AIConfPaper
← Search

Vishnu Suresh Lokhande

12 accepted papers

2026

Forget Less by Learning from Parents Through Hierarchical Relationships

Arjun Ramesh Kaushik, Naresh Kumar Devulapally, Vishnu Suresh Lokhande, Nalini K. Ratha, Venu Govindaraju
AAAI 2026technical

Custom Diffusion Models (CDMs) offer impressive capabilities for personalization in generative modeling, yet they remain vulnerable to catastrophic forgetting when learning new concepts sequentially. Existing approaches primarily focus on minimizing interference between concepts, often neglecting th

Cited by 0Source ↗PDF ↗Scholar ↗
2026

Interpretable Prompts made Edit-Friendly: Token-to-Token Similarity Reduction in dLLMs for Edit-Friendly Hard Prompt Inversion

Naresh Kumar Devulapally, Shruti Agarwal, Vishal Asnani, Vishnu Suresh Lokhande
CVPR 2026

Crafting prompts via Prompt Engineering that steer a model's internal representations toward specific and pre-defined outcomes can be time-consuming, often requiring multiple iterations. Hard Prompt Inversion offers a complementary workflow: start from a reference image and generate a prompt that co

Cited by 0Source ↗Scholar ↗
2026

ManifoldGD: Training-Free Hierarchical Manifold Guidance for Diffusion-Based Dataset Distillation

Ayush Roy, Wei-Yang Alex Lee, Rudrasis Chakraborty, Vishnu Suresh Lokhande
CVPR 2026

In recent times, large datasets hinder efficient model training while also containing redundant concepts. Dataset distillation aims to synthesize compact datasets that preserve the knowledge of large-scale training sets while drastically reducing storage and computation. Recent advances in diffusion

Cited by 0Source ↗Scholar ↗
2025

Your Text Encoder Can Be An Object-Level Watermarking Controller

Naresh Kumar Devulapally, Mingzhen Huang, Vishal Asnani, Shruti Agarwal, Siwei Lyu, Vishnu Suresh Lokhande
ICCV 2025poster

Invisible watermarking of AI-generated images can help with copyright protection, enabling detection and identification of AI-generated media. In this work, we present a novel approach to watermark images of T2I Latent Diffusion Models (LDMs). By only fine-tuning text token embeddings \mathcal W _*,…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

ParallelEdits: Efficient Multi-Aspect Text-Driven Image Editing with Attention Grouping

Mingzhen Huang, Jialing Cai, Shan Jia, Vishnu Suresh Lokhande, Siwei Lyu
NeurIPS 2024poster

Text-driven image synthesis has made significant advancements with the development of diffusion models, transforming how visual content is generated from text prompts. Despite these advances, text-driven image editing, a key area in computer graphics, faces unique challenges. A major challenge is ma…

Cited by 2Source ↗PDF ↗Scholar ↗
2024

Pooling Image Datasets with Multiple Covariate Shift and Imbalance

Sotirios Panagiotis Chytas, Vishnu Suresh Lokhande, Vikas Singh
ICLR 2024poster

Small sample sizes are common in many disciplines, which necessitates pooling roughly similar datasets across multiple sites/institutions to study weak but relevant associations between images and disease incidence. Such data often manifest shifts and imbalances in covariates (secondary non-ima…

Cited by 3Source ↗PDF ↗Scholar ↗
2023

Efficient Discrete Multi Marginal Optimal Transport Regularization

Ronak Mehta, Jeffery Kline, Vishnu Suresh Lokhande, Glenn Fung, Vikas Singh
ICLR 2023top-25%

Optimal transport has emerged as a powerful tool for a variety of problems in machine learning, and it is frequently used to enforce distributional constraints. In this context, existing methods often use either a Wasserstein metric, or else they apply concurrent barycenter approaches when more than…

Cited by 6Source ↗PDF ↗Scholar ↗
2022

Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets

Vishnu Suresh Lokhande, Rudrasis Chakraborty, Sathya N. Ravi, Vikas Singh
CVPR 2022poster

Pooling multiple neuroimaging datasets across institutions often enables significant improvements in statistical power when evaluating associations (e.g., between risk factors and disease outcomes) that would otherwise be too weak to detect. When there is only a single source of variability (e.g.…

Cited by 5PDF ↗code ↗Scholar ↗
2021

Graph reparameterizations for enabling 1000+ Monte Carlo iterations in Bayesian deep neural networks

Jurijs Nazarovs, Ronak R. Mehta, Vishnu Suresh Lokhande, Vikas Singh
UAI 2021poster

Uncertainty estimation in deep models is essential in many real-world applications and has benefited from developments over the last several years. Recent evidence suggests that existing solutions dependent on simple Gaussian formulations may not be sufficient. However, moving to other distributions…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2021

Learning Invariant Representations using Inverse Contrastive Loss

Aditya Kumar Akash, Vishnu Suresh Lokhande, Sathya N. Ravi, Vikas Singh
AAAI 2021technical

Learning invariant representations is a critical first step in a number of machine learning tasks. A common approach is given by the so-called information bottleneck principle in which an application dependent function of mutual information is carefully chosen and optimized. Unfortunately, in practi…

Cited by 9Source ↗PDF ↗code ↗Scholar ↗
2020

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

Vishnu Suresh Lokhande, Aditya Kumar Akash, Sathya N. Ravi, Vikas Singh
ECCV 2020poster

Algorithmic decision making based on computer vision and machine learning technologies continue to permeate our lives. But issues related to biases of these models and the extent to which they treat certain segments of the population unfairly, have led to concern in the general public. It is now acc…

Cited by 39Source ↗PDF ↗code ↗Scholar ↗
2020

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

Vishnu Suresh Lokhande, Songwong Tasneeyapant, Abhay Venkatesh, Sathya N. Ravi, Vikas Singh
CVPR 2020poster

Rectified Linear Units (ReLUs) are among the most widely used activation function in a broad variety of tasks in vision. Recent theoretical results suggest that despite their excellent practical performance, in various cases, a substitution with basis expansions (e.g., polynomials) can yield signifi…

Cited by 42PDF ↗code ↗Scholar ↗