Reinforcing Dual-Path Reasoning in Spatial Vision Language Models

• URL: http://arxiv.org/abs/2606.17539v1
• Date: Tue, 16 Jun 2026 05:32:39 GMT
• Title: Reinforcing Dual-Path Reasoning in Spatial Vision Language Models
• Abstract summary: We present a unified framework that equips a spatial VLM with two complementary reasoning paths: Language-Only Reasoning (LOR) and Detect-Then-Reason (DTR)<n>Across diverse spatial benchmarks, SR-REAL significantly outperforms spatial VLM baselines.
• Score: 113.86271063627782
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spatial VLMs have made substantial progress in geometric perception, yet complex spatial reasoning requiring multi-step inference over depth, distance, and scene relations remains challenging. Moreover, different spatial queries call for fundamentally different strategies: some are best addressed through purely linguistic, step-by-step deduction, while others require explicit 3D grounding before quantitative inference. We present Dual-Path Spatial Reasoning via Reinforcement Learning for Spatial VLMs (SR-REAL), a unified framework that equips a spatial VLM with two complementary reasoning paths: Language-Only Reasoning (LOR), which performs step-by-step linguistic deduction, and Detect-Then-Reason (DTR), which detects 3D geometric cues (e.g., centers or bounding boxes) via region tokens before explicit geometric inference. SR-REAL begins with a cold-start supervised fine-tuning stage that constructs LOR and DTR chain-of-thought supervision and exposes a region-to-3D interface, followed by RL that optimizes the policy model with accuracy and format rewards; for DTR, a discrete center-based detection reward further refines geometric alignment. Across diverse spatial benchmarks, SR-REAL significantly outperforms spatial VLM baselines: (i) a single RL-trained model supports both reasoning paths, with DTR excelling in region-aware tasks through precise 3D localization and LOR enhancing general spatial reasoning; (ii) jointly training both paths fosters mutual reinforcement; (iii) high-quality, blended cold-start data is crucial for stable RL optimization; and (iv) the model generalizes across datasets and domains without per-task tuning, demonstrating positive transfer between LOR and DTR.

Related papers

• SpaR3D-MoE: Adaptive 3D Spatial Reasoning from Sparse Views Meets Geometry-Inductive Mixture-of-Experts [9.401672754315614]
  SpaR3DMoE is an end-to-end framework that enables adaptive spatial reasoning by MLLMs with geometryaware capabilities from only sparse RGB inputs.
  arXiv  Detail & Related papers  (2026-07-07T09:27:38Z)
• The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning [65.67266333751569]
  Current Large Reasoning Models (LRMs) exhibit remarkable general capabilities but significantly underperform in spatial reasoning tasks.<n>We propose a self-supervised reinforcement learning framework that targets the internal reasoning process without requiring ground-truth annotations.<n>We show that this label-free consistency training approaches the accuracy of models trained with ground-truth supervision and achieves similar generalization across diverse tasks and data domains.
  arXiv  Detail & Related papers  (2026-06-10T10:50:06Z)
• SpatialFly: Geometry-Guided Representation Alignment for UAV Vision-and-Language Navigation in Urban Environments [49.966170814478915]
  We propose a geometry-guided spatial representation framework for UAV VLN.<n>Running on RGB observations without explicit 3D reconstruction, SpatialFly introduces a geometry-guided 2D representation alignment mechanism.<n> Experimental results show that SpatialFly consistently outperforms state-of-the-art UAV VLN baselines across both seen and unseen environments.
  arXiv  Detail & Related papers  (2026-03-22T03:56:58Z)
• JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments [34.02990381039783]
  We present JAEGER, a framework that extends AV-LLMs to 3D space to enable joint spatial grounding and reasoning.<n>A core contribution of our work is the neural intensity vector (Neural IV), a learned spatial audio representation.<n>Our approach consistently surpasses 2D-centric baselines across diverse spatial perception and reasoning tasks.
  arXiv  Detail & Related papers  (2026-02-20T04:06:07Z)
• RSGround-R1: Rethinking Remote Sensing Visual Grounding through Spatial Reasoning [61.84363374647606]
  Remote Sensing Visual Grounding (RSVG) aims to localize target objects in large-scale aerial imagery based on natural language descriptions.<n>These descriptions often rely heavily on positional cues, posing unique challenges for Multimodal Large Language Models (MLLMs) in spatial reasoning.<n>We propose a reasoning-guided, position-aware post-training framework, dubbed textbfRSGround-R1, to progressively enhance spatial understanding.
  arXiv  Detail & Related papers  (2026-01-29T12:35:57Z)
• Let Language Constrain Geometry: Vision-Language Models as Semantic and Spatial Critics for 3D Generation [34.44214123004662]
  We propose VLM3D, a framework for differentiable semantic and spatial critics.<n>Our core contribution is a dual-language critic signal derived from the VLM's Yes or No log-odds.<n>VLM3D establishes a principled and general path to inject the VLM's rich, language-grounded understanding of both semantics and space into diverse 3D generative pipelines.
  arXiv  Detail & Related papers  (2025-11-18T09:05:26Z)
• SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards [37.39035418889281]
  We introduce SpatialThinker, a 3D-aware MLLM trained with RL to integrate structured spatial grounding with multi-step reasoning.<n>The model simulates human-like spatial perception by constructing a scene graph of task-relevant objects and spatial relations, and reasoning towards an answer via dense spatial rewards.
  arXiv  Detail & Related papers  (2025-11-10T18:52:47Z)
• SVQA-R1: Reinforcing Spatial Reasoning in MLLMs via View-Consistent Reward Optimization [57.484274282231226]
  We propose SVQA-R1, the first framework to extend R1-style training to spatial VQA.<n>In particular, we introduce Spatial-GRPO, a novel group-wise RL strategy that constructs view-consistent rewards by perturbing spatial relations between objects.<n>Our model, SVQA-R1, not only dramatically improved accuracy on spatial VQA benchmarks but also exhibits interpretable reasoning paths even without using supervised fine-tuning data.
  arXiv  Detail & Related papers  (2025-06-02T06:58:43Z)
• Directional ASR: A New Paradigm for E2E Multi-Speaker Speech Recognition with Source Localization [73.62550438861942]
  This paper proposes a new paradigm for handling far-field multi-speaker data in an end-to-end neural network manner, called directional automatic speech recognition (D-ASR) In D-ASR, the azimuth angle of the sources with respect to the microphone array is defined as a latent variable. This angle controls the quality of separation, which in turn determines the ASR performance.
  arXiv  Detail & Related papers  (2020-10-30T20:26:28Z)

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.