activity
20242026
collaborators

10 papers

cs.CV2026

Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representation

Xingtai Gui, Meijie Zhang, Tianyi Yan +5

End-to-end autonomous driving aims to generate safe and plausible planning policies from raw sensor input. Driving world models have shown great potential in learning rich represen…

cs.CV2026

AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models

Tianyi Yan, Tao Tang, Xingtai Gui +11

End-to-end models for autonomous driving hold the promise of learning complex behaviors directly from sensor data, but face critical challenges in safety and handling long-tail eve…

cs.CV2025

TrajDiff: End-to-end Autonomous Driving without Perception Annotation

Xingtai Gui, Jianbo Zhao, Wencheng Han +5

End-to-end autonomous driving systems directly generate driving policies from raw sensor inputs. While these systems can extract effective environmental features for planning, rely…

cs.CV2025

HiCoGen: Hierarchical Compositional Text-to-Image Generation in Diffusion Models via Reinforcement Learning

Hongji Yang, Yucheng Zhou, Wencheng Han +4

Recent advances in diffusion models have demonstrated impressive capability in generating high-quality images for simple prompts. However, when confronted with complex prompts invo…

cs.CV2025

RLGF: Reinforcement Learning with Geometric Feedback for Autonomous Driving Video Generation

Tianyi Yan, Wencheng Han, Xia Zhou +4

Synthetic data is crucial for advancing autonomous driving (AD) systems, yet current state-of-the-art video generation models, despite their visual realism, suffer from subtle geom…

cs.CV2025

ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictions

Dubing Chen, Jin Fang, Wencheng Han +5

3D semantic occupancy and flow prediction are fundamental to spatiotemporal scene understanding. This paper proposes a vision-based framework with three targeted improvements. Firs…