Yangxu Liao — accepted AI-conference papers

2026

DeformTrace: A Deformable State Space Model with Relay Tokens for Temporal Forgery Localization

Xiaodong Zhu, Suting Wang, Yuanming Zheng, Junqi Yang, Yangxu Liao, Yuhong Yang +2

AAAI 2026technical

Temporal Forgery Localization (TFL) aims to precisely identify manipulated segments in video and audio, offering strong interpretability for security and forensics. While recent State Space Models (SSMs) show promise in precise temporal reasoning, their use in TFL is hindered by ambiguous boundaries

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models

Yangxu Liao, Wenke Huang, G. W., Jian Liang, Bin Yang, Mang Ye

ICML 2025poster

Federated learning provides an efficient privacy-preserving distributed training framework for large language models, addressing the growing scarcity of publicly available training data while enabling the utilization of private datasets. While integrating large language model fine-tuning with federa…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