7 papers
Oracle-Budgeted Molecular Optimization with Short-Term Graph Memory
Jiannan Yang, Veronika Thost, Xiang Ling +1
Molecular optimization is commonly performed under a limited oracle budget, which makes deciding what to evaluate as important as deciding what to generate. We introduce short-term…
Beyond Visibility and Technical Reuse: Public Application Transformation in Open-Source Model Ecosystems
Duorong Wang, Xiaoting Wei, Bin Liu +1
Open-source model platforms have made it easier to publish AI models, but model release alone does not reveal whether models become visible, technically reused, or incorporated int…
Racing to Release: Priority, Congestion, and Community Recognition in Open-Source LLM Ecosystems
Bin Liu, Lele Kang, Jiannan Yang
Open-source large language models have made platforms such as Hugging Face central hubs for decentralized AI innovation. Yet these ecosystems are shaped not only by collaboration,…
Identifying Disruptive Models in the Open-Source LLM Community
Xiaoting Wei, Lele Kang, Xuelian Pan +1
The rapid growth of open-source large language models (LLMs) has created a complex ecosystem of model inheritance and reuse. However, existing research has focused mainly on descri…
Efficient Imputation for Patch-based Missing Single-cell Data via Cluster-regularized Optimal Transport
Yuyu Liu, Jiannan Yang, Ziyang Yu +3
Missing data in single-cell sequencing datasets poses significant challenges for extracting meaningful biological insights. However, existing imputation approaches, which often ass…
Self-Supervised Learning on Molecular Graphs: A Systematic Investigation of Masking Design
Jiannan Yang, Veronika Thost, Tengfei Ma
Self-supervised learning (SSL) plays a central role in molecular representation learning. Yet, many recent innovations in masking-based pretraining are introduced as heuristics and…
Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity
Haotian Xu, Jiannan Yang, Tian Gao +2
Activation sparsity offers a compelling route to accelerate large language model (LLM) inference by selectively suppressing hidden activations, yet existing approaches exhibit seve…