Iβm a PhD student at Stony Brook University, New York, trying to figure out how to make AI a bit more sensible, controllable, and interpretable, particularly in the space of generative models and multimodal learning. Before this, I did my undergrad in Computer Science & Engineering from Jadavpur University, Kolkata.
I mostly work on questions like: "How do we get generative models to do something meaningful, not random?" or "Can models learn from vision and language together without mountains of labels?"
Iβve collaborated with top academic labs, industry research teams, and startups to build practical generative pipelines.
If any of this sounds remotely interesting β or if you just want to chat about AI, life, or pandas β shoot me an email: [email protected]
- X (I still call it Twitter) β Mostly rants, occasional research, and life stuff.
- Google Scholar β The serious academic side.
- LinkedIn β Work things. Collaboration stuff. Pretending to be formal.
When I'm not thinking about models, Iβm thinking about pandas. The panda in my profile picture is He Hua (εθ±), a genuinely adorable creature who reminds me that not everything in life has to be optimized.
If you also believe pandas are peak existence (or just wanna discuss generative AI), you know where to find me.
When I ask ChatGPT to paint me, this is how it does. To be fair... I kind of like it.
