Amartya
banner
amartyaroy.bsky.social
Amartya
@amartyaroy.bsky.social
Applied ML Engineer@Bosch
My Profile: https://amartya-roy.github.io/

My research is centred on Causal AI, Deep Learning Theory, and LLM Interpretability, specifically focusing on understanding the internal mechanisms of large language models.
I’m thrilled to announce that I have been accepted into the PhD program at IIT Delhi, where I’ll be pursuing research in Causal AI. A heartfelt thank you to my professors , collaborators, parents.A huge thanks to Bosch for approving my study leave.

#PhD #IITDelhi
December 26, 2024 at 6:33 PM
Thrilled to share some fantastic news 🎉 Our paper has been accepted into the top tier conference - COLING 2025 industry track (Core A conference) Huge thanks and congratulations to my co-authors from IIT-Kgp. Feeling grateful for this opportunity to contribute to the field.

#NLP
November 19, 2024 at 8:07 PM
Any Causal AI starter pack? #causalAI
November 16, 2024 at 9:11 PM
Reposted by Amartya
New here? Interested in AI/ML? Check out these great starter packs!

AI: go.bsky.app/SipA7it
RL: go.bsky.app/3WPHcHg
Women in AI: go.bsky.app/LaGDpqg
NLP: go.bsky.app/SngwGeS
AI and news: go.bsky.app/5sFqVNS

You can also search all starter packs here: blueskydirectory.com/starter-pack...
November 9, 2024 at 9:13 AM
Recently I have gone through this paper - arxiv.org/abs/2405.12411. Really an interesting overview. Hopefully much more cool papers will come in causal inference.
Decomposing causality into its synergistic, unique, and redundant components
Causality lies at the heart of scientific inquiry, serving as the fundamental basis for understanding interactions among variables in physical systems. Despite its central role, current methods for ca...
arxiv.org
November 16, 2024 at 8:39 PM