Open-Sourced LingBot-VA 2.0 Robot Foundation Model
philfung · x · 2026-07-11
- Released LingBot-VA 2.0: A native video-action foundation model designed for general robot control.
- The author emphasizes it was pre-trained from scratch, unlike many works adapted from VLMs or pre-trained video models, and is fully open-source.
- Key designs include:
- Native video-action pre-training: Learns world knowledge to enhance generalization;
- Semantic Visual-Action Tokenizer: Improves action prediction accuracy and prompt-following capabilities;
- Foresight Reasoning: Enables the robot to "think one step ahead" during execution for smoother, more responsive control.
Related event: LingBot-VA/VLA 2.0 Released: Native Embodied Foundation Model(24 posts)→
More from Embodied
- Skyfall AI's SKY-001 world model turns sketches into CAD builds in 3.9s, vs 199s for GPT-6 Astra — rohanpaul_ai · 2026-10-27
- Tesla FSD approved in Latvia, the 10th European country; Musk praises smaller nations for moving fastest — elonmusk · 2026-10-27
- WanGP v18.81 adds Tencent's Hy-Nomas world model, playable on 8GB VRAM — cocktailpeanut · 2026-10-27
- NVIDIA open-sources FLORA, a robotics data engine ~125x cheaper than GPT-6 Astra — nvidia · 2026-10-27
- Embodied AI startups need a different operational discipline, investor says — ___Mufasaa · 2026-10-27
- π0.5 study: raising demos from 10 to 438 lifts Place Ball in Bowl success from 7% to 83% — stingning · 2026-10-27