6 papers
SR-OPSD: Self-Referenced On-Policy Self-Distillation
Zhuo Sun, Entong Li, Yanlong Zhao +7
On-policy self-distillation (OPSD) converts feedback into dense token-level supervision on trajectories generated by the policy to be optimized, providing a useful complement to re…
Uncertainty-Aware Domain Adaptation for Vitiligo Segmentation in Clinical Photographs
Wentao Jiang, Vamsi Varra, Caitlin Perez-Stable +3
Accurately quantifying vitiligo extent in routine clinical photographs is crucial for longitudinal monitoring of treatment response. We propose a trustworthy, frequency-aware segme…
Quantizing Time-Series Models As Dynamical Systems: Trajectory-Based Quantization Sensitivity Score
Mariya Pavlova, Harrison Bo Hua Zhu, Lidia Vitanova +2
We introduce the Trajectory-based Quantization Sensitivity Score (TQS), a metric that reframes post-training quantization (PTQ) through the lens of dynamical-systems stability. By…
Saliency-Aware Regularized Quantization Calibration for Large Language Models
Yanlong Zhao, Xiaoyuan Cheng, Huihang Liu +6
Post-training quantization (PTQ) is an effective approach for deploying large language models (LLMs) under memory and latency constraints. Most existing PTQ methods determine quant…
Recurrent Memory for Online Interdomain Gaussian Processes
Wenlong Chen, Naoki Kiyohara, Harrison Bo Hua Zhu +3
We propose a novel online Gaussian process (GP) model that is capable of capturing long-term memory in sequential data in an online learning setting. Our model, Online HiPPO Sparse…
Configurable Multilingual ASR with Speech Summary Representations
Harrison Zhu, Ivan Fung, Yingke Zhu +1
Approximately half of the world's population is multilingual, making multilingual ASR (MASR) essential. Deploying multiple monolingual models is challenging when the ground-truth l…