We're releasing HY-Embodied-0.5, a family of foundation models for real-world embodied agents. The 2B model is now open source.
It strengthens spatial-temporal perception and embodied reasoning for prediction, interaction, and planning. 🤖
The suite includes:
🔹 2B for edge deployment
🔹 32B for complex reasoning
Key innovations:
🔹 Mixture-of-Transformers (MoT) architecture for modality-specific computation
🔹 Latent tokens for improved perceptual representation
🔹 Self-evolving post-training
🔹 On-policy distillation from large to small models
Across 22 benchmarks, the 2B model outperforms similarly sized SOTA systems on 16 tasks. The 32B model approaches frontier-level performance.
🔗 GitHub: https://t.co/LknJzqiNOX
🤗 Hugging Face:
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
distillation — Training a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
Why it matters
open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → for a 2B embodied-AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → foundation model that claims to beat same-size SOTA on 16 of 22 benchmarks gives robotics and spatial-reasoning builders an edge-deployable starting point.
