Publications

Mansi Gupta, Nikhar Waghela, Sarthak Gupta, Shourya Goel, Sanjif Shanmugavelu (2025). Pruning as a Defense: Reducing Memorization in Large Language Models. ICLR Workshop.

Preprint PDF

Abhinav Kumar, Adesh Gupta, Shivank Garg, Mansi Gupta (2025). Positional Embeddings in Transformer Models: Evolution from Text to Vision Domains. ICLR Blogpost.

Preprint

Amitoj Miglani, Shweta Singh, Vidit Aggarwal (2025). Analysing The Spectral Biases in Generative Models. ICLR Blogpost.

Preprint

Ayush Singh, Rajdeep Aher, Shivank Garg (2024). LoRA-Mini : Adaptation Matrices Decomposition and Selective Training. AAAI CoLoRAI Workshop.

Preprint PDF

Pratham Singla, Ayush Singh, Adesh Gupta, Shivank Garg (2024). Adaptive Urban Planning: A Hybrid Framework for Balanced City Development. AAAI-25 Workshop on Urban Planning.

Preprint PDF

Aakash Gupta, Siddharth Gupta (2024). Model Merging using Geometric Median of Task Vectors. NeurIPS 2024.

Preprint PDF Code

Shivank Garg, Manyana Tiwari (2024). Attention Shift: Steering AI Away from Unsafe Content. NeurIPS'24, RBFM Workshop.

Preprint PDF Code

Atharv Mittal (2024). Low Rank Adaptations for Effective Machine Unlearning. AAAI 2025 CoLoRAI Workshop.

Preprint PDF

Atharv Mittal (2024). LoRA Unlearns More and Retains More. AAAI-25 Student Abstract.

Preprint PDF Code

Abhinav Kumar, Pratham Singla, Aayan Yadav (2024). StegaVision: Enhancing Steganography with Attention Mechanism. AAAI-25 Student Abstract.

Preprint PDF

Vansh Agrawal, Pratham Singla, Amitoj Singh Miglani, Shivank Garg, Ayush Mangal (2024). Give me a hint: Can LLMs take a hint to solve math problems?. NeurIPS MATH-AI 24.

Preprint PDF Code

Shivank Garg, Manyana Tiwari (2024). Unmasking the Veil: An Investigation into Concept Ablation for Privacy and Copyright Protection in Images. TMLR'24/NeurIPS'24/MLRC'24.

Preprint PDF Code

Shweta Singh, Aayan Yadav, Jitesh Jain, Humphrey Shi, Justin Johnson, Karan Desai (2024). Benchmarking Object Detectors with COCO: A New Path Forward. ECCV 24.

Preprint PDF Code Poster

Abhishek Sinha, Himanshi Tibrewal, Mansi Gupta, Nikhar Waghela, Shivank Garg (2024). Confidence Is All You Need for MI Attacks. AAAI 24.

Preprint PDF Code Poster

Jitesh Jain, ✱Jiachen Li, ✱MangTik Chiu, Ali Hassani, Nikita Orlov, Humphrey Shi (2023). OneFormer: One Transformer to Rule Universal Image Segmentation. CVPR 23.

Preprint PDF Code Poster Video

✱Jitesh Jain, ✱Yuqian Zhou, Ning Yu, Humphrey Shi (2022). Keys to Better Image Inpainting: Structure and Texture Go Hand in Hand. WACV'23.

Preprint PDF Code

Divyam Goel, Raksha Sharma (2022). Leveraging Dependency Grammar for Fine-Grained Offensive Language Detection using Graph Convolutional Networks. SocialNLP @ NAACL 2022.

Preprint PDF

Divyam Goel, Kunal Pratap Singh, Jonghyun Choi (2022). Language Guided Meta-Control for Embodied Instruction Following. Workshop CVPR'22.

PDF

Divyam Goel, Ramansh Grover, Fatemeh H Fard (2022). On The Cross-Modal Transfer from Natural Language to Code through Adapter Modules. ICPC'22.

Preprint PDF

Jun Chen, Aniket Agarwal, Sherif Abdelkarim, Deyao Zhu, Mohamed Elhoseiny (2022). RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition. CVPR'22.

Preprint PDF Code

Jitesh Jain, Anukriti Singh, Nikita Orlov, Zilong Huang, Jiachen Li, Steven Walton, Humphrey Shi (2021). SeMask: Semantically Masked Transformers for Semantic Segmentation. Under Review.

Preprint PDF Code

Aniket Agarwal*, Sherif Abdelkarim*, Panos Achlioptas, Jun Chen, Jiaji Huang, Boyang Li, Kenneth Church, Mohamed Elhoseiny (2021). Exploring Long tail Visual Relationship Recognition with Large Vocabulary. ICCV21.

Preprint PDF Code

Ramit Sawhney, Puneet Mathur, Ayush Mangal*, Piyush Khanna, Rajiv Ratn Shah, Roger Zimmermann (2020). Multimodal Multi-Task Financial Risk Forecasting. MM'20.

PDF Video

✱Ayush Mangal, ✱Jitesh Jain, ✱Keerat Kaur Gullani, ✱Omkar Bhalero (2020). DEAP Cache: Deep Eviction Admission and Prefetching for Cache. Under Review.

Preprint Code

Raghav Awasthi, Keerat Kaur Guliani*, Arshita Bhatt, Mehrab Singh Gill, Aditya Nagori, Ponnurangam Kumaraguru, Tavpritesh Sethi (2020). VacSIM: Learning Effective Strategies for COVID-19 Vaccine Distribution using Reinforcement Learning. Under Review.

PDF

Aditya Nagori, Raghav Awasthi, Vineet Joshi, Suryatej Reddy Vyalla, Akhil Jarodia, Chandan Gupta, Amogh Gulati, Harsh Bandhey, Keerat Kaur Guliani*, Mehrab Singh Gill, Ponnurangam Kumaraguru, Tavpritesh Sethi (2020). Less Wrong COVID-19 Projections With Interactive Assumptions. Under Review.

PDF

Aniket Agarwal*, Ayush Mangal*, Vipul* (2020). Visual Relationship Detection using Scene Graphs: A Survey.

Preprint

Ashutosh Chaubey*, Nikhil Agrawal*, Kavya Barnwal*, Keerat K. Guliani*, Pramod Mehta* (2020). Universal Adversarial Perturbations: A Survey.

Preprint

Arnab Kumar Mondal, Aniket Agarwal, Jose Dolz, Christain Desrosiers (2019). Revisiting CycleGAN for Semi-Supervised Segmentation. arXiv preprint, Submitted to WACV 2020.

Preprint Code

Jaynil Jaiswal, Ashutosh Chaubey, Bhimavarapu Sasi Kiran Reddy, Shashank Kashyap, Puneet Kumar, Balasubramanian Raman, Partha Pratim Roy (2019). A Generative Adversarial Network based Ensemble Technique for Automatic Evaluation of Machine Synthesized Speech. ACPR 2019.

Jogendra Nath Kundu, Maharshi Gor, Dakshit Agrawal, R. Venkatesh Babu (2019). GAN-Tree: An Incrementally Learned Hierarchical Generative Framework for Multi-Modal Data Distributions. ICCV 2019.

Preprint Code Poster

Aarush Gupta, Dakshit Agrawal, Hardik Chauhan, Jose Dolz, Marco Pedersoli (2018). An Attention Model for Group Level Emotion Recognition. ICMI 2018.

Preprint PDF Code Poster Slides