3 citations · 8 across the 29 of their papers we have counts for
31 papers
Adaptive Adversarial Augmentation for Controllable Face Synthesis
Saransh Suri, Shivang Agarwal, Mayank Vatsa +1
Synthetic data provides a scalable alternative to real-world datasets for training face recognition models, particularly under challenging conditions such as low resolution, occlus…
Semantically Aligned Gradient-Driven Context-Preserving Image Editing
Chiranjeev Chiranjeev, Muskan Dosi, Mayank Vatsa +1
Instruction-guided image editing has a training-time blind spot. Generative editors are never required to semantically verify whether their outputs actually satisfy the instruction…
NumBench: Diagnosing Counting Failures in Text-to-Image Models
Sandeep Wadhwa, Mayank Vatsa, Richa Singh +2
Text-to-image (T2I) models often generate the wrong number of objects, yet existing benchmarks are too small or weakly controlled to explain why. We introduce \textbf{NumBench}, a…
CricRAG: Retrieval Augmented Vision-Language Models for Personalized Cricket Coaching
Agamdeep Singh, Sujit PB, Mayank Vatsa
Vision-Language Models (VLMs) offer promising capabilities for automated sports coaching but face a fundamental limitation: they implicitly compare against professional standards,…
Latent Performance Profiling of Large Language Models
Tanmoy Chakraborty, Ayan Sengupta, Suparna Bhattacharya +7
Large language models (LLMs) frequently achieve impressive scores on standardized benchmarks, yet accuracy alone offers a limited view of their capabilities. Evaluating open-source…
Unbiased Model Prediction Without Using Protected Attribute Information
Puspita Majumdar, Surbhi Mittal, Saheb Chhabra +2
The problem of bias persists in the deep learning community as models continue to provide disparate performance across different demographic subgroups. Therefore, several algorithm…
DivAS: Interactive 3D Segmentation by Depth-Weighted Voxel Aggregation
Ayush Pande, Mayank Vatsa
Interactive 3D segmentation of a reconstructed scene should not require a representation-specific optimization loop. We observe that the recipe for lifting 2D foundation-model mask…
NutriScreener: Retrieval-Augmented Multi-Pose Graph Attention Network for Malnourishment Screening
Misaal Khan, Mayank Vatsa, Kuldeep Singh +1
Child malnutrition remains a global crisis, yet existing screening methods are laborious and poorly scalable, hindering early intervention. In this work, we present NutriScreener,…
Right Looks, Wrong Reasons: Compositional Fidelity in Text-to-Image Generation
Mayank Vatsa, Aparna Bharati, Richa Singh
The architectural blueprint of today's leading text-to-image models contains a fundamental flaw: an inability to handle logical composition. This survey investigates this breakdown…
TAIGen: Training-Free Adversarial Image Generation via Diffusion Models
Susim Roy, Anubhooti Jain, Mayank Vatsa +1
Adversarial attacks from generative models often produce low-quality images and require substantial computational resources. Diffusion models, though capable of high-quality genera…
Quantum-Inspired Audio Unlearning: Towards Privacy-Preserving Voice Biometrics
Shreyansh Pathak, Sonu Shreshtha, Richa Singh +1
The widespread adoption of voice-enabled authentication and audio biometric systems have significantly increased privacy vulnerabilities associated with sensitive speech data. Comp…
Harmonizing Geometry and Uncertainty: Diffusion with Hyperspheres
Muskan Dosi, Chiranjeev Chiranjeev, Kartik Thakral +2
Do contemporary diffusion models preserve the class geometry of hyperspherical data? Standard diffusion models rely on isotropic Gaussian noise in the forward process, inherently f…
Multimodal Zero-Shot Framework for Deepfake Hate Speech Detection in Low-Resource Languages
Rishabh Ranjan, Likhith Ayinala, Mayank Vatsa +1
This paper introduces a novel multimodal framework for hate speech detection in deepfake audio, excelling even in zero-shot scenarios. Unlike previous approaches, our method uses c…
SynHate: Detecting Hate Speech in Synthetic Deepfake Audio
Rishabh Ranjan, Kishan Pipariya, Mayank Vatsa +1
The rise of deepfake audio and hate speech, powered by advanced text-to-speech, threatens online safety. We present SynHate, the first multilingual dataset for detecting hate speec…
LitMAS: A Lightweight and Generalized Multi-Modal Anti-Spoofing Framework for Biometric Security
Nidheesh Gorthi, Kartik Thakral, Rishabh Ranjan +2
Biometric authentication systems are increasingly being deployed in critical applications, but they remain susceptible to spoofing. Since most of the research efforts focus on moda…
Can Quantized Audio Language Models Perform Zero-Shot Spoofing Detection?
Bikash Dutta, Rishabh Ranjan, Shyam Sathvik +2
Quantization is essential for deploying large audio language models (LALMs) efficiently in resource-constrained environments. However, its impact on complex tasks, such as zero-sho…
Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models
Kartik Thakral, Tamar Glaser, Tal Hassner +2
Existing unlearning algorithms in text-to-image generative models often fail to preserve the knowledge of semantically related concepts when removing specific target concepts: a ch…
Continual Unlearning for Foundational Text-to-Image Models without Generalization Erosion
Kartik Thakral, Tamar Glaser, Tal Hassner +2
How can we effectively unlearn selected concepts from pre-trained generative foundation models without resorting to extensive retraining? This research introduces `continual unlear…
From No to Know: Taxonomy, Challenges, and Opportunities for Negation Understanding in Multimodal Foundation Models
Mayank Vatsa, Aparna Bharati, Surbhi Mittal +1
Negation, a linguistic construct conveying absence, denial, or contradiction, poses significant challenges for multilingual multimodal foundation models. These models excel in task…
Enhancing Quantum Diffusion Models with Pairwise Bell State Entanglement
Shivalee Shah, Mayank Vatsa
This paper introduces a novel quantum diffusion model designed for Noisy Intermediate-Scale Quantum (NISQ) devices. Unlike previous methods, this model efficiently processes higher…
Poze: Sports Technique Feedback under Data Constraints
Agamdeep Singh, Sujit PB, Mayank Vatsa
Access to expert coaching is essential for developing technique in sports, yet economic barriers often place it out of reach for many enthusiasts. To bridge this gap, we introduce…
Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noises
Anubhooti Jain, Susim Roy, Kwanit Gupta +2
Deep learning models, such as those used for face recognition and attribute prediction, are susceptible to manipulations like adversarial noise and unintentional noise, including G…
HyperSpaceX: Radial and Angular Exploration of HyperSpherical Dimensions
Chiranjeev Chiranjeev, Muskan Dosi, Kartik Thakral +2
Traditional deep learning models rely on methods such as softmax cross-entropy and ArcFace loss for tasks like classification and face recognition. These methods mainly explore ang…
Navigating Text-to-Image Generative Bias across Indic Languages
Surbhi Mittal, Arnav Sudan, Mayank Vatsa +3
This research investigates biases in text-to-image (TTI) models for the Indic languages widely spoken across India. It evaluates and compares the generative performance and cultura…