5 papers
InstructMove: A Text-Indispensable Benchmark for Instruction-Following Manipulation
Mengao Zhao, Ziang Li, Chaodong Huang +15
Vision-language-action (VLA) models have made general-purpose robot manipulation increasingly plausible by conditioning robot actions on natural-language instructions. A key test o…
EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AI
Xinjie Wang, Liu Liu, Taojun Ding +9
We present EmbodiedGen V2, a generative 3D world engine for building executable policy-ready environments for embodied intelligence. Sim-ready 3D asset generation has advanced rapi…
WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models
Haiyu Wang, Yutong Wang, Jack Jiang +1
Singular Value Decomposition (SVD) has become an important technique for reducing the computational burden of Vision Language Models (VLMs), which play a central role in tasks such…
CATS-V2V: A Real-World Vehicle-to-Vehicle Cooperative Perception Dataset with Complex Adverse Traffic Scenarios
Hangyu Li, Bofeng Cao, Zhaohui Liang +16
Vehicle-to-Vehicle (V2V) cooperative perception has great potential to enhance autonomous driving performance by overcoming perception limitations in complex adverse traffic scenar…
Realistic and Controllable 3D Gaussian-Guided Object Editing for Driving Video Generation
Jiusi Li, Jackson Jiang, Jinyu Miao +10
Corner cases are crucial for training and validating autonomous driving systems, yet collecting them from the real world is often costly and hazardous. Editing objects within captu…