René's URL Explorer Experiment


Title: Partha Pratim Saha — AI Researcher & Mechanistic Interpretability

Open Graph Title: Partha Pratim Saha | AI Researcher

Description: Partha Pratim Saha — AI Safety researcher specialising in Mechanistic Interpretability, AI Deception Detection, Geometric Deep Learning, AI Alignment, and LLMs. GRAFT accepted at ICML 2026 Mechanistic Interpretability Workshop. BITS Pilani M.Tech, NeurIPS author, Springer published.

Open Graph Description: Mechanistic Interpretability, Geometric Deep Learning, AI Alignment. GRAFT accepted at ICML 2026 Mech. Interp. Workshop. NeurIPS 2025, SpringerNature.

Keywords:

Mail addresses
technical.partha@gmail.com
technical.partha@gmail.com
technical.partha@gmail.com

direct link

Domain: pps121.github.io

Links:

Abouthttps://pps121.github.io/#about
Awardshttps://pps121.github.io/#awards
Papershttps://pps121.github.io/#publications
Researchhttps://pps121.github.io/#research
Expertisehttps://pps121.github.io/#expertise
Experiencehttps://pps121.github.io/#experience
Contacthttps://pps121.github.io/#contact
LinkedIn https://in.linkedin.com/in/partha121
GitHub https://github.com/pps121
Scholar https://scholar.google.com/citations?user=M0nZ5pEAAAAJ&hl=en
CV / Resume https://pps121.github.io/images/CV_Partha.pdf
View Researchhttps://pps121.github.io/#research
All Publicationshttps://pps121.github.io/#publications
Download CVhttps://pps121.github.io/images/CV_Partha.pdf
SpringerNature ICOMP’24https://link.springer.com/chapter/10.1007/978-3-031-72171-7_3
BITS Pilanihttps://www.bits-pilani.ac.in/
LinkedIn: partha121https://in.linkedin.com/in/partha121
GitHub: pps121https://github.com/pps121
8-week MIT AISF programhttps://aialignment.mit.edu/aisf/
Harvard AI Safety Student Teamhttps://aisst.ai/
Cooperative AI Foundationhttps://www.cooperativeai.com/foundation
LASR (Learning from AI Safety Research) Labshttps://www.lasrlabs.org/
Neuromatch Academyhttps://neuromatch.io/
Armenian LLM Summer School 2025https://llmsummerschool.am/
Deep Learninghttps://deeplearning.neuromatch.io/
arXivhttps://arxiv.org/pdf/2509.00849
DOIhttps://doi.org/10.5281/zenodo.15126395
SpringerNaturehttps://link.springer.com/chapter/10.1007/978-3-031-72171-7_3
OpenReviewhttps://openreview.net/forum?id=4YwcNzD4pa
Workshop Postershttps://mechinterpworkshop.com/posters/
Codehttps://github.com/pps121/graft-belief-geometry
GitHubhttps://github.com/pps121/torsional-belief-vector-field
GitHubhttps://github.com/pps121/torsional-belief-vector-field
DOI: 10.5281/ZENODO.15126395https://doi.org/10.5281/zenodo.15126395
SpringerNaturehttps://link.springer.com/chapter/10.1007/978-3-031-72171-7_3
LinkedInlinkedin.com/in/partha121 https://in.linkedin.com/in/partha121
GitHubgithub.com/pps121 https://github.com/pps121
Google ScholarAcademic publications https://scholar.google.com/citations?user=M0nZ5pEAAAAJ&hl=en
Curriculum VitaeDownload PDF https://pps121.github.io/images/CV_Partha.pdf
Source on GitHubhttps://github.com/pps121/pps121.github.io

Viewport: width=device-width, initial-scale=1.0

URLs of crawlers that visited me.