Technology areas
Robot models and learning
Robot VLA models, general action and world models, imitation and reinforcement learning, skill and motion policy learning, online adaptation, and transfer across tasks and robot bodies. The contribution is a model, policy, or learning method. Dataset releases belong under Data and simulation; inference deployment belongs under Software and compute systems.
206 selected · 116 in the last 30 days
X Square Robot/自变量机器人 ·
X Square Robot releases DMuon optimizer, improving embodied model distributed training efficiency by about 30%
X Square Robot has released the DMuon optimizer, a distributed adaptation of the Muon optimizer that improves embodied model distributed training efficiency by about 30%, reducing per-step training time from 2.2 times that of AdamW to 1.02 times. The improvements include Owner-centric execution and communication optimization, automatic selection of compute kernels based on matrix shape, and balanced workload distribution across Owners. DMuon is fully open source and compatible with Muon usage, requiring only 3 lines of code to introduce into training.
LimX Dynamics ·
LimX Dynamics releases humanoid VLA model V³-0 alongside COSA 0.5
LimX Dynamics released V³-0 alongside COSA 0.5, a humanoid VLA technology stack in its VLA-tools layer that supports mobile whole-body manipulation, running on the 43-DOF LimX humanoid robot Oli.
PsiBot/灵初智能 ·
Lingchu Intelligence and PKU-Lingchu Joint Lab Release and Open-Source Dual Dexterous Hand General Manipulation Model and Full-Stack System EgoSteer
Lingchu Intelligence and the PKU-Lingchu Joint Lab released and open-sourced the dual dexterous hand general manipulation model and full-stack system EgoSteer, comprising the data processing pipeline EgoSmith, the robotics technology stack Robot-Stack, and a world-model-enhanced VLA model.
蚂蚁灵波科技 · YouTube ·
LingBot-VA 2.0 released: a world-action model for physical-world robot control
Ant Group's Lingbo Technology has released LingBot-VA 2.0, which it describes as a world-action model pretrained from scratch for physical-world robot control, running real-time inference at 150 Hz on a single GPU and able to play air hockey, tidy desks, and pick chips from a conveyor belt.
蚂蚁灵波科技 · YouTube ·
Ant Lingbo Open-Sources Embodied Video Foundation Model LingBot-Video, Scoring 0.620 on RBench
Ant Lingbo has open-sourced LingBot-Video, a MoE video foundation model for embodied intelligence. It uses a DiT plus sparse MoE architecture with 30B parameters and 3B activated at inference, and is claimed to be about 3 times more efficient than dense models.
Hugging Face LeRobot ·
LeRobot v0.6.0 released with multiple breaking changes and new policies
Hugging Face LeRobot has released v0.6.0: pip install lerobot no longer includes dataset and training dependencies by default, requiring extras to be added as needed; GR00T N1.5 has been replaced by N1.7; and the minimum PyTorch version has been raised to 2.7.
PKU EPIC Lab ·
WAM-TTT: Steering World-Action Models at Test Time by Watching Human Videos
PKU EPIC Lab proposes WAM-TTT, a test-time training framework that steers world-action models from raw human videos without robot actions, human-side annotations, or task-specific fine-tuning. The method absorbs human videos into a lightweight adaptive memory inside a frozen WAM through self-supervised video prediction, and uses a meta-training stage with paired human-robot data and a key-value memory reconstruction objective to align human demonstrations with robot behaviors. Experiments show it consistently outperforms in-context human-video conditioning baselines across diverse manipulation tasks and generalization settings.
蚂蚁灵波科技 · YouTube ·
LingBot-VLA 2.0 open-sourced: supports 20 robot configurations and full-body control
LingBot-VLA 2.0 has been open-sourced. It is a next-generation embodied foundation model pretrained on 60,000 hours of real-world physical data, built on a redesigned data processing pipeline curated from 90,000 hours of robotic data and 20,000 hours of egocentric human videos.
智源研究院 · 微信公众号 ·
BAAI releases multimodal representation world model Wujie·RoboBrain Orca
BAAI has released the multimodal representation world model Wujie·RoboBrain Orca. Its core idea is to shift from predicting the next word, next frame, or next action to predicting the next world state: it first learns a unified latent world representation, then adapts to downstream tasks through three lightweight readout modules for text, images, and actions.
X Square Robot/自变量机器人 ·
X Square Robot completes four financing rounds, valuation exceeds 20 billion yuan
Shenzhen embodied intelligence company X Square Robot has completed four consecutive financing rounds from Series B through Series C, all fully closed, with a valuation exceeding 20 billion yuan, making it the first embodied intelligence company in the Guangdong-Hong Kong-Macao Greater Bay Area to surpass a 20 billion yuan valuation with the rounds closed. There are more than 30 investors, including the National Artificial Intelligence Industry Investment Fund, Sequoia China, and Xiaomi Strategic Investment. The company released its embodied large model WALL-B in April 2026, partnered with 58 Daojia to provide robot home housekeeping services to nearly 1,000 households in Shenzhen, and partnered with SF Express on flexible intelligent sorting and parcel feeding.
