4 papers · 1 filter
Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents
Peng Xu, Sijia Chen, Junzhuo Li +1
Group-based reinforcement learning effectively post-trains LLM agents for long-horizon, sparse-reward tasks by deriving step-level credit from trajectory outcomes. However, this ti…
Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design
Junzhuo Li, Peijie Jiang, Changxin Tian +3
This paper presents a novel extension of neural scaling laws to Mixture-of-Experts (MoE) models, focusing on the optimal allocation of compute between expert and attention sub-laye…
Dynamic Expert Specialization: Towards Catastrophic Forgetting-Free Multi-Domain MoE Adaptation
Junzhuo Li, Bo Wang, Xiuze Zhou +1
Mixture-of-Experts (MoE) models offer immense capacity via sparsely gated expert subnetworks, yet adapting them to multiple domains without catastrophic forgetting remains an open…
LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning
Junyu Chen, Junzhuo Li, Zhen Peng +4
Quantization and fine-tuning are crucial for deploying large language models (LLMs) on resource-constrained edge devices. However, fine-tuning quantized models presents significant…