Author

Steven Euijong Whang

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Preference Data Selection for Mitigating the Alignment Tax in Large Language Models

This paper proposes BALIGN, a balanced data selection strategy that explicitly mitigates catastrophic forgetting while optimizing alignment efficacy, and identifies three key data-centric features that dictate parameter drift: the reference model's log-probability margin, the token length between chosen and rejected responses, and the TF-IDF similarity to general capability corpora.

Minsu Kim, Jianxun Lian, Xing Xie et al. · 0 citations

Preprint Aug 2026

Multimodal Federated Learning under Dual-Axis Modality Missingness

Flux is proposed, a multimodal federated learning framework built around two complementary components, modality-aware confidence tempering and gradient-decoupled private adaptation, that enables sample-specific, client-local confidence adaptation without allowing confidence-dependent gradients to perturb shared representation learning.

Adiba Orzikulova, Jaehyun Kwak, Jaemin Shin et al. · 0 citations