Publications

Arjun Choudhry, Chang Liu, Nina Żukowska, Yifu Cai, Mononito Goswami, Artur Dubrawski (2026). LayerMerge: Modality-Agnostic Depth Pruning for Efficient Foundation Model Deployment. NeurIPS 2025 Workshop on Efficient Reasoning.

Mikołaj Piórczy\ŉski, Wojciech Łapacz, Xinyu Li, Chang Liu, Abby Turner, Artur Dubrawski (2026). From Aggregation to Guidance: Strategies for Personalized Federated Fine-Tuning of Foundation Models. UniReps: 3rd Edition of the Workshop on Unifying Representations in Neural Models.

Chang Liu, Arjun Choudhry, Yifu Cai, Nina Żukowska, Mononito Goswami, Artur Dubrawski (2026). Depth as a Scaling Vector: Simple Pruning and Evaluation of Emergent Abilities in Pruned LLMs. NeurIPS 2025 Workshop on Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling.

Chang Liu, Jieshi Chen, Lee H Harrison, Artur Dubrawski (2025). Bridging the utility gap between MALDI-TOF and WGS for affordable outbreak cluster detection. Conference on Health, Inference, and Learning.

Chang Liu, Jieshi Chen, Lee H Harrison, Artur Dubrawski (2024). Multimodal Structure Preservation Learning. arXiv preprint arXiv:2410.22520.

Chang Liu, Kaimin Xiao, Cuinan Yu, Yipin Lei, Kangbo Lyu, Tingzhong Tian, Dan Zhao, Fengfeng Zhou, Haidong Tang, Jianyang Zeng (2024). A probabilistic knowledge graph for target identification. PLOS Computational Biology.

Chang Liu, Cuinan Yu, Yipin Lei, Kangbo Lyu, Tingzhong Tian, Qianhao Li, Dan Zhao, Fengfeng Zhou, Jianyang Zeng (2022). Improving target-disease association prediction through a graph neural network with credibility information. PACIFIC SYMPOSIUM ON BIOCOMPUTING 2023: Kohala Coast, Hawaii, USA, 3–7 January 2023.