Zixuan Lin — accepted AI-conference papers

2026

Distilling Quasi-Conformal Mapping: A Generalizable and Efficient Solution for Wide-Angle Correction

Chengyang Liu, Zixuan Lin, Miaolin Han, Michael K. Ng, Huibin Li

CVPR 2026

This paper introduces a novel framework for wide-angle correction by distilling the geometric principles of quasi-conformal (QC) mapping into a generalizable and efficient deep neural network. Our methodology can be divided into two primary stages. In the first stage, we develop an annotation-free t

Cited by 0 Source ↗Scholar ↗

2025

LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encoding

Junlong Tong, Jinlan Fu, Zixuan Lin, Yingqi Fan, Anhao Zhao, Hui Su +1

ACL 2025finding

Large Language Models (LLMs) are primarily designed for batch processing. Existing methods for adapting LLMs to streaming rely either on expensive re-encoding or specialized architectures with limited scalability. This work identifies three key mismatches in adapting batch-oriented LLMs to streaming…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