We are open-sourcing Wall-OSS-0.5. Pretrain Once, Act Anywhere....

Uploaded: 2026-05-28T05:49:38.000Z
Duration: PT132.560S
Channel: X Square Robot

5:47

X Square Robot just closed its Series C at a valuation above RMB 20 billion, about $2.8 billion 🤖 IDG came into this round. The bigger signal is the cap table. HongShan and Xiaomi were already in across earlier rounds, while Meituan, Alibaba, ByteDance, and Xiaomi have each led rounds at different stages. That puts X Square in a rare position for an embodied AI company: top-tier financial capital on one side, and four of China’s biggest tech platforms on the other. This is not just a money story. Meituan, Alibaba, ByteDance, and Xiaomi bring very different strategic assets: real-world scenarios, cloud infrastructure, consumer traffic, supply chains, and hardware ecosystems. The deployment side is already moving: robot home-cleaning services first, then a “Robots Into Homes” program with the first batch entering real households. The model stack is worth watching too. X Square has open-sourced WALL-OSS-0.5 for robot manipulation and WALL-WM for world modeling. WALL-OSS-0.5 showed strong real-robot performance without post-training, while WALL-WM uses event-level prediction to align language, vision, and action around meaningful physical-world events. They are also building a model-driven data pipeline for large-scale collection, cleaning, annotation, quality control, and augmentation. That matters because home robotics dies in the long tail: weird rooms, messy objects, bad lighting, and tasks that never look the same twice. Founded in 2023, X Square is building general-purpose embodied AI robots and foundation models for real-world environments, tying models, robot hardware, high-precision manipulation, data, and deployment into one system.

RoboHub🤖

12,975 views • 3 months ago

1:15

Excited to introduce SOLE-R1, a video-language reasoning model for zero-shot reward prediction for robot manipulation tasks! SOLE-R1 reasoning can serve as the SOLE signal for learning new tasks (completely from scratch) through online RL - i.e., robots start with random actions and learn previously unseen tasks guided only by SOLE-R1 rewards, without any demonstrations, ground-truth rewards, success indicators, or task-specific tuning. SOLE-R1 significantly outperforms strong baselines (e.g., Robometer, RoboReward, TOPReward, GPT-5, Gemini-3-Pro) in zero-shot online RL when evaluated across 40 tasks - including a real-world tabletop manipulation setting and 4 sim environments (LIBERO, ManiSkill, Meta-World, RoboSuite). We open source all models, training data, and code. Website, demos, and paper at: 🧵 (1/6)

Philip Schroeder

19,408 views • 3 months ago

1:10

Introducing FLUX 3 Action. An open weights 7B World Action Model that achieves first place on the RoboLab benchmark. It outperforms the previous best open model by 6.1 percentage points while using 56% fewer parameters and running up to 3.95x faster.⁠⁠ FLUX 3 Action removes the usual trade-off between world action model performance and VLA speed: it still predicts video and actions together, but plans more than twice as far ahead and runs faster per second of robot motion than the strongest open VLA. Teams can fine-tune FLUX 3 Action on their own demonstrations to create policies for a particular robot and task. Together with NVIDIA, we also integrated FLUX 3 Action natively into Hugging Face's LeRobot, with fine-tuning recipes included and edge deployment on NVIDIA Jetson. Beyond robotics, we’re also seeing promising results training task-specific policies for acting in simulated environments like gaming, controlling a vehicle, computer use, and wherever else a model needs to understand a visual environment and then choose what to do next. FLUX 3 Action builds on the same image, video, and audio pretraining as FLUX 3, but uses a smaller architecture designed for practical deployment. In midtraining, we trained the model to predict actions and future frames together. We’re releasing the weights, code, fine-tuning recipe, benchmarks, and reproducible examples so researchers and developers can build on the model with their own robots, environments, and tasks (see below).

