13 papers
Large Language Model-Assisted Preparation of Transportation Management Plans: A Case Study with WisDOT WisTMP System
Zihao Sheng, Pei Li, Zilin Huang +6
Work zones are critical yet hazardous components of transportation infrastructure, requiring carefully designed Transportation Management Plans (TMPs) to ensure safety and mobility…
Acceleration of Diffusion Language Model through Discrete Average Generator
Yidong Ouyang, Zhengyan Wan, Themis Haris +8
Discrete diffusion models and flow matching have emerged as powerful frameworks for generative modeling over discrete state spaces, yet efficient few-step generation remains a fund…
Iterative Exact Discrete Guidance for Energy-Based Sampling
Yuwen Qian, Yidong Ouyang, Zhengyan Wan +1
Sampling from unnormalized distributions over large discrete state spaces becomes difficult when a multimodal target is far from a tractable reference. We introduce Iterative Exact…
Beyond the Leaderboard: Counterfactual Diagnosis of End-to-End and VLA Driving Policies Under Domain Shift
Ruolin Yang, Zilin Huang, Buoyue Wang +4
End-to-end and vision-language-action (VLA) driving policies are compared by leaderboard rank, but a rank reports an outcome, not the behaviour behind it, so it predicts poorly how…
dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models
Zhengyan Wan, Yidong Ouyang, Panwen Hu +1
Discrete flow models (DFMs) are a class of flexible generative models for generating discrete data, and diffusion large language models (dLLMs) can be viewed as a special case with…
Sim2Real-AD: A Modular Sim-to-Real Framework for Deploying VLM-Guided Reinforcement Learning in Real-World Autonomous Driving
Zilin Huang, Zhengyang Wan, Zihao Sheng +3
Vision-language-model (VLM)-guided reinforcement learning (RL) has recently attracted significant attention for it, replacing brittle hand-crafted rewards with semantically grounde…
DriveVLM-RL: Neuroscience-Inspired Reinforcement Learning with Vision-Language Models for Safe and Deployable Autonomous Driving
Zilin Huang, Zihao Sheng, Zhengyang Wan +4
Traditional reinforcement learning (RL) methods rely on manually engineered rewards or sparse collision signals, which fail to capture the rich contextual understanding required fo…
Training-Free Self-Correction for Multimodal Masked Diffusion Models
Yidong Ouyang, Panwen Hu, Zhengyan Wan +7
Masked diffusion models have emerged as a powerful framework for text and multimodal generation. However, their sampling procedure updates multiple tokens simultaneously and treats…
Corrected Samplers for Discrete Flow Models
Zhengyan Wan, Yidong Ouyang, Liyan Xie +3
Discrete flow models (DFMs) have been proposed to learn the data distribution on finite state space, offering a flexible framework as an alternative to discrete diffusion models. A…
Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching
Zhengyan Wan, Yidong Ouyang, Liyan Xie +3
Guidance provides a simple and effective framework for posterior sampling by steering the generation process towards the desired distribution. When modeling discrete data, existing…
Error Analysis of Discrete Flow with Generator Matching
Zhengyan Wan, Yidong Ouyang, Qiang Yao +4
Discrete flow models offer a powerful framework for learning distributions over discrete state spaces and have demonstrated superior performance compared to the discrete diffusion…
High-Dimensional Model Averaging via Cross-Validation
Zhengyan Wan, Fang Fang, Binyan Jiang
Model averaging is an important alternative to model selection with attractive prediction accuracy. However, its application to high-dimensional data remains under-explored. We pro…
Sky-Drive: A Distributed Multi-Agent Simulation Platform for Human-AI Collaborative and Socially-Aware Future Transportation
Zilin Huang, Zihao Sheng, Zhengyang Wan +10
Recent advances in autonomous system simulation platforms have significantly enhanced the safe and scalable testing of driving policies. However, existing simulators do not yet ful…