collaborators

7 papers

cs.LG2025

Memory-Driven Self-Improvement for Decision Making with Large Language Models

Xue Yan, Zijing Ou, Mengyue Yang +4

Large language models (LLMs) have emerged as effective action policies for sequential decision-making (SDM) tasks due to their extensive prior knowledge. However, this broad yet ge…

cs.LG2025

Inference-Time Scaling of Discrete Diffusion Models via Importance Weighting and Optimal Proposal Design

Zijing Ou, Chinmay Pani, Yingzhen Li

Discrete diffusion models have become highly effective across various domains. However, real-world applications often require the generative process to adhere to certain constraint…

cs.LG2025

Discrete Neural Flow Samplers with Locally Equivariant Transformer

Zijing Ou, Ruixiang Zhang, Yingzhen Li

Sampling from unnormalised discrete distributions is a fundamental problem across various domains. While Markov chain Monte Carlo offers a principled approach, it often suffers fro…

cs.LG2025

TabRep: Training Tabular Diffusion Models with a Simple and Effective Continuous Representation

Jacob Si, Zijing Ou, Mike Qu +2

Diffusion models have been the predominant generative model for tabular data generation. However, they face the conundrum of modeling under a separate versus a unified data represe…

cs.LG2025

Neural Flow Samplers with Shortcut Models

Wuhao Chen, Zijing Ou, Yingzhen Li

Sampling from unnormalized densities presents a fundamental challenge with wide-ranging applications, from posterior inference to molecular dynamics simulations. Continuous flow-ba…

stat.ML2024

Energy-Based Modelling for Discrete and Mixed Data via Heat Equations on Structured Spaces

Tobias Schröder, Zijing Ou, Yingzhen Li +1

Energy-based models (EBMs) offer a flexible framework for probabilistic modelling across various data domains. However, training EBMs on data in discrete or mixed state spaces pose…