Black Forest Labs

167,788 views • 4 days ago

0:39

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):

Léo

32,331 views • 2 months ago

1:17

Announcing DreamDojo: our open-source, interactive world model that takes robot motor controls and generates the future in pixels. No engine, no meshes, no hand-authored dynamics. It's Simulation 2.0. Time for robotics to take the bitter lesson pill. Real-world robot learning is bottlenecked by time, wear, safety, and resets. If we want Physical AI to move at pretraining speed, we need a simulator that adapts to pretraining scale with as little human engineering as possible. Our key insights: (1) human egocentric videos are a scalable source of first-person physics; (2) latent actions make them "robot-readable" across different hardware; (3) real-time inference unlocks live teleop, policy eval, and test-time planning inside a dream. We pre-train on 44K hours of human videos: cheap, abundant, and collected with zero robot-in-the-loop. Humans have already explored the combinatorics: we grasp, pour, fold, assemble, fail, retry—across cluttered scenes, shifting viewpoints, changing light, and hour-long task chains—at a scale no robot fleet could match. The missing piece: these videos have no action labels. So we introduce latent actions: a unified representation inferred directly from videos that captures "what changed between world states" without knowing the underlying hardware. This lets us train on any first-person video as if it came with motor commands attached. As a result, DreamDojo generalizes zero-shot to objects and environments never seen in any robot training set, because humans saw them first. Next, we post-train onto each robot to fit its specific hardware. Think of it as separating "how the world looks and behaves" from "how this particular robot actuates." The base model follows the general physical rules, then "snaps onto" the robot's unique mechanics. It's kind of like loading a new character and scene assets into Unreal Engine, but done through gradient descent and generalizes far beyond the post-training dataset. A world simulator is only useful if it runs fast enough to close the loop. We train a real-time version of DreamDojo that runs at 10 FPS, stable for over a minute of continuous rollout. This unlocks exciting possibilities: - Live teleoperation inside a dream. Connect a VR controller, stream actions into DreamDojo, and teleop a virtual robot in real time. We demo this on Unitree G1 with a PICO headset and one RTX 5090. - Policy evaluation. You can benchmark a policy checkpoint in DreamDojo instead of the real world. The simulated success rates strongly correlate with real-world results - accurate enough to rank checkpoints without burning a single motor. - Model-based planning. Sample multiple action proposals → simulate them all in parallel → pick the best future. Gains +17% real-world success out of the box on a fruit packing task. We open-source everything!! Weights, code, post-training dataset, eval set, and whitepaper with tons of details to reproduce. DreamDojo is based on NVIDIA Cosmos, which is open-weight too. 2026 is the year of World Models for physical AI. We want you to build with us. Happy scaling! Links in thread:

Jim Fan

229,512 views • 7 months ago

2:21

Excited to announce GR00T N1, the world’s first open foundation model for humanoid robots! We are on a mission to democratize Physical AI. The power of general robot brain, in the palm of your hand - with only 2B parameters, N1 learns from the most diverse physical action dataset ever compiled and punches above its weight: - Real humanoid teleoperation data. - Large-scale simulation data: we are open-sourcing 300K+ trajectories! - Neural trajectories: we apply SOTA video generation models to “hallucinate” new synthetic data that features accurate physics in pixels. Using Jensen’s words, “systematically infinite data”! - Latent actions: we develop novel algorithms to extract action tokens from in-the-wild human videos and neural generated videos. GR00T N1 is a single end-to-end neural net, from photons to actions: - Vision-Language Model (System 2) that interprets the physical world through vision and language instructions, enabling robots to reason about their environment and instructions, and plan the right actions. - Diffusion Transformer (System 1) that “renders” smooth and precise motor actions at 120 Hz, executing the latent plan made by System 2. We deploy N1 on GR1 robot, 1X Neo robot, and a large collection of simulation benchmarks. N1 achieves up to +30% boost in diverse manipulation tasks for household and industrial settings. While humanoid robots are the main focus of N1, our model also supports cross-embodiment. We finetune it to work on the $110 HuggingFace LeRobot SO100 robot arm! Open robot brain runs on open hardware. Sounds just right. Let’s solve robotics, together, one token at a time. Links to our Whitepaper, Github repo, HuggingFace model, and open dataset page in the thread: 🧵

