2 citations · 3 across the 5 of their papers we have counts for
5 papers
Forward Euler for Wasserstein Gradient Flows: Breakdown and Regularization
Yewei Xu, Qin Li
Wasserstein gradient flows have become a central tool for optimization problems over probability measures. A natural numerical approach is forward-Euler time discretization. We sho…
Correcting Noisy Multilabel Predictions: Modeling Label Noise through Latent Space Shifts
Weipeng Huang, Qin Li, Yang Xiao +5
Noise in data appears to be inevitable in most real-world machine learning applications and would cause severe overfitting problems. Not only can data features contain noise, but l…
Forward-Euler time-discretization for Wasserstein gradient flows can be wrong
Yewei Xu, Qin Li
In this note, we examine the forward-Euler discretization for simulating Wasserstein gradient flows. We provide two counter-examples showcasing the failure of this discretization e…
FinVerse: An Autonomous Agent System for Versatile Financial Analysis
Siyu An, Qin Li, Junru Lu +2
With the significant advancements in cognitive intelligence driven by LLMs, autonomous agent systems have attracted extensive attention. Despite this growing interest, the developm…
IEKM: A Model Incorporating External Keyword Matrices
Cheng Luo, Qin Li, Zhao Yan +2
A customer service platform system with a core text semantic similarity (STS) task faces two urgent challenges: Firstly, one platform system needs to adapt to different domains of…