Linrong Cai — accepted AI-conference papers

2024

Stronger Than You Think: Benchmarking Weak Supervision on Realistic Tasks

Tianyi Zhang, Linrong Cai, Jeffrey Li, Nicholas Roberts, Neel Guha, Frederic Sala

NeurIPS 2024poster

Weak supervision (WS) is a popular approach for label-efficient learning, leveraging diverse sources of noisy but inexpensive *weak labels* to automatically annotate training data. Despite its wide usage, WS and its practical value are challenging to benchmark due to the many knobs in its setup, inc…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Zero-Shot Robustification of Zero-Shot Models

Dyah Adila, Changho Shin, Linrong Cai, Frederic Sala

ICLR 2024poster

Zero-shot inference is a powerful paradigm that enables the use of large pretrained models for downstream classification tasks without further training. However, these models are vulnerable to inherited biases that can impact their performance. The traditional solution is fine-tuning, but this under…

Cited by 21 Source ↗PDF ↗code ↗Scholar ↗