PhysicalAI+

PhysicalAI+

[PhysicalAI+ @elianchen111]

With the shortage of embodied AI data, which type of data is more valuable: teleoperation data, simulation data, ego-centric data, or human motion data? Professor Su Hang, Tsinghua University #EmbodiedAI #Data #AI #FoundationModels #PreTraining #Robotics #PhysicalAI #Maniformer

[PhysicalAI+ @elianchen111]

An impressive real-world demonstration of a World Action Model is here! This video shows the actual deployment of GigaAI’s WAM model, with no speed acceleration.
#EmbodiedAI #FoundationModels #PhysicalAI #WorldModel #WorldActionModel #WAM #VLA

[PhysicalAI+ @elianchen111]

Do robots really need five-fingered dexterous hands?When answering this question, Tony Zhao, Co-founder and CEO of Sunday Robotics, highlighted the 80/20 trade-off between cost and performance.#PhysicalAI #Robotics #EmbodiedAI #DexterousHands #DexterousManipulation

[PhysicalAI+ @elianchen111]

Which is better, VLA or WAM? Tencent Robotics X Lab’s answer is not to commit to a single model architecture. Instead, it starts from the perspective of building a complete embodied agent.#EmbodiedAI #Robotics #Tencent #RoboticsX #Apexio #EndToEnd #IntelligentAgent #AIagent #VLA

[PhysicalAI+ @elianchen111]

Dyna Robotics is moving away from the VLA approach and choosing WAM—World Action Models—instead. How does Dr. Ma, Co-founder and Chief Scientist of Dyna Robotics, explain this decision? #robotics #dyna #dynarobotics #embodiedai #physicalai #model #WAM

[PhysicalAI+ @elianchen111]

Which is more powerful, VLA or WAM? Let’s hear how Prof. Danfei Xu, Assistant Professor at the School of Interactive Computing at Georgia Tech and NVIDIA AI Researcher, answers this question.#embodied #robotics #robot #physicalai

[PhysicalAI+ @elianchen111]

The model architecture for Physical AI has yet to converge. Some say VLA is dead—but what does a research scientist at Physical Intelligence think?

#physicalAI #physicalintelligence #PI #π #VLA #worldmodel #worldactionmodel #π07

[PhysicalAI+ @elianchen111]

For ten years, AheadForm has focused on one thing: giving Physical AI a face that can truly express itself. #PhysicalAI #AheadForm #EmbodiedAI #HumanoidRobots #WAIC #Robotics #BionicRobots

[PhysicalAI+ @elianchen111]

Fysics’ next-generation physical world model, Fysiverse, brings Fei-Fei Li’s vision for world models into reality: it is a renderer, a simulator, and, more importantly, a planner. #worldmodel #physicalai #robotics #embodiedai #physicsengine

[PhysicalAI+ @elianchen111]

【Part 2】Physical AI+ | Fysiverse, the Next-Generation Physical World Model from Fysics CTO Dingkang Yang, Is Breaking Down the Boundaries of WM https://t.co/OU2TwwlgSZ

[PhysicalAI+ @elianchen111]

【1】Physical AI+ | Fysiverse, the Next-Generation Physical World Model from Fysics CTO Dingkang Yang, Is Breaking Down the Boundaries of World Models https://t.co/jinlkx8SF9

[PhysicalAI+ @elianchen111]

WAIC 2026 Robotics in Physical AI

[PhysicalAI+ @elianchen111]

At WAIC 2026, "Physical AI" is a major buzzword. So, what exactly is Physical AI? Why are embodied AI companies talking about it? And when will Physical AI reach its moment of emergent intelligence? This is "Physical AI+"