Embodied AI

Singapore-based embodied AI startup Ropedia said it has released Ropedia W0, a cross-embodiment mobile manipulation world model developed with researchers from Nanyang Technological University, Duke University, the University of California San Diego and Tsinghua University. The model uses a unified action representation to predict first-person future scene changes after actions by humans, robotic arms and humanoid robots, allowing one model to cover different robot embodiments. Ropedia said W0 ranked first across five evaluation benchmarks and 11 tests. In the Ψ₀ and ω-HOME benchmarks, W0 outperformed comparison models trained on full data without post-training, the company said. On the DreamDojo official benchmark, W0 exceeded DreamDojo trained on full data using only 1% of post-training data. The model takes initial frames, text...

WorldOracle, which its developers describe as the first benchmark for action-driven world models that uses real-world execution as the yardstick, launched on Oct. 16 and opened evaluation submissions to developers. The project was jointly completed by researchers from AGIBOT, NVIDIA, Princeton University, the University of Texas at Austin and the University of Toronto, combining world-model developers with benchmark researchers. The platform addresses a question the industry has lacked a benchmark to answer directly: given a set of actions, how far is a model’s predicted future from what actually happens? WorldOracle defines this as “Execution Coherence.” The researchers said a reliable world model must withstand three stress tests: causal obedience, meaning it must follow the given action sequence, including wrong or...

ACE Robotics has released a visual-spatial grounding-enhanced embodied foundation model, ACE-Brain-0.6, and said the 9-billion-parameter system outperformed OpenAI’s GPT-6 Astra on six of eight grounding benchmarks. The company said the model is designed to improve target identification, spatial localization and interaction anchoring—capabilities it described as critical for translating high-level task reasoning into reliable physical action. It builds on the earlier ACE-Brain-0.5 and focuses on visual grounding: identifying target objects, interaction areas and spatial references, and linking them to position, displacement and motion parameters. In seven public benchmarks, ACE-Brain-0.6 averaged 74.53 points versus 73.68 for GPT-6 Astra, according to the company. It said the model beat GPT-6 Astra on six of eight evaluations, including Where2Place (76.55 vs. 71.10), PixMo-Count (89.41 vs....

DexForce, an Chinese embodied-AI developer, has unveiled UNITAS, a 3D-native world action model for robot manipulation, saying it is designed to give robots a unified representation of the physical world. The company described UNITAS as the first robot-task-native 3D world model. UNITAS is built on a central premise: just as large language models unify diverse knowledge through text, embodied AI needs a native space for physical experience. DexForce argues that space should be the 3D physical world itself, rather than 2D images or latent features from which 3D relationships must be inferred. The model jointly represents observation, action and scene change in a single 3D coordinate system. Observation corresponds to the 3D positions of objects; action flow corresponds to the...

Researchers at Caltech and Stanford have unveiled HomeBody, a system that gives GPT Astra persistent spatial memory and the ability to execute compound humanoid actions for long-horizon tasks. In a kitchen demo, a Unitree G1 robot guided by Astra cleaned the room and retrieved remembered items from ambiguous requests. The team said the system requires no environment-specific training or additional policy learning. HomeBody replaces the trained intermediate VLA layer in conventional three-part architectures—System2 VLM for vision and instructions, System1 VLA for control commands, and System0 for coordinated motion. As frontier models such as Astra improve, the researchers argue trained VLAs are no longer necessary and System2 can directly manage reusable motion skills. A plug-and-play VLM calls a composable skill library....

Figure, the U.S. humanoid robot developer, has released Helix 2.5, its most advanced neural network model to date, and said it enabled zero-shot whole-body autonomy in 30 real homes. Figure called it the first demonstration at that scale of zero-shot whole-body behaviour generalisation for a humanoid robot. The company said a single pre-trained foundation model was applied to three types of behaviour: locomotion; manipulation of rigid and deformable objects; and bimanual coordination, as well as active perception. Figure said that, with task-specific data, architecture, training method and evaluation unchanged, pre-training on Index alone raised zero-shot recognition success to 56% from 9%. Index is Figure’s robot dataset project built for global scale. The model also validated a Human-to-Humanoid Robot Transfer Scaling...

What happens if robot model training data is expanded from 300 hours to 30,000 hours? Can robotic systems, similar to large language models, continuously gain new capabilities as datasets grow? AGIBOT’s newly released native World Action Model (WAM), GE-Act 2.0, systematically answers that question for the first time. Unlike mainstream approaches that build upon existing video generation models, every parameter of GE-Act 2.0 — including core modules for visual representation, future prediction and action forecasting — is initialized from scratch and trained end-to-end on embodied manipulation data. After pre-training, the model undergoes zero-shot real robot tests on unfamiliar scenes and unseen objects without fine-tuning or demonstration for benchmark tasks. The evaluation covers 100 atomic tasks, 20 skill categories and two...

Chinese robotics company Unitree said it has fully open-sourced an upgraded version of its general-purpose humanoid foundation model, UnifoLM-WLA-1.0, setting new state-of-the-art results on multiple global open-source embodied model benchmarks. The model can perform both tabletop manipulation and whole-body mobile manipulation with a single model, enabling cross-task and cross-end-effector generalization, Unitree said. It achieves a “one-model-driven, whole-body coordination” effect, the company added. Unitree said UnifoLM-WLA-1.0 was trained on large-scale general-purpose multimodal perception and understanding datasets and incorporates interaction-centric world modeling, significantly strengthening spatial perception and scene understanding. It outperformed several open-source competitors in China and overseas on multiple embodied reasoning benchmarks, with some capabilities comparable to mainstream closed-source models, according to the company. In real-robot tests, a single model completed...

Astribot, a Chinese robotics startup, has unveiled SmoothRL, an online reinforcement learning framework designed to train policies during asynchronous execution – a growing reality for embodied AI deployments where inference and action run at different frequencies. The work, led by the company’s foundation model team, addresses a fundamental mismatch: when a robot receives new action chunks before previous ones finish, conventional RL that updates on entire chunks ends up crediting or blaming actions that were never actually executed. The framework partitions each action chunk into three regions – committed (already fixed), execution (actually performed), and discarded (overwritten by later inference) – and backpropagates gradients only through the execution region. This ensures that optimisation mirrors the robot’s real experience. SmoothRL also...

Fei-Fei Li’s startup World Labs has released Atlas, a next-generation world model billed as the first multimodal system capable of pixel-level camera-controllable image and video generation paired with native 3D scene reconstruction. Trained from scratch on text, image, video and 3D data, the so-called “omni model” unifies four distinct modalities within a single unified architecture. Its flagship innovation, termed “spatial context”, grounds each input image in a precise 3D coordinate space with explicit camera pose parameters. By treating geometric camera controls as native inputs, Atlas eliminates reliance on textual prompts to describe camera motion, letting users specify exact viewing angles and trajectories to generate up to 1440p-resolution videos with a maximum one-minute duration. World Labs frames the upgrade as letting...