4 papers
DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing
Jinyu Guo, Zhihan Zhang, Jiehui Xie +7
The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-context inference. While existing…
Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game
HuaDong Jian, Chenghao Li, Haoyu Wang +4
In long-horizon open-world multi-agent systems, existing methods often treat local anomalies as automatic triggers for communication. This default design introduces coordination no…
TDA-RC: Task-Driven Alignment for Knowledge-Based Reasoning Chains in Large Language Models
Jiaquan Zhang, Qigan Sun, Chaoning Zhang +11
Enhancing the reasoning capability of large language models (LLMs) remains a core challenge in natural language processing. The Chain-of-Thought (CoT) paradigm dominates practical…
Learning Wisdom from Errors: Promoting LLM's Continual Relation Learning through Exploiting Error Cases
Shaozhe Yin, Jinyu Guo, Kai Shuang +2
Continual Relation Extraction (CRE) aims to continually learn new emerging relations while avoiding catastrophic forgetting. Existing CRE methods mainly use memory replay and contr…