6 papers
DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching
Jiayi Chen, Wenxuan Song, Jiaxin Fang +12
Vision-Language-Action (VLA) models that encode actions using a discrete tokenization scheme have been widely adopted for robotic manipulation, but existing decoding paradigms rema…
PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios
Jingbo Wang, Zhengyi Luo, Ye Yuan +2
We address the challenge of content diversity and controllability in pedestrian simulation for driving scenarios. Recent pedestrian animation frameworks have a significant limitati…
MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model
Wenxun Dai, Ling-Hao Chen, Jingbo Wang +3
This work introduces MotionLCM, extending controllable motion generation to a real-time level. Existing methods for spatial-temporal control in text-conditioned motion generation s…
Cinematic Behavior Transfer via NeRF-based Differentiable Filming
Xuekun Jiang, Anyi Rao, Jingbo Wang +2
In the evolving landscape of digital media and video production, the precise manipulation and reproduction of visual elements like camera movements and character actions are highly…
InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint
Zhenzhi Wang, Jingbo Wang, Yixuan Li +2
Text-conditioned motion synthesis has made remarkable progress with the emergence of diffusion models. However, the majority of these motion diffusion models are primarily designed…
Unified Human-Scene Interaction via Prompted Chain-of-Contacts
Zeqi Xiao, Tai Wang, Jingbo Wang +5
Human-Scene Interaction (HSI) is a vital component of fields like embodied AI and virtual reality. Despite advancements in motion quality and physical plausibility, two pivotal fac…