a lot of my work is made private for various reasons, if you want to collaborate, please reach out on this email address : sauravpanigrahi@protonmail.com
I also write research summaries and walkthroughs @ narrowfoc.us :
- Using RL to make Databases go Brrr (maybe)
- RL for LLMs (important works -- Research Walkthrough)
- Preference Optimisation Methods
- Adaptive Sampling Networks
Currently I am working on :
- MedARC-AI/med-lm-envs - Benchmarks for LLM Evals on Medical Reasoning Tasks
- saurav1004/EnrichRAG - Online Graph Enrichment
- Adaptive-Sampling-Networks - Learned Logit Transforms for Adaptive Sampling
thanks !!
