Yikang Shen

Do Larger Language Models Generalize Better? A Scaling Law for Implicit Reasoning at Pretraining Time

SELECT: Search-Enhanced Language Models for Analog Circuit Topology Generation

PaTH Attention: Position Encoding via Accumulating Householder Transformations

Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study

API Pack: A Massive Multi-Programming Language Dataset for API Call Generation

LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation

Power Scheduler: A Batch Size and Token Number Agnostic Learning Rate Scheduler

Towards Efficient and No Forgetting Domain Continual Pretraining by Mitigating the Stability Gap