4 papers
Role-aware Heuristic Episodic Attention for Conversational LLMs
Wanyang Hong, Zhaoning Zhang, Yi Chen +5
Large language models often lose track of persistent instructions and relevant information as multi-turn conversations grow. We study this cumulative contextual decay through three…
Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference
Baihui Liu, Kaiyuan Tian, Wei Wang +3
Mixture-of-Experts (MoE) has become a dominant architecture for scaling large language models due to their sparse activation mechanism. However, the substantial number of expert ac…
Let the Agent Search: Autonomous Exploration Beats Rigid Workflows in Temporal Question Answering
Xufei Lv, Jiahui Yang, Haoyuan Sun +5
Temporal Knowledge Graph Question Answering (TKGQA) is challenging because it requires multi-hop reasoning under complex temporal constraints. Recent LLM-based approaches have impr…
Role-aware Heuristic Episodic Attention for Conversational LLMs
Wanyang Hong, Zhaoning Zhang, Yi Chen +5
Large language models often lose track of persistent instructions and relevant information as multi-turn conversations grow. We study this cumulative contextual decay through three…