SHANGHAI, July 23, 2026 /PRNewswire/ — TARS showcased its vision for “Trustworthy Physical AI” at the World Artificial Intelligence Conference (WAIC 2026), held July 17–20 at the Shanghai World Expo Exhibition & Convention Center, where its AWE (AI World Engine) embodied foundation model received the prestigious SAIL (Superior Al Leader) Award for technical innovation and industrial potential.
At the WAIC main forum, TARS Founder and CEO Dr. Chen Yilun introduced AWE 3.5, the company’s latest embodied-native foundation model. Built on more than one million hours of human-centric, real-world data validated in industrial settings, AWE 3.5 integrates action, perception, geometry, and tactile sensing within a unified framework. Compared with Pi 0.5, the model approximately doubles task-execution efficiency, improves complex-task performance, and maintains closed-loop interaction across tasks lasting several minutes. AWE 3.5 is also the first to complete an embodied-native “pre-training + post-training” paradigm designed to support reproducible, scalable, and continuous iteration.
TARS demonstrated AWE-powered robots performing phone packing, backpack organization, and precision screw sorting, showing how the model translates physical understanding into deployable actions and generalizes to unfamiliar objects and scenarios. Having surpassed 1 million hours of high-quality human-centric data, TARS plans to expand its pre-training dataset to 10 million hours by the end of 2026, further strengthening generalization, long-horizon reasoning, and real-task execution.
TARS also recreated a full-scale circular automotive wiring-harness production line using multiple A1 robots to grasp, route, connect, and assemble flexible wiring harnesses. The scenario was selected for WAIC’s official embodied-robotics exhibition zone, “Model Era • Partner City,” as a featured display in the “Smart Manufacturing Hub.” The demonstration highlighted the technology’s stability, reliability, and delivery value in advanced manufacturing. TARS is working with Jiading District of Shanghai and industry partners to validate the technology at scale and advance China’s first thousand-unit-scale industrial embodied-robot cluster.
Another highlight was the debut of DexHand, mounted on an A1 robot, in a live performance with magician Deng Nanzi. DexHand performed card spreading and shuffling, handwriting, and Rubik’s Cube solving, demonstrating real-time perception, high-precision control, and trustworthy human-robot collaboration.
Together, AWE 3.5, the industrial production line, and DexHand reflected TARS’ three-part vision for trustworthy physical AI: understanding complex environments, delivering value on real production lines, and performing high-precision tasks. TARS will continue moving embodied intelligence from demonstration to delivery and accelerating adoption at scale.
Contact:
TARS PR Team
Email: TarsPR@tars-ai.com