Pratinav Seth

pratinavsetharya

·

AI & ML interests

Explainable AI (XAI), AI Alignment & Safety, Trustworthy Machine Learning, Computer Vision, Medical Imaging, AI for Social Good & Sustainability.

Recent Activity

updated a collection 1 day ago

SafeTune-Artifacts

authored a paper 12 days ago

AlignTune: Modular Toolkit for Post-Training Alignment of Large Language Models

authored a paper 12 days ago

Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution

View all activity

Organizations

upvoted a paper about 2 months ago

Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution

Paper • 2605.15138 • Published May 14 • 7

upvoted a paper 5 months ago

C-ΔΘ: Circuit-Restricted Weight Arithmetic for Selective Refusal

Paper • 2602.04521 • Published Feb 4 • 1

upvoted 2 papers 8 months ago

Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning

Paper • 2511.02818 • Published Nov 4, 2025 • 15

TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models

Paper • 2511.02802 • Published Nov 4, 2025 • 16