5 papers
D-MEM: Dopamine-Gated Agentic Memory via Reward Prediction Error Routing
Yuru Song, Qi Xin
Autonomous LLM agents require structured long-term memory, yet current "append-and-evolve" systems like A-MEM face O(N^2) write-latency and excessive token costs. We introduce D-ME…
Compress to Focus: Efficient Coordinate Compression for Policy Optimization in Multi-Turn GUI Agents
Yurun Song, Jiong Yin, Rongjunchen Zhang +1
Multi-turn GUI agents enable complex task completion through sequential decision-making, but suffer from severe context inflation as interaction history accumulates. Existing strat…
Fine-Tuning vs. RAG for Multi-Hop Question Answering with Novel Knowledge
Zhuoyi Yang, Yurun Song, Iftekhar Ahmed +1
Multi-hop question answering is widely used to evaluate the reasoning capabilities of large language models (LLMs), as it requires integrating multiple pieces of supporting knowled…
AMAQ: Adaptive Mixed-bit Activation Quantization for Collaborative Parameter Efficient Fine-tuning
Yurun Song, Zhuoyi Yang, Ian G. Harris +1
Large Language Models (LLMs) are scaling rapidly, creating significant challenges for collaborative server client distributed training, particularly in terms of communication effic…
ShareLoRA: Parameter Efficient and Robust Large Language Model Fine-tuning via Shared Low-Rank Adaptation
Yurun Song, Junchen Zhao, Ian G. Harris +1
In this paper, we introduce \textbf{Share}d \textbf{Lo}w \textbf{R}ank \textbf{A}daptation (ShareLoRA), a Large Language Model (LLM) fine-tuning technique that balances parameter e…