Xingjian Wu
PulseAugur coverage of Xingjian Wu — every cluster mentioning Xingjian Wu across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
FLAME: New Lightweight Time Series Foundation Models Unveiled
Researchers have introduced FLAME, a novel family of lightweight Time Series Foundation Models designed for versatile forecasting tasks. FLAME leverages Legendre Memory, including translated (LegT) and scaled (LegS) var…
-
New ST-EVO Framework Enhances Multi-Agent Communication Topologies
Researchers have introduced ST-EVO, a novel framework for generative spatio-temporal evolution in multi-agent systems (MAS). This approach enhances collaborative intelligence by enabling dialogue-wise communication sche…
-
SEER framework tackles noisy, missing, and shifted time series data
Researchers have introduced SEER, a Transformer-based framework designed to enhance time series forecasting robustness. SEER addresses common data quality issues such as noise, anomalies, missing values, and distributio…
-
DMoA enables LLMs to dynamically adapt agent collaboration
Researchers have introduced Differentiable Mixture-of-Agents (DMoA), a novel framework that allows large language models to dynamically adapt their collaboration strategies during inference. Unlike existing systems that…