GeoAlign: Beyond Semantics with State-Guided Spatial Alignment in VLA Models
Current Vision--Language--Action (VLA) models often optimize for semantic grounding, whereas executable manipulation requires geometry-aware spatial alignment and dynamic affordance selection. We introduce GeoAlign, a state-guided spatial alignment architecture for VLA policy learning. GeoAlign post-trains an RGB geometry branch with robot-domain RGB-D supervision, yielding RGB-derived Geometry-Enhanced Post-Trained (GEP) features for policy rollout. The robot's proprioceptive state queries the GEP feature grid, producing compact, phase-dependent geometry tokens for action prediction. GeoAlign achieves 99.0% on LIBERO, 85.3% across three SimplerEnv-Fractal tasks, and 78.8% on eight geometry-critical real-world ALOHA tasks, with ablations confirming the value of geometry post-training and proprioceptive-state-guided querying.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
GeoAlign: Geometric Feature Realignment for MLLM Spatial Reasoning
Multimodal large language models (MLLMs) have exhibited remarkable performance in various visual tasks, yet still struggle with spatial reasoning. Recent efforts mitigate this by injecting geometric features from 3D foun…
Spatial ReasoningGEOALIGN: Geometric Rollout Curation for Robust LLM Reinforcement Learning
Online reinforcement learning is widely used to align large language models (LLMs) with reward signals, yet training can be unstable under noisy or misspecified rewards. We identify a failure mode we call directional inc…
Reinforcement LearningMathematical ReasoningAll You Need is a Second Look: Towards Arbitrary-Shaped Text Detection
Arbitrary-shaped text detection is a challenging task since curved texts in the wild are of the complex geometric layouts. Existing mainstream methods follow the instance segmentation pipeline to obtain the text regions.…
AllInstance SegmentationSegmentationSemantic Segmentation+1GeoAlignCLIP: Enhancing Fine-Grained Vision-Language Alignment in Remote Sensing via Multi-Granular Consistency Learning
Vision-language pretraining models have made significant progress in bridging remote sensing imagery with natural language. However, existing approaches often fail to effectively integrate multi-granular visual and textu…
Beyond AlphaEarth: Toward Human-Centered Geospatial Foundation Models via POI-Guided Contrastive Learning
Recent geospatial foundation models (GFMs) produce spatially extensive representations of the Earth's surface that capture rich physical and environmental patterns. Among them, the AlphaEarth Foundation (AE) represents a…
Natural Language QueriesRepresentation LearningContrastive Learning