Basab Jha
I'm the founder of SAGEA, which is an applied AI research company building ultra-efficient reasoning models and infrastructure for scalable AI systems, and previously built Apparatus.ai.
Reach Out
Papers
- Thinking About Thinking: SAGE-nano's Inverse Reasoning for Self-Aware Language Models
- Fragile Mastery: Are Domain-Specific Trade-Offs Undermining On-Device Language Models?
- The Rosetta Paradox: Domain-Specific Performance Inversions in Large Language Models
- The Babel Effect: Analyzing Multilingual Performane Discrepancies in Large Language Models
Also on Google Scholar
Blogs
I unfortunately have 2 blogs. my oldest and most unfortunate one was my first blog on Medium, and then i switched to writing blogs here where i write weekly (or as much as i can)
here are some of my popular blogs: