activity
20242026
collaborators

9 papers

cs.RO2026

OmniSCS: Omni Safety-Critical Scenario Synthesis for Autonomous Driving via a Fully Editable Driving World

Xiaoyun Dong, Qian Xu, Yang Lu +3

The synthesis of safety-critical scenarios (SCS) and their evaluation through closed-loop simulations are crucial for developing robust autonomous driving systems. A key aspect of…

cs.CV2026

Geometry Reinforced Efficient Attention Tuning Equipped with Normals for Robust Stereo Matching

Jiahao Li, Xinhong Chen, Zhengmin Jiang +3

Despite remarkable advances in image-driven stereo matching over the past decade, Synthetic-to-Realistic ZeroShot (Syn-to-Real) generalization remains an open challenge. This subop…

cs.CV2026

Mode-as-Sequence: Translating Multimodal Motion Prediction into Unified Sequential Mode Modeling

Zikang Zhou, Haibo Hu, Xinhong Chen +5

Multimodal motion forecasting is inherently under-supervised: each training scene provides only one realized future, yet multiple plausible futures exist. This sparse supervision o…

cs.CV2025

SATMapTR: Satellite Image Enhanced Online HD Map Construction

Bingyuan Huang, Guanyi Zhao, Qian Xu +3

High-definition (HD) maps are evolving from pre-annotated to real-time construction to better support autonomous driving in diverse scenarios. However, this process is hindered by…

cs.CL2025

Profile-LLM: Dynamic Profile Optimization for Realistic Personality Expression in LLMs

Shi-Wei Dai, Yan-Wei Shie, Tsung-Huan Yang +2

Personalized Large Language Models (LLMs) have been shown to be an effective way to create more engaging and enjoyable user-AI interactions. While previous studies have explored us…

cs.CV2025

Global Regulation and Excitation via Attention Tuning for Stereo Matching

Jiahao Li, Xinhong Chen, Zhengmin Jiang +3

Stereo matching achieves significant progress with iterative algorithms like RAFT-Stereo and IGEV-Stereo. However, these methods struggle in ill-posed regions with occlusions, text…