Personal Page

My name is Yang Xiao (肖扬). a Ph.D. student in Computer Science at the University of Tulsa, Tulsa, Oklahoma, USA. I come from China and graduated from Nankai University, Tianjin, China. Now, my research interests are trustworthy artificial intelligence and AI for Science.

News

Selected Projects

[Preprint]LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation

Generative Models; Video Generation; Diffusion Models; Training-Free Acceleration.
The code is available at here。

[ICCV 2025] Optimal Transport for Brain-Image Alignment: Unveiling Redundancy and Synergy in Neural Information Processing

Generative Models; Vision-Language-Brain Model; Large Language Model;Optimal Transport; Neuroscience.
The code is available at here。

[NeuraIPS 2025 workshop] The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models. Oral Invitation (Didn't go)

Trustworthy Artificial Intelligence;; Machine Unlearning; Sparse models.
The code is available at here。

[CIKM 2025] Efficient Knowledge Graph Unlearning with Zeroth-order Information

Trustworthy Artificial Intelligence; Machine Unlearning; Knowledge Graphs; Zeroth-order Optimization.
The code is available at here。

[COLING 2025] Knowledge Graph Unlearning with Schema

Trustworthy Artificial Intelligence; Machine Unlearning; Knowledge Graphs; Knowledge Schema.
The code is available at here。

[CIKM 2024] Advancing Certified Robustness of Explanation via Gradient Quantization

Trustworthy Artificial Intelligence; Explanable Algorithms; Gradient Quantization; Certified Radius.
The code is available at here。

Publication

Regular Conference Papers

• ICCV 2025 Optimal Transport for Brain-Image Alignment: Unveiling Redundancy and Synergy in Neural Information Processing
  • Yang Xiao, Wang Lu, Jie Ji, Ruimeng Ye, Gen Li, Xiaolong Ma, Bo Hui
• CIKM 2025 Efficient Knowledge Graph Unlearning with Zeroth-order Information
  • Yang Xiao, Ruimeng Ye, Bohan Liu, Xiaolong Ma, Bo Hui
• CIKM 2024 Advancing Certified Robustness of Explanation via Gradient Quantization
  • Yang Xiao, Zijie Zhang, Yuchen Fang, Da Yan, Yang Zhou, Wei-Shinn Ku, Bo Hui
• ICCV 2025 Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware Optimization
  • Gen Li, Yang Xiao, Jie Ji, Kaiyuan Deng, Bo Hui, Linke Guo, Xiaolong Ma
• ECAI 2025 DBA-DFL: Towards Distributed Backdoor Attacks with Network Detection in Decentralized Federated Learning.
  • Bohan Liu, Yang Xiao, Ruimeng Ye, Zinan Ling, Xiaolong Ma, Bo Hui.
• ICIP 2024 BMT-BENCH: A Benchmark Sports Dataset for Video Generation
  • Ziang Shi, Yang Xiao, Da Yan, Min-Te-Sun, Wei-Shinn Ku, Bo Hui

Short Conference Papers

• COLING 2025 Knowledge Graph Unlearning with Schema
  • Yang Xiao, Ruimeng Ye, Bo Hui
• LoG 2024 Knowledge Graph Unlearning with Schema (Extented Abstract)
  • Yang Xiao, Ruimeng Ye, Bo Hui

Workshop Papers

• ICML 2025 Workshop DBA-DFL: Towards Distributed Backdoor Attacks with Network Detection in Decentralized Federated Learning. Oral
  • Bohan Liu, Yang Xiao, Ruimeng Ye, Zinan Ling, Xiaolong Ma, Bo Hui.
• ICLR 2025 Workshop Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning.
  • Ruimeng Ye, Yang Xiao, Bo Hui.
• NIPS 2025 Workshop The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models.
  • Yang Xiao, Gen Li, Jie Ji, Ruimeng Ye, Xiaolong Ma, Bo Hui.
• NIPS 2025 Workshop Weak-to-Strong Generalization with Failure Trajectories: A Tree-based Approach to Elicit Optimal Policy in Strong Models.
  • Ruimeng Ye, Zihan Wang, Yang Xiao, Zinan Ling, Manling Li, Bo Hui

Pre-print Papers

• arXiv LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation.
  • Yang Xiao, Gen Li, Kaiyuan Deng, Yushu Wu, Zheng Zhan, Yanzhi Wang, Xiaolong Ma, Bo Hui.
• arXiv A Survey of Lottery Ticket Hypothesis.
  • Bohan Liu, Zijie Zhang, Peixiong He, Zhensen Wang, Yang Xiao, Ruimeng Ye, Yang Zhou, Wei-Shinn Ku, Bo Hui.

Submitted Papers

• [ICLR 2026] A paper about Diffusion.
• [ICLR 2026] A paper about Machine Unlearning.
• [Clinical Trials on Alzheimer’s Disease conference (CTAD) 2025] A paper about AI for Healthcare.

Statistic

CCF Paper Statistics

屡败屡战

[2025.09] NIPS reject

[2025.05] ACL reject → CIKM 2025

[2025.05] ICML reject → NIPS 2025

[2024.12] AAAI reject → ACL 2025

[2024.07] ACL desk reject for stupid reason (don’t ask me) → COLING 2025 and LoG 2024

[2024.05] UAI withdrawn → CIKM 2024