IAI

Research Interest and specialization:

• • Safe AI, LLM Alignment, LLM reasoning, NLP, Trustworthy AI. Making AI systems safe, reliable, and socially beneficial.
    
    Expertise and focus area:
    • LLM alignment
    • Multilinguality
    • Building Interpretable and Responsible Intelligence
    • Continuous Red teaming and Agentic Robustness
    • Natural Language Processing

Collaborators and Professional Engagement

• Academic collaborations (India): IIT Kharagpur, IIT Bombay

• Academic collaborations (outside India): Eindhoven University of Technology (TU/e), New York University, USA, National University of Singapore (NUS), Nanyang Technological University (NTU)

• Industry collaborations (India & outside India): Microsoft, Oracle (in progress)
  
  Professional Engagement:

• Delivered 3 hour tutorial at AACL 2025 on AI safety and alignment

• Served as Pan-India forum chair at IndoML 2025, Webchair at IndoML 2024

• Area Chair at ACL ARR 2026, Reviewer at ACL 2024, 2025 EMNLP 2024, 2025, ICLR 2025, AAAI 2025, ECIR 2024, 2025, ECML PKDD 2023, 2024
  
  Mentoring:

• Mentored more than 12 students B.Tech and M.Teach students and published papers at several top-tier conferences.
• Mentoring 2 PhD students from IIT KGP – 1 submitted PhD thesis (Tutoring Large Language Models to be Domain-adaptive, Precise, and Safe)
  
  Awards and grants:

• Paligemma award 2024 (~15K USD) from Google for conducting AI & Safety research work

• Microsoft Academic Research Grant (MAPG) 2024 (~15 Lakhs) in collaboration with Prof. Animesh Mukherjee, IIT KGP for AI & Safety work  (only five proposal selected from India)

• ANRF-ARG Grant (2025) (~1 crore) for project Subtle Logic, Serious Risk: Uncovering Reasoning-Based Exploits in LLMs (jointly)

• Received google cloud academic grant (~5K USD) 2025