Summary of Lora-switch: Boosting the Efficiency Of Dynamic Llm Adapters Via System-algorithm Co-design, by Rui Kong et al.
LoRA-Switch: Boosting the Efficiency of Dynamic LLM Adapters via System-Algorithm Co-designby Rui Kong, Qiyang Li,…
LoRA-Switch: Boosting the Efficiency of Dynamic LLM Adapters via System-Algorithm Co-designby Rui Kong, Qiyang Li,…
MeteoRA: Multiple-tasks Embedded LoRA for Large Language Modelsby Jingwei Xu, Junyu Lai, Yunpeng HuangFirst submitted…
Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Expertsby Yunxin Li, Shenyuan Jiang, Baotian Hu,…
Many Hands Make Light Work: Task-Oriented Dialogue System with Module-Based Mixture-of-Expertsby Ruolin Su, Biing-Hwang JuangFirst…
SUTRA: Scalable Multilingual Language Model Architectureby Abhijit Bendale, Michael Sapienza, Steven Ripplinger, Simon Gibbs, Jaewon…
A Mixture-of-Experts Approach to Few-Shot Task Transfer in Open-Ended Text Worldsby Christopher Z. Cui, Xiangyu…
Mix of Experts Language Model for Named Entity Recognitionby Xinwei Chen, Kun Li, Tianyou Song,…
MMoE: Robust Spoiler Detection with Multi-modal Information and Domain-aware Mixture-of-Expertsby Zinan Zeng, Sen Ye, Zijian…
ConstitutionalExperts: Training a Mixture of Principle-based Promptsby Savvas Petridis, Ben Wedin, Ann Yuan, James Wexler,…