Jim Fan

467,416 views • 1 year ago

0:24

We trained a robot dog to balance and walk on top of a yoga ball purely in simulation, and then transfer zero-shot to the real world. No fine-tuning. Just works. I’m excited to announce DrEureka, an LLM agent that writes code to train robot skills in simulation, and writes more code to bridge the difficult simulation-reality gap. It fully automates the pipeline from new skill learning to real-world deployment. The Yoga ball task is particularly hard because it is not possible to accurately simulate the bouncy ball surface. Yet DrEureka has no trouble searching over a vast space of sim-to-real configurations, and enables the dog to steer the ball on various terrains, even walking sideways! Traditionally, the sim-to-real transfer is achieved by domain randomization, a tedious process that requires expert human roboticists to stare at every parameter and adjust by hand. Frontier LLMs like GPT-4 have tons of built-in physical intuition for friction, damping, stiffness, gravity, etc. We are (mildly) surprised to find that DrEureka can tune these parameters competently and explain its reasoning well. DrEureka builds on our prior work Eureka, the algorithm that teaches a 5-finger robot hand to do pen spinning. It takes one step further on our quest to automate the entire robot learning pipeline by an AI agent system. One model that outputs strings will supervise another model that outputs torque control. We open-source everything! Welcome you all to check out the paper, more videos, and try the codebase today: Code:

Jim Fan

909,210 views • 2 years ago

1:06:07

Today, we're joined by Nikita Rudin, co-founder and CEO of Flexion to discuss the gap between current robotic capabilities and what’s required to deploy fully autonomous robots in the real world. Nikita explains how reinforcement learning and simulation have driven rapid progress in robot locomotion—and why locomotion is still far from “solved.” We dig into the sim2real gap, and how adding visual inputs introduces noise and significantly complicates sim-to-real transfer. We also explore the debate between end-to-end models and modular approaches, and why separating locomotion, planning, and semantics remains a pragmatic approach today. Nikita also introduces the concept of "real-to-sim", which uses real-world data to refine simulation parameters for higher fidelity training, discusses how reinforcement learning, imitation learning, and teleoperation data are combined to train robust policies for both quadruped and humanoid robots, and introduces Flexion's hierarchical approach that utilizes pre-trained Vision-Language Models (VLMs) for high-level task orchestration with Vision-Language-Action (VLA) models and low-level whole-body trackers. Finally, Nikita shares the behind-the-scenes in humanoid robot demos, his take on reinforcement learning in simulation versus the real world, the nuances of reward tuning, and offers practical advice for researchers and practitioners looking to get started in robotics today. 🗒️ For the full list of resources for this episode, visit the show notes page: 📖 CHAPTERS =============================== 00:00 - Introduction 04:07 - Is robot locomotion solved? 06:04 - Sim-to-real gap 08:58 - Adding semantics to policies 09:42 - Modular vs end-to-end architectures 10:29 - Planner model 12:21 - Adapting RL techniques from quadrupeds to humanoids 15:39 - Behind robot demos 18:09 - Humanoid robots in home environments 22:03 - Training approach 23:56 - VLA models 27:59 - Closing the sim-to-real gap 32:55 - Task orchestration using VLMs 36:38 - Tool use 38:10 - Model hierarchy 43:37 - Simulator versus simulation environment 44:57 - Combining imitation learning and reinforcement learning 46:42 - RL in real world versus RL in simulation 52:58 - Reward tuning and value functions in robotics 56:38 - Predictions 1:00:10 - Humanoids, quadropeds, and wheeled platforms 1:02:45 - Advice, recommended robot kits, and community pla

