Skip to content
Only Models#Embodied AI
November 11Wednesday
  1. MarkTechPost60

    MBZUAI's IFM Releases PAN 2, an Open 29B World Model for Physical AI

    MBZUAI's Institute of Foundation Models released PAN 2, a 29B-parameter open world model that takes a scene plus a text action and simulates the outcome as video, with weights, training code and inference code under Apache 2.0. It pairs an LLM planner that writes structured JSON world states with a 29B MMDiT diffusion transformer conditioned by a frozen Qwen3.5-9B encoder, and IFM reports 34.0% full-plan completion on 100 multi-step tasks, ahead of MiniMax-H3 at 32.50%, while trailing MiniMax-H3 on single actions and human preference (Elo 1595 vs 1620). IFM's ablation shows removing the LLM planner drops full-plan completion to 0.0% and step completion from 75.1% to 8.7%.

November 10Tuesday
  1. Ars Technica · AI71

    DeepMind unveils Gemini Robotics 2.5 and open safety benchmark ASIMOV-jailbreak

    Google DeepMind revealed Gemini Robotics 2.5, a new version of its vision-language-action model that generates robot actions, saying it is much better at tasks requiring high dexterity. The model was evaluated across more than 200 activities, including serving food with tongs and using a pipette, and Apptronik's Apollo 2 humanoid robot running it can now tie a bow with its five-fingered hands. DeepMind also introduced an open source safety benchmark, ASIMOV-jailbreak, as it prepares for robots to operate alongside humans, and said some Gemini robots did actual work in Mercedes-Benz factories.

  2. Google DeepMind78

    Google DeepMind releases Gemini Robotics 2.5 VLA model for real-world dexterity

    Google DeepMind introduced Gemini Robotics 2.5, its most capable vision-language-action model to date, which expands the range of skills a robot can learn and speeds up how fast it acquires them. Evaluated across 200 distinct tasks, the model achieves a 30% to 100% higher success rate than previous baselines while completing tasks 20% to 30% faster, and in a Mercedes-Benz production-line proof-of-concept, Apptronik's Apollo 2 humanoid picked and packed automotive parts with a 96% success rate. The release also adds inference-time reasoning guidance for physical safety, which raised safe task completion by 33% around obstacles and 43% around nearby people, plus ASIMOV-Jailbreak, an open-source benchmark on which Gemini 4 Argon reaches 99.5% jailbreak resistance.

    Why it matters: Gemini Robotics 2.5 improved its success rate on 200 tasks by 30% to 100%, and achieved a 96% pick-and-place success rate in a pilot on the Mercedes-Benz production line, providing reference data for evaluating the real-world deployment of VLA models.