Skip to content
Only First party#Data and simulation
  1. PsiBot/灵初智能71

    Lingchu Intelligence and collaborators propose FAFM, a continuous action generation method for heterogeneous-frequency data, accepted to NeurIPS 2026

    Lingchu Intelligence, together with Beihang University, Peking University, and The Chinese University of Hong Kong, proposed a frequency-aware flow matching method called FAFM; the paper was accepted to the NeurIPS 2026 main conference. The method uses the discrete cosine transform (DCT-II) to represent actions as frequency-domain coefficients corresponding to real time, performs flow matching in coefficient space and constrains the first-order time derivative, requires no additional learnable parameters, and can be used independently or integrated into VLA models such as π₀ and π₀.₅.

    Why it matters: The paper presents a frequency-domain action representation that adds no learnable parameters and can be integrated into existing VLA models, offering a transferable approach for joint training on heterogeneous-frequency data.

  2. PsiBot/灵初智能71

    PKU-Spirit AI Joint Lab's RoboFFT Accepted to CoRL2026, Uses Reinforcement Learning Post-Training to Generate Robotic Policies

    RoboFFT, proposed by the PKU-Spirit AI Joint Lab, has been accepted to CoRL2026. It is a reinforcement learning post-training method for generative robotic policies that reuses the forward noising process from diffusion model and flow model pretraining to construct an approximate probability ratio for PPO-style clipped updates.

    Why it matters: The method reuses the forward noising loss of diffusion and flow models to construct policy update signals, offering a reusable approach for post-training generative policies.

  1. CMU Robotics Institute62

    CMU proposes Wiggle and Go: estimating physical properties of ropes by wiggling to plan manipulation

    A team at CMU's Robotics Institute has proposed the Wiggle and Go system, in which a robot first briefly wiggles a rope or cable while an overhead camera records how the waves propagate; a computer vision algorithm then tracks the motion and estimates the object's physical properties, which are used to plan subsequent actions without repeated trial and error. The model is trained entirely in simulation, and properties are then estimated from the motion of real ropes being wiggled to improve prediction accuracy on real hardware. The research has been accepted to the 2026 Conference on Robot Learning (CoRL) and will be presented next month in Austin; it is partly funded by the U.S. National Science Foundation.

    Why it matters: The method estimates a rope's physical properties from a single wiggle and then plans actions accordingly, offering a transferable approach to deformable object manipulation.

  1. 戴盟机器人72

    Daimon Robotics completes hundreds of millions in strategic financing, led by Ant Group

    Daimon Robotics announced the completion of a strategic funding round of hundreds of millions, led by Ant Group with existing shareholders oversubscribing, just two months after its hundred-million-yuan Series A. The company also launched its tactile-anchored world model Daimon-TWM, with parameter scale at the 10B level, capable of real-time inference on the NVIDIA RTX 5090 platform, and claims that its average success rate on contact-intensive manipulation tasks is twice that of π0.5. Daimon has also built the tactile full-modality dataset Daimon-Infinity; after the first 10,000 hours of data were open-sourced, it received nearly 5 million downloads on the ModelScope community.

    Why it matters: Beyond the funding news, the original article also details the architecture and data-collection layout of the tactile world model Daimon-TWM, which helps in understanding the technical proposition of the tactile approach.

  2. AgiBot72

    AgiBot releases embodied foundation model GO-3 Preview, ranks first on three embodied intelligence benchmarks

    AgiBot has released the embodied foundation model GO-3 Preview, built on its self-developed WRAM (World Reasoning Action Model) architecture that unifies task understanding, future state prediction, and action generation, and it ranks first on three embodied intelligence benchmarks: RoboDojo, RoboTwin, and RoboColiseum. It is planned to be fully open-sourced by the end of 2026.

    Why it matters: The original article fully discloses GO-3 Preview's three-stage design of pretraining, post-training, and post-deployment learning, which can be used to understand the engineering path for scaling embodied models across their full lifecycle.

  1. 云启资本60

    PHYMI Tech releases first robot Sagi, featuring four-wheeled-legged humanoid configuration and PHYMI BRAIN 1.0

    PHYMI officially released its first robot, Sagi, on October 28. It adopts a "four-wheeled-legged humanoid configuration" combining four wheeled legs with a humanoid upper body, dual arms, and a rear box, targeting scenarios such as office delivery, community errands, and outdoor camping transport.

