Ploutos, 02 June 2025
R3: Robust Rubric-Agnostic Reward Models
A technical talk to Machine Learning researchers, professionals and entrepreneurs based on previously published paper R3: Robust Rubric-Agnostic Reward Models.
Talks & Services
Talks
Toronto Machine Learning Summit, 15 July 2024
ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models
A technical talk to Machine Learning researchers, professionals and entrepreneurs based on previously published paper ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models.
Professional Services
Reviewer
- ICLR (2025)
- NAACL (2025)
- ACL (2025)
- EMNLP (2025)