7 papers
MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories
Guangzhi Xiong, Xinyuan Zhang, Xiao Yang +14
Long-term egocentric video enables personalized AI assistants to reason about daily life. However, as video histories grow to hundreds of hours spanning months or years, reprocessi…
Function Over Form: Distributional Orthogonalization in Mixture-of-Experts with Replica Expert Mechanism
Jinfan He, Yunzhuo Liu, Kai Zhang +3
The scaling of LLMs increasingly relies on MoE architectures to decouple active computation from total parameter count. However, the efficacy of MoE is often constrained by expert…
Learning What to Share and What to Personalize: Hierarchical Strategy Co-Evolution for Agent Memory
Yupeng Han, Shuochen Liu, Kai Zhang +3
Memory-augmented agents maintain compact user profiles throughout extended conversations, enabling personalized and consistent responses without the need to process the entire dial…
Meta-Task: Turning Terminal Task Synthesis into a Terminal Task for Scalable Agent Training
Zhihong Pan, Jiyuan He, Kai Zhang +5
Training terminal agents at scale requires diverse, verifiable terminal tasks and high-quality interaction trajectories, yet acquiring such data remains a significant challenge. Ex…
SaliMory: Orchestrating Cognitive Memory for Conversational Agents
Kai Zhang, Xinyuan Zhang, Hongda Jiang +11
Conversational agents that serve as lifelong companions must maintain persistent memory across all interactions. However, simply expanding context windows with raw retrieval degrad…
From Entity Reliability to Clean Feedback: An Entity-Aware Denoising Framework Beyond Interaction-Level Signals
Ze Liu, Xianquan Wang, Shuochen Liu +5
Implicit feedback is central to modern recommender systems but is inherently noisy, often impairing model training and degrading user experience. At scale, such noise can mislead l…
Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection
Zhihong Pan, Kai Zhang, Yuze Zhao +1
The inherent capabilities of a language model (LM) and the reasoning strategies it employs jointly determine its performance in reasoning tasks. While test-time scaling is regarded…