The TWIML AI Podcast

22,592 views • 8 months ago

3:08

X Square Robot Unveils New Embodied AI Model, Says Robots Will Arrive in Homes in 35 Days Backed by Alibaba, ByteDance, Xiaomi and Meituan, X Square Robot unveiled a next-generation embodied AI foundation model for home robots and said its first deployments in everyday households will begin within 35 days. X Square Robot on Tuesday unveiled WALL-B, a new embodied AI foundation model designed for deployment in real-world homes, marking what the company described as a major step toward bringing general-purpose robots into daily family life. At a launch event themed "Born to Bot, Bot to Family," the company also introduced its World Unified Model (WUM) architecture, a training framework that combines vision, language, action and physical prediction within a single system from the outset. X Square said the model is intended to help robots operate in the far more unpredictable setting of a home, where tasks, layouts and interactions vary from moment to moment. "Robots in factories and in homes are completely different. In factories, they repeat the same action 10,000 times without variation. In a home, however, they need to perform 10,000 different actions, each unique and non-repetitive. Therefore, the challenge of a truly intelligent robot lies not in repeating a single action, but in the ability to execute new, untrained movements within unstructured environments. Deploying robots in the home is one of the most significant technical hurdles of our time," said Qian Wang, founder and CEO of X Square Robot. WALL-B is the first real-world implementation of the World Unified Model architecture. Unlike modular systems that train perception, language and control separately, X Square Robot said World Unified Model optimizes those capabilities jointly from the very beginning. The company said that allows physical prediction — including force, friction and collision dynamics — to emerge as part of the model itself, rather than being layered on afterward. "We train all capabilities—vision, language, action, and prediction—within the same network from day one. Much like infants, who do not learn to see, move and speak in isolated, sequential stages, but instead see, move listen and act simultaneously while receiving feedback, we have integrated all these capabilities into a unified whole," said Wang Hao, CTO of X Square. X Square Robot said the development of WALL-B rests on two pillars. The first is a data strategy that prioritizes training on authentic, non-staged home environments to cover the “long-tail” distribution of real-world scenarios, such as misplaced objects and temporary occlusions. Unlike models primarily trained on synthetic data or laboratory datasets, this strategy exposes WALL-B to the natural clutter of lived-in spaces—misplaced items, unexpected obstacles, and spontaneous human activity—ensuring that the training data reflects real-world conditions rather than a simplified version. The second is a physics-aware predictive mechanism that anticipates physical outcomes before an action is taken, enabling the model to respond to contact dynamics instead of just reacting. The development of the self-developed WUM architecture on physical robotic platforms highlights the company’s accumlated experience in bridging sim-to-real gaps across varied operational contexts. Wang commented that the current AI model is still in an "intern" stage, subject to errors requiring remote assistance. For instance, it may mistakenly place slippers in the kitchen or pause while wiping a table to "think". However, the model operates nonstop 24 hours a day, becoming increasingly "intelligent" as each day of operation generates new data. In 35 days, on May 25, X Square Robot will officially bring its robots into everyday homes, underscoring the company’s long-term commitment to the home robotics sector.

X Square Robot

52,968 views • 5 months ago

1:06

Can vision-language-action (VLA) models generalize to diverse OOD tasks and align with customized objectives? 🤔 🚀 We introduce GRAPE, a plug-and-play algorithm to generalize robot policies via preference alignment. GRAPE unfolds three benefits to boost the generalizability of VLAs: 👉1. GRAPE aligns VLAs on a trajectory level and endows the model with the ability for global decision-making, instead of merely cloning behavior; 👉2. GRAPE implicitly models reward from both successful and failed trials to boost generalizability to diverse tasks; 👉3. GRAPE adopts a scalable preference synthesis algorithm to rank trajectories with preferences that align with arbitrary objectives. Our experiments on a diverse array of real-world and simulated robotic tasks reveal: 1⃣GRAPE enhances the performance of state-of-the-art VLA models, increasing success rates on in-domain and unseen manipulation tasks by 51.79% and 60.36%; 2⃣GRAPE is versatile to be aligned with diverse objectives and reduce collision rates by 44.31% or rollout length by 11.15% when aligning towards safer or more efficient manipulation policy, respectively. Check out our full project for more details: 🔥 Paper: 🔥 Project: 🔥 Code:

