4 papers
Dysco: Dynamic Subspace Boosting to Mitigate LoRA Interference in Federated Learning
Haobo Zhang, Jiankun Wang, Suraj Rajendran +5
Federated fine-tuning of large pre-trained models increasingly relies on Low-Rank Adaptation (LoRA) to reduce communication and computation, but heterogeneous clients can make adap…
Molecular Lead Optimization via Agentic Tool Planning
Lingxiao Li, Haobo Zhang, Ruohao Fan +2
Drug discovery is a lengthy and resource-intensive process composed of multiple stages. Among these stages, lead optimization plays a critical role in transforming early hit compou…
Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design
Lingxiao Li, Haobo Zhang, Bin Chen +1
Text-conditioned molecular generation aims to translate natural-language descriptions into chemical structures, enabling scientists to specify functional groups, scaffolds, and phy…
Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging
Haobo Zhang, Jiayu Zhou
Fine-tuning large language models (LMs) for individual tasks yields strong performance but is expensive for deployment and storage. Recent works explore model merging to combine mu…