Andrew Luo

I am a PhD student at Carnegie Mellon University.

At CMU, I am affiliated with the Neuroscience Institute and the Machine Learning Department, pursuing a joint PhD in Neural Computation & Machine Learning. I am co-advised by Leila Wehbe and Michael Tarr. I earned my undergraduate degree in Computer Science from MIT in 2019, and a Master of Science in Machine Learning Research from CMU.

My current research focuses on computational methods for studying visual perception in the human brain, with experience in 3D generative models.

Email  /  CMU Email  /  Google Scholar  /  Github /  WeChat

Research

I'm interested in generative models and their applications in studying the brain. My current research focuses on semantic divisions within the human visual cortex.

We propose a way to leverage contrastive image-language models (CLIP) and fine-tuned language models to generate natural language descriptions of voxel-wise selectivity in the higher order visual areas.

We propose a way to generate images that activate regions of the brain by leveraging natural image priors from Diffusion models.

We examine the selectivity of the brain to real-world size in complex natural images.

We propose a learnable and compact implicit encoding for acoustic impulse responses. We find that our NAFs can achieve state-of-the-art performance at a tiny size footprint.

We show that having a prototype memory with attention mechanisms can improve image synthesis quality, and learn interpretable visual concept clusters.

We propose a surface based discriminator for implicit shape generation. Our discriminator uses differentiable ray-casting and marching cubes.

We propose contrained scene synthesis using graph neural networks, we show that generated scenes can be refined using differentiable rendering.

We propose a learnable decomposition of 3D shapes into symbolic programs that can be executed.