Skip to content
#Open source
  1. 3D视觉工坊 · 微信公众号78

    Any3R goes open source: one model unifies 3D reconstruction and pose estimation for pinhole, fisheye, and panoramic cameras

    South Dakota State University and other institutions propose Any3R, which uses a dense ray field to describe arbitrary central cameras, reconstructing a 3D point cloud and estimating pose from mixed-camera images in a single forward pass. The method replaces the row and column indices of rotary position encoding with angular coordinates and weights the pixel loss by solid angle, so one set of weights covers pinhole, fisheye beyond 180°, and 360° panoramic cameras. On benchmarks spanning 13 central camera types and 3 datasets, it leads in both reconstruction accuracy and pose accuracy; the inference code, 13 camera models, and weights are open-sourced.

    Why it matters: The article presents a feed-forward 3D reconstruction method that replaces the pinhole assumption with a dense ray field, offering insight into handling mixed inputs from multiple camera types.

  2. arXiv cs.RO78

    ∇Mimic: Efficient Whole-Body Control for Humanoid Robots with Differentiable Simulation

    The authors propose ∇Mimic, which uses exact gradients from a differentiable simulator to train whole-body motion-tracking policies for humanoid robots, reaching a score of 0.82 in 20 minutes and 0.874 in 1.8 hours on a single GPU, whereas the world-model method takes 1.2 hours to reach 0.82.

    Why it matters: The paper presents a complete scheme for training humanoid policies with exact gradients under differentiable simulation and open-sources the engine and code, making it easy to compare the efficiency of first-order and zeroth-order methods.

  1. 3D视觉工坊 · 微信公众号78

    HKU open-sources GenSfM: jointly reconstructing 3D objects and camera poses from four uncalibrated images

    A University of Hong Kong team has open-sourced GenSfM, which uses a native 3D diffusion model to jointly denoise object shape and per-view camera poses within a single multimodal sequence, requiring only 2 to 4 uncalibrated images and no camera intrinsics or extrinsics. Evaluated on Toys4k and GSO, it improves novel-view PSNR by 3.2–4.5 dB over the multi-view baseline TRELLIS-M, reduces median Chamfer distance by about 64%–74%, and achieves pose Acc@5° above 96%.

    Why it matters: The work turns a native 3D diffusion model into the main inference mechanism for joint denoising of shape and camera poses, and releases code and models as a reference for sparse-view reconstruction.

  1. OFweek Robotics82

    X-Era AI Tuoyuan Zhihui releases open-source 4D world action model E0.5, with out-of-distribution real-robot success rate surpassing π0.5

    X-Era AI Tuoyuan Zhihui released the open-source native 4D world action model E0.5, which uses a 3D foundation model as its backbone and integrates future 3D geometry prediction directly into action learning. On the AgileX Piper dual-arm robot and the Zerith H1 humanoid robot, after pretraining on about 160,000 robot trajectories, E0.5 achieved overall average success rates of 85.0% and 88.3%, respectively, improving on π0.5 by 13.3 and 26.7 percentage points; its out-of-distribution average success rates were 73.3% and 76.7%.

    Why it matters: The original text provides a comparison of E0.5 and π0.5 success rates on out-of-distribution real-robot tasks, which readers can use to judge the effect of 3D geometry supervision on manipulation generalization.

  1. Xbotics具身智能实验室 · 微信公众号82

    RLinf v0.4 released: open-source training framework upgrade for embodied reinforcement learning

    RLinf, an open-source training framework for embodied reinforcement learning developed by Tsinghua University, Infinigence AI, and the Beijing Zhongguancun Academy, has officially released v0.4, with updates across four areas: a Lego-style real-machine system, real-machine post-training algorithms, full-modality model support, and a domestic computing power foundation.

    Why it matters: It outlines the framework's evolution from simulation to real-machine training, helping readers understand the capability boundaries of the embodied reinforcement learning engineering stack.

