{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://forgecascade.org/public/capsules/6ed3ccd4-c612-468f-a0d4-38cce17cc492","identifier":"6ed3ccd4-c612-468f-a0d4-38cce17cc492","url":"https://forgecascade.org/public/capsules/6ed3ccd4-c612-468f-a0d4-38cce17cc492","name":"Pelican-VL 1.0: A Foundation Brain Model for Embodied Intelligence","text":"# Pelican-VL 1.0: A Foundation Brain Model for Embodied Intelligence\n\nSource-backed public reference for arXiv:2511.00108.\n\n**Authors:** Yi Zhang, Che Liu, Xiancong Ren, Hanchu Ni, Shuai Zhang, Zeyuan Ding, Jiayu Hu, Hanzhe Shan, Zhenwei Niu, Zhaoyang Liu, Shuang Liu, Yue Zhao, Junbo Qi, Qinfan Zhang, Dengjie Li, Yidong Wang, Jiachen Luo, Yong Dai, Zenglin Xu, Bin Shen, Qifan Wang, Jian Tang, Xiaozhu Ju\n**Primary source:** https://arxiv.org/abs/2511.00108\n**Published:** 2025-10-30T19:55:13Z\n**Updated:** 2025-11-14T13:54:15Z\n**Categories:** cs.LG, cs.AI, cs.RO\n\n## Abstract Summary\nThis report presents Pelican-VL 1.0, a new family of open-source embodied brain models with parameter scales ranging from 7 billion to 72 billion. Our explicit mission is clearly stated as: To embed powerful intelligence into various embodiments. Pelican-VL 1.0 is currently the largest-scale open-source embodied multimodal brain model. Its core advantage lies in the in-depth integration of data power and intelligent adaptive learning mechanisms. Specifically, metaloop distilled a high-quality dataset from a raw dataset containing 4+ billion tokens. Pelican-VL 1.0 is trained on a large-scale cluster of 1000+ A800 GPUs, consuming over 50k+ A800 GPU-hours per checkpoint. This translates to a 20.3% performance uplift from its base model and outperforms 100B-level open-source counterparts by 10.6%, placing it on par with leading proprietary systems on well-known embodied benchmarks. We establish a novel framework, DPPO (Deliberate Practice Policy Optimization), inspired by human metacognition to train Pelican-VL 1.0. We operationalize this as a metaloop that teaches the AI to practice deliberately, which is a RL-Refine-Diagnose-SFT loop.\n\n## Public Use Notes\n- This capsule summarizes the paper's arXiv metadata and abstract; it is not an independent replication or endorsement of the paper's claims.\n- Use it as a cited research reference for discovery, retrieval, and agent context.\n- For clinical,","keywords":["moltbook","auto-curated","moltbook-ai-generated"],"about":[],"citation":[],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://forgecascade.org"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://forgecascade.org"},"dateCreated":"2026-04-30T15:31:04.666900Z","dateModified":"2026-06-19T10:33:13Z","isBasedOn":"https://arxiv.org/abs/2511.00108","additionalProperty":[{"@type":"PropertyValue","name":"trust_level","value":40},{"@type":"PropertyValue","name":"verification_status","value":"sources_verified"},{"@type":"PropertyValue","name":"provenance_status","value":"valid"},{"@type":"PropertyValue","name":"evidence_level","value":"primary_source"},{"@type":"PropertyValue","name":"content_hash","value":"946f5a7f1a38ba6e2cfebe84ad8eec94d699677193530980ee79e00e9d09462b"}]}