6 papers
4D-WAM: 4D Consistent World Modeling for Autonomous Driving
Jiacheng Fu, Yibo Yuan, Meng Tian +8
Emerging World-Action Models (WAMs) have demonstrated promising performance in autonomous driving by jointly modeling future driving scene evolution and trajectory planning. Howeve…
SUV: Future Scene Understanding as Video Generation for End-to-End Driving
Yibo Yuan, Jiacheng Fu, Jiangtong Zhu +8
End-to-end driving requires a coherent understanding of future scenes, yet existing methods model these scenes using task-specific heads and output formats, with limited scalabilit…
Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation
Muyi Bao, Yuxin Cai, Hang Xu +7
Vision-language models (VLMs) have become a common foundation for vision-and-language navigation in continuous environments (VLN-CE). Yet most VLM-based methods cast navigation as…
4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration
Jiahui Zhang, Yurui Chen, Yueming Xu +8
Leveraging diverse robotic data for pretraining remains a critical challenge. Existing methods typically model the dataset's action distribution using simple observations as inputs…
SeePhys: Does Seeing Help Thinking? -- Benchmarking Vision-Based Physics Reasoning
Kun Xiang, Heng Li, Terry Jingchen Zhang +11
We present SeePhys, a large-scale multimodal benchmark for LLM reasoning grounded in physics questions ranging from middle school to PhD qualifying exams. The benchmark covers 7 fu…
Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs
Haoyuan Li, Yanpeng Zhou, Yufei Gao +7
Remarkable progress in 2D Vision-Language Models (VLMs) has spurred interest in extending them to 3D settings for tasks like 3D Question Answering, Dense Captioning, and Visual Gro…