Naquee Rizwan

About me

Hello 👋 . I am Naquee Rizwan, a researcher enrolled in the department of Computer Science and Engineering at IIT Kharagpur as Ph.D. fellow. I work with Prof. Animesh Mukherjee and I am also a member of two research groups: CNeRG and HateAlert. My Ph.D. work is at the intersection of generative AI and social computing where I primarily work with multimodal models to build frameworks for "content moderation of social media and streaming platforms".

Before my research journey, I worked as a software engineer for nearly 3 years at Adobe Systems, Jio Platforms Limited and Samsung Research where I built products reaching millions of users monthly. My professional journey started after graduating from IIT (ISM) Dhanbad with a Bachelor (B.Tech) degree in Computer Science and Engineering in 2020.

[e-mail: naqueerizwan1998@gmail.com, nrizwan@kgpian.iitkgp.ac.in] [Google Scholar] [LinkedIn] [Research Gate]

Updates

Oct, 2026: One long paper accepted at ICVGIP 2026 (main) - "Anyone Can Be a Doctor: Debiasing VLMs via Task-Vector Negation". [Website]
Sept, 2026: Joined Walmart Global Tech India as research intern in Bengaluru, India.
Sept, 2026: Received recognition as one of India's Top 100 AI/ML Researchers by Amazon.
Aug, 2026: One long paper accepted at EMNLP 2026 (main) - "FBHM: Functional Benchmarking and Steering of VLMs for Hateful Meme Detection". [Paper]
July, 2026: One long paper accepted at ACM Multimedia 2026 (main) - "PEST: Parameter Efficient Steering of Blackbox VLMs via Agentic Few-shot Alignment for Hateful Meme Moderation". [Paper]
July, 2026: One long paper accepted at TACL - "STEMTOX: From Collaborative Tags to Fine-Grained Toxic Meme Detection via Entropy-Guided Multi-Task Learning". [Paper]
June, 2026: Joined Uber AI Solutions as research intern in Hyderabad, India.
Jan, 2026: One long paper accepted at EACL 2026 (main, oral) - "NLP for Social Good: A Survey and Outlook of Challenges, Opportunities, and Responsible Deployment". [Paper]
July, 2025: One long paper accepted at ACM Multimedia 2025 (main, oral) - "Toxicity Begets Toxicity: Unraveling Conversational Chains in Political Podcasts". [Paper]
July, 2025: Joined Sony Research India as research intern.
May, 2025: One long paper accepted at ACL 2025 (findings) - "HATEPRISM: Policies, Platforms, and Research Integration. Advancing NLP for Hate Speech Proactive Mitigation". [Paper]
March, 2025: One long paper accepted at ICWSM 2025 (main) - "Exploring the Limits of Zero Shot Vision Language Models for Hate Meme Detection: The Vulnerabilities and their Interpretations". [Paper]
Nov, 2024: One long paper accepted at COLING 2025 (main, oral) - "Multilingual and Explainable Text Detoxification with Parallel Corpora". [Paper]