activity
20242026
most citedEnhancing Foundation Models in Transaction Understanding with LLM-based Sentence Embeddings

2 citations · 2 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Dataset-Level Metrics Attenuate Non-Determinism: A Fine-Grained Non-Determinism Evaluation in Diffusion Language Models

Zhengyu Fang, Zhimeng Jiang, Huiyuan Chen +5

Diffusion language models (DLMs) have emerged as a promising paradigm for large language models (LLMs), yet the non-deterministic behavior of DLMs remains poorly understood. The ex…

cs.LG2025

TransactionGPT

Yingtong Dou, Zhimeng Jiang, Tianyi Zhang +26

We present TransactionGPT (TGPT), a foundation model for consumer transaction data within one of the world's largest payment networks. TGPT is designed to understand and generate t…

cs.LG2025

A Closer Look on Memorization in Tabular Diffusion Model: A Data-Centric Perspective

Zhengyu Fang, Zhimeng Jiang, Huiyuan Chen +4

Diffusion models have shown strong performance in generating high-quality tabular data, but they carry privacy risks by reproducing exact training samples. While prior work focuses…

cs.LG2025

Towards Efficient Large Scale Spatial-Temporal Time Series Forecasting via Improved Inverted Transformers

Jiarui Sun, Chin-Chia Michael Yeh, Yujie Fan +10

Time series forecasting at scale presents significant challenges for modern prediction systems, particularly when dealing with large sets of synchronized series, such as in a globa…

cs.LG2025

UltraSTF: Ultra-Compact Model for Large-Scale Spatio-Temporal Forecasting

Chin-Chia Michael Yeh, Xiran Fan, Zhimeng Jiang +9

Spatio-temporal data, prevalent in real-world applications such as traffic monitoring, financial transactions, and ride-share demands, represents a specialized case of multivariate…

cs.LG2024

Understanding and Mitigating Memorization in Diffusion Models for Tabular Data

Zhengyu Fang, Zhimeng Jiang, Huiyuan Chen +2

Tabular data generation has attracted significant research interest in recent years, with the tabular diffusion models greatly improving the quality of synthetic data. However, whi…