Huaxiu Yao

20,071 views • 1 year ago

1:17

Most video-action robot models are a content-creation video generator with an action module attached. LingBot-VA 2.0 from Robbyant, a video-action foundation model, throws that starting point out and trains the whole stack natively for control. And it runs closed-loop at a peak 225 Hz. It's so important because A robot cannot move responsively when its controller pauses to imagine the next few frames. LingBot-VA 2.0 predicts during execution, then corrects using each real observation. And it carries only about 13B video parameters while activating roughly 1.9B per token. Bigger robot models usually mean slower reactions, creating a direct conflict between intelligence and control. LingBot-VA 2.0 is trained from scratch for robot control rather than adapted from a video generator built for content creation. Robbyant, an embodied AI company under Ant Group, built it to learn how scenes change under actions, predict what should happen next, and turn those predictions into real-time robot movements. Most video-action systems inherit a tokenizer and video backbone trained mainly to reproduce visual appearance. LingBot-VA 2.0 rebuilds both parts around physical control. Its semantic visual-action tokenizer maps observations toward features from a frozen vision foundation model and learns compact latent actions from frame-to-frame changes using self-supervised inverse and forward dynamics. Unlabeled web video can therefore carry action-relevant training signals without robot action labels. The policy is causal from the start, so every prediction can use only past observations. Its sparse Mixture-of-Experts video backbone has about 13B total parameters, while about 1.9B are active per token, keeping the compute lower during each step. A high-level vision-language planner breaks long tasks into smaller instructions, while the low-level video-action policy handles continuous movement. Foresight Reasoning predicts future visual states while the robot is already acting, then replaces imagined states with every new real observation. Combined with few-step distillation and systems acceleration, the paper reports a peak asynchronous execution frequency of 225 Hz. The model adapts from 10–15 demonstrations, transfers across robot embodiments, and handles some new tasks zero-shot. In the paper’s own evaluations, it reaches 93.6 average on RoboTwin 2.0 and reports stronger real-world results than LingBot-VA and π0.5 across the tested tasks. 🧵 1.

Rohan Paul

11,253 views • 2 months ago

1:31

The power of the Claw, in the palm of a robot hand. Agentic robotics is here! Today, we open-source CaP-X: vibe agents, alive in the physical world. They incarnate as robot arms and humanoids with a rich set of perception APIs, actuation APIs, and auto synthesize skill libraries as they go. CaP-X is a strict superset of our old stack, because policies like VLAs are “just” API calls as well. It solves many tasks zero-shot that a learned policy would struggle with. And we are doing much more than vibing. CaP-X is our most systematic, scientific study on agentic robotics so far: - We build a comprehensive agentic toolkit: perception (SAM3 segmentation, Molmo pointing, depth, point cloud), control (IK solvers, grasp planner, navigation), and visualization (EEF, mask overlays) that work across different robots. - CaP-Gym: LLM’s first Physical Exam! 187 manipulation tasks across RoboSuite, LIBERO-PRO, and BEHAVIOR. Tabletop, bimanual, mobile manipulation. Sim and real. Can’t wait to see the gradients flow from CaP-Gym to the next wave of frontier LLM releases. - CaP-Bench: we benchmark 12 frontier LLMs/VLMs (Gemini, GPT, Opus, Qwen, DeepSeek, Kimi, and more) across 8 evaluation tiers. We systematically vary API abstraction level, agentic harness, and visual grounding methods. Lots of insights in our paper. - CaP-Agent0: a training-free agentic harness that matches or exceeds human expert code on 4 out of 7 tasks without task-specific tuning. - CaP-RL: if you get a gym, you get RL ;). A 7B OSS model jumps from 20% to 72% success after only 50 training iterations. The synthesized programs transfer to real robots with minimal sim-to-real gap. 3 years ago, our team created Voyager, one of the earliest agentic AI that plays and learns in Minecraft continuously. Its key ideas — skill libraries, self-reflection loops, and in-context planning — have since influenced many modern agentic designs. Today, the agent graduates from Minecraft and gets a real job. It’s April Fool’s, but this Claw is getting its hands dirty for real! Link in thread:

