19 citations · 23 across the 5 of their papers we have counts for
5 papers
TRAPSBench: Vision-Language Models Encode but Fail to Express Epistemic Restraint
Fnu Pramono, John Cai, Sourabh Kulkarni
When visual evidence is occluded or chaotic, models should abstain. In this paper, we show that Vision-Language Models (VLMs) can internally distinguish when abstention is required…
A Systematic Paradigm for Detecting, Surfacing, and Characterizing Heterogeneous Treatment Effects (HTE)
John Cai, Weinan Wang
To effectively optimize and personalize treatments, it is necessary to investigate the heterogeneity of treatment effects. With the wide range of users being treated over many onli…
DAMSL: Domain Agnostic Meta Score-based Learning
John Cai, Bill Cai, Shengmei Shen
In this paper, we propose Domain Agnostic Meta Score-based Learning (DAMSL), a novel, versatile and highly effective solution that delivers significant out-performance over state-o…
SB-MTL: Score-based Meta Transfer-Learning for Cross-Domain Few-Shot Learning
John Cai, Bill Cai, Sheng Mei Shen
While many deep learning methods have seen significant success in tackling the problem of domain adaptation and few-shot learning separately, far fewer methods are able to jointly…
Cross-Domain Few-Shot Learning with Meta Fine-Tuning
John Cai, Sheng Mei Shen
In this paper, we tackle the new Cross-Domain Few-Shot Learning benchmark proposed by the CVPR 2020 Challenge. To this end, we build upon state-of-the-art methods in domain adaptat…