Ishaan Ganti
I'm a research engineer at Rowan and a student at Brown studying applied mathematics,
physics, and computer science.
This site consolidates my writing, research, current work, and jumbled thoughts. I share various
readings that interest me at the bottom of this page.
I've
biked from
Denver to New York City, developed lots of drug discovery tooling at Rowan, and
done work in theoretical cavity QED at MIT.
Gallery
What I'm Reading
Pen emoticons link to my thoughts on the work. Dates are when I read the work. I don't log everything I read, just the writings I find most interesting, moving, and/or insightful.
- Chess Story
- Training Large Language Models for Small-Molecule Design with Synthetic Task Scaling
- How Claude is accelerating protein design and analytical chemistry
- Language model harnesses are compositional generalizers
- The fall of the theorem economy
- America Will Keep Succeeding
- How I Learned to Read Way, Way More
- The Problem With Elsewhere
- Folding, Reasoning, and Scaling with Open-source Drug Discovery Engine
- Sesame: Structure-Aware Molecular Generation via Spatial Density-Map Conditioning
- Zero-shot design of drug-binding proteins via neural iterative selection−expansion
- What Does a Chemical Language Model Know About Molecules?
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
- Tool Use and "AI Scientists"
- A note on de novo binder design model evaluation
- Nuclear Quantum Effects in liquid water at near classical computational cost using the adaptive Quantum Thermal Bath
- Atomic-level protein–ligand recognition with PBCNet2.0 for probe discovery
- Policy On the AI Exponential
- Distilling Foundation Models via Energy Hessians
- Few-step Cofolding with All-Atom Flow Maps
- Why A.I. Isn’t Going to Make Art
- Never Let Me Go
- The lessons of large-deviation theory for liquid crystalline systems