Skip to content
#Model releases
TodayNov 11Wed1 updates
  1. Apptronik Social67

    Apptronik shares Gemini Robotics 2.5 release, highlighting its breadth of skills

    Google DeepMind has released Gemini Robotics 2.5, saying this physical AI can learn hundreds of everyday skills, including folding clothes, serving pastries, and autonomously sorting car parts in factories. Apptronik shared the news and added examples such as tying a bow and sorting car parts, saying this reflects the model's breadth of skills.

    Why it matters: Gemini Robotics 2.5 demonstrates hundreds of skills spanning household chores and factory sorting, offering a view of the capability boundaries of general-purpose manipulation models.

Nov 10Tue
  1. The Humanoid Hub78

    Robbyant open-sources LingBot-Touch tactile foundation model

    Robbyant has open-sourced LingBot-Touch, a tactile foundation model pretrained on about 5,000 hours of real tactile data that reads magnetic, vision-based tactile, and piezoresistive sensor inputs into a unified token space. Across 26 real robot tasks and two dexterous hands, four policies using these tokens all achieved the highest average success rates; on specific sensor models unseen during pretraining, a frozen encoder reduced contact-center error from 5.89 mm to 0.16 mm, outperforming an adapter built specifically for it.

    Why it matters: The tactile foundation model unifies multiple types of tactile sensors into the same token space and provides cross-sensor and cross-task transfer results.

  2. APPSO · 微信公众号0

    NVIDIA launches GR00T 2 to let robots learn fine manipulation from human demonstrations

    At CoRL, NVIDIA unveiled the GR00T 2 robot learning model, built on NVIDIA Cosmos, which can learn from human demonstrations and transfer skills across different robot embodiments. Of the 50 tasks it evaluated, 40 were successfully completed at least once with no task demonstrations; after one demonstration per task, the average success rate was 71%, and after five demonstrations it reached 95%.

  3. 机器人前瞻 · 微信公众号88

    NVIDIA releases GR00T 2 series world-action models, trained on 400,000 hours of human video

    At CoRL 2026, NVIDIA launched the open-source world-action model series GR00T 2, comprising two versions, GR00T 2 and GR00T 2 Turbo. The former focuses on generalization and fine manipulation, while the latter has fewer parameters and can be deployed directly on the Unitree G1, with a single inference taking 124 milliseconds on the onboard Jetson Thor.

    Why it matters: NVIDIA released the GR00T 2 series at CoRL 2026 and disclosed the scale of three types of pre-training data along with success rates for cross-embodiment transfer and few-shot adaptation, which can be used to assess the current capability boundaries of world-action models.

  4. Google DeepMind · X73

    Google DeepMind releases Gemini Robotics 2.5 physical AI model

    Google DeepMind has released Gemini Robotics 2.5, saying this physical AI model can learn hundreds of everyday skills, including folding clothes, serving pastries, and autonomously sorting auto parts on a factory floor. The official announcement outlined its capability scope with a set of images and did not disclose the model size, training data, or evaluation metrics.

    Why it matters: The official announcement gives the capability scope of Gemini Robotics 2.5, which can learn hundreds of everyday skills, making it easy to compare against the previous generation to judge progress.

  5. Google DeepMind · X53

    Google DeepMind, Apptronik and Mercedes-Benz complete Gemini Robotic 2.5 proof of concept; Apollo 2 achieves 96% accuracy sorting car parts

    Google DeepMind, Apptronik and Mercedes-Benz conducted a proof of concept in which Gemini Robotic 2.5 drove the Apollo 2 robot to pick and organize car parts for assembly, achieving 96% accuracy. The result is currently at the proof-of-concept stage; deployment scale and production-line conditions have not been specified.

  7. 量子位87

    NVIDIA releases world action model GR00T 2, enabling cross-embodiment transfer of human demonstrations

    NVIDIA's GEAR team released its next-generation world action model GR00T 2 at the CoRL conference. It can simultaneously predict future frames and robot actions. The model, data, simulation environment, and collection hardware will be open-sourced progressively, and 100,000 hours of human data have already been released first.

    Why it matters: NVIDIA GR00T 2 pretrains on a mix of human video, UMI, and teleoperation data, and reports quantitative success rates for cross-embodiment transfer, which can be used to assess the data strategy for robot foundation models.

  8. 芯东西78

    Ant Group's Lingbo open-sources LingBot-Touch tactile pretrained model, unifying signals from multiple sensor types

    Ant Group's Lingbo on November 10 open-sourced LingBot-Touch, a tactile pretrained foundation model for dexterous manipulation that can encode different sensing signals such as piezoresistive and vision-based tactile signals into unified tactile tokens for use by different dexterous hands and policy models.

