12 papers
Controllable Sim Agents with Behavior Latents
Juanwu Lu, Junyu Zhu, Ziran Wang
Realistic traffic simulation requires agents that imitate logged behavior and can also be steered along interpretable axes. Such controllability enables engineers to isolate variab…
On Variance Reduction in Learning Mean Flows
Juanwu Lu, Ziran Wang
One-step generative modeling has emerged as a leading approach for amortizing the inference cost of diffusion and flow-matching models. Among distillation-free methods, MeanFlow tr…
OmniV2X: A Generative Foundation Planner for Efficient End-to-End Cooperative Driving
Juntong Peng, Juanwu Lu, Yupeng Zhou +3
We present OmniV2X, a generative foundation model for vehicle-to-everything (V2X) cooperative driving. The model directly interprets independent context sequences comprising multi-…
SIMSplat: Language-Aligned 4D Gaussian Splatting for Driving Scenario Generation
Sung-Yeon Park, Adam Lee, Juanwu Lu +6
Driving scene manipulation using real-world sensor data has emerged as a promising alternative to traditional driving simulators. Despite advances in language control and neural sc…
Mollified Value Learning
Hrishikesh Viswanath, Juanwu Lu, S. Talha Bukhari +4
Offline goal-conditioned reinforcement learning (GCRL) learns goal-reaching behaviors from static datasets, but accurate value estimation remains challenging under limited state-ac…
Model Merging on Loss Landscape: A Geometry Perspective
Juanwu Lu, Anand Bhaskar, Brian Axelrod +2
Model merging offers a promising avenue for knowledge integration and parallel development without retraining. Yet, existing methods either ignore the geometry of the loss landscap…