BLM$_1$：面向跨空间、跨任务与跨具身学习的无界大模型
BLM$_1$: A Boundless Large Model for Cross-Space, Cross-Task, and Cross-Embodiment Learning
AI总结：
针对现有多模态大模型跨空间、跨具身泛化能力不足的问题，研究提出具备三大核心能力的BLM$_1$多模态空间基础模型，通过两阶段训练范式实现跨场景适配，在数字与物理任务上均优于现有四类模型。
摘要：
多模态大语言模型（MLLMs）已推动视觉-语言推理取得进展，且正越来越多地部署在具身智能体中，但仍存在显著局限：MLLMs在数字-物理空间及不同具身形态间的泛化能力较差；视觉-语言-动作模型（VLAs）虽能生成底层动作，却缺乏可靠的高层具身推理能力；且大多数具身大语言模型（ELLMs）仅适用于数字空间，向物理世界的泛化效果不佳。因此，目前仍缺少可在数字与物理空间间无缝运行、同时能跨具身形态与任务泛化的统一模型。\n我们提出了**无界大模型（Boundless Large Model, BLM$_1$）**，这是一款多模态空间基础模型，既保留了指令遵循与推理能力，又融入了具身知识，可支持可靠的跨具身控制。BLM$_1$通过两阶段训练范式整合了三大核心能力——*跨空间迁移、跨任务学习与跨具身泛化*。第一阶段通过精心整理的数字语料库，将具身知识注入MLLM中，同时保留其语言能力。第二阶段通过意图桥接接口训练策略模块，该接口从MLLM中提取高层语义以指导控制，且无需微调MLLM主干网络。该训练流程依托一套自主收集的跨具身演示数据集，涵盖4种机器人具身形态与6项难度递进的任务。\n在数字与物理基准上的评估结果显示，单个BLM$_1$实例的性能优于MLLMs、ELLMs、VLAs和GMLMs这四类模型家族，在数字任务中取得约6%的性能提升，在物理任务中取得约3%的性能提升。
英文摘要：
Multimodal large language models (MLLMs) have advanced vision-language reasoning and are increasingly deployed in embodied agents. However, significant limitations remain: MLLMs generalize poorly across digital-physical spaces and embodiments; vision-language-action models (VLAs) produce low-level actions yet lack robust high-level embodied reasoning; and most embodied large language models (ELLMs) are constrained to digital-space with poor generalization to the physical world. Thus, unified models that operate seamlessly across digital and physical spaces while generalizing across embodiments and tasks remain absent. We introduce the \textbf{Boundless Large Model (BLM$_1$)}, a multimodal spatial foundation model that preserves instruction following and reasoning, incorporates embodied knowledge, and supports robust cross-embodiment control. BLM$_1$ integrates three key capabilities -- \textit{cross-space transfer, cross-task learning, and cross-embodiment generalization} -- via a two-stage training paradigm. Stage I injects embodied knowledge into the MLLM through curated digital corpora while maintaining language competence. Stage II trains a policy module through an intent-bridging interface that extracts high-level semantics from the MLLM to guide control, without fine-tuning the MLLM backbone. This process is supported by a self-collected cross-embodiment demonstration suite spanning four robot embodiments and six progressively challenging tasks. Evaluations across digital and physical benchmarks show that a single BLM$_1$ instance outperforms four model families -- MLLMs, ELLMs, VLAs, and GMLMs -- achieving $\sim\!\textbf{6%}$ gains in digital tasks and $\sim\!\textbf{3%}$ in physical tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
