporal Grounding

CVPR 2023

citations

Vishnu Naresh Boddeti

Affiliations

papers (16)

NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search

Spatially-Adaptive Image Restoration Using Distortion-Guided Networks

MUXConv: Information Multiplexing in Convolutional Neural Networks

Revisiting Residual Networks for Adversarial Robustness

FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs

Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing With Non-Learnable Primitives

Utility-Fairness Trade-Offs and How to Find Them

Generating Diverse 3D Reconstructions From a Single Occluded Face Image

Do Learned Representations Respect Causal Relationships?

Generative Zero-Shot Composed Image Retrieval

SEAL: Semantic Attention Learning for Long Video Representation

DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flows

CoInD: Enabling Logical Compositions in Diffusion Models

CryptoFace: End-to-End Encrypted Face Recognition

PolyJuice Makes It Real: Black-Box, Universal Red Teaming for Synthetic Image Detectors

ProTeGe: Untrimmed Pretraining for Video Temporal Grounding by Video Temporal Grounding

papers (16)

NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search

Spatially-Adaptive Image Restoration Using Distortion-Guided Networks

MUXConv: Information Multiplexing in Convolutional Neural Networks

Revisiting Residual Networks for Adversarial Robustness

FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs

Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing With Non-Learnable Primitives

Utility-Fairness Trade-Offs and How to Find Them

Generating Diverse 3D Reconstructions From a Single Occluded Face Image

Do Learned Representations Respect Causal Relationships?

Generative Zero-Shot Composed Image Retrieval

SEAL: Semantic Attention Learning for Long Video Representation

DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flows

CoInD: Enabling Logical Compositions in Diffusion Models

CryptoFace: End-to-End Encrypted Face Recognition

PolyJuice Makes It Real: Black-Box, Universal Red Teaming for Synthetic Image Detectors

ProTeGe: Untrimmed Pretraining for Video Temporal Grounding by Video Temporal Grounding