GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning

• URL: http://arxiv.org/abs/2606.17480v1
• Date: Tue, 16 Jun 2026 03:45:24 GMT
• Title: GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning
• Abstract summary: GeneralVLA provides a hierarchical interface for converting language and RGB-D observations into 3D end-effector paths.<n>We introduce GeoFuse-MV3D, a geometry-prior-guided MV-SAM3D reconstruction branch.<n>We upgrade KnowledgeBank into a governed long-term memory system.
• Score: 61.35267583855844
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Generalist vision-language-action systems need object-centric 3D evidence and reusable manipulation experience to plan reliable robot trajectories. GeneralVLA provides a hierarchical interface for converting language and RGB-D observations into 3D end-effector paths, but two bottlenecks remain. First, monocular SAM3D-style object reconstruction can hallucinate pose and unseen geometry, while manipulation benefits from stable object shape when calibrated multi-view observations are available. Second, the original KnowledgeBank mainly retrieves semantically similar snippets and appends new knowledge, which makes it difficult to control memory quality, conflicts, confidence, and geometric relevance. To address the first challenge, we introduce GeoFuse-MV3D, a geometry-prior-guided MV-SAM3D reconstruction branch that verifies external geometry cues with input-view masks, applies soft visual-hull support, performs axis-wise refinement, and fuses only geometry while preserving appearance. To address the second challenge, we upgrade KnowledgeBank into a governed long-term memory system with explicit quality, confidence, lifecycle, verifier, and conflict metadata, together with precision-oriented retrieval. Finally, we evaluate the reconstruction branch on GSO-30 and the memory module on Terminal-Bench 2.0 and SWE-Bench Verified; GeoFuse-MV3D improves over the MV-SAM3D baseline by reducing CD and LPIPS by 2.20% and 2.02% while increasing PSNR and SSIM by 2.36% and 1.03%, and KnowledgeBank improves over ReasoningBank by 4.53% on Terminal-Bench SR and 3.73% on SWE-Bench resolve rate, while reducing AS by 4.95% and 5.65%, respectively. Code: https://github.com/AIGeeksGroup/GeneralVLA-2. Website: https://aigeeksgroup.github.io/GeneralVLA-2.

Related papers

• Dual-Grained Agent Memory and Shapley Context Attribution for Multimodal Agentic Learner [55.80248281761638]
  multimodal large language models (MLLMs) deliver impressive perception yet still falter on scientific and mathematical reasoning.<n>We propose DG-Mem, a dual-grained agentic memory framework that augments a frozen MLLM with a non- externally stored memory built once from training-time rollouts and consulted read-only at test time.
  arXiv  Detail & Related papers  (2026-08-24T13:56:01Z)
• Reliability-Aware 3D Geometric Injection for Universal Person Re-identification [47.874819213762926]
  We propose a Universal Monocular 3D-Enhanced ReID framework driven by a Consistency-Aware Reliability Gate and Dual-Stream Residual Fusion.<n>Our method improves challenging, structure-sensitive scenarios while preserving competitive performance on clean domains.
  arXiv  Detail & Related papers  (2026-07-21T08:54:25Z)
• LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows [10.300202521638274]
  We introduce the Large Sparse Reconstruction Model to study how scaling transformer context windows impacts feed-forward 3D reconstruction.<n>We show that expanding the context window -- by substantially increasing the number of active object and image tokens -- remarkably narrows this gap and enables high-fidelity 3D object reconstruction and inverse rendering.
  arXiv  Detail & Related papers  (2026-04-06T21:21:12Z)
• 3AM: 3egment Anything with Geometric Consistency in Videos [32.069894075133305]
  3AM is a training-time enhancement that integrates 3D-aware features from MUSt3R into SAM2.<n>Our method requires only RGB input at inference, with no camera poses or preprocessing.<n>On challenging datasets with wide-baseline motion (ScanNet++, Replica), 3AM substantially outperforms SAM2 and extensions.
  arXiv  Detail & Related papers  (2026-01-13T18:59:54Z)
• MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation [59.75554954111619]
  We introduce Multi-view 3D Referring Expression (MV-3DRES), where the model must recover scene structure and segment the referred object directly from sparse multi-view images.<n>We propose the Multimodal Visual Geometry Grounded Transformer (MVGGT), an efficient end-to-end framework that integrates language information into sparse-view geometric reasoning.<n>Experiments show that MVGGT establishes the first strong baseline and achieves both high accuracy and fast inference, outperforming existing alternatives.
  arXiv  Detail & Related papers  (2026-01-11T11:44:07Z)
• Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models [79.18306680174011]
  DSR Suite bridges gap across aspects of dataset, benchmark and model.<n>We propose an automated pipeline that generates multiple-choice question-answer pairs from in-the-wild videos for DSR.<n>The pipeline extracts rich geometric and motion information, including camera poses, local point clouds, object masks, orientations, and 3D trajectories.
  arXiv  Detail & Related papers  (2025-12-23T17:56:36Z)
• GeoSAM2: Unleashing the Power of SAM2 for 3D Part Segmentation [81.0871900167463]
  We introduce GeoSAM2, a prompt-controllable framework for 3D part segmentation.<n>Given a textureless object, we render normal and point maps from predefined viewpoints.<n>We accept simple 2D prompts - clicks or boxes - to guide part selection.<n>The predicted masks are back-projected to the object and aggregated across views.
  arXiv  Detail & Related papers  (2025-08-19T17:58:51Z)
• Geometric-aware Pretraining for Vision-centric 3D Object Detection [77.7979088689944]
  We propose a novel geometric-aware pretraining framework called GAPretrain. GAPretrain serves as a plug-and-play solution that can be flexibly applied to multiple state-of-the-art detectors. We achieve 46.2 mAP and 55.5 NDS on the nuScenes val set using the BEVFormer method, with a gain of 2.7 and 2.1 points, respectively.
  arXiv  Detail & Related papers  (2023-04-06T14:33:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.