Logan Grosenick — accepted AI-conference papers

2026

Contrastive Diffusion Alignment: Learning Structured Latents for Controllable Generation

Ruchi Sandilya, Sumaira Perez, Charles Lynch, Lindsay Victoria, Benjamin Zebley, Derrick Buchanan +6

ICML 2026poster

Diffusion models excel at generation, but their latent spaces are high dimensional and not explicitly organized for interpretation or control. We introduce ConDA (Contrastive Diffusion Alignment), a plug-and-play geometry layer that applies contrastive learning to pretrained diffusion latents using …

Cited by 1 Source ↗Scholar ↗

2025

Learning to Route: Per-Sample Adaptive Routing for Multimodal Multitask Prediction

Marzieh Ajirak, Oded Bein, Ellen Rose Bowen, Dora Kanellopoulos, Avital Falk, FAITH M. GUNNING +2

NeurIPS 2025poster

We propose a unified framework for adaptive routing in multitask, multimodal prediction settings where data heterogeneity and task interactions vary across samples. We introduce a routing-based architecture that dynamically selects modality processing pathways and task-sharing strategies on a per-sa…

Cited by 0 Source ↗Scholar ↗

2024

EpiCare: A Reinforcement Learning Benchmark for Dynamic Treatment Regimes

Mason Hargrave, Alex Spaeth, Logan Grosenick

NeurIPS 2024poster

Healthcare applications pose significant challenges to existing reinforcement learning (RL) methods due to implementation risks, low data availability, short treatment episodes, sparse rewards, partial observations, and heterogeneous treatment effects. Despite significant interest in using RL to gen…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Generalizing CNNs to graphs with learnable neighborhood quantization

Isaac Osafo Nkansah, Neil Gallagher, Ruchi Sandilya, Conor Liston, Logan Grosenick

NeurIPS 2024poster

Convolutional neural networks (CNNs) have led to a revolution in analyzing array data. However, many important sources of data, such as biological and social networks, are naturally structured as graphs rather than arrays, making the design of graph neural network (GNN) architectures that retain the…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Simple and scalable algorithms for cluster-aware precision medicine

Amanda M. Buch, Conor Liston, Logan Grosenick

AISTATS 2024poster

AI-enabled precision medicine promises a transformational improvement in healthcare outcomes. However, training on biomedical data presents significant challenges as they are often high dimensional, clustered, and of limited sample size. To overcome these challenges, we propose a simple and scalable…

Cited by 1 Source ↗PDF ↗Scholar ↗