Decoupling Semantics and Geometric Grounding: Spatial Visual Prompts for Language-Conditioned Imitation Learning

• URL: http://arxiv.org/abs/2606.25360v1
• Date: Wed, 24 Jun 2026 03:45:06 GMT
• Title: Decoupling Semantics and Geometric Grounding: Spatial Visual Prompts for Language-Conditioned Imitation Learning
• Abstract summary: We propose SVP-IL, a decoupled architecture that explicitly extracts spatial visual grounding from the action generation loop.<n>In experiments, SVP-IL significantly outperforms state-of-the-art VLAs and pure visuomotor baselines.
• Score: 21.67233368353003
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While end-to-end Vision-Language-Action (VLA) models show promise in robotic manipulation, their monolithic paradigm inherently couples semantic reasoning and spatial control. This creates a severe alignment bottleneck, limiting precise target disambiguation in data-constrained imitation learning. To overcome this, we propose SVP-IL, a decoupled architecture that explicitly extracts spatial visual grounding from the action generation loop. By leveraging vision-language foundation models, we parse instructions into zero-shot geometric masks, translating language into explicit Spatial Visual Prompts (SVP). These priors are injected into a continuous action generator via a lightweight direct feature-level fusion mechanism. This integration provides explicit and uncorrupted spatial gradient guidance while ensuring highly stable optimization under low-data regimes. Extensive experiments demonstrate that SVP-IL significantly outperforms state-of-the-art VLAs and pure visuomotor baselines. Trained on as few as 50 to 100 demonstrations, SVP-IL improves average success rates on highly ambiguous language-conditioned tasks from 24.0% to 39.5%, achieving 67.8% on standard benchmarks. Real-world robotic experiments further validate its robustness and data efficiency in unstructured physical environments.

Related papers

• GaussianDream++: Efficient 3D Gaussian World Modeling for Robotic Manipulation [55.47130289185285]
  Vision-Language-Action (VLA) policies have advanced language-conditioned robotic manipulation.<n>We present textbfMethodname, a compact, policy-native extension that inserts textbfWorld State Tokens and textbfWorld Prediction Tokens directly into the VLA backbone.
  arXiv  Detail & Related papers  (2026-08-26T11:41:55Z)
• Grounded Semantic Re-Binding for Robust Instruction Generalization in Vision-Language-Action Models [20.8047896631941]
  Vision-Language-Action (VLA) models excel in robotic manipulation but suffer catastrophic performance drops when canonical instructions are paraphrased.<n>We show that current VLAs successfully retain the correct task identity internally.<n>We propose Grounded Semantic Re-binding (GSR), an elegant intervention that bypasses unstable joint routing.
  arXiv  Detail & Related papers  (2026-08-03T17:02:04Z)
• VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models [55.12929235609365]
  Visual backbones of current vision-language-action (VLA) models are predominantly pretrained on 2D image data without explicit 3D geometric supervision.<n>Existing implicit grounding methods partially address this by aligning VLA features with those of 3D-aware foundation models.<n>We propose VEGA, a framework that directly aligns the output of the VLA's visual encoder with spatially-aware features from DINOv2-FiT3D.
  arXiv  Detail & Related papers  (2026-05-11T12:44:26Z)
• MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation [47.2088748094605]
  Vision-Language-Action (VLA) models aim to control robots for manipulation from visual observations and natural-language instructions.<n>We present MMaDA-VLA, a fully native pre-trained large diffusion VLA model that unifies multi-modal understanding and generation in a single framework.
  arXiv  Detail & Related papers  (2026-03-26T12:55:51Z)
• TagaVLM: Topology-Aware Global Action Reasoning for Vision-Language Navigation [70.23578202012048]
  Vision-Language Navigation (VLN) presents a unique challenge for Large Vision-Language Models (VLMs) due to their inherent architectural mismatch.<n>We propose TagaVLM (Topology-Aware Global Action reasoning), an end-to-end framework that explicitly injects topological structures into the VLM backbone.<n>To enhance topological node information, an Interleaved Navigation Prompt strengthens node-level visual-text alignment.<n>With the embedded topological graph, the model is capable of global action reasoning, allowing for robust path correction.
  arXiv  Detail & Related papers  (2026-03-03T13:28:07Z)
• Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted Pretraining [59.2578488860426]
  Heterogeneous multi-modal remote sensing object detection aims to accurately detect objects from diverse sensors.<n>Existing approaches largely adopt a late alignment paradigm, in which modality alignment and task-specific optimization are entangled during downstream fine-tuning.<n>We propose BabelRS, a unified language-pivoted pretraining framework that explicitly decouples modality alignment from downstream task learning.
  arXiv  Detail & Related papers  (2026-03-02T11:38:12Z)
• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination [55.982504915794514]
  We propose Self-Correcting VLA (SC-VLA), which achieve self-improvement by intrinsically guiding action refinement through sparse imagination.<n>SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher success rate than the best-performing baselines.
  arXiv  Detail & Related papers  (2026-02-25T06:58:06Z)
• Universal Pose Pretraining for Generalizable Vision-Language-Action Policies [83.39008378156647]
  Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency.<n>We propose Pose-VLA, a decoupled paradigm that separates VLA training into a pre-training phase for extracting universal 3D spatial priors.<n>Our framework follows a two-stage pre-training pipeline, establishing fundamental spatial grounding via poses followed by motion alignment.
  arXiv  Detail & Related papers  (2026-02-23T11:00:08Z)
• DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning [35.44151923549777]
  Vision-Language-Action (VLA) models have recently shown impressive generalization and language-guided manipulation capabilities.<n>Their performance degrades on tasks requiring precise spatial reasoning due to limited spatial reasoning inherited from Vision-Language Models (VLMs)<n>We present DepthVLA, a simple yet effective VLA architecture that explicitly incorporates spatial awareness through a pretrained depth prediction module.
  arXiv  Detail & Related papers  (2025-10-15T10:09:00Z)
• DexVLG: Dexterous Vision-Language-Grasp Model at Scale [59.5613919093295]
  There is little research on functional grasping with large models for human-like dexterous hands.<n>We introduce DexVLG, a large Vision-Language-Grasp model for Dexterous grasp pose prediction aligned with language instructions.<n>We generate a dataset of 170 million dexterous grasp poses mapped to semantic parts across 174,000 objects in simulation, paired with detailed part-level captions.
  arXiv  Detail & Related papers  (2025-07-03T16:05:25Z)
• From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation [35.79160868966466]
  We propose FSD (From Seeing to Doing), a novel vision-language model that generates intermediate representations through spatial relationship reasoning.<n>Our approach combines a hierarchical data pipeline for training with a self-consistency mechanism that aligns spatial coordinates with visual signals.<n>We show that FSD achieves 40.6% success rate in SimplerEnv and 72% success rate across 8 real-world tasks, outperforming the strongest baseline by 30%.
  arXiv  Detail & Related papers  (2025-05-13T13:20:46Z)

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.