Metraipolis › archive › dc_5a24c005aefd
ME-VLM: A Unified VLM for Embodied Cognition and Agent Coordination — arXiv:2609.24526
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.24526
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T22:06:09.578Z
- SHA-256 of the archived text
50228ee33831bfecfbfa15967c264fd00c8d54f108139e18ca40187398c43815- Stable URL of this page
https://metraipolis.com/documento/dc_5a24c005aefd
How to cite
ME-VLM: A Unified VLM for Embodied Cognition and Agent Coordination — arXiv:2609.24526 — arXiv (en), https://arxiv.org/abs/2609.24526 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5a24c005aefd (Metraipolis archive dc_5a24c005aefd, sha256 50228ee33831bfecfbfa15967c264fd00c8d54f108139e18ca40187398c43815)
BibTeX
@misc{dc5a24c005aefd,
title = {ME-VLM: A Unified VLM for Embodied Cognition and Agent Coordination — arXiv:2609.24526},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.24526},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5a24c005aefd; sha256 50228ee33831bfecfbfa15967c264fd00c8d54f108139e18ca40187398c43815},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24526. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Physical AI requires models to ground visual and linguistic understanding in real-world environments while accounting for environmental constraints and execution feedback. We introduce MachEmbodied-VLM (ME-VLM), a unified vision-language model with two variants, 4B and 35B-A3B, that brings together embodied cognition and multimodal agent capabilities. Our work emphasizes physical perception and spatiotemporal reasoning, together with planning, interaction, and outcome assessment in both digital and physical environments. We construct training data spanning embodied and multimodal agent tasks, including execution observations and feedback to support outcome assessment and decision refinement. The training pipeline comprises embodied capability injection, separate reinforcement learning of embodied and multimodal-agent experts, and multi-teacher on-policy distillation that consolidates their complementary capabilities into a single model. Experiments show competitive performance on both embodied and agent benchmarks, as well as on autonomous-driving and embodied-navigation tasks. For edge deployment, visual token compression, W4A8 quantization, and hardware-software co-optimization enable on-device inference of the 4B variant on the M100, reducing prefill latency from 400 ms to 188 ms. Project Page: this https URL Code Repository: this https URL Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.24526 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T21:45:21.056Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).