  1. arXiv cs.RO76

    RAX: An open-source framework for scaling robot agent capabilities through online exploration

    The paper proposes RAX (Robot Agent eXploration), an open-source robot agent framework centered on scaling online exploration, in which a general-purpose coding agent generates robot control code without using action demonstration data, hand-engineered action primitives, or value-function guidance.

    Why it matters: The paper compares the imitation learning paradigm that relies on demonstration data with a demonstration-free online exploration approach, and reports quantitative gaps in simulation and on real robots, helping readers assess the feasibility of this direction.

  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. Intrinsic74

    Intrinsic releases open-source Intrinsic Core physical AI platform and OMTS reference solution

    Intrinsic has released the open-source Intrinsic Core platform, which includes hardware-agnostic real-time control, 6-DoF pose estimation based on NVIDIA FoundationPose, motion and grasp planning, Gazebo simulation, camera calibration, and Intrinsic-ROS drivers.

    Why it matters: The official announcement describes the open-source platform's core capabilities in control, perception, and planning, as well as its reference solution, which readers can use to assess its reusability in manipulation-oriented industrial automation.

  1. Dexmal 原力灵机 · 微信公众号73

    Force Spirit DM0.5 Tops All Four RoboColiseum Leaderboards

    Force Spirit announced that DM0.5 has topped all four RoboColiseum leaderboards (instruction following, spatial understanding, perturbation adaptation, and general manipulation), making it the only model on the leaderboards to rank first in every evaluation.

    Why it matters: The original article lists DM0.5's specific scores on multiple leaderboards and its inference latency reduction data, which can be used to assess the practical effectiveness of its pretraining approach.

  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.

  1. RoboParty · 微信公众号75

    RoboParty Lab Established, Open-Sources Three Humanoid Robot Toolchains for Training, Control, and Data

    RoboParty announced the establishment of RoboParty Lab and open-sourced three humanoid robot toolchains: the supervised learning training framework MimicLite, the unsupervised reinforcement learning control framework UFO, and the motion retargeting tool hhtools.

    Why it matters: The three toolchains provide specific figures on training compute, time required, and the policies already integrated, which readers can use to assess their reuse value in their own R&D workflows.

  1. LimX Dynamics67

    LimX Dynamics Open-Sources FluxVLA Engine, a Standardized VLA Engineering Foundation

    LimX Dynamics has officially open-sourced FluxVLA Engine, a standardized VLA engineering foundation for embodied intelligence that covers the full pipeline from data and training to simulation evaluation and real-robot deployment.

    Why it matters: LimX Dynamics has officially open-sourced its VLA engineering foundation, which lets readers understand how unified configuration and real-robot deployment workflows lower the barrier to research and development.

  1. 简智机器人 · X71

    Genrobot open-sources Phase 3 UMI dual-arm manipulation dataset

    Genrobot has open-sourced the Phase 3 UMI dataset, containing 13K+ hours of dual-arm data that is ready to use and supports sub-1ms frame-level synchronization and high-fidelity trajectory reconstruction. The data was collected by 3K+ contributors in 10K+ real homes, covering diverse everyday manipulation skills. Download at https://huggingface.co/datasets/genrobot2025/10Kh-RealOmin-OpenData.

    Why it matters: The data scale and real-home collection background help readers judge whether this kind of UMI data can be used to train their own manipulation tasks.

  1. 松灵机器人66

    NYU open-sources YOR, a low-cost dual-arm mobile robot, with bill of materials under $10,000

    A research team at New York University has open-sourced YOR (Your Own Robot), a mobile dual-arm manipulation robot, with a bill of materials cost below $10,000. The project homepage is www.yourownrobot.ai, and the paper is at arxiv.org/abs/2602.11150.

    Why it matters: An open-source dual-arm mobile platform under $10,000 offers a reproducible hardware path and measured data, making it suitable for evaluating the cost and capability trade-offs of building a mobile manipulation system in-house.

You’re all caught up