    Why it matters: The first four-wheeled-legged humanoid robot presents a complete design approach covering configuration trade-offs, a three-layer model, and a data system, allowing comparison with existing bipedal routes to understand the choice of form.

  2. Shanghai AI Laboratory - Embodied Intelligence60

    Shanghai AI Laboratory and partners jointly launch materials multimodal large model "Caihua·MatVerse"

    Suzhou National Laboratory, Shanghai AI Laboratory, Shanghai Jiao Tong University and others jointly launched the "Caihua·MatVerse" materials multimodal large model and agent application system, which uses an "independent encoders plus unified decoder" architecture to align XRD spectra, electron microscope images and molecular structures into the same semantic space.

    Why it matters: The materials present a multimodal unified representation architecture and 19-category disciplinary evaluation benchmarks, offering insight into how materials large models can move from retrieval to mechanistic reasoning.

  1. Kinetix AI · YouTube67

    Kinetix AI releases KAI World Model, supporting locomotion and manipulation tasks

    Kinetix AI has released the KAI World Model, which is based on parallel video generation and 4D spatial modeling and can simultaneously generate virtual worlds and reconstruct spatial scenes. The model was pre-trained on millions of videos and supports pure locomotion, pure manipulation, and coordinated locomotion-manipulation tasks; it claims generalization across tasks and across robot embodiments. Live demonstrations include a robotic arm autonomously opening a beverage can and a humanoid robot playing real-time table tennis rallies.

    Why it matters: The original shows live demonstrations of the world model on two types of tasks—a robotic arm opening a can and a humanoid playing table tennis—which can be used to understand its approach to generalization across tasks and embodiments.

  2. AgiBot73

    AgiBot releases Genie Studio 2.0 embodied intelligence development and deployment platform

    AgiBot has released Genie Studio 2.0, an embodied intelligence application platform covering development, deployment, and operations. It consists of three modules—Flywheel, Agent, and Monitor—that connect data collection, model training, evaluation, inference, task orchestration, and robot fleet management.

    Why it matters: The original text provides the platform's three major modules and validation data from multiple production lines, which can be used to assess the engineering chain of embodied applications from development to operations.

  1. Kinetix AI · YouTube62

    KAI Halo case study EgoWild2Dex: training bimanual dexterous manipulation with first-person data

    The KAI Halo case study EgoWild2Dex shows how high-quality bimanual dexterous manipulation capabilities can be derived from highly challenging egocentric data. The project page is https://mmlab.hk/egowild2dex.

    Why it matters: The material presents a complete training path from first-person human data to robotic bimanual manipulation, along with success rates; its transferable aspect lies in its approach to data utilization.

  1. NEURA Robotics74

    NEURA Robotics unveils 4NE1 Gen 4 humanoid robot and opens TUM RoboGym with Technical University of Munich

    NEURA Robotics and the Technical University of Munich (TUM) have opened TUM RoboGym at LabCampus near Munich Airport, covering more than 2,300 square meters. TUM MIRMI is a co-builder, the initial collaboration runs for three years, and the two parties are jointly investing about 17 million euros, of which NEURA is contributing about 11 million euros.

    Why it matters: The original text covers both the new robot's hardware changes and the three sources of training data, letting readers understand NEURA's approach of tying data infrastructure to the hardware launch.

  2. 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. NVIDIA80

    NVIDIA Expands Isaac Platform with New Humanoid Reference Platform, Isaac OS, and Isaac Lab 3.0

    At GTC Berlin, NVIDIA announced an expansion of the Isaac open-source robotics development platform, adding the Isaac OS runtime, the officially released Isaac Lab 3.0 learning framework, and an open-source reference workflow based on DGX Station.

    Why it matters: The original text lists the runtime, learning framework, and open-source workflow newly added to the Isaac platform, allowing readers to judge the specific changes in the data-to-deployment pipeline.

  1. Pollen Robotics · YouTube64

    Pollen Robotics launches Microduck Arena virtual competition arena

    Pollen Robotics has released Microduck Arena, a virtual arena where Microduck robots race, train, and compete without the need for physical robots. Users train policies with reinforcement learning and publish them to their own Hugging Face accounts to enter challenges; each submission is evaluated uniformly by the Arena, and results can be compared across players. Published policies can be downloaded as .onnx files to watch replays and learn from the best runs.

