← Search

Zhoutong Wu

2 accepted papers

2025

Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads

NeurIPS 2025poster

Transformer models have driven breakthroughs across various language tasks by their strong capability to learn rich contextual representations. Scaling them to improve representation, however, often demands substantial memory and compute costs, such as the Key-Value (KV) cache used during auto-regre…

Cited by 0SourcecodeScholar
2024

Separation and Bias of Deep Equilibrium Models on Expressivity and Learning Dynamics

NeurIPS 2024poster

The deep equilibrium model (DEQ) generalizes the conventional feedforward neural network by fixing the same weights for each layer block and extending the number of layers to infinity. This novel model directly finds the fixed points of such a forward process as features for prediction. Despite emp…

Cited by 0SourcePDFScholar