1 citations · 1 across the 10 of their papers we have counts for
11 papers
Synthesis Without Training: An Inference-Only Pipeline for Tabular, Temporal, and Relational Synthetic Data
Zilong Zhao, Abdul Raheem, Jiayu Li +5
Synthetic data generation is dominated by the fit-then-sample paradigm: a generative model is trained on a private dataset and then sampled from. Despite its widespread adoption, t…
Towards Irreversible Machine Unlearning for Diffusion Models
Xun Yuan, Zilong Zhao, Jiayu Li +3
Diffusion models are renowned for their state-of-the-art performance in generating synthetic images. However, concerns related to safety, privacy, and copyright highlight the need…
Instruction Tuning of Large Language Models for Tabular Data Generation-in One Day
Milad Abdollahzadeh, Abdul Raheem, Zilong Zhao +5
Tabular instruction tuning has emerged as a promising research direction for improving LLMs understanding of tabular data. However, the majority of existing works only consider que…
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought
Tencent Hunyuan Team, Ao Liu, Botong Zhou +248
As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mam…
Generating Synthetic Data with Formal Privacy Guarantees: State of the Art and the Road Ahead
Viktor Schlegel, Anil A Bharath, Zilong Zhao +1
Privacy-preserving synthetic data offers a promising solution to harness segregated data in high-stakes domains where information is compartmentalized for regulatory, privacy, or i…
TabTreeFormer: Tabular Data Generation Using Hybrid Tree-Transformer
Jiayu Li, Bingyin Zhao, Zilong Zhao +3
Transformers have shown impressive results in tabular data generation. However, they lack domain-specific inductive biases which are critical for preserving the intrinsic character…
TAEGAN: Generating Synthetic Tabular Data For Data Augmentation
Jiayu Li, Zilong Zhao, Kevin Yee +2
Synthetic tabular data generation has gained significant attention for its potential in data augmentation and privacy-preserving data sharing. While recent methods like diffusion a…
CombU: A Combined Unit Activation for Fitting Mathematical Expressions with Neural Networks
Jiayu Li, Zilong Zhao, Kevin Yee +2
The activation functions are fundamental to neural networks as they introduce non-linearity into data relationships, thereby enabling deep networks to approximate complex data rela…
VFLGAN-TS: Vertical Federated Learning-based Generative Adversarial Networks for Publication of Vertically Partitioned Time-Series Data
Xun Yuan, Zilong Zhao, Prosanta Gope +1
In the current artificial intelligence (AI) era, the scale and quality of the dataset play a crucial role in training a high-quality AI model. However, often original data cannot b…
Stepwise Self-Consistent Mathematical Reasoning with Large Language Models
Zilong Zhao, Yao Rong, Dongyang Guo +3
Using Large Language Models for complex mathematical reasoning is difficult, primarily due to the complexity of multi-step reasoning. The main challenges of this process include (1…
IRG: Modular Synthetic Relational Database Generation with Complex Relational Schemas
Jiayu Li, Zilong Zhao, Milad Abdollahzadeh +2
Relational databases (RDBs) are widely used by corporations and governments to store multiple related tables. Their relational schemas pose unique challenges to synthetic data gene…