12 papers
Robust-WAM: Bridging Generative Pretraining and Semantic Foresight in World-Action Models
Haodong Yan, Junfeng Li, Junjie He +12
Mainstream World-Action Models (WAMs) adapt pretrained video generation models (VGMs) for robot control, transferring their learned dynamics prior for action prediction. These VGMs…
InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving
Xiaoyu Ye, Leheng Li, Xinyu Ji +8
Generating realistic, controllable, and temporally coherent urban environments is a critical yet unresolved challenge in the autonomous driving community. In this paper, we introdu…
DLWM: Dual Latent World Models enable Holistic Gaussian-centric Pre-training in Autonomous Driving
Yiyao Zhu, Ying Xue, Haiming Zhang +8
Vision-based autonomous driving has gained much attention due to its low costs and excellent performance. Compared with dense BEV (Bird's Eye View) or sparse query models, Gaussian…
DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Models
Zhide Zhong, Junfeng Li, Junjie He +10
Vision-Language-Action (VLA) models map visual observations and language instructions directly to robotic actions. While effective for simple tasks, standard VLA models often strug…
Lean Learning Beyond Clouds: Efficient Discrepancy-Conditioned Optical-SAR Fusion for Semantic Segmentation
Chenxing Meng, Wuzhou Quan, Yingjie Cai +3
Cloud occlusion severely degrades the semantic integrity of optical remote sensing imagery. While incorporating Synthetic Aperture Radar (SAR) provides complementary observations,…
S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresight
Haodong Yan, Zhide Zhong, Jiaguan Zhu +10
Video action models (VAMs) have emerged as a promising paradigm for robot learning, owing to their powerful visual foresight for complex manipulation tasks. However, current VAMs,…
SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving
Haiming Zhang, Yiyao Zhu, Wending Zhou +5
Sparse Perception Models (SPMs) adopt a query-driven paradigm that forgoes explicit dense BEV or volumetric construction, enabling highly efficient computation and accelerated infe…
Occ-LLM: Enhancing Autonomous Driving with Occupancy-Based Large Language Models
Tianshuo Xu, Hao Lu, Xu Yan +3
Large Language Models (LLMs) have made substantial advancements in the field of robotic and autonomous driving. This study presents the first Occupancy-based Large Language Model (…
VisionPAD: A Vision-Centric Pre-training Paradigm for Autonomous Driving
Haiming Zhang, Wending Zhou, Yiyao Zhu +7
This paper introduces VisionPAD, a novel self-supervised pre-training paradigm designed for vision-centric algorithms in autonomous driving. In contrast to previous approaches that…
DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation
Jing He, Haodong Li, Yongzhe Hu +4
In the realm of image generation, creating customized images from visual prompt with additional textual instruction emerges as a promising endeavor. However, existing methods, both…
OmniBooth: Learning Latent Control for Image Synthesis with Multi-modal Instruction
Leheng Li, Weichao Qiu, Xu Yan +6
We present OmniBooth, an image generation framework that enables spatial control with instance-level multi-modal customization. For all instances, the multimodal instruction can be…
SyntheOcc: Synthesize Geometric-Controlled Street View Images through 3D Semantic MPIs
Leheng Li, Weichao Qiu, Yingjie Cai +4
The advancement of autonomous driving is increasingly reliant on high-quality annotated datasets, especially in the task of 3D occupancy prediction, where the occupancy labels requ…