Anvil：通过知识循环扩展具身空间智能
Anvil: Scaling Embodied Spatial Intelligence through Knowledge Recirculation
AI总结：
本文提出统一框架Anvil，通过数据生成、基准测试及9B学生模型Anvil-MOPD的蒸馏学习，在7个公共基准上优于Qwen3.5-9B和RynnBrain-8B，提升具身空间智能性能。
摘要：
具身空间智能不仅需要视觉识别，模型还需定位实体、推理其关系，并以与行动相关的形式表达该知识。然而联合训练可能混淆不同阶段所需的知识，因为监督信号分散在不兼容的几何与语义输出中。本文提出Anvil，一个用于具身空间智能的数据生成、训练和基准测试的统一框架：（1）Anvil-Gen是一个异构数据飞轮，结合了特定形式的生成、跨阶段一致性验证，以及在11种“接地-关系-行动”形式下的失败驱动回忆；（2）Anvil-Ben为学习多样化的具身空间能力提供场景对齐的监督，并提供将阶段能力与错误传播区分开的场景关联评估；（3）Anvil-MOPD是一个90亿参数的学生模型，通过从专家教师模型的蒸馏来整合异构空间知识，其中语义优先故障路由将教师监督定向到学生最早的决定性故障，而阶段归一化则控制不同长度原生输出的损失规模。我们构建了580万条基于源接地的记录，涵盖16万张图像，保留58万条空间记录用于留出评估，其余522万条记录用于训练。在7个公共基准的平均表现上，Anvil-MOPD分别比Qwen3.5-9B和RynnBrain-8B高出9.29和11.03个百分点，在VABench-Point上达到80.67%。对照研究支持目标覆盖、选择性迁移和反馈引导修复是该框架的互补组件。
英文摘要：
Embodied spatial intelligence requires more than visual recognition: models must localize entities, reason about their relations, and express this knowledge in action-relevant forms. Yet joint training can conflate the knowledge needed at different stages because supervision is fragmented across incompatible geometric and semantic outputs. We introduce Anvil, a unified framework for data generation, training, and benchmarking for embodied spatial intelligence. (1) Anvil-Gen is a heterogeneous data flywheel that combines form-specific generation, cross-stage consistency verification, and failure-driven recollection across 11 Ground--Relation--Act forms. (2) Anvil-Ben provides scene-aligned supervision for learning diverse embodied spatial capabilities and scene-linked assessments that distinguish stage competence from error propagation. (3) Anvil-MOPD is a 9B student that consolidates heterogeneous spatial knowledge through distillation from specialist teachers. Semantic-first-fault routing targets teacher supervision to the student's earliest decisive failure, while stage normalization controls the loss scale across native outputs of different lengths. We construct 5.8M source-grounded records spanning 160K images, reserving 580K spatial records for held-out evaluation and using the remaining 5.22M records for training. On average across seven public benchmarks, Anvil-MOPD outperforms Qwen3.5-9B and RynnBrain-8B by 9.29 and 11.03 percentage points, respectively, while reaching 80.67% on VABench-Point. Controlled studies support targeted coverage, selective transfer, and feedback-guided repair as complementary framework components.
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。
