Andrew Luo

我是香港大学助理教授，由香港大学数据科学研究院和心理学系于 2024 年 10 月合聘。

我在2024从卡内基梅隆大学 (CMU) 获得了机器学习和计算神经科学联合博士学位。在那里我与 Michael Tarr and Leila Wehbe 一起工作。在此之前，我于 2019 年获得了麻省理工学院 (MIT) 计算机科学本科学位。我也从 CMU 获得了机器学习硕士学位。

我的工作重点是理解视觉感知背后的计算原理，以及这些原理如何能帮助我们改善并设计更好的AI生成模型。最终，我的目标是弥合人类和机器视觉之间的差距，从而加深对人类认知的理解 & 达到人工智能的进步。

2024 年末和2025 夏天，我正在招有机器视觉, AI for Neuroscience (NeuroAI), 和图像生成模型背景的博士生加入我的研究团队(加入港大)。也欢迎博士生，硕士生和本科生远程合作或者远程RA。请发送电子邮件至 aluo@hku.hk，附上简历和自我介绍。

Email  /  HKU Email  /  Google Scholar  /  Github /  WeChat / English

研究

我想理解人类的感知机理，并构建更好的生成模型和具有类人推理能力的机器。

We propose an efficient gradient-free distillation module capable of extraction high quality dense CLIP embeddings, and utilize these embeddings to understand semantic selectivity in the visual cortex.

We investigate the problem of visual-acoustic navigation conditioned on a continuous acoustic field representation of audio.

We leverage ideas from information theory to understand the contributions of individual text tokens and their interactions when generating images.

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.