InternRobotics is open-source! 🚀 A Sim-Data-Train/Eval inclusive engine for Embodied AI: ⚙️ 1-line sim deploy 📦 Massive hybrid datasets 🧠 One-click training & eval across 50+ models 🔗 Click to explore:

Great release! Gallant demonstrates a clean voxel-grid pipeline for perceptive humanoid locomotion — unified policy, strong generalization across stairs, gaps, stepping stones, and cluttered spaces.

Introducing Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains 🤖 Project page: https://t.co/eC1ftH5ozx Arxiv: https://t.co/5K9sXDNQWv Gallant is, to our knowledge, the first system to run a single policy that handles full-space

X-VLA is fully open-source！The first complete open pipeline for long-horizon cloth folding. #VLA #embodiedai #Robotics https://t.co/O9i4q2K76t

🎉IROS 2025 Workshop & Challenge Highlights On Oct 20, the Workshop on Multimodal Robot Learning in Physical Worlds, hosted by Shanghai AI Lab, successfully concluded at #IROS2025. 💡 The event gathered experts from UC Berkeley, MIT, Stanford, Tsinghua, Zhejiang University, and

🤖 Go from a task like "set the table" to a complete 3D tabletop scene, ready for robot simulation. Meet MesaTask 🚀 [NeurIPS 2025 Spotlight] ✨ 10K+ physics-verified tabletop scenes ✨ 12K+ curated 3D assets ✨ Outperforms baselines in alignment, realism & physicality All data

🚨 Important Notice 🚨 Challenge update: 📅 Test server closing extended → Oct 7 ⏰ Final sprint — registered teams, make sure to submit on time! Don’t miss your chance!🔥

🤖 Behavior Foundation Model (BFM) for Humanoid Robots #robotics #embodiedai We are excited to re-introduce our Behavior Foundation Model for Humanoid Robots, built upon a unified perspective of diverse WBC tasks —— a promising step toward a foundation model for general humanoid

We are trending fast on @huggingface ! 🔥🔥🔥 Thanks for all the love on our models, datasets, and papers 🥰 Fuel us with more LIKES & STARS so we can push even harder 🚀 https://t.co/gayHWuvXu0

Shanghai AI Laboratory has launched InternVLA·A1, the first integrated “embodied manipulation model” capable of understanding, imagining, and executing ❗️ Real-world evaluations show it significantly outperforms π0 and GR00T N1.5, demonstrating strong adaptability in highly

InternRobotics has 3 models trending on @huggingface #Robotics 🚀 🏆 #2, #3, #7 — climbing the charts fast! 👉 https://t.co/gayHWuwvjy

🚀 We're excited to introduce OmniWorld, a large-scale, multi-Domain, multi-modal dataset for 4D world modeling. Currently, building truly general-purpose 4D world models faces a major challenge: the scarcity of high-quality data resources 🚧. To address this, we have

Through experiments 📈, we verify that mainstream SOTA models—whether 3D geometric foundation models (DUSt3R / CUT3R / Reloc3r) or camera-controllable video generation models (AC3D)—achieve substantial performance improvements on OmniWorld after lightweight fine-tuning. We hope

🚀 We're excited to introduce OmniWorld, a large-scale, multi-Domain, multi-modal dataset for 4D world modeling. Currently, building truly general-purpose 4D world models faces a major challenge: the scarcity of high-quality data resources 🚧. To address this, we have

We also want to highlight the datasets construction pipeline: - Multi-source integration: real-to-sim replica from scanned scenes, procedural generation, designer-created scenes. - Fine-grained annotation: region, categories, text descriptions, assets' orientations & quality,

🚀 We're excited to introduce InternScenes, a large-scale interactive indoor scene dataset! 🌟 Key Insights - Massive scale: ~40K indoor scenes & 1.96M 3D objects — 10× larger than existing open-sourced datasets. - Realistic & complex layouts: Avg. 41.5 objects per scene,