Publications: 'Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive', 'LiveBench: A Challenging, Contamination-Free LLM Benchmark', etc.; Awards: Top 10% of reviewers at NeurIPS 2020-2022, ICML 2021-2022, ICLR 2022; Service: Senior Area Chair for ICML 2024, Senior Area Chair for NeurIPS Track on Datasets and Benchmarks 2023-2024, etc.
Research Experience
Research Scientist at Meta Superintelligence Labs, working on generative AI; Head of Research at Abacus.AI, co-created and maintained LiveBench benchmark.
Education
Ph.D. in Computer Science from Carnegie Mellon University, advised by Nina Balcan, supported by the NDSEG Fellowship; Undergraduate degree from Amherst College.
Background
Research Interests: Evaluating generative AI models. Professional Fields: Generative AI, Automated Machine Learning (AutoML), Model Interpretability and Debiasing, Machine Learning for Tabular Data. Brief Introduction: Research Scientist at Meta Superintelligence Labs, previously Head of Research at Abacus.AI.