Ruike Zhang

SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM

2024 · arXiv (Cornell University)

While Large Language Models (LLMs) have achieved remarkable success in various fields, the efficiency of training and inference remains a major challenge. To address this issue, we propose SUBLLM, short for Subsampling-Upsampling-Bypass Large Language Model, …

TARA: Token-level Attribute Relation Adaptation for Multi-Attribute Controllable Text Generation

2024

Multi-attribute controllable text generation (CTG) aims to generate fluent text satisfying multiple attributes, which is an important and challenging task.The majority of previous research on multi-attribute CTG has ignored the interrelations of attributes that affect …