4 papers · 1 filter
PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning
Daize Dong, Junlin Chen, Haolong Jia +9
Mixture of Experts (MoE) Large Language Models (LLMs) achieve strong performance at scale. However, reinforcement learning (RL) on MoE-based LLMs often suffers from training instab…
Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques
Shwai He, Daize Dong, Liang Ding +1
Scaling large language models has driven remarkable advancements across various domains, yet the continual increase in model size presents significant challenges for real-world dep…
DLO: Dynamic Layer Operation for Efficient Vertical Scaling of LLMs
Zhen Tan, Daize Dong, Xinyu Zhao +3
In this paper, we introduce Dynamic Layer Operations (DLO), a novel approach for vertically scaling transformer-based Large Language Models (LLMs) by dynamically expanding, activat…
A Graph is Worth Words: Euclideanizing Graph using Pure Transformer
Zhangyang Gao, Daize Dong, Cheng Tan +3
Can we model Non-Euclidean graphs as pure language or even Euclidean vectors while retaining their inherent information? The Non-Euclidean property have posed a long term challenge…