6 papers
HorizonComposer: Spatiotemporally Consistent Driving Video Editing with Enriched Traffic Semantics
Mauricio Soroco, Yuqiu Liu, Zaid Tasneem +5
Instruction-guided video generative models offer a scalable solution for stress-testing autonomous driving systems by simulating diverse environmental conditions. However, driving…
HorizonWeaver: Generalizable Multi-Level Semantic Editing for Driving Scenes
Mauricio Soroco, Francesco Pittaluga, Zaid Tasneem +5
Ensuring safety in autonomous driving requires scalable generation of realistic, controllable driving scenes beyond what real-world testing provides. Yet existing instruction guide…
Hybrid Neural-MPM for Interactive Fluid Simulations in Real-Time
Jingxuan Xu, Hong Huang, Chuhang Zou +3
We propose a neural physics system for real-time, interactive fluid simulations. Traditional physics-based methods, while accurate, are computationally intensive and suffer from la…
Data-Efficient Inference of Neural Fluid Fields via SciML Foundation Model
Yuqiu Liu, Jingxuan Xu, Mauricio Soroco +2
Recent developments in 3D vision have enabled significant progress in inferring neural fluid fields and realistic rendering of fluid dynamics. However, these methods require dense…
Collapsed Language Models Promote Fairness
Jingxuan Xu, Wuyang Chen, Linyi Li +2
To mitigate societal biases implicitly encoded in recent successful pretrained language models, a diverse array of approaches have been proposed to encourage model fairness, focusi…
Transferable and Principled Efficiency for Open-Vocabulary Segmentation
Jingxuan Xu, Wuyang Chen, Yao Zhao +1
Recent success of pre-trained foundation vision-language models makes Open-Vocabulary Segmentation (OVS) possible. Despite the promising performance, this approach introduces heavy…