CodeCytos is a novel coding-based reasoning agent framework that enables dynamic, programmable interaction with spatial molecular imaging data, significantly improving the automation and customization…

The paper proposes GC-MoE, a graph-conditioned Mixture of Experts framework, to improve traffic forecasting by assigning personalized, specialized forecasting experts to individual road segments.

The paper introduces a novel framework that aligns single white blood cell images with genetic data (karyotype and somatic mutations) to significantly improve the diagnosis of blood cancers, outperfor…

The paper proposes Task-Aware Coactivation Grouping (TACG) to significantly reduce communication costs in multi-task MoE inference by grouping experts based on task-specific co-activation patterns, ou…

DOT-MoE introduces a novel framework that treats the decomposition of dense layers into Mixture of Experts (MoE) as a Differentiable Optimal Transport problem, achieving superior efficiency while pres…

The paper introduces SpatialBench-Long, a comprehensive benchmark designed to test AI agents' ability to perform end-to-end scientific reasoning and derive biological claims from complex, raw spatial…

The paper introduces Optimal Mixture Transport (OMT), a scalable framework that reformulates optimal transport by using mixtures of subpopulations, resulting in a unique, biconvex optimization problem…

The paper introduces CORE, a contrastive evidence organization method, which significantly improves the accuracy of LLM-based predictions of gene expression changes following cellular perturbations by…

The paper proposes finetuning the Segment Anything Model (SAM) using large-scale synthetic fluorescence microscopy data to achieve robust and high-performing instance segmentation of mitochondria, add…

The paper introduces RA-MoE, a novel fine-tuning framework that leverages the internal routing structure of Mixture-of-Experts (MoE) models to improve performance on multilingual downstream tasks by a…

RouteScan introduces a non-intrusive framework that audits the safety of Mixture-of-Experts (MoE) LLMs by analyzing low-level GPU expert routing telemetry, achieving high accuracy even on unseen harmf…

The paper introduces Influence-Guided Symbolic Regression (IGSR), a novel framework that uses granular influence scores to guide LLMs in efficiently searching for and discovering complex mathematical…

This paper introduces BBOmix, an open-source benchmark for unsupervised representation learning on real-world biological data.

Agentic-J is a containerized, multi-agent AI assistant designed to enable biologists to perform complex, reproducible biological microscopy image analysis by specifying tasks in natural language.

dMoE proposes a block-level Mixture-of-Experts (MoE) framework for Diffusion Large Language Models (dLLMs) that aggregates token-level expert distributions into a unified block-level distribution, sig…

The paper introduces ProbMoE, a probabilistic routing framework that tackles the non-differentiability of top-$k$ routing in Mixture-of-Experts (MoE) models, achieving strong performance with improved…

This paper proposes a new router redesign for Mixture-of-Experts models using Manifold Power Iteration to align router rows with the principal singular directions of associated experts.

The paper proposes a novel Generative Counterfactual Attention-guided Network (GCAN) that uses multimodal connectomes and brain atlas knowledge to provide explainable and highly accurate diagnosis of…

The paper proposes MoEIoU, a novel mixture-of-experts based regression loss that adaptively models bounding-box localization errors, achieving superior convergence and accuracy in object detection.