← Search

Gefei Tan

2 accepted papers

2025

Pin the Tail on the Model: Blindfolded Repair of User-Flagged Failures in Text-to-Image Services

NeurIPS 2025poster

Diffusion models are increasingly deployed in real-world text-to-image services. These models, however, encode implicit assumptions about the world based on web-scraped image-caption pairs used during training. Over time, such assumptions may become outdated, incorrect, or socially biased--leading t…

Cited by 0SourceScholar
2024

Confidential-DPproof: Confidential Proof of Differentially Private Training

ICLR 2024spotlight

Post hoc privacy auditing techniques can be used to test the privacy guarantees of a model, but come with several limitations: (i) they can only establish lower bounds on the privacy loss, (ii) the intermediate model updates and some data must be shared with the auditor to get a better approximation…

Cited by 5SourcePDFScholar