7 papers
Multimodal Alignment Through Joint Kernel Entropic Gromov--Wasserstein Optimal Transport
Yixuan Florence Wu, Yilun Zhu, Naichen Shi
We study the problem of aligning data from multiple modalities into a shared representation space, focusing on settings where strong pretrained unimodal encoders are available but…
Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG
Naihao Deng, Yilun Zhu, Joan Nwatu +2
Warning: This paper contains several toxic and offensive statements. While reasoning generally improves fairness in recent large language models (LLMs), failures persist. In this w…
It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO
Naihao Deng, Yilun Zhu, Naichen Shi +2
Warning: This paper contains several toxic and offensive statements. Modern large language models (LLMs) are typically aligned through large-scale post-training to ensure fair and…
Calibrated Principal Component Regression
Yixuan Florence Wu, Yilun Zhu, Lei Cao +1
We propose a new method for statistical inference in generalized linear models. In the overparameterized regime, Principal Component Regression (PCR) reduces variance by projecting…
Text-to-Distribution Prediction with Quantile Tokens and Neighbor Context
Yilun Zhu, Yuan Zhuang, Nikhita Vedula +6
Many applications of LLM-based text regression require predicting a full conditional distribution rather than a single point value. We study distributional regression under empiric…
Domain Generalization Under Posterior Drift
Yilun Zhu, Naihao Deng, Naichen Shi +2
Domain generalization (DG) is the problem of generalizing from several distributions (or domains), for which labeled training data are available, to a new test domain for which no…