3D VLMs

Vision-Language Models (VLMs) achieve strong performance on spatial question answering benchmarks, yet it remains unclear whether such gains reflect genuine spatial intelligence. We show that existing spatial VLMs lack basic camera motion understanding, a key component of spatial cognition. We propose the Spatial Narrative Score (SNS), an evaluation framework that requires VLMs to generate explicit spatial narratives capturing both scene semantics and camera motion, followed by reasoning with a frozen proxy LLM. Under SNS, state-of-the-art spatial VLMs exhibit significant performance degradation despite high direct question answering accuracy. To address this gap, we introduce CaMo, a camera motion grounded VLM that achieves consistent performance across SNS evaluation and direct spatial question answering accuracy. Our results highlight the importance of explicit spatial narrative externalization for evaluating VLMs with transferable 3D spatial understanding. Our code, data, and model is available at https://github.com/hsiangwei0903/CaMo

Existing 3D foundation models typically align point clouds to frozen vision-language spaces like CLIP, which achieve strong cross-modal retrieval by compressing 3D shape into a global vector. However, this global-only alignment cannot establish fine-grained pixel-to-point correspondence. To solve this, we present Tango3D, a foundation model that unifies dense correspondence and global retrieval. We use a geometry-aware 2D visual backbone and a pretrained 3D VAE to encode images into 2D patches and point clouds into 3D tokens. These are mapped into a single shared space to achieve both local pixel-to-point alignment and global semantic alignment. To stabilize the joint learning of dense and global objectives, we introduce a three-stage progressive training strategy. Experiments show our model successfully achieves object-level pixel-to-point alignment while maintaining competitive global retrieval, a joint capability not offered by existing 3D foundation models. By establishing a fine-grained alignment feature space, Tango3D injects rich semantics into purely geometric 3D tokens, paving the way for a wide range of dense 3D downstream tasks.

3D localization in Multimodal Large Language Models (MLLMs), including 3D object detection and 3D visual grounding, is fundamentally limited by camera intrinsic ambiguity: the same image admits different 3D scenes under different cameras. Existing MLLMs either ignore camera parameters and overfit to a canonical training intrinsic, or retrieve depth and 3D cues from external tools but treat the returned values as reference cues (numerical hints that the model is free to interpret implicitly), both preventing camera information from being deterministically propagated into the prediction. We propose an equation-anchored tool-use framework that re-purposes spatial tools as formula variables. The proposed framework proactively retrieves camera intrinsics and samples multi-point metric depths, writes the pinhole back-projection equation $\hat{X} = (u_c - c_x)\bar{Z}/f_x$ explicitly in Chain-of-Thought (CoT), and substitutes tool outputs into the formula before regressing the final 9-DoF bounding box. On both 3D object detection and 3D visual grounding tasks under rescaled camera intrinsics from $0.5\times$ to $1.5\times$, our method outperforms RGB-only and tool-augmented baselines, with significant gains where the camera deviates most from the training scale. Code and data will be released.

Recent advances in 3D datasets and multimodal models have greatly improved natural language 3D scene understanding. However, most 3D referring segmentation methods do not explicitly represent the observer viewpoint, making spatial relations such as "left," "right," "front," and "behind" ambiguous and difficult to evaluate. We introduce a viewpoint-aware 3D referring segmentation dataset containing 220k benchmark samples, and scalable to tens of millions of viewpoint-conditioned samples through dense viewpoint sampling. In this dataset, target objects can only be identified through observer-centric spatial relations, making viewpoint-conditioned grounding necessary. We construct the benchmark by leveraging camera poses to automatically annotate observer-centric relations (left/right, front/behind) together with viewpoint-independent relations (above/under). Using this benchmark, we evaluate several existing 3D large multimodal models in a zero-shot setting and find that current models struggle with viewpoint-dependent spatial instructions. We further study how explicit viewpoint information can be incorporated into 3D large multimodal models. We introduce a viewpoint representation that encodes camera poses and conditions the model on the observation viewpoint, improving segmentation accuracy on viewpoint-dependent relations and increasing mIoU from 0.30 to 0.47 compared to a model without viewpoint conditioning. The dataset, code, and trained models will be made publicly available upon acceptance.

Multimodal large laboratory models (MLLMs) still struggle with spatial understanding under the dominant perspective-image paradigm, which inherits the narrow field of view of human-like perception. For navigation, robotic search, and 3D scene understanding, 360-degree panoramic sensing offers a form of supersensing by capturing the entire surrounding environment at once. However, existing MLLM pipelines typically decompose panoramas into multiple perspective views, leaving the spherical structure of equirectangular projection (ERP) largely implicit. In this paper, we study pano-native understanding, which requires an MLLM to reason over an ERP panorama as a continuous, observer-centered space. To this end, we first define the key abilities for pano-native understanding, including semantic anchoring, spherical localization, reference-frame transformation, and depth-aware 3D spatial reasoning. We then build a large-scale metadata construction pipeline that converts mixed-source ERP panoramas into geometry-aware, language-grounded, and depth-aware supervision, and instantiate these signals as capability-aligned instruction tuning data. On the model side, we introduce PanoWorld with Spherical Spatial Cross-Attention, which injects spherical geometry into the visual stream. We further construct PanoSpace-Bench, a diagnostic benchmark for evaluating ERP-native spatial reasoning. Experiments show that PanoWorld substantially outperforms both proprietary and open-source baselines on PanoSpace-Bench, H* Bench, and R2R-CE Val-Unseen benchmarks. These results demonstrate that robust panoramic reasoning requires dedicated pano-native supervision and geometry-aware model adaptation. All source code and proposed data will be publicly released.