X Square Robot/自变量机器人 ·
X Square Robot releases cross-modal embodied action tokenizer X-Tokenizer, with 13.5% gain in multimodal alignment and 8.25% gain in long-horizon tasks
X Square Robot has released X-Tokenizer, a cross-modal embodied action tokenizer built on a semantic residual quantization (SRQ) architecture and pretrained on 17 robotic arm series and 2.4 million trajectories (including 2 billion action frames). Compared with FAST, it improves multimodal alignment by 13.5% and long-horizon task performance by 8.25%, and scores 82.8 on RoboTwin 2.0; in real-robot tests it outperforms comparison methods such as FAST and 4-level RVQ.
Figure AI ·
Figure 03 arrives at BMW Spartanburg plant for sequencing sorting tasks
Figure AI announced that the Figure 03 humanoid robot has entered Hall 52 at BMW Group Plant Spartanburg, shifting from the sheet metal loading and unloading work previously done by Figure 02 to a sequencing sorting use case; Figure 02 took part in assembling 30,000 vehicles last year.
HUMANOID ·
KinetIQ Ascend uses real-world reinforcement learning to boost humanoid robot manipulation throughput and success rate
HUMANOID has launched KinetIQ Ascend, an end-to-end visual reinforcement learning method that operates under production deployment conditions, extending its KinetIQ framework to let robots improve manipulation skills through trial and error rather than relying solely on human demonstration; the company says this is the first such method publicly demonstrated on production-line humanoid robot manipulation.
Harbin Institute of Technology Robotics ·
HIT's Zhu Yanhe Team Publishes Paper on Cooperative Reconfiguration for Self-Repair in Modular Robots
Professor Zhu Yanhe's team at Harbin Institute of Technology (HIT) published a paper in the International Journal of Extreme Manufacturing (IJEM), proposing an autonomous fault-tolerant repair strategy for modular robots based on cooperative reconfiguration, which restores joint fault damage by changing morphology without backup module replacement. The method combines topological description and kinematic self-modeling, particle swarm optimization to search for target configurations, and an improved RRT cooperative reconfiguration algorithm. In experiments, the fault-tolerance upper limit was 7 times higher than that of fixed-configuration redundancy methods. HIT is the sole completing institution, and doctoral student Qi Jian is the first author.
OFweek Robotics ·
Galbot releases AstraBrain-WBC 0.5, validating Scaling Law with humanoid motion data
Galbot released AstraBrain-WBC 0.5 (paper titled Humanoid-GPT, accepted to CVPR 2026), training a Transformer whole-body controller on about 2 billion frames of retargeted motion data, achieving a 92.58% zero-shot motion tracking success rate with 0.39 ms inference latency; code and data are open-sourced.
Holiday Robotics ·
South Korea's Ministry of Science and ICT Launches Physical AI Leading Technology R&D Project, Investing 34 Billion Won Over Two Years to Advance World Model Localization
South Korea's Ministry of Science and ICT held a launch briefing for the Physical AI Leading Technology R&D Project in Seoul on June 9, planning to invest 34 billion won over two years to jointly develop a Korean-style world model and domestic simulator with 10 industry-academia-research institutions including LG Electronics, aiming to raise robots' final action success rate by more than 20 percentage points compared with not using a world model, and planning to achieve an MVP within one year and eight months and conduct validation at manufacturing and logistics sites.
PKU EPIC Lab ·
KPGrasp: A Scalable Keypoint Flow Matching Method for Dexterous Grasp Generation
PKU EPIC Lab proposes KPGrasp, a dexterous grasp generation method that combines an all-Euclidean 3D hand-keypoint parameterization with a Transformer flow-matching model to learn grasp priors from large-scale data, without contact losses or contact-based test-time optimization.
PKU EPIC Lab ·
PKU EPIC Lab proposes LIMMT, a data-centric study for humanoid motion tracking, accepted to ICML 2026
PKU EPIC Lab released LIMMT (Less Is More for Motion Tracking), which it describes as the first data-centric study for physics-based simulated humanoid motion tracking. The method defines motion data quality along three dimensions: physics feasibility, diversity, and complexity. Training on less than 3% of AMASS achieves better tracking performance than training on the full dataset, and the team also cleaned web-sourced mocap data. The paper has been accepted to ICML 2026; see arXiv:2606.06953.
1X Technologies ·
1X Establishes World Model Lab, Sam Sinha Appointed Head of World Models
1X announced the formal establishment of the 1X World Model Lab, focused on large-scale pretraining of embodied world models, with the goal of accelerating the realization of fully autonomous humanoid robots. Sam Sinha, formerly a founding research scientist at Luma AI, has joined as Founding AI Researcher and Head of World Models.
Lumos Robotics/鹿明机器人 ·
Lumos Robotics completes several hundred million yuan A1 and A2 funding rounds, with Mitsubishi Electric leading both
Lumos Robotics has completed several hundred million yuan in A1 and A2 funding. The A1 round was led by Mitsubishi Electric, with participation from Puhua Capital and Wuzhong Financial Holdings, among others. Mitsubishi Electric continued to lead the A2 round, with participation from Hundsun Electronics, Haigao Group, and Kunshi Investment, among others. The funding will be used for embodied large-model R&D and scenario expansion. After the funding, the company's cash reserves reached several hundred million yuan. Its flexible quality-inspection embodied intelligence solution, co-created with Mitsubishi Electric, has been put into trial use at Mitsubishi Electric's factory in China. Its self-developed Lumos Nexcore physical AI engine and bodyless data-collection system Lumos FastUMI Pro support industrial deployment and data feedback.