8 papers
JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models
Haoran Sun, Wentao Zhang, Junyang Hua +18
The post-training of Vision-Language-Action (VLA) models is essential due to the diversity of simulators, robot embodiments, and task objectives. Existing compute services, whether…
Building a Scalable, Reproducible, Evaluatable, and Closed-Loop Simulation Environment Foundation for Embodied Intelligence
Junwu Xiong, Yongjian Guo, Mingxi Luo +17
This paper presents a cloud-native simulation infrastructure framework for embodied intelligence that supports large-scale training, standardized evaluation, and simulation-based d…
AdaptiveLoad: Towards Efficient Video Diffusion Transformer Training
Yucheng Guo, Yongjian Guo, Zhong Guan +6
In video generation models, particularly world models, training large-scale video diffusion Transformers (such as DiT and MMDiT) poses significant computational challenges due to t…
Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction
Zhong Guan, Yongjian Guo, Haoran Sun +5
Asynchronous reinforcement learning improves rollout throughput for large language model agents by decoupling sample generation from policy optimization, but it also introduces a c…
D-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action Models
Yucheng Guo, Yongjian Guo, Zhong Guan +9
The rapid evolution of Embodied AI has enabled Vision-Language-Action (VLA) models to excel in multimodal perception and task execution. However, applying Reinforcement Learning (R…
NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models
Wen Huang, Haoran Sun, Yongjian Guo +8
World Action Models (WAMs) are an emerging family of policies that tie robot action generation to future-observation modeling. In this work, we focus on the joint video--action mod…