11 papers
Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR
Yulong Zhang, Tianyi Liang, Xinyue Huang +5
Optical Character Recognition (OCR) is fundamental to Vision-Language Models (VLMs) and high-quality data generation for LLM training. Yet, despite progress in average OCR accuracy…
NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networks
Fangzhou Lin, Yuping Wang, Yuliang Guo +7
Partially Supervised Multi-Task Learning (PS-MTL) aims to leverage knowledge across tasks when annotations are incomplete. Existing approaches, however, have largely focused on the…
3DGEER: 3D Gaussian Rendering Made Exact and Efficient for Generic Cameras
Zixun Huang, Cho-Ying Wu, Yuliang Guo +2
3D Gaussian Splatting (3DGS) achieves an appealing balance between rendering quality and efficiency, but relies on approximating 3D Gaussians as 2D projections--an assumption that…
No Calibration, No Depth, No Problem: Cross-Sensor View Synthesis with 3D Consistency
Cho-Ying Wu, Zixun Huang, Xinyu Huang +1
We present the first study of cross-sensor view synthesis across different modalities. We examine a practical, fundamental, yet widely overlooked problem: getting aligned RGB-X dat…
End-to-End Visual Autonomous Parking via Control-Aided Attention
Chao Chen, Shunyu Yao, Yuanwu He +7
Precise parking requires an end-to-end system where perception adaptively provides policy-relevant details - especially in critical areas where fine control decisions are essential…
Dino-Diffusion Modular Designs Bridge the Cross-Domain Gap in Autonomous Parking
Zixuan Wu, Hengyuan Zhang, Ting-Hsuan Chen +4
Parking is a critical pillar of driving safety. While recent end-to-end (E2E) approaches have achieved promising in-domain results, robustness under domain shifts (e.g., weather an…