Brandon is currently a Ph.D. student at CMU in the Machine Learning Department advised by Professor Ruslan Salakhutdinov, and was an undergraduate at UC Berkeley working with Professor Sergey Levine. Brandon's research includes reasoning, generative models, and agents. He produces electronic music and considers how machine learning research can enhance creative workflows.
Brandon is an NDSEG Fellow and Amazon alumni. His research is published in top ML conferences, and featured as oral presentations at NeurIPS 2024, the NeurIPS 2023 Synthetic Data Workshop, and CVPR Embodied AI Workshop, where his work MaSS won the Rearrangement Challenge.
Research
Towards Internet-Scale Training For Agents
ICLR 2025 Workshop on Data Problems for Foundation Models (oral, top 4%)
[pdf] [code]
Wayward Concepts In Large Multimodal Models
NeurIPS 2024 Workshop on Scientific Methods for Understanding Deep Learning
ICLR 2025
[pdf] [code]
Stylus: Automatic Adapter Selection For Diffusion Models
NeurIPS 2024 (oral, top 0.39%)
[pdf] [code]
Effective Data Augmentation With Diffusion Models
ICLR 2023 Foundation Models Workshop (oral)
NeurIPS 2023 Foundation Models Workshop (oral)
NeurIPS 2023 Synthetic Data Workshop (oral, top 2%)
ICLR 2024
[pdf] [code] [talk]
A Simple Approach for Visual Room Rearrangement: 3D Mapping and Semantic Search
CVPR 2022 Embodied AI Workshop (oral)
ICLR 2023
[pdf] [code] [talk]
