4 papers
DRIP: Dynamic patch Reduction via Interpretable Pooling
Yusen Peng, Sachin Kumar
Recently, the advances in vision-language models, including contrastive pretraining and instruction tuning, have greatly pushed the frontier of multimodal AI. However, owing to the…
CE-Bench: Towards a Reliable Contrastive Evaluation Benchmark of Interpretability of Sparse Autoencoders
Alex Gulko, Yusen Peng, Sachin Kumar
Sparse autoencoders (SAEs) are a promising approach for uncovering interpretable features in large language models (LLMs). While several automated evaluation methods exist for SAEs…
CascadeFormer: A Family of Two-stage Cascading Transformers for Skeleton-based Human Action Recognition
Yusen Peng, Alper Yilmaz
Skeleton-based human action recognition leverages sequences of human joint coordinates to identify actions performed in videos. Owing to the intrinsic spatiotemporal structure of s…
E.A.R.T.H.: Structuring Creative Evolution through Model Error in Generative AI
Yusen Peng, Shuhua Mao
How can AI move beyond imitation toward genuine creativity? This paper proposes the E.A.R.T.H. framework, a five-stage generative pipeline that transforms model-generated errors in…