Som Banerjee
PhD, Computer Science and Engineering, IIT Kharagpur
Software Engineer Technical Leader @Cisco Systems, Inc.
Hello নমস্কার,
I’m Somnath Banerjee (সোমনাথ ব্যানার্জি), a research scholar working on identifying vulnerabilities in large language models (LLM) and transforming them into systems that are safe, coherent, and factually grounded. I aim to make gen AI more equitable and impactful, under the guidance of Prof. Animesh Mukherjee.
Parallel to my research, I work as a Software Engineer Technical Leader at Cisco, where I lead high-impact projects and drive technological excellence. My journey has also included roles as a Software Technical Engineer Expert at Fujitsu Labs, where I led AI initiatives for Australia’s largest Telco organization, and as a Technical Lead and Software Engineer at Cognizant and IBM India.
I hold an M.Tech in Computer Science and Engineering from IIT (ISM) Dhanbad, where I explored extreme classification and earned the university gold medal(🥇) for academic distinction.
Beyond my professional life, I am a fitness enthusiast, an avid reader of bengali literature (প্রধানত শরদিন্দু বন্দ্যোপাধ্যায়, বিভূতিভূষণ বন্দ্যোপাধ্যায়, হেমেন্দ্রকুমার রায়, রূপক সাহা, অভীক সরকার), and a budding guitarist. My love for exploration extends to photography, where I capture life’s fleeting moments with my Fujifilm and Nikon cameras. Whether on my bike or in my car, I seek out lesser-traveled roads to uncover hidden stories.
Be it technology, political debates, traveling, or lifting weights, I believe in living with purpose and passion.
News
| Jan 02, 2026 | Cloud Support: Received Google Cloud Research Credits ($5,000 USD) to support ongoing research initiatives. |
|---|---|
| Jan 02, 2026 | Presentation: Six papers selected for the Global South Research & Posters Showcase, a Govt. of India Initiative at the Research Symposium on AI and its Impact, Bharat Mandapam, New Delhi, as part of the India AI Impact Summit 2026. |
| Dec 27, 2025 | Recognition: Three papers nominated for ACM ARCS 2026 as India representative papers from premier A* venues — (1) SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models, (2) Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment, (3) Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models. |
| Dec 24, 2025 | 📢 I am pleased to share that I will be conducting a tutorial at AACL-IJCNLP 2025 in Mumbai, India with Dr. Rima Hazra and Prof. Animesh Mukherjee , titled “Beyond Guardrails: Advanced Safety for Large Language Models — Monolingual, Multilingual and Multimodal Frontiers.” 🔗 For more details, please visit: AACL-IJCNLP 2025 Tutorials, Softminer Trace |
| Dec 15, 2025 | Research Grant: Awarded the prestigious ANRF-ARG Grant (~₹1 Crore) in collaboration with Prof. Animesh Mukherjee, IIT Kharagpur. PhD positions will be available soon. |
| Dec 08, 2025 | 🎉 Two new papers are out! 🎯 "Attributional Safety Failures in Large Language Models under Code-Mixed Perturbations" with Microsoft and "ProSocialAlign: Preference Conditioned Test Time Alignment in Language Models" with TU/e. |
| Nov 15, 2025 | 🎉 Paper accepted at AAAI 2026! 🎯 "AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models" |
| Nov 12, 2025 | 📢 I am pleased to share that I have received an invitation from NIMHANS (National Institute of Mental Health and Neurosciences), India to deliver a talk on “Responsible AI for Psychiatry in India." 🔗 "For more details, please visit: Heads AI" |
| Oct 23, 2025 | 🎉 Paper accepted at TMLR 2025! 🎯 "MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation" |
| Sep 15, 2025 | 🎉 Paper accepted at EMNLP 2025! 🎯 "Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment" |