Jim Fan

82,550 views • 5 months ago

0:46

Synthetic data will provide the next trillion tokens to fuel our hungry models. I'm excited to announce MimicGen: massively scaling up data pipeline for robot learning! We multiply high-quality human data in simulation with digital twins. Using 50,000 training episodes across 18 tasks, multiple simulators, and even in the real-world! The idea is simple: 1. Humans tele-operate the robot to complete a task. It is extremely high-quality but also very slow and expensive. 2. We create a digital twin of the robot and the scene in high-fidelity, GPU-accelerated simulation. 3. We can now move objects around, replace with new assets, and even change the robot hand - basically augment the training data with procedural generation. 4. Export the successful episodes, and feed that to a neural network! You now have an near-infinite stream of data. One of the key reasons that robotics lags far behind other AI fields is the lack of data: you cannot scrape control signals from the internet. They simply don't exist in-the-wild. MimicGen shows the power of synthetic data and simulation to keep our scaling laws alive. I believe this principle apply beyond robotics. We are quickly exhausting the high-quality, real tokens from the web. Artificial intelligence from artificial data will be the way forward. We are big fans of the OSS community. As usual, we open-source everything, including the generated dataset! - Website: - Paper: - Dataset is hosted on HuggingFace (thanks AK!!): - Code: MimicGen is led by Ajay Mandlekar, deep dive in the thread:

Jim Fan

332,238 views • 2 years ago

2:55

CHINA JUST SOLVED THE PROBLEM THAT'S BEEN BREAKING ROBOT AI FOR A DECADE. and the fix wasn't a smarter model. for years, every robot AI failure got the same diagnosis. the model isn't smart enough. so everyone scaled intelligence. bigger models. more parameters. better reasoning. AGIBOT asked a different question: what if the reasoning was never the problem? there's a gap that runs through every traditional robot AI system. reasoning on one side & motor commands on the other. the brain decides but the body executes something different, because thinking and moving were never actually connected. GO-2 fixes this by reasoning INSIDE the action space, not above it. before moving, it runs a complete mental simulation of every step - like a basketball player mentally tracing the arc of a shot before releasing the ball. watch the demo and you'll see exactly what this means. the robot works through a task queue autonomously. classify toiletries. upright the drink bottle. place headphones in the leather box. mid-execution, a new instruction drops: "my phone's missing. help me find it." it doesn't pause. doesn't reset. it processes the new task and keeps moving. that's not a scripted sequence. that's real-time instruction following on top of an active task queue. that one architectural change is where the numbers come from. > #1 on LIBERO across Spatial, Object, Goal, and Long tasks → 98.5% average success > 86.6% zero-shot accuracy in active disturbance environments > 47.4 on VLABench → best-in-class on objects and textures it's never seen before > 82.9% success trained on simulation only, tested on real hardware sim-to-real is the graveyard of robotics research. models trained in simulation collapse the moment they touch the real world. 82.9% means that graveyard just got a lot smaller. it holds because of how GO-2 trains. deliberately fed imperfect reasoning conditions, then trained to execute robustly anyway. not a researcher assumption. a design decision from a team that ships hardware and knows exactly what breaks. then there's the infrastructure layer. Genie Studio. fleet-wide data collection. cloud training. online post-training in live environments. 10x improvement in training efficiency. task startup reduced to minutes. 2-4x better success rates with 50%+ less data. the model gets smarter every time a robot fails in the field. this isn't a benchmark story. it's a compounding moat. dual CVPR 2026 + ACL 2026 acceptance. computer vision AND natural language processing. top conferences. simultaneously. that doesn't happen with incremental research. the US-China robotics race has been framed as a compute race. a model quality race. it was always an execution race. the robot that wins won't be the smartest one in the lab. it'll be the most reliable one on the floor. full breakdown: is execution reliability the real bottleneck, or are we still underestimating how far reasoning needs to go?

