16 papers
A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs
Bizu Feng, Zhimu Yang, Shuming Wang +4
We study feature-level and node-level explanations for graph neural networks (GNNs) through the lens of Aumann-Shapley attribution. Path-integral methods such as Integrated Gradien…
Monkey King Bang: A Unified Scientific Multimodal Foundation Model
Hesen Chen, Xinyu Su, Xiaomeng Yang +11
Scientific discovery is increasingly shifting from isolated disciplines to multi-domain reasoning, and AI for science faces a similar transition. Existing systems are either specia…
Mind the Tool Failures: Achieving Synergistic Tool Gains for Medical Agents
Yunhui Gan, Tan Pan, Kaiyu Guo +5
Medical AI agents increasingly use external tools for diagnosis, treatment recommendation, and evidence retrieval, yet most existing approaches assume that task-appropriate tools a…
FLAG: Foundation model representation with Latent diffusion Alignment via Graph for spatial gene expression prediction
Qi Si, Penglei Wang, Yushuai Wu +5
Predicting spatial gene expression from routine H\&E enables large-scale molecular profiling, yet current models treat this as isolated pointwise tasks, thereby overlooking essenti…
Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging
Tan Pan, Shuhao Mei, Yixuan Sun +8
Self-supervised pre-training methods in medical imaging typically treat each individual as an isolated instance, learning representations through augmentation-based objectives or m…
Project and Generate: Divergence-Free Neural Operators for Incompressible Flows
Xigui Li, Hongwei Zhang, Ruoxi Jiang +6
Learning-based models for fluid dynamics often operate in unconstrained function spaces, leading to physically inadmissible, unstable simulations. While penalty-based methods offer…