Dual-Pathway Geometry-Aware MLLM for Spatial Intelligence

• URL: http://arxiv.org/abs/2605.25334v1
• Date: Mon, 25 May 2026 01:33:19 GMT
• Title: Dual-Pathway Geometry-Aware MLLM for Spatial Intelligence
• Abstract summary: We propose GAMSI, a dual-pathway Geometry-Aware MLLM for Spatial Intelligence.<n>It takes only RGB images as input while internalizing both forms of geometric prior within a unified autoregressive backbone.<n>GAMSI achieves state-of-the-art performance on seven spatial intelligence benchmarks.
• Score: 63.11502936651325
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spatial understanding of the physical world from 2D visual inputs hinges on two complementary forms of geometric knowledge: holistic 3D structural perception and fine-grained metric scale estimation. Existing multimodal large language models (MLLMs) typically address only one facet, ingesting either depth maps or point clouds as additional model inputs, which incurs substantial computational overhead and inherits the generalization limitations of upstream prediction models. We propose GAMSI, a dual-pathway Geometry-Aware MLLM for Spatial Intelligence that takes only RGB images as input while internalizing both forms of geometric prior within a unified autoregressive backbone. Specifically, we introduce Metric-Structure Decoupled Queries (MSDQ) which employ two groups of learnable queries to respectively extract dense metric signals and sparse structural cues from the shared visual context, with a task-decoupled attention mask further preventing the two pathways from contaminating each other. Building on this, an Expert-Guided Visual Grounding (EVG) module projects the aggregated cues back to frame-level visual features and aligns them with vision foundation models, which serve purely as training-time supervision, rather than as model inputs. We further build a multi-task spatial instruction-tuning dataset (MTS) comprising 152{,}776 samples spanning 13 task types and three visual modalities, consolidated from six public datasets. Trained with a two-stage curriculum, GAMSI achieves state-of-the-art performance on seven spatial intelligence benchmarks.

Related papers

• OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping [69.48762031013514]
  We propose OmniView-Space, a framework designed to maintain spatial consistency through multimodal egocentric evidence.<n>Our approach consists of three core components: (1) Multi-Perspective Spatial Mapping (MPSM), which re-anchors reconstructed geometry into a query-aligned visual cognitive map and a textual spatial graph; (2) Tool-Guided Egocentric Reasoning, an interleaved policy trained to actively select the ego anchor required by the query and request the corresponding MPSM evidence; and (3) Cognitive-Map Distillation, which uses MPSM-generated trajectories and ego-frame rewards to train the model to reason with self-generated cognitive maps
  arXiv  Detail & Related papers  (2026-07-01T12:45:12Z)
• AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding [55.535374902204296]
  AffordanceVLA is a unified framework that introduces structured affordance forecasting as a task-oriented intermediate representation.<n>We show that AffordanceVLA achieves strong performance across diverse manipulation scenarios.
  arXiv  Detail & Related papers  (2026-06-04T13:28:51Z)
• Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models [31.851717131965824]
  We present the first systematic frozen-feature probing study of Vision-Language Models (VLMs) and Video Generation Models (VGMs)<n>Using the lightweight probe, our framework enables a controlled comparison of what information is already encoded in frozen representations from two model families.<n>Results reveal a clear complementarity: VLMs are stronger at semantic tagging and instance grouping, while VGMs provide more accessible signals for dense geometry and camera motion.
  arXiv  Detail & Related papers  (2026-05-27T08:20:04Z)
• Semantic Generative Tuning for Unified Multimodal Models [62.18894352635965]
  Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture.<n> prevailing training paradigms independently optimize understanding via sparse text signals and generation through dense pixel objectives.<n>This work presents the first systematic investigation into generative post-training, where we formulate hierarchical visual tasks as generative proxies to bridge the isolation in UMMs.
  arXiv  Detail & Related papers  (2026-05-18T17:46:46Z)
• Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images [81.94999489820974]
  UniSplat is a feed-forward framework for learning 3D representations from unposed multi-view images.<n>We introduce a dual-masking strategy that strengthens geometry induction in the encoder.<n>Second, we develop a coarse-to-fine Gaussian splatting strategy that reduces appearance-semantics inconsistencies.<n>Third, we introduce a pose-conditioned recalibration mechanism that interrelates predicted 3D point and semantic maps into the image plane.
  arXiv  Detail & Related papers  (2026-04-12T10:36:18Z)
• Make Geometry Matter for Spatial Reasoning [62.61667611352403]
  Vision-language models (VLMs) achieve strong image and video understanding, yet their ability to perform spatial reasoning in both static scenes and dynamic videos remains limited.<n>Recent advances try to handle this limitation by injecting geometry tokens from pretrained 3D foundation models into VLMs.<n>We propose GeoSR, a framework designed to make geometry matter by encouraging VLMs to actively reason with geometry tokens.
  arXiv  Detail & Related papers  (2026-03-27T17:45:12Z)
• GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models [70.61152292499737]
  We argue that this gap does not arise from insufficient geometric priors, but from a misalignment in the training paradigm.<n>Existing approaches typically resort to naive feature concatenation and optimize directly for downstream tasks without geometry-specific supervision.<n>We propose GAP-MLLM, a Geometry-Aligned Pre-training paradigm that explicitly activates structural perception before downstream adaptation.
  arXiv  Detail & Related papers  (2026-03-17T12:43:48Z)
• GS-CLIP: Zero-shot 3D Anomaly Detection by Geometry-Aware Prompt and Synergistic View Representation Learning [11.364765496753074]
  3D Anomaly Detection is an emerging task that aims to detect anomalies in a target dataset without any target training data.<n>Current methods adapt CLIP by projecting 3D point clouds into 2D representations, but they face challenges.<n>We propose the Geometry-Aware Prompt and Synergistic View Representation Learning framework, which enables the model to identify geometric anomalies through a two-stage learning process.
  arXiv  Detail & Related papers  (2026-02-22T14:30:41Z)
• Video2Layout: Recall and Reconstruct Metric-Grounded Cognitive Map for Spatial Reasoning [19.549136366694572]
  Video2 is a framework for reconstructing metric-grounded spatial layouts from video.<n>The framework employs continuous object boundary coordinates to quantify inter-object physical and object size.<n>Our model, V2LO-7B, achieves an average improvement of 4.92% over the model trained on grid maps.
  arXiv  Detail & Related papers  (2025-11-20T08:57:14Z)
• Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence [13.168559963356952]
  We present Spatial-MLLM, a novel framework for visual-based spatial reasoning from purely 2D observations.<n>Our key insight is to unleash the strong structure prior to the feed-forward visual geometry foundation model.<n>A connector then integrates both features into unified visual tokens for enhanced spatial understanding.
  arXiv  Detail & Related papers  (2025-05-29T17:59:04Z)
• Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model [51.83436609094658]
  We introduce Coarse Correspondences, a simple lightweight method that enhances MLLMs' spatial-temporal reasoning with 2D images as input. Our method uses a lightweight tracking model to identify primary object correspondences between frames in a video or across different image viewpoints. We demonstrate that this simple training-free approach brings substantial gains to GPT4-V/O consistently on four benchmarks.
  arXiv  Detail & Related papers  (2024-08-01T17:57:12Z)

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.