3 citations · 11 across the 24 of their papers we have counts for
3 papers · 1 filter
The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering
Yefan Zhou, Yilun Zhou, Austin Xu +3
Generative verifiers have emerged as a promising paradigm for step-wise verification, but their verification behavior is often poorly calibrated: they may be under-critical and mis…
Least-Loaded Expert Parallelism: Load Balancing An Imbalanced Mixture-of-Experts
Xuan-Phi Nguyen, Shrey Pandit, Austin Xu +2
Mixture-of-Experts (MoE) models are typically pre-trained with explicit load-balancing constraints to ensure statistically balanced expert routing. Despite this, we observe that ev…
Active metric learning and classification using similarity queries
Namrata Nadagouda, Austin Xu, Mark A. Davenport
Active learning is commonly used to train label-efficient models by adaptively selecting the most informative queries. However, most active learning strategies are designed to eith…