    Why it matters: The original article provides comparative data on the cross-sensor tactile pretrained model across 26 real-robot tasks, which can be used to assess the actual impact of tactile representations on policy success rates.

  9. 量子位88

    Ant Group's Lingbo open-sources LingBot-Touch, a tactile pretraining foundation model

    Ant Group's Lingbo has open-sourced LingBot-Touch, a tactile pretraining foundation model that uniformly encodes magnetic, visuotactile, and piezoresistive tactile signals into tactile tokens, which are then passed to the action model. Team experiments showed that when π0.5 was directly fed raw tactile readings on a zipper-pulling task, its success rate dropped from 39% to 15%; after connecting LingBot-Touch, it rose to 59%.

    Why it matters: The original provides a controlled experiment showing that feeding raw tactile signals into the action model instead lowers the success rate, along with the improvement after unifying tactile tokens, which can serve as a reference for tactile representation design.

  10. 量子位80

    Ant Group's Lingbo open-sources LingBot-Touch tactile foundation model

    On November 10, Ant Group's Lingbo Technology open-sourced LingBot-Touch, a tactile foundation model pre-trained on nearly 5,000 hours of real tactile data. It covers three sensing principles—magnetic tactile, visuotactile, and piezoresistive—and outputs unified tactile tokens for use by different dexterous hands and action models.

    Why it matters: The original text provides a unified representation across three types of tactile sensing and data from 26 real-machine tests, which can be used to assess the gains a tactile foundation model brings to existing action models.

  11. 36Kr Embodied Intelligence60

    Anthropic unveils new versions of Fable 5.2 and Mythos 5.2 models

    Anthropic has unveiled new versions of its Mythos and Fable AI models. Fable 5.2, scheduled for release on Monday, can perform more hardware-related tasks such as controlling robots, and can coordinate more than 1,000 AI agents simultaneously. Mythos 5.2, the same model line, has fewer safeguards in cybersecurity and life sciences and will be rolled out to select organizations through a previously announced verification program. Anthropic says both models are faster than previous versions, and Fable is cheaper.

  12. The Robot Report88

    NVIDIA launches GR00T 2 world action model and Isaac Lab 3.0 at CoRL

    NVIDIA launched the open world action model GR00T 2 and the open-source robot learning framework Isaac Lab 3.0 at CoRL. GR00T 2 was trained on 100,000 hours of NVIDIA open-source first-person data; with only one demonstration per task, it reached an average success rate of 71% across 50 tasks, rising to 95% with five demonstrations, and without task-specific demonstrations it completed at least once each of 40 of the 50 tasks.

    Why it matters: GR00T 2's few-shot success rates and Isaac Lab 3.0's training throughput gains provide the current baseline for embodied models and the simulation training stack.

  13. Robotics & Automation News72

    Nature Will releases 50-billion-parameter dexterous hand model Natura-1

    Nature Will has released Natura-1, a 50-billion-parameter physical general foundation model for dexterous hand control and zero-shot instruction following. The model is based on a mixture-of-experts architecture, jointly trained on language, images, video, and actions, pre-trained on more than 1 million hours of first-person human data, and runs with a 100-millisecond control loop. The company says it can autonomously execute sustained workflows and handle spatial constraints, multi-object relationships, and negation conditions.

  14. 达纳灵动 · X58

    Dyna Robotics unboxes Taku live at CoRL, powered by Dyna-2.1 for zero-shot long-horizon whole-body mobile manipulation

    Dyna Robotics unboxed Taku on-site at the CoRL conference and put it straight to work. Driven by Dyna-2.1, the robot completed long-horizon whole-body mobile manipulation zero-shot, with no on-site data collection or post-training. The team demonstrated it live at Booth 500 in Griffin Hall.

Nov 9Mon
  1. Union Square Ventures · X58

    Tutor launches TRACE deployment-time compute scaling method and releases TI-0.1 model

    Tutor launches TRACE, which uses deployment-time compute scaling for robot learning: starting from a small number of Tutor demonstrations, a frontier large language model agent reconstructs the task in simulation and trains reliable, human-speed policies. TI-0.1 is the first model trained with TRACE. USV believes this further shows that deploying robots in the field accelerates learning, with each deployment generating training data, giving Tutor a new way to make robot learning continuously accumulate.

Nov 8Sun
Nov 7Sat
  1. 量子位67

    Moxin Technology releases MoWorld 2.0 general-purpose 4D world model, integrating more than ten physical elements

    At the World Internet Conference in Wuzhen, Moxin Technology released MoWorld 2.0, a new-generation general-purpose 4D world model that integrates more than ten physical elements, including gravity, elasticity, buoyancy, lighting, soft bodies, fluids, rigid bodies, deformable bodies, and thermal dynamics, into a single model to more accurately simulate object motion, collisions, and environmental changes.

