most citedSkill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills

2 citations · 3 across the 2 of their papers we have counts for

collaborators

6 papers

q-bio.QM20261 cited

SPATIA: Multimodal Generation and Prediction of Spatial Cell Phenotypes

Zhenglun Kong, Mufan Qiu, John Boesen +5

Understanding how cellular morphology, gene expression, and spatial context jointly shape tissue function is a central challenge in biology. Image-based spatial transcriptomics tec…

cs.CL20262 cited

Skill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills

Justin Chih-Yao Chen, Sukwon Yun, Elias Stengel-Eskin +2

Combining existing pre-trained LLMs is a promising approach for diverse reasoning tasks. However, task-level expert selection is often too coarse-grained, since different instances…

cs.LG2025

Oldie but Goodie: Re-illuminating Label Propagation on Graphs with Partially Observed Features

Sukwon Yun, Xin Liu, Yunhak Oh +4

In real-world graphs, we often encounter missing feature situations where a few or the majority of node features, e.g., sensitive information, are missed. In such scenarios, direct…

cs.CV2025

SparseC-AFM: a deep learning method for fast and accurate characterization of MoS with C-AFM

Levi Harris, Md Jayed Hossain, Mufan Qiu +6

The increasing use of two-dimensional (2D) materials in nanoelectronics demands robust metrology techniques for electrical characterization, especially for large-scale production.…

cs.CL2025

Spatial Coordinates as a Cell Language: A Multi-Sentence Framework for Imaging Mass Cytometry Analysis

Chi-Jane Chen, Yuhang Chen, Sukwon Yun +2

Image mass cytometry (IMC) enables high-dimensional spatial profiling by combining mass cytometry's analytical power with spatial distributions of cell phenotypes. Recent studies l…

cs.LG2025

I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts

Jiayi Xin, Sukwon Yun, Jie Peng +4

Modality fusion is a cornerstone of multimodal learning, enabling information integration from diverse data sources. However, vanilla fusion methods are limited by (1) inability to…