    Why it matters: It connects policy training, unified evaluation, and replay-based learning into a closed loop, letting readers learn how to train and compare reinforcement learning policies without physical robots.

  2. Shanghai AI Laboratory - Embodied Intelligence68

    Shanghai AI Lab launches Shusheng SCP-Lab experimental equipment access and collaboration protocol

    Shanghai AI Lab has launched Shusheng SCP-Lab, an experimental equipment access and collaboration protocol based on the Scientific Context Protocol (SCP), providing research agents with a unified mechanism for device capability discovery, task interaction, and trusted feedback. It has been open-sourced.

    Why it matters: The original text presents the specific design of the layered architecture, five control granularity levels from L1 to L5, and the trusted feedback mechanism, allowing readers to understand the protocol approach for research agents to connect to heterogeneous experimental equipment.

  1. PsiBot/灵初智能66

    Lingchu Intelligence releases Psi-R2.5, using strong Pair Data to solve human-machine data alignment challenges

    Lingchu Intelligence has officially released its embodied model Psi-R2.5, which uses a two-tier architecture with a QwenVL3.5-4B high-level planner plus a Wan2.2-IT2V-5B low-level controller, and proposes the strong Pair Data standard. The model reverse-invokes the Psi-W0 world model to generate human demonstration videos backward from real-robot data, enabling mass production of paired data, and supports in-context learning (ICL) for zero-shot generalization to new tasks. It comes with a HIL+RL post-training framework and is claimed to raise task success rates to 99% after a few iterations taking only 1-2 working days, and has already been deployed at customer sites.

    Why it matters: The original article details the model architecture, the strong Pair Data data standard, and the reverse-generation method, letting readers understand how its data approach supports real-robot generalization.

  1. Skild AI62

    Skild AI releases physical self-play post-training results; S1 model learns soccer in simulation and transfers to humanoid robots

    Skild AI announced that it post-trained its foundation model S1 through physical self-play, letting the policy play against a recent version of itself with scoring as its sole objective. In NVIDIA Isaac Sim, over 140 years of simulated time, it learned skills such as dribbling past opponents, shielding the ball, and tackling, and these skills were successfully transferred to humanoid robots for matches. The authors believe self-play can break through the capability ceiling of pretrained human data, and the next step will be to extend it to everyday tasks such as collaborative manipulation and city-scale navigation.

    Why it matters: The authors describe using physical self-play to let a foundation model acquire soccer skills in simulation and transfer them to real robots, which lets readers learn about a feasible path for self-play-style post-training.

  1. PsiBot/灵初智能73

    Psi Robotics Releases Psi-R2.5 Model: Scaling Human Data for Embodied Intelligence with Strong Pair Data

    Psi Robotics released the Psi-R25 robot manipulation model. Its core upgrades are improved data quality and data attribute compression: it reviewed and extracted high-quality data from 100,000 hours of data, and used strong pair data to align human data with robot data.

    Why it matters: The original article details how strong pair data is generated and the data quality standards, giving readers a referenceable path for aligning human data to robot data.

  1. Figure AI79

    Figure AI releases Helix 2.5, achieving zero-shot full-body autonomy in 30 unfamiliar homes

    Figure AI released Helix 2.5, which completed three long-horizon full-body behaviors—tidying a living room, folding towels, and making a bed—zero-shot in 30 Bay Area homes where no data had ever been collected, without collecting data or fine-tuning in the evaluation environments.

    Why it matters: The original article provides controlled comparison data on Index pretraining for zero-shot generalization and evaluation details, helping readers understand the actual level of humanoid robot pretraining transfer.

  1. PKU EPIC Lab73

    FoldNet++: A Large-Scale Synthetic Dataset for Robotic T-Shirt Folding and Unfolding

    PKU EPIC Lab has released FoldNet++, a large-scale synthetic dataset for robotic T-shirt folding and unfolding, covering 6 robotic embodiments, 1K T-shirts, 1K environmental assets, and 120K richly annotated demonstrations.

    Why it matters: The source gives the dataset scale and the real-world deployment success rate, so readers can assess the feasibility of training garment manipulation policies purely on synthetic data.