Yau-Meng Wong

CS @ Columbia University

Projects


An Abstraction Metric for Language Model Features


Developed and evaluated a novel abstraction metric for sparse auto-encoder features, streamlining the identification of conceptually deep and relevant features in large language models. Conducted experiments on Gemma-2-2B.


CLIP2CLAP: Joint Embedding Space Alignment for Image to Audio Generation


How similar are two joint embedding spaces? Can a small feed forward network map one to the other?


SkateMAE: Synthetic Data for Skateboard Pose Estimation


Skateboard pose estimation is a novel problem but lacks any labeled data. Is synthetic data the solution?


NICE-Transeg: Non-iterative Coarse-to-fine Transformer Network For Joint Affine and Deformable 2D Image Registration and Segmentation


Can combining the techniques of two different state of the art MRI registration techniques shave a few points off the evals? Not this time.


Tools
Translate to