Ravenor Davion
I research transformers and study computer science at Stanford.
Currently
Incoming Research Intern @ NVIDIA
Post-training agents to write domain-specific language. Fall '26.
Researcher @ Stanford AI Lab | Advised by Christopher Ré and Azalia Mirhoseini
Post-training agents for intelligence-per-joule.
Previously
- Researcher @ Robust Systems Group | Advised by Subhasish Mitra Accelerating transformer inference. Publication pending.
Projects
AR-saLM: A fine-tuned AutoRater for search-augmented LMs
Our work. Thanks to Cyrus R. and Barry Z. for mentoring this.
Ultradense IC for Accelerating Transformer Decode
Proposed + simulated custom NoC that reduced inference latency in Llama3-9B 10.9x from SOTA.
Get in Touch
I like chatting about research and early-stage companies. Reach me at rdavion [at] stanford [dot] edu.
