4 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…
RL-VLA: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training
Haoran Sun, Yongjian Guo, Zhong Guan +13
Reinforcement learning (RL) has emerged as a critical paradigm for post-training Vision-Language-Action (VLA) models, enabling embodied agents to adapt and improve through environm…
Enhancing Affine Maximizer Auctions with Correlation-Aware Payment
Haoran Sun, Xuanzhi Xia, Xu Chu +1
Affine Maximizer Auctions (AMAs), a generalized mechanism family from VCG, are widely used in automated mechanism design due to their inherent dominant-strategy incentive compatibi…
Mechanism Design for LLM Fine-tuning with Multiple Reward Models
Haoran Sun, Yurong Chen, Siwei Wang +3
Fine-tuning large language models (LLMs) to aggregate multiple preferences has attracted considerable research attention. With aggregation algorithms advancing, a potential economi…