Dr. Murari Mandal
Assistant Professor, KIIT Bhubaneswar
Post-Doc, National University of Singapore (NUS)
101-H, Campus 14
KIIT Bhubaneswar
Odisha, India 751024
I am an Assistant Professor at the School of Computer Engineering, KIIT Bhubaneshwar. I lead the RespAI Lab where we work on the topics related to responsible AI, machine unlearning, data valuation, ethical use of large language models (LLMs) and diffusion models. My research work has been published in ICML, KDD, AAAI, ACM MM, CVPR. Check out my research group’s website here: RespAI Lab. I regularly serve as a Reviewer to NeurIPS, ICML, ICLR, AAAI, CVPR, ICCV, and ECCV. Indexed in CSRankings.
Research Impact: My pioneering works on Machine Unlearning is cited by Anthropic, Yoshua Bengio, Hugo Larochelle, Google Deepmind, University of Cambridge, etc. Our works Fast Unlearning [TNNLS], Zero shot Unlearning [TIFS], and Bad Teacher [AAAI] are among top 10 highly cited papers in the field of Machine Unlearning. Ayush and Vikram (co-authors and my students) have joined EPFL and University of Cambridge, respectively.
Earlier, I was a Postdoctoral Research Fellow at National University of Singapore (NUS). I worked with Prof. Mohan Kankanhalli in the School of Computing. Long time back, I graduated in 2011 with a Bachelors in Computer Science from BITS, Pilani. Find me on X @murari_ai.
"When you go to hunt, hunt for rhino. If you fail, people will say anyway it was very difficult. If you succeed, you get all the glory"
Research Interests
- Large Language Models
- Diffusion Models
- Regulatable AI
- Machine Unlearning
- Data Valuation
- Privacy and Security in AI
- Data Privacy and Data Synthesis
- Explaianable AI
News
Nov 18, 2024 | I will be presenting our recent works on Unlearning in Generative AI Unlearning in Diffusion Models, Unlearning in LLMs at IndoML 2024. Would love to connect and discuss all things Gen AI! |
---|---|
Oct 25, 2024 | Preprint of UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs is available on Arxiv. |
Oct 10, 2024 | Preprint of ConDa: Fast Federated Unlearning with Contribution Dampening is available on Arxiv. |
Sep 11, 2024 | Preprint of Unlearning or Concealment? A Critical Analysis and Evaluation Metrics for Unlearning in Diffusion Models is available on Arxiv. |
Sep 10, 2024 | Preprint of A Unified Framework for Continual Learning and Machine Unlearning is available on Arxiv. |
Jul 13, 2024 | Invited Guest in a Panel Discussion on “AI: The Dual Edge of Innovation”, World Salon. You can find more details about the event on LinkedIn and World Salon. |
May 20, 2024 | Preprint of “Multimodal Recommendation Unlearning” paper is available on Arxiv |
May 10, 2024 | EcoVal Data Valuation Paper Accepted to KDD-2024, Barcelona. |
Feb 10, 2024 | Received the Google Cloud Education Grant for teaching Natural Language Processing at KIIT Bhubaneswar. [Grant Amount: INR 3,16,000] |
Nov 10, 2023 | Delivered a talk on Machine Unlearning at BITS Pilani, Pilani Campus. PPT |
Oct 23, 2023 | Preprint of “Distill to Delete: Unlearning in Graph Networks with Knowledge Distillation” paper is available on Arxiv |
Sep 10, 2023 | Received 30 Lacs SERB-DST Start-up Research Grant (SRG) to further my work in the field of Machine Unlearning and AI Regulation |
Jun 10, 2023 | Received SERB-ITS Travel grant to present our paper in ICML-2023, Honolulu, Hawaii, USA |
May 25, 2023 | paper accepted in IEEE Transactions on Information Forensics and Security |
Apr 10, 2023 | 1 paper accepted in ICML 2023, Hawaii Convention Center, USA |
Selected Publications
- Deep Regression UnlearningIn Proceedings of the 40th International Conference on Machine Learning , 23–29 jul 2023
- EcoVal: An Efficient Data Valuation Framework for Machine Learning23–29 jul 2024
- Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks Using an Incompetent TeacherProceedings of the AAAI Conference on Artificial Intelligence, Jun 2023