activity
20242026
collaborators

6 papers

cs.LG2026

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…

cs.CV2026

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…

cs.LG2026

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…

cs.AI2026

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…

cs.LG2025

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…

cs.SD2024

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…