sanyam jain
  • journey
  • projects
  • writing
  • life
human agent

writing

notes on ai, engineering, and building things.

world models and how they work and their lineage

tracing the path from pixel-space simulators (iris, storm, diamond) through latent-space compression, into dreamer's planning loop, and now watching jepa — my learnings on world models so far.

twitter ↗

e3: issue-level backtesting for automated research critique

the research behind noteweave's review engine — an automated critic that flags unsupported claims, incomplete ablations, weak baselines, and data leakage risks, backtested against 100 iclr 2026 papers.

arxiv ↗

agentic search — how we built it at discoverminds.ai

the architecture behind arya: finding the right people in your network using agentic search

twitter ↗

resources for classical ml, dl & genai

a curated list of courses, books, and resources for learning classical machine learning, deep learning, and generative ai — from nptel, iit, and beyond.

linkedin ↗

more coming soon — some threads on twitter and linkedin.

pages

home journey projects writing life

social

github linkedin twitter

profiles

scholar openreview kaggle huggingface leetcode email

sanyam jain — 2026