  2. 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.

  3. 机器之心 · 微信公众号78

    Yuance Future Releases Anchor 1 Whole-Body Control Model for Humanoid Robots

    Yuance Future has released Anchor 1, a whole-body control model positioned as the System 0 cerebellum layer within a whole-body intelligence architecture. It uses five anchor points—the pelvis, left and right wrists, and left and right ankles—as commands and does not rely on online retargeting.

    Why it matters: The original article provides quantitative comparisons of the whole-body control model's real-machine error and teleoperation collection efficiency, which can be used to assess how the cerebellum layer's precision affects the success rate of upper-layer VLA tasks.

  5. CVer · 微信公众号69

    miHoYo and Tsinghua University and others open-source GameScaling general game agent models

    miHoYo, together with Tsinghua University, the University of Hong Kong, the National University of Singapore, and other institutions, has open-sourced the GameScaling series of general game models, covering four size tiers—0.8B, 2B, 9B, and 27B—for a total of eight models. The weights and inference code are released under the Apache 2.0 license.

Nov 6Fri
  1. Beijing Humanoid Robot Innovation Center70

    Beijing Humanoid releases Hi-WBC general whole-body control model on "Huisikaiwu" platform

    Beijing Humanoid released the Hi-WBC general whole-body control model on the "Huisikaiwu" platform on November 2. The model combines human motion references with real physical constraints, enabling robots to adjust how they execute tasks as payload, external forces, and terrain change. It uses a continual skill expansion framework based on MoE and policy distillation, Contact-aware Learning that incorporates contact force prediction, and Perceptive Control that introduces terrain awareness.

    Why it matters: The original text discloses Hi-WBC's technical approach to handling payload, external force, and terrain constraints beyond motion tracking, offering insight into how whole-body control is moving from demonstrations toward real work.

  2. 机器之心 · 微信公众号80

    LiberAI releases world action model Liber-0, publishes technical report and online simulator

    LiberAI, founded by Liu Songming, has released Liber-0, a new-generation world action model that uses three expert streams for language, vision, and action along with Multimodal Attention to jointly predict future frames and actions.

    Why it matters: The technical report uses controlled experiments to break down the contributions of human data, action supervision, and embodiment diversity to dexterous manipulation, which can inform judgments about data-mix strategies.

Nov 5Thu
  2. Robotics & Automation News78

    AGIBOT releases embodied foundation model GO-3 Preview, tops three embodied AI benchmarks

    AGIBOT has released GO-3 Preview, an embodied foundation model built on its self-developed WRAM (World Reasoning Action Model) architecture that unifies task understanding, future state prediction, and action generation. It ranks first on three embodied AI benchmarks: RoboDojo, RoboTwin, and RoboColiseum, and is planned for full open source release by the end of 2026.

    Why it matters: AGIBOT has disclosed the architecture and three-stage training design of GO-3 Preview, which can be compared against its technical roadmap evolution from GO-1 to GO-3.

  3. 机器人前瞻 · 微信公众号72

    LiberAI releases world action model Liber-0, pretrained on 2.2 million hours of human data

    Physical world model startup LiberAI has released the world action model Liber-0, pretrained on over 2.2 million hours of human experience data, converting human manipulation experience into robot manipulation capability. In 60 tasks randomly generated by GPT-6 and 600 real-robot tests, Liber-0 achieved a zero-shot overall success rate of 36.0%, reaching 63.5% on pick-and-place tasks; the GPT-6 Astra control achieved an overall success rate of only 5%.

Nov 4Wed
  1. Guyuehome29

    Flex-π explained: from multi-stream world prediction to switchable robot policies

    Flex-π targets dual-arm robot manipulation, using a single approximately 6-billion-parameter model to jointly learn actions, future appearance, 3D geometry, and object semantics, then selecting at deployment which content to generate. It addresses the tension that predicting the future can provide more information, yet not all tasks require all prediction content.

  2. 未来不远 · 微信公众号76

    Future Not Far releases Self-Evolving WAM self-evolving world-action model

    Future Not Far released the Self-Evolving WAM self-evolving world-action model, integrating joint world-action modeling, interactive experience learning, and training-effect feedback into a single system. In update attempts from round 0 to round 30, all four groups of household tasks showed gains in autonomous full-completion success rates: folding clothes rose from 54.6% to 96.8%, hanging clothes from 46.2% to 91.2%, making pasta from 42.7% to 89.5%, and stir-fried pork with chili peppers from 38.2% to 68.9%.

    Why it matters: The original text gives the success-rate changes for four groups of household tasks from round 0 to round 30 updates, showing the practical benefits of the self-evolving training loop.

