3 papers
cs.RO2026
In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics
Xiaomeng Fu, Junfan Lin, Yang Liu +4
Synthesizing human motion from textual descriptions is essential for immersive digital applications, yet existing methods face a persistent trade-off between semantic fidelity and…
cs.CV2025
LaneDiffusion: Improving Centerline Graph Learning via Prior Injected BEV Feature Generation
Zijie Wang, Weiming Zhang, Wei Zhang +4
Centerline graphs, crucial for path planning in autonomous driving, are traditionally learned using deterministic methods. However, these methods often lack spatial reasoning and s…
cs.CV2025
DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering
Jingzhou Luo, Yang Liu, Weixing Chen +4
3D Question Answering (3D QA) requires the model to comprehensively understand its situated 3D scene described by the text, then reason about its surrounding environment and answer…