@robbyant_brain: LingBot-VLA 2.0 is now open-source — our next-gen embodied foundation model. 60,000 hours of high-quality pretraining d…
Summary
LingBot-VLA 2.0, an open-source embodied foundation model, has been released with 60,000 hours of pretraining data supporting 20 robot configurations across 17 brands, capable of sub-130ms inference on RTX 4090.
View Cached Full Text
Cached at: 07/07/26, 11:38 PM
LingBot-VLA 2.0 is now open-source — our next-gen embodied foundation model. 60,000 hours of high-quality pretraining data — combining curated robotic demonstrations and egocentric human operation videos 20 robot configurations across 17 brands — Astribot, Leju, Unitree, Franka, Fourier, Realman, and more Whole-body DoF: heads, waists, dexterous hands, and mobile bases — enabling far more complex task scenarios Inference under 130ms on RTX 4090 — developer events launching soon #EmbodiedAI #Robotics #OpenSource #VLA
Similar Articles
From Foundation to Application: Improving VLA Models in Practice
This paper presents LingBot-VLA 2.0, which enhances VLA foundation models for robotics by improving generalization across tasks and embodiments, expanding action space to whole-body degrees of freedom, and incorporating predictive dynamics modeling for better temporal reasoning.
@rohanpaul_ai: Most video-action robot models are a content-creation video generator with an action module attached. LingBot-VA 2.0 fr…
LingBot-VA 2.0 is a video-action foundation model trained from scratch for robot control, achieving 225 Hz closed-loop execution with 13B parameters (1.9B active per token) and outperforming prior models on RoboTwin 2.0.
@AdinaYakup: Powered by the new LingBot Vision https://huggingface.co/collections/robbyant/lingbot-vision… - Apache 2.0 - 4 versions…
LingBot Vision is a new visual foundation model released under Apache 2.0, available in four sizes (small, base, large, giant) and pretrained with masked boundary modeling. It powers a depth estimation system that tops multiple benchmarks.
@_akhaliq: LingBot-Video is out on Hugging Face MoE-based video foundation model built for embodied intelligence 30B params, only …
LingBot-Video, a 30B parameter MoE-based video foundation model for embodied intelligence, has been released on Hugging Face with only 3B active parameters at inference, augmented with 70K hours of embodied data.
Another Ling model comes out, same receipt, 2 weeks free to use, then open source. Chinese labs do contribute a lot to open source community
Another Ling model, Ling 3.1 Flash, has been released with free promotional access for two weeks before open-sourcing, following the same pattern as previous Ling releases from Chinese labs. The model supports a 262K-token context window, 32K output tokens, and configurable reasoning effort, and is routed through Vercel AI Gateway via multiple providers.