Shruti

18,622 views • 5 months ago

0:40

Today, we give robots a /skills library that self-evolves and compounds indefinitely! Introducing ASPIRE: a robot solving its 100th task is no longer as clueless as solving its first. Coding agents observe multimodal sensory traces from simulation and real robots, launch an evolutionary search over control programs, and distill the best know-how into an ever-expanding library. ASPIRE is a new type of continual learning: "training" is skill refinement instead of gradient descent. "Trained model" is a repo of sensorimotor skills instead of floating weights. “Distributed training” is a panel of agents each practicing a different skill instead of sharded minibatches. Here's the beauty: ASPIRE gives the tired terms "sim2real transfer" and "cross-embodiment transfer" a whole new meaning. Bridging the sim-to-real gap is notoriously brutal. An end-to-end policy has to swallow both the visual shift (sim looks toyish next to a real camera) and the subtle contact physics it never quite gets right. ASPIRE sidesteps the mess, because it doesn't ship pixels or weights across the gap, but ships the know-how. The robot still has to practice in the real world, not zero-shot, but it gets there way faster because it isn't rediscovering the strategy from scratch. Same for going single-arm to bimanual hardware, which usually requires new data and retraining from zero. ASPIRE achieves up to ~10x cut in "transfer learning” tokens (yes, tokens are the new unit of training compute ;) Check out our gallery of 150+ tasks and 90+ skills the robots taught themselves, all on the website! Kind of wild that we can ship the "learned weights" as an HTML page rather than a GGUF. We'll open-source the full stack so your own robot library starts compounding from ours! Deep dive in thread:

Jim Fan

213,962 views • 2 months ago

0:36

NEW ROBOT BENCHMARK: If your robot can do Origami, it can do anything! Called The Robotic Origami Challenge, it is a dexterous-manipulation competition and benchmark held at IROS 2026, organized by 13 co-organizers with the Nippon Origami Association as judge and task curator -> pretty cool to have them on board imho. The evaluation consists of single task: a traditional Japanese paper airplane, in exactly six folds, from a 15×15 cm sheet of ≥60 gsm paper, on a competition-supplied standardized rig (bimanual arms + Sharpa Hands), both remotely and on-site. Teams bring policies, not hardware. An "Origami Grand Master" declares pass/fail on crease accuracy, structural fidelity, symmetry and paper integrity. Among passes, faster folds rank higher, with a 10-minute-per-attempt ceiling and flight explicitly irrelevant to the score. -> I find it interesting how they chose to evaluate the task. Quality is a binary pass or fail, therefore speed becomes the only thing graded here. Speed is currently the bottleneck in dexterous manipulation though, so this choice makes sense. I wonder whether there could be finer ways to grade the qaulity of such a creative task though. When it comes to data, registered teams get 500+ teleoperation episodes (six camera streams, 65-D joint state/action, 10-fingertip 6-axis tactile), an NVIDIA Isaac Sim environment with thin-shell paper physics (plastic creasing + fold memory), digital twins of every partner hand, and a remote eval lab (upload a policy, queue an eval, get scored). Still, I think it is a great dexterity benchmark the field badly needs, it supplies the hardware, an outside human judges, and the pass criterion is externally defined -> all three degrees of freedom are checked! Neutral measurement layer, here we go! The task is engineered to be un-gameable and to isolate pure dexterity. A known figure, exactly six folds, judged on creases, with flight explicitly declared irrelevant (the latter makes sense to me). Therefore, this underlines the goal to focus on dexterity, not task-selection or other strategies. I really like origami as an ideal controlled dexterity task: deterministic goal, deformable medium, sequential, bimanual, precision-bound. I am just not quite satisfied again by the binary pass or fail, I think quality of execution could be finely graded! But again, I understand this is not the goal yet. Also interesting to see the Sharpa Hands as de facto standard for everyone. Total land-grab that anoints Sharpa as the reference dexterous hand, also featured in Google's Gemini Robotics 2. By providing the hardware, the benchmark measures software while quietly making "good on Sharpa" the definition of good, and Sharpa gets real world data and feedback as a bonus. That's smart, the data flywheel starts spinning. The provided dataset is the richest tactile-manipulation corpus I have seen yet: 10-fingertip 6-axis tactile, plus plastic creasing and fold memory. 500+ teleop episodes with six camera streams, 65-D joint state/action, and ten fingertip 6-axis tactile sensors. The force/tactile channel are parts of the the benchmark's data, this is the first time I see this. Credits where it's due: organizers include Yang Gao, Noriaki Hirose, Steve Xie, Chris Paxton, Jiafei Duan, Michael Cho - Rbt/Acc, Michael Yuan, Haoquan Fang, and others.

