Working on a new topic and hardware for a... while: Feet Language Action models. VLAs teach robots to act through vision and language FLAs teach legged robots to act through contact Given a task, terrain, body state, and instruction - decide where, when, and how to make contactshow more

Travis Hunter Run Blocking Teach Tape 🎥 • Runs... feet through contact • Fights to get hands inside • Understands where run is going and positions himself accordinglyshow more

Qualia has been selected for the Google DeepMind Robotics... Program. We train embodied models that put a robot on a real manual task and make it work, on the floor, not in a demo. Foundation models and reasoning are where robotics is heading, and doing that work alongside DeepMind, who are pushing this frontier, is exactly where we want to be. If you are a company looking to see how a new generation of robots can help your manual tasks, contact us at [email protected] More soonshow more

Introducing ✨ Aya Vision ✨ - an open-weights model... to connect our world through language and vision Aya Vision adds breakthrough multimodal capabilities to our state-of-the-art multilingual 8B and 32B models. 🌿show more

Selvaggia and Daniela met around five years ago on... an Ersties shoot, and now they’re back together to teach us the science of flirting 🤭🔥 The two girls discuss the green and red flags; from eye contact, question asking and body language, there’s a lot to dissect from the art of seduction 🥰💕 Watch here! ➡️show more

gemini: teach me how to fly using mediapipe computer... vision and threejs to make a first-person flappy bird gameshow more

How can we leverage diverse human videos to improve... robot manipulation? Excited to introduce EgoVLA — a Vision-Language-Action model trained on egocentric human videos by explicitly modeling wrist & hand motion. We build a shared action space between humans and robots, enabling seamless transfer. With some robot demos, EgoVLA becomes a powerful, generalizable robot policy.show more

This #CVPR2026 paper from our research team is trending... #1 on Hugging Face 🤗 Meet LocateAnything: a vision-language detection model that rethinks bounding box prediction. For AI agents and robots, “seeing” is only useful if a model can pinpoint where something is fast enough to act. Trained on 138M high-quality samples, LocateAnything decodes bounding boxes in parallel instead of one coordinate at a time, improving localization accuracy while dramatically increasing throughput for visual grounding and detection. Project page:show more

Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely... on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and causal confusion. Online Reinforcement Learning offers a promising pathway to address these issues through trial-and-error learning. However, applying online reinforcement learning to VLA models in autonomous driving is hindered by inefficient exploration in continuous action spaces. MindDrive, a VLA framework comprising a large language model (LLM) with two distinct sets of LoRA parameters. The one LLM serves as a Decision Expert for scenario reasoning and driving decision-making, while the other acts as an Action Expert that dynamically maps linguistic decisions into feasible trajectories. Paper Title: MindDrive: A Vision-Language-Action Model for Autonomous Driving via Project: Link:show more

During missions in The Expanse: Osiris Reborn, you'll be... pulled into constant action where focus and ability to act without hesitation make all the difference. Sometimes you'll have only a moment to decide, and it will determine how everything ends. Ready to test yourself?show more

🤖 NVIDIA’s Gr00t N1.5 is now available in LeRobot!... This is the result of a great collaboration between the Hugging Face LeRobot team and NVIDIA Robotics ! Gr00t N1.5 highlights: 🦾 Cross-embodiment foundation model for robots 🧠 Multimodal inputs: vision, language, and proprioception 🪛Tested on the Libero benchmark and real-world hardware tasks 🌍Trained on real robot, synthetic, and internet-scale video data ⚙️ Flow matching action transformer for action predictionshow more

Yesterday, I visited a student learning camp to teach... young boys and girls how to shake hands confidently, greet respectfully, maintain eye contact, and carry themselves with composure. I also spoke to them about the importance of time management in today's highly distracting world. Simple lessons that open big doors. We are building great men and women for Africa through faith, discipline, and character.show more

How can we responsibly deploy agentic AI robots in... real-world environments? As we close the gap between AI reasoning and physical action, developing a new safety framework is key to advancing helpful robots. 🤖show more

Converting video models ➡️ ego-centric world models capable of... humanoids manipulating objects, robots navigating through paintings, and beyond! Huge effort led by Anurag Bagchi over a year! Special thanks to 1X for releasing so much data!show more

These devs are working on a futuristic parkour game... where you must deliver to make a living - Only a compass and landmarks to navigate the map - Repair gear, upgrade loadouts, prepare for next run - Movement is your language, master it Called PANLINEshow more

MolmoAct2 is landing in LeRobot! Ai2's open Action Reasoning... Model combines a Molmo2-ER vision-language backbone with a flow-matching continuous action expert to predict robot action chunks from images, language instructions, and proprioceptive state. An open robot foundation model built for real-world control, with strong out-of-the-box performance and easy fine-tuning in LeRobot. Pick-and-place inference running on NVIDIA DGX Spark! Blog: Paper: Thanks to Ai2 Jiafei Duan Haoquan Fangshow more

Openly flirting with a taken woman while being a... married man and a father. My heart breaks for his lovely wife and children. Can’t wait for Topuria to knock him cold out and teach him how to properly respect womenshow more

Robotics keeps hitting the same wall. Single task RL... works, but... it does not scale to hundreds of tasks or new embodiments. This new paper looks like a real step toward fixing that. The team introduces MMBench, a benchmark with 200 tasks across many domains and robots, and Newt, a language conditioned world model trained online across all 200 tasks at once. The simple idea behind Newt: The model learns from demos to get the right priors It trains across many tasks through online interaction It uses language to ground the goal It adapts fast when a new task shows up What stood out to me: ✅ One model trained on 200 tasks at the same time ✅ Language conditioned control for both states and RGB ✅ Better data efficiency than strong baselines ✅ Strong open loop control ✅ Fast adaptation to new tasks and embodiments ✅ Full release of 200 checkpoints, 4000 demos, code, and benchmark This is a good push toward general control instead of one model per task. If you want the full paper: Project page: —- Weekly robotics and AI insights. Subscribe free:show more

Mika and Bianca, two hearts learning the language of... consistency. Mika, with quiet efforts and loud love. Bianca, with soft gratitude and open hands. In a world that often forgets how to stay, may this friendship teach us how to hold on not just when it’s easy, but especially when it’s not. May this bond be the kind that grows through seasons where love is not just spoken, but shown. May we always meet halfway, again and again. Never FO my MiBi! 🌷 Mika Salamanca Bianca De Verashow more