BEIJING, Oct. 9, 2026 /PRNewswire/ -- ROBOTERA's World Action Model (WAM), VPP2 (Video Prediction Policy 2), has ranked No. 1 on RoboDojo without additional data or agent-based reinforcement self-improvement (Agent RSI). Developed by the University of Hong Kong's MMLab in collaboration with nearly 20 leading academic institutions worldwide, RoboDojo is a rigorous benchmark for general-purpose robot manipulation that evaluates performance across challenging simulation and real-world tasks, going beyond simple demonstrations.
VPP2 achieved an average success rate of 32.26% and an average score of 39.26, ranking first in Generalization, Precision, and Memory among evaluated methods.
ROBOTERA has open-sourced VPP2 on GitHub, with further details available on the project website.
Building a More Generalizable World Action Model
VPP2 enables robots to better predict how actions will change their surroundings and translate instructions into physical movements. Unlike video models designed primarily to generate visual content, VPP2 is trained to understand object movements and follow precise manipulation instructions. It combines video prediction with action generation, helping robots perform tasks more reliably across different objects, environments, and scenarios.
For complex tasks involving multiple steps, VPP2 can also work with a vision-language model (VLM) that breaks down high-level instructions into smaller, executable actions.
Validated Across Simulation and Real-World Tasks
VPP2 was evaluated across video prediction, instruction following, and robotic manipulation tasks.
On the ALOHA platform, VPP2 achieved a 58.5% average success rate across 10 task categories, outperforming leading baselines in nine. It also achieved 45.0% on LIBERO-Pro, a benchmark for robotic manipulation and generalization. With high-level task planning, average success rates across five task groups more than doubled, from 27.6% to 57.6%.
These results demonstrate VPP2's ability to connect visual understanding, instruction following, and physical action, advancing general-purpose robotics toward practical applications.
From Research Breakthroughs to Real-World Deployment
VPP2 marks ROBOTERA's fourth benchmark championship in embodied intelligence in 2026, following top results at World Arena, Benjie's Humanoid Olympic Games, and RoboChallenge. Combined with ongoing humanoid-robot deployments with China Post and SF Express across more than 10 logistics centers in China, these achievements reflect ROBOTERA's progress in both advancing general-purpose robot intelligence and bringing it into real-world applications.
Building on its advances in world-action modeling and real-world deployment experience, ROBOTERA is working to make general-purpose robots reliable partners in everyday work.
** This press release is distributed by PR Newswire through automated distribution system, for which the client assumes full responsibility. **
ROBOTERA Tops Embodied AI Benchmark RoboDojo Without Additional Data or Agent RSI
Portfolio spans high-performance enterprise computing and edge AI, supporting deployment in customers' own IT environments.
TAIPEI, Oct. 10, 2026 /PRNewswire/ -- Senao Networks Inc. today announced the launch of its new x86 enterprise server portfolio, featured on the company's Senao Computing website at www.senaocomputing.com.
The portfolio, which includes the SR810, SR710, SR610, SE210, and SE110, is designed to support a broad range of enterprise computing and AI workloads, including generative AI, AI inference, model fine-tuning, data analytics, visualization, and intelligent edge computing. NVIDIA RTX GPU support is available in selected configurations.
Bringing AI Closer to Enterprise Data
As enterprises accelerate AI adoption, organizations increasingly need computing infrastructure that can address different workload requirements while maintaining greater control over sensitive corporate data.
Senao Networks' scalable x86 platforms allow enterprises to deploy computing resources according to their workload, performance, and deployment requirements.
For organizations that prefer to operate AI applications within their own IT environments, on-premises deployment can provide greater control over enterprise data, infrastructure, security policies, and AI workloads. Meeting data governance and regulatory requirements depends on the deployment, operational controls, and applicable rules.
"Enterprises are looking for practical ways to bring AI closer to their data and business operations," said Dr. Bou Lin, President at Senao Networks Inc. "Our new x86 enterprise server portfolio provides flexible computing building blocks that allow customers to deploy AI according to their own performance, security, and infrastructure requirements—from the data center to the edge."
Computing Platforms for Enterprise AI Workloads
The portfolio addresses different enterprise computing and AI requirements, with GPU acceleration available in selected configurations:
High-Performance Enterprise Compute – SR810 & SR710
Designed for demanding enterprise computing and AI workloads, including generative AI applications, LLM inference, model fine-tuning, data analytics, visualization, and other GPU-accelerated workloads.
Mainstream Enterprise Compute – SR610
Optimized for enterprise AI inference, data analytics, virtualization, and general-purpose enterprise computing applications.
Edge Intelligence – SE210 & SE110
Compact and efficient platforms designed for localized AI inference, intelligent edge applications, real-time processing, and deployments closer to where enterprise data is generated.
From Enterprise Computing to Edge AI
The portfolio expands Senao Networks' enterprise computing offering.
Building on decades of experience in networking, security appliances, system engineering, and global manufacturing, Senao Networks is extending its capabilities into enterprise computing and AI infrastructure.
The company aims to provide customers and technology partners with flexible computing platforms spanning enterprise servers, AI servers, edge servers, network appliances, and AI infrastructure solutions—helping organizations build practical and scalable computing environments from the data center to the edge.
Explore Senao Computing
The Senao Computing website brings together the company's computing platforms, product specifications, AI solutions, and information on its engineering and manufacturing capabilities for customers and partners.
Senao Computing
https://www.senaocomputing.com
Product Information and Inquiries
For detailed product information, technical specifications, or business inquiries, please visit Senao Computing at www.senaocomputing.com.
About Senao Networks Inc.
Senao Networks Inc. is a provider of networking, security, computing, and AI infrastructure solutions. With extensive capabilities in system design, hardware engineering, software integration, manufacturing, and global supply-chain management, Senao Networks delivers infrastructure platforms for enterprises and technology partners worldwide.
As AI continues to reshape enterprise infrastructure, Senao Networks is expanding its capabilities from networking and security into enterprise computing, AI servers, and intelligent edge platforms—supporting customers as they build the infrastructure required for the AI era.
Media Contact
Contact Name: Jean Chen
Title: Product Marketing
Company: Senao Networks Inc.
Email: jean.chen@senao.com
Phone: +886-3-3289289 #6188
Intel, the Intel logo, and Xeon are trademarks of Intel Corporation or its subsidiaries. NVIDIA and RTX are trademarks and/or registered trademarks of NVIDIA Corporation in the U.S. and other countries. All other trademarks are the property of their respective owners.
** This press release is distributed by PR Newswire through automated distribution system, for which the client assumes full responsibility. **
Senao Networks Launches x86 Enterprise Server Series for Enterprise AI
Senao Networks Launches x86 Enterprise Server Series for Enterprise AI
