← Search

Michael Duan

2 accepted papers

2026

Frustratingly Simple Retrieval Improves Challenging, Reasoning-Intensive Benchmarks

ICLR 2026poster

Retrieval augmentation has primarily been studied in limited settings, such as factoid question answering; more challenging, reasoning-intensive benchmarks have seen limited success from minimal RAG. In this work, we challenge this prevailing view on a set of established, reasoning-intensive benchma…

Cited by 0SourceScholar
2026

Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch

ICML 2026poster

Research involving privacy-sensitive data has always been constrained by data scarcity, standing in sharp contrast to other areas that have benefited from data scaling. To quench this thirst, we present Privasis (i.e., privacy oasis), the first million-scale fully synthetic dataset entirely built fr…

Cited by 0SourceScholar