  3. 量子位67

    China Merchants Group Lion Rock Lab releases embodied reasoning model Lion-ER-35B-A3B

    The Lion Rock AI Lab under the China Merchants Group Advanced Technology Research Institute has released an embodied reasoning vision-language model, Lion-ER-35B-A3B. It uses a MoE architecture with about 35B total parameters and about 3B activated per token. On ten public embodied-related benchmarks, all metrics improved over the base model, with an equal-weight composite average score of 65.29.

  4. Robotics & Automation News71

    LiberAI launches Liber-0 world action model, pretrained on 2.2 million hours of human experience

    LiberAI has released Liber-0, a world action model pretrained on more than 2.2 million hours of human experience, combining large-scale human video, hand motions recorded with data gloves, and robot demonstrations, with the goal of giving robots generalizable manipulation capabilities. In an eight-task evaluation, a policy trained with 25% robot demonstrations plus 100% glove demonstrations scored 75.6 on progress, higher than the 72.8 scored using only all robot demonstrations. In a 60-task zero-shot evaluation, Liber-0 achieved a 36% success rate.

Nov 3Tue
  1. 3D视觉工坊 · 微信公众号72

    XPENG ROBOTICS releases embodied VLM Capek 0.5: 2B and 35B-A3B sizes, improving on 30 and 28 of 34 benchmarks respectively

    XPENG ROBOTICS proposes the embodied vision-language model Capek 0.5, training separate experts for four execution capability categories—spatial reasoning, temporal understanding, action guidance, and state verification—then integrating them into a single model via TIES merging and routed MOPD distillation.

  2. 机器人全球资讯 · 微信公众号70

    AgiBot releases embodied Agent framework Genie Master; Genie G2 works and evolves in a convenience store

    AgiBot has released its embodied Agent framework Genie Master. A Genie G2 running the framework, when deployed in a real convenience store, does not rely on human demonstrations or debugging; it can identify the causes of failures on its own, adjust strategies, and accumulate experience, improving continuously on tasks such as packaged-food packing, picking, and restocking. AgiBot says this is the industry's first validation of Physical RSI (embodied recursive self-improvement) outside simulation in a real business scenario, and it plans to arrange 6 Genie G2 units on November 2 for a continuous 24-hour livestreamed convenience-store operation test.

Nov 1Sun
  1. 机器之心 · 微信公众号67

    Xingyan Intelligence Releases General Embodied Harness Framework Auriga, Leading RoboDojo Leaderboard in Zero-Shot Setting

    Xingyan Intelligence has launched Auriga, a general embodied Harness framework. Under a zero-shot protocol that involves no task-specific pre-tuning, no reliance on expert demonstrations, single-attempt execution, and no environment resets, it achieved a 57.74% average task success rate and an average process score of 64.00 across 42 tasks and 6,300 test episodes on RoboDojo, using GPT-6 Astra as the base model. It leads the leaderboard on both metrics.

  2. 机器之心 · 微信公众号78

    Fysics AI and Fudan propose Fysiverse-UniWAM unified world-action model, ranks first in both navigation and mobile manipulation across 24 real-robot tests

    Fysics AI, together with Fudan University's CITLab, proposed the unified world-action model Fysiverse-UniWAM, which uses a single model to handle autonomous navigation, mobile manipulation, and fixed-workstation dexterous manipulation.

    Why it matters: Readers can see a unified world-action model approach that does not rely on large-scale robot pretraining, along with the specific design of a shared backbone for navigation and manipulation.

Oct 31Sat
  2. 36氪 · 微信公众号22

    Google DeepMind releases Genie 4 world model research preview; Zhou Qunfei becomes China's newest richest woman with 127 billion yuan

    Google DeepMind released the Genie 4 world model research preview on October 27, marking the first native support for synchronized audio-video generation, extending the duration of a single coherent world from 1 minute in the previous generation to about 2 minutes, and supporting real-time scene modification via typing. Google also demonstrated an experiment in which Genie 4 worked with Gemini 4 Argon to direct a humanoid robot in playing checkers, but it is currently available only to a small number of testers, and ordinary users need a Google AI Ultra subscription.

  3. 36氪 · 微信公众号6

    Qiyuan Robotics launches PrimeSim world model, tops WorldSimProbe LIBERO leaderboard

    Qiyuan Robotics launched PrimeSim, a world-model simulator for robot training, on October 30 and topped the WorldSimProbe LIBERO leaderboard. The simulator builds an interactive, trial-and-error-friendly, continuously learning virtual world for robots, used for policy validation and reinforcement learning. In testing, reinforcement learning with it raised policy success rates from 61.7% to 73.2%.