Robbyant

@robbyant_brain

@AntGroup Affiliate | Building One Brain for All Robots 🌟 Intelligence in Action, Benefits for Everyone. #SpatialIntelligence #ActionModels #WorldModel

robbyant.com

Joined January 2026

Following

3,001

Followers

Replies Reposts Media

Pinned
Robbyant
@robbyant_brain
Jul 11
That's a wrap on LingBot 2.0 Release Week — 6 models in 4 days. 👀LingBot-Vision & LingBot-Depth 2.0 for spatial. 🧠LingBot-VLA 2.0 for one brain across many robots. 🎮LingBot-World 2.0 for real-time interaction. 🎦LingBot-Video for efficient video generation 🦾And the finale:
33
Robbyant
@robbyant_brain
21h
Glad to see @openroboto bring LingBot-VLA 2.0 to its platform as a base model for community post-training. We open-sourced LingBot-VLA 2.0 so people could build on it, adapt it, and push it further. Excited to see where the community takes it. Kudos to the team 👏
OpenRoboto
@openroboto
21h
LingBot-VLA 2.0—the latest open-weight VLA model from Robbyant (@robbyant_brain)—is now live as the new base model for an OpenRoboto tournament. Now the network gets to find out how far open builders can push its capabilities.
00:00
3
Robbyant
@robbyant_brain
Aug 29
Can robots learn new tasks directly from human‑operation videos?✅ Meet Zero‑WAM: video‑based in‑context learning for robotics. No heavy retraining, no verbose text instructions. Given human demo videos, it infers objects, interactions & task flows to generate robot‑executable
00:00
1
Robbyant
@robbyant_brain
Aug 27
Great to see KUAVO-VLA built on LingBot-VLA 2.0. A strong general VLA model provides the starting point. With high-quality real-robot data, it can be adapted into domain-specific models for industrial scenarios. This is the path from general embodied intelligence to real-world
LejuRobotics
@LejuRobotics_
Aug 27
We have released the domain‑specific large model KUAVO‑VLA. It is derived from secondary base‑model training with real‑robot data of identical configuration. Taking LingBot‑VLA 2.0 as its capability foundation, it delivers higher task success rates.@robbyant_brain
Robbyant
@robbyant_brain
Aug 25
Huge shout‑out to the @sgl_project community! 🙌 LingBot‑Video gets native support in SGLang v0.5.18. Run our 30B‑A3B MoE text‑to‑video model with optimized SGLang‑Diffusion serving. Cookbook👉 docs.sglang.io/cookbook/diffu…
SGLang
@sgl_project
Aug 24
SGLang v0.5.18 is out! We have 710 PRs from 212 contributors, and 61 of them were new contributors. Welcome🧡 Highlights: 🔸 New models: Muse Glimmer and Intern-S2-Mobius, plus SANA-Video, LTX-2.5, LingBot-Video, Cosmos3, and LongCat-Image on SGLang-Diffusion 🔸 Engine startup
1