10 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…
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…
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…
Thousand-GPU Large-Scale Training and Optimization Recipe for AI-Native Cloud Embodied Intelligence Infrastructure
Yongjian Guo, Yunxuan Ma, Haoran Sun +22
Embodied intelligence is a key step towards Artificial General Intelligence (AGI), yet its development faces multiple challenges including data, frameworks, infrastructure, and eva…
Probing the Difficulty Perception Mechanism of Large Language Models
Sunbowen Lee, Qingyu Yin, Chak Tou Leong +5
Large language models (LLMs) are increasingly deployed on complex reasoning tasks, yet little is known about their ability to internally evaluate problem difficulty, which is an es…
PoolingVQ: A VQVAE Variant for Reducing Audio Redundancy and Boosting Multi-Modal Fusion in Music Emotion Analysis
Dinghao Zou, Yicheng Gong, Xiaokang Li +2
Multimodal music emotion analysis leverages both audio and MIDI modalities to enhance performance. While mainstream approaches focus on complex feature extraction networks, we prop…