GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot
Overview
This research, led by Peking University and the Chinese Academy of Sciences, introduces GeneralVLA-2, a robot planning system that improves geometric perception and memory management. GeoFuse-MV3D enhances 3D shape reconstruction using multi-view geometry, while the governed KnowledgeBank refines memory retrieval with validation and lifecycle management. The system achieves improvements in shape reconstruction metrics and task success rates in both simulation and real-world settings.
From Chinese robotics — Research news discovery
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · test_set_size: 30 other · Basis not reported
“这个测试集来自谷歌扫描物体数据集,包含30个真实家居物品的高精度三维模型,评估协议与MV-SAM3D完全一致:输入相同的五个视角,评估其余视角下的渲染质量。”
Exact source · revision 2Source owner not reported
Evidence dependency changes (3)
- 2026-10-30T19:56:01.502Z · evidence updated · source revision 2. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T19:55:41.030Z · evidence updated · source revision 2. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T17:30:57.070Z · evidence updated · source revision 2. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- Chinese robotics — Research news discoverySignalGeneralVLA-2: Giving Robots 'Spatial Memory' to Improve Planning Accuracy
This research, led by Peking University and the Chinese Academy of Sciences, introduces GeneralVLA-2, a robot planning system that improves geometric perception and memory management. GeoFuse-MV3D enhances 3D shape reconstruction using multi-view geometry, while the governed KnowledgeBank refines memory retrieval with validation and lifecycle management. The system achieves improvements in shape reconstruction metrics and task success rates in both simulation and real-world settings.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).