activity
20242026
most citedMemory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning

2 citations · 9 across the 23 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

DynImmune-BERT: Dynamic Immune Repertoire Modeling with Neural ODE Driven Continuous Transformers

Rong Fu, Yongtai Liu, Xiaowen Ma +5

Longitudinal T cell receptor repertoires contain signals of clonal expansion, contraction, disappearance, and reappearance after immune perturbation. Static repertoire language mod…

cs.LG20261 cited

SphUnc: Hyperspherical Uncertainty Decomposition and Causal Identification via Information Geometry

Rong Fu, Chunlei Meng, Jinshuo Liu +8

Reliable decision-making in complex multi-agent systems requires calibrated predictions and interpretable uncertainty. We introduce SphUnc, a unified framework combining hyperspher…

cs.LG2025

Ada-MoGE: Adaptive Mixture of Gaussian Expert Model for Time Series Forecasting

Zhenliang Ni, Xiaowen Ma, Zhenkai Wu +3

Multivariate time series forecasts are widely used, such as industrial, transportation and financial forecasts. However, the dominant frequencies in time series may shift with the…

cs.LG2025

Expert Merging: Model Merging with Unsupervised Expert Alignment and Importance-Guided Layer Chunking

Dengming Zhang, Xiaowen Ma, Zhenliang Ni +4

Model merging, which combines multiple domain-specialized experts into a single model, offers a practical path to endow Large Language Models (LLMs) and Multimodal Large Language M…

cs.LG2025

TimeExpert: Boosting Long Time Series Forecasting with Temporal Mix of Experts

Xiaowen Ma, Shuning Ge, Fan Yang +5

Transformer-based architectures dominate time series modeling by enabling global attention over all timestamps, yet their rigid 'one-size-fits-all' context aggregation fails to add…

cs.LG2025

Self-Evolving Multi-Agent Systems via Textual Backpropagation

Xiaowen Ma, Yunpu Ma, Chenyang Lin +6

Leveraging multiple Large Language Models (LLMs) has proven effective for addressing complex, high-dimensional tasks, but current approaches often rely on static, manually engineer…