6 papers
PsyMemBehav: Psychology-Informed and Memory-Grounded Two-Level Identity-to-Action Reasoning for Social-Media Behavior Simulation
Wenji Zhang, Xilong Cheng, Yunxiao Qin +8
Large language models (LLMs) support social simulation, but faithfully reproducing real users requires grounding both structured platform decisions and language in sparse, noisy be…
RippleMem: From Isolated Retrieval to Associative Recollection for Long-Term Agent Memory
Jingbo Ji, Lingyi Li, Xilong Cheng +4
LLM-based agents increasingly rely on external memory to support long-horizon reasoning and interaction. However, the main bottleneck is not simply storing past experience, but rec…
Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric Video
Yuting Tan, Xilong Cheng, Yunxiao Qin +2
Humans develop visual intelligence through perceiving and interacting with their environment - a self-supervised learning process grounded in egocentric experience. Inspired by thi…
PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs
Xilong Cheng, Yunxiao Qin, Yuting Tan +4
Existing LLM-based role-playing methods often rely on superficial textual descriptions or simplistic metrics, inadequately modeling both intrinsic and extrinsic character dimension…
FSMLP: Modelling Channel Dependencies With Simplex Theory Based Multi-Layer Perceptions In Frequency Domain
Zhengnan Li, Haoxuan Li, Hao Wang +3
Time series forecasting (TSF) plays a crucial role in various domains, including web data analysis, energy consumption prediction, and weather forecasting. While Multi-Layer Percep…
FTMixer: Frequency and Time Domain Representations Fusion for Time Series Modeling
Zhengnan Li, Yunxiao Qin, Xilong Cheng +1
Time series data can be represented in both the time and frequency domains, with the time domain emphasizing local dependencies and the frequency domain highlighting global depende…