ACID Test: A Benchmark for Cultural Safety and Alignment in LALMs
2026Dutta, Jain, Ranjan, Vatsa, Singh
AAAI
Publications
Research Publications
Research from Srijan:CoE published at top-tier venues including ICML, AAAI, IJCAI, ECCV, ICCV, MICCAI, ISBI, Interspeech, ICASSP, and IEEE Transactions. Our work spans responsible generative AI, deepfake detection and anti-spoofing, medical image synthesis and diagnosis, multimodal language models, fairness and bias mitigation, aggressive behavior forecasting, and watermarking for synthetic media authenticity.
IndicAG: An Explainable Agentic Framework for Indic-Multilingual Multidimensional Aggression Detection
2026Mane, Sharma, Kundu
WWW
MPD-CXR: Diffusion Model With Multi-Perspective Semantic Conditioning For Chest X-Ray Synthesis From Report
2026Kabadi, Paul
ISBI
QHDM: Quantum Hidden Diffusion Watermarking with Variational Quantum Bottleneck
2026Soni, Vatsa, Singh
IEEE IJCB
Hide Identity, Preserve Pathology: Diffusion-Based Anonymization for Chest X-rays
2026Akhter, Dosi, Vatsa, Singh
AAAI Bridge Program on AI for Medicine and Healthcare
When Sketches Are Not Enough: MLLM-Guided Semantic Enrichment for Sketch-to-Face Recognition
2026Chiranjeev, Dosi, Dutta, Vatsa, Singh
IJCB
Semantically Aligned Gradient-Driven Context-Preserving Image Editing
2026Chiranjeev, Dosi, Vatsa, Singh
ECCV
HSMamba: Unified Cross set Attribution and Open-set Detection of Synthetic speech via shared Mamba Embeddings
2026Nishant, Ranjan, Vatsa, Singh
IJCB
NutriScreener: Retrieval-Augmented Multi-Pose Graph Attention Network for Malnourishment Screening
2026Khan, Vatsa, Singh, Singh
Proceedings of AAAI
Genm: The Generative Machine Unlearning Challenge
2025Thakral, Pathak, Glaser, Hassner, Garcia-Olano, Masi, Singh, Vatsa
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops
ILLUSION: Unveiling Truth with a Comprehensive Multi-Modal, Multi-Lingual Deepfake Dataset
2025Thakral, Ranjan, Singh, Jain, Vatsa, Singh
ICLR
Words Over Pixels? Rethinking Vision in Multimodal Large Language Models
2025Jain, Vatsa, Singh
IJCAI
Non-Invasive TB Detection using Acoustic and Semantic Features from Cough Sounds
2025Akhter, Ranjan, Dutta, Singh, Vatsa
MICCAI
SHIELD: A Self-supervised, Silicosis-focused Hierarchical Imaging framework for occupational Lung disease Diagnosis
2025Akhter, Ranjan, Singh, Vatsa
IJCAI (AI and Social Good)
TSGAN: Temporal Social Graph Attention Network for Aggressive Behavior Forecasting
2025Mane, Kundu, Sharma
AAAI
Can RAG-Driven Enhancements Amplify Audio LLMs for Low-Resource Languages?
2025Ranjan, Dutta, Vatsa, Singh
ICASSP
SynHate: Detecting Hate Speech in Synthetic Deepfake Audio
2025Ranjan, Pipariya, Vatsa, Singh
Interspeech
Can Quantized Audio Language Models Perform Zero-Shot Spoofing Detection?
2025Dutta, Ranjan, Sathvik, Vatsa, Singh
Interspeech
Multimodal Zero-Shot Framework for Deepfake Hate Speech Detection in Low-Resource Languages
2025Ranjan, Ayinala, Vatsa, Singh
Interspeech
LitMAS: A Lightweight and Generalized Multi-Modal Anti-Spoofing Framework for Biometric Security
2025Gorthi, Thakral, Ranjan, Singh, Vatsa
Interspeech
FLICSNet: Cooking Action Segmentation from Video
2025Khanna, Chattopadhyay, Kundu
MMFOOD workshop, ACM MM
ExaCraft: Dynamic Learning Context Adaptation for Personalized Educational Examples
2025Chatterjee, Kundu
CODS
Erasing Shadows: Residual-Guided Watermark Removal Via Reverse Diffusion
2025Soni, Saxena, Vatsa, Singh
IEEE IJCB
Harmonizing geometry and uncertainty: Diffusion with hyperspheres
2025Dosi, Chiranjeev, Thakral, Vatsa, Singh
ICML
Beyond shadows and light: Odyssey of face recognition for social good
2025Chiranjeev, Dosi, Agarwal, Chaudhary, Pant, Vatsa, Singh
Computer Vision and Image Understanding
Multimodal Dual-Stage Feature Refinement for Robust Skin Lesion Classification
2025Khurshid, Singh, Vatsa
Scientific Reports
LearnDiff: MRI Image Super-Resolution Using a Diffusion Model with Learnable Noise
2025Goswami, Gupta, Paul
Computerized Medical Imaging and Graphics
DecordFace: A Framework for Degraded and Corrupted Face Recognition
2025Mittal, Dey Chowdhury, Vatsa, Singh
Journal of Data-centric Machine Learning Research
Genμ: The Generative Machine Unlearning Challenge
2025Thakral, Pathak, Glaser, Hassner, Garcia-Olano, Masi, Singh, Vatsa
IEEE/CVF International Conference on Computer Vision Workshops (ICCV)
Residual-Guided Watermark Removal via Latent Noise Injection & Reverse Diffusion
2025Soni, Saxena, Singh, Vatsa
IEEE International Joint Conference on Biometrics (IJCB)
Can RAG-Driven Enhancements Amplify Audio LLMs for Low-Resource Languages?
2025Dutta, Ranjan, Jain, Singh, Vatsa
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Cross-Aligned Fusion for Multimodal Understanding
2025Rajora, Gupta, Kundu
Proceedings of the Winter Conference on Applications of Computer Vision (WACV)
You are what your feeds makes you: A study of user aggressive behaviour on Twitter
2025Mane, Kundu, Sharma
Applied Intelligence
EA2N: Evidence-Based AMR Attention Network for Fake News Detection
2025Gupta, Rajora, Kundu
IEEE Transactions on Knowledge and Data Engineering
A Survey on Online Aggression: Content Detection and Behavioural Analysis on Social Media Platforms
2025Mane, Kundu, Sharma
ACM Computing Surveys
Unified Framework for Complex Graph-Data: Introducing the Hybrid Layered Network Model
2024Chatterjee, Kundu
GraphViz2Vec: A Structure-aware Feature Generation Model to Improve Classification in GNNs
2024Chatterjee, Kundu
FakEDAMR: Fake News Detection Using Abstract Meaning Representation Network
2024Gupta, Yadav, Kundu, Sankepally
Complex Networks & Their Applications XII
CrisisKAN: Knowledge-Infused and Explainable Multimodal Attention Network for Crisis Event Classification
2024Gupta, Saini, Kundu, Das
European Conference on Information Retrieval (ECIR)
Cyberbully: Aggressive Tweets, Bully and Bully Target Profiling from Multilingual Indian Tweets
2023Karan, Kundu
PReMI