Skip to content
Only Models#Software and compute systems
  1. 机器人前瞻 · 微信公众号80

    NVIDIA releases VFlash visual planning decoding framework, robot action decoding up to 12x faster

    NVIDIA has released VFlash, a general-purpose decoding framework for fast visual planning that replaces token-by-token coordinate generation with parallel decoding of complete visual primitives, allowing it to predict robot grasp positions and motion trajectories in one pass. At batch size 1 on H100, single-generation speed improved by about 25x; across four MolmoSpaces tasks, the world action model averaged a 70.2% success rate versus a 62.6% baseline. Jim Fan shared that it achieves up to 12x faster action decoding, 5.1x overall robot inference speedup, and up to 61% lower 3D trajectory error.

    Why it matters: NVIDIA's new decoding framework changes visual planning from token-by-token generation to parallel prediction, and provides speedup and success-rate comparisons across multiple robot and autonomous-driving benchmarks.

  1. 机器人前瞻 · 微信公众号78

    AgiBot releases WITA-OMNI interaction model and Lingqu OS 1.0, full open source by year-end

    At its 2026 Innovation Day, AgiBot released WITA-OMNI, an embodied omni-modal end-to-end interaction large model. It ranked first on four benchmarks: Daily-Omni, TimeLens-Bench, EmbSpatialBench, and MMAU, with an average response time of about 600 milliseconds.

    Why it matters: AgiBot released an interaction model, a native operating system, and an ecosystem plan all at once, giving readers a way to understand its path to opening up its technology foundation and how it accumulates real-world interaction data.

  2. 机器之心 · 微信公众号76

    PokeBot releases embodied API RoboAPI, world-action model Poke-Aurora debuts

    PokeBot released its first model product, RoboAPI, in the early hours of October 30. It is a publicly accessible, out-of-the-box embodied API: after developers connect and adapt a robotic arm, they need neither to collect data nor train models, and can issue commands with a single prompt to execute tasks the model was not specifically trained on.

    Why it matters: Readers can learn how a publicly accessible embodied API hands zero-shot generalization capability over to external developers for testing, as well as its success-rate data from its own evaluation.

  1. NVIDIA75

    NVIDIA Cosmos Expands with New Tools for Training, Evaluating and Deploying World Models

    NVIDIA has expanded the Cosmos platform with new training tools, simulation checkpoints and Cosmos Data Factory blueprints for training, evaluating and deploying world models.

    Why it matters: The original lists Cosmos's new training tools, simulation checkpoints and data blueprints, and gives specific data on users such as Porsche and ANYbotics, which can be used to assess changes in the world model development workflow.

  1. 智源研究院 · 微信公众号68

    BAAI's FlagOS 2.2 released: over 1,454 operators, 27% cross-chip performance gain

    BAAI presented FlagOS 2.2 progress at the 2026 AI Open Computing Conference and FlagOS Technical Conference; the version was released on September 30. Public operators in the nine operator libraries rose from 564 to 1,454 (890 added). In tests covering over a thousand operators and 10 heterogeneous AI chips, cross-chip operator performance improved by about 27% over the previous version. The FlagOS-Compressor weight conversion and quantization tool was released for the first time, enabling a new model to be adapted to as many as 12 chips within one day.

    Why it matters: The original text provides specific figures for operators, quantization, and serving throughput, which readers can use to assess the performance and cost potential of existing chips for running new models.

  1. Shanghai AI Laboratory - Embodied Intelligence73

    Shanghai AI Lab launches decision model Intern·Mingjue, outperforming Jev and releasing 0.8B, 2B, and 4B weights

    Shanghai AI Laboratory has launched the decision model Intern·Mingjue (Decision), which outperforms Jev and is available in 0.8B, 2B, and 4B parameter versions. In RTX 4090 tests, the 0.8B and 2B models had an average end-to-end latency of about 33 milliseconds and about 30 decisions per second, while the 4B model was 44.16 milliseconds and Jev was 109.70 milliseconds.

    Why it matters: The original text provides measured latency, benchmark scores, and a mechanism for routing between large and small models, which readers can use to judge the decision model's suitability for interactive scenarios.

  1. 至简动力 · 微信公众号72

    Simplexity Robotics releases and open-sources world-action model SimpleWAM, with 6B model achieving on-device inference as low as 42.31ms

    Simplexity Robotics has launched and open-sourced the world-action model SimpleWAM; the 6B-parameter version reduces inference latency on NVIDIA ThorX (T5000) from 181.23ms to 42.31ms, enabling high-frequency closed-loop operation on-device at nearly 24Hz.

    Why it matters: The original article presents the on-device optimization path from 181ms to 42ms and four architectural designs, which can be transferred to understand how world-action models can meet high-frequency closed-loop control requirements.

  1. 小鹏机器人66

    XPeng XOS 6.3.0 OTA Deploys Second-Generation VLA Upgrade, Adds InfiniVLA and X-Foresight World Model

    XPeng XOS 6.3.0 deploys a second-generation VLA upgrade via OTA, restructuring the model architecture around the time dimension: InfiniVLA lets historical visual information continuously participate in current judgments, with the vehicle side selecting 30 seconds of historical context alongside streaming autoregressive inference.

    Why it matters: The article explains concretely the trade-offs in co-designing model architecture and deployment under onboard compute constraints, making it a useful engineering reference for deploying large models on limited hardware.

  1. 小鹏机器人63

    XPeng's second-generation VLA large model gets its first major upgrade, XOS 6.3.0 to debut globally on the G9L

    XPeng held a sharing and experience day themed "TIME," announcing the first major upgrade to its second-generation VLA large model. The new XOS 6.3.0 version will make its global debut on the XPeng G9L, with the core aim of moving AI from 3D spatial understanding to 4D spatiotemporal understanding.

    Why it matters: The original breaks the upgrade into three specific changes: contextual memory, reasoning approach, and world model. Readers can use these to understand how the shift from spatial understanding to spatiotemporal understanding is realized.

  1. 智源研究院 · 微信公众号72

    Zhongzhi FlagOS completes Day0 adaptation of Qwen3.8-2.4T across nine chips

    On the first day of Alibaba's open-source release of the 2.4-trillion-parameter MoE model Qwen3.8-2.4T-A95B, the Zhongzhi FlagOS community completed multi-chip adaptation, precision alignment, and deployment validation across 9 AI chips, providing BF16, FP8, INT8, and other multi-precision versions.

    Why it matters: The article presents a zero-code-change adaptation path and a quantization compression scheme, which readers can use to assess how existing domestic compute can support ultra-large models.

You’re all caught up