Léo

28,783 views • 1 month ago

1:05

Welcome to the Lab of the Future! 🧬🤖 Excited to share LUMI-lab, out today in Cell — a self-driving platform that pairs an AI foundation model with a robotic lab to autonomously discover ionizable lipids (LNPs) for mRNA delivery. The core problem: Designing lipid nanoparticles (LNPs) is hard. The chemical space of ionizable lipids is vast, experimental cycles are slow, and — critically — historical LNP datasets are far too small to train a predictive model from scratch. Most AI approaches in this space hit a wall immediately: not enough data to learn from. Our solution: lab-in-the-loop foundation model learning. Instead of training on LNP data alone, LUMI starts as a transformer-based foundation model pretrained across broad chemical space, building rich molecular representations before it ever sees a single LNP experiment. Then it enters a closed loop with a robotic synthesis platform: predict → synthesize → assay → update. Each round of real wet-lab experiments fine-tunes the model, which then proposes smarter candidates for the next round. The lab isn't just validating AI predictions — it's actively teaching the model, continuously. What happened when we let it run: LUMI-lab autonomously synthesized and screened 1,700+ ionizable lipids in human bronchial epithelial cells. The top candidate — LUMI-6 — features a brominated lipid tail, a structural motif that had been largely overlooked in LNP design. LUMI found it without being told where to look. When formulated into LNPs and delivered intratracheally to mice, LUMI-6 achieved 20.3% gene editing efficiency in lung epithelial cells — a compelling result for one of the hardest-to-reach therapeutic targets, directly relevant to diseases like cystic fibrosis and alpha-1 antitrypsin deficiency. Why this matters beyond LNPs: This is a proof of concept for a broader thesis — that foundation model pretraining + active learning + robotic experimentation can overcome the data scarcity bottleneck that plagues AI-driven discovery in biology. You don't need a massive domain-specific dataset to start. You need a model that can generalize, a lab that can generate the right data, and a loop that connects them. Huge congratulations to first authors Yue Xu, Haotian Cui, and Kuan Pang, and to the entire Bowen LI team. Grateful to our collaborators at University Health Network and Leslie Dan Faculty of Pharmacy, and to Princess Margaret Cancer Centre Research Princess Margaret Cancer Centre Research. 📄 Paper:

Bo Wang

57,640 views • 7 months ago

Live Cam

Video Failed to Load

X Square Robot

Anya Rossi• Live Now

0 Comments

Related Videos