Large-scale 3D vision-language models (VLMs) like LLaVA-3D offer strong spatial reasoning but are difficult to deploy due to high computational costs. We propose a knowledge distillation framework that transfers spatial reasoning from a 7B teacher to a 2.29B student model. Our approach achieves 8.7x lower inference latency and a 3x reduction in model size while retaining 54-72% of the teacher's performance. The framework utilizes VGGT as the vision encoder and a multi-task distillation pipeline with uncertainty-aware loss weighting. To improve reasoning without chain-of-thought (CoT) data, we introduce "Hidden CoT": learnable latent tokens that serve as an internal scratchpad before answer generation. This is the first use of latent scratchpad reasoning in distilled 3D VLMs. The student model jointly performs spatial description, depth estimation, and object detection. Experiments on ScanNet and 3D-FRONT show strong spatial understanding, reaching 68-72% accuracy on proximity and contact tasks. Our framework enables efficient 3D scene QA on resource-constrained platforms.

Accurate 3D scene description is fundamental to robotic navigation and augmented reality, yet current dense captioning methods face significant limitations in processing sparse point cloud data. % Existing approaches that apply Euclidean embedding spaces struggle to simultaneously preserve fine-grained local geometric details and model exponentially growing global semantic hierarchies, leading to either inaccurate localization or disjointed, shallow scene descriptions. % In this work, we propose a novel Curvature-Aware Captioning framework, integrating novel non-Euclidean geodesic attention mechanisms, to resolve the localization-contextualization conflict. % Specifically, self-attention within Oblique space enforces dimensional homogeneity while establishing long-range dependencies. Bidirectional geodesic cross-attention within Lorentz space models hierarchical semantic relationships across scene instances, enabling simultaneous precision in object localization and coherence in scene descriptions. % Theoretical analysis confirms that the curvature complementarity between the Oblique manifold and Lorentz hyperboloid resolves the Euclidean-hyperbolic conflict, ensuring feature stability via isotropic optimization while preserving inherent hierarchical relationships. Extensive experiments on ScanRefer and Nr3D benchmarks demonstrate state-of-the-art performance, with significant gains in both localization accuracy and descriptive richness.

Spatial intelligence in vision-language models (VLMs) attracts research interest with the practical demand to reason in the 3D world.Despite promising results, most existing methods follow the conventional 2D pipeline in VLMs and use pixel-aligned representations for the vision modality. However, correspondence-based models with implicit 3D scene understanding often fail to achieve spatial consistency, and representation-based models with 3D geometric priors lack efficiency in vision sequence serialization. To address this, we propose a Proxy3D method with compact yet comprehensive 3D proxy representations for the vision modality. Given only video frames as input, we employ semantic and geometric encoders to extract scene features and then perform their semantic-aware clustering to obtain a set of proxies in the 3D space. For representation alignment, we further curate the SpaceSpan dataset and apply multi-stage training to adopt the proposed 3D proxy representations with the VLM. When using shorter sequences for vision information, our method achieves competitive or state-of-the-art performance in 3D visual question answering, visual grounding and general spatial intelligence benchmarks.

Decades of cognitive science establish that humans navigate environments by forming cognitive maps, defined as allocentric and topology-preserving representations of 3D space. While modern Vision-Language Models (VLMs) demonstrate emergent spatial reasoning from 2D egocentric inputs, it remains unclear whether they construct an analogous 3D internal representation. In this paper, we demonstrate that current VLMs do possess a latent topological map of 3D scenes, but it is heavily overshadowed by non-geometric visual semantics, such as color and shape. By isolating this spatial subspace through cross-scene linear feature extraction, we extract a clean spatial subspace that causally controls the model's spatial outputs. We mathematically shape this latent representation and prove its correspondence to the Laplacian eigenmaps of the scene's 3D Gaussian-kernel graph, converging to the physical 3D space in the continuous limit. Motivated by this geometric identification, we further introduce a mathematically principled latent regularization method for VLMs, based on Dirichlet energy. Applying this single-term regularizer to a minimal 500-step supervised VLM fine-tuning (SFT) on simple synthetic data yields significant improvements on real-world spatial benchmarks, outperforming standard SFT and competitive baselines by up to 12.1% in spatial tasks involving scene topology understanding. Source code is available at https://github.com/pittisl/vlm-latent-shaping

Open-vocabulary 3D affordance detection requires localizing interaction regions on point clouds given novel affordance descriptions. Recent methods extend multimodal large language models (MLLMs) with special output tokens that are decoded into segmentation masks. However, these tokens are produced through autoregressive generation, which models sequential dependencies rather than spatial neighborhood relations, leaving them semantically rich but spatially impoverished for 3D localization. We propose Voxel-enhanced Affordance detection (VoxAfford), which bypasses this bottleneck by injecting multi-scale geometric features from a frozen pre-trained 3D VQVAE encoder into the output tokens after generation. Each output token uses its affordance semantics as a query to retrieve relevant geometric patterns from its paired voxel scale via cross-attention, with a learned compatibility gate controlling the injection strength. The enhanced tokens are then aggregated into a spatially-aware affordance prompt through semantic-conditioned attention and propagated alongside per-point features to generate the final mask. Experiments on open-vocabulary affordance detection tasks show that VoxAfford achieves state-of-the-art performance with approximately an 8% improvement in mIoU, and real robot experiments confirm zero-shot transfer to novel objects.

Zero-shot 3D Visual Grounding (3DVG) is a critical capability for open-world embodied AI. However, existing methods are fundamentally bottlenecked by the poor quality of open-vocabulary 3D proposals, suffering from inaccurate categories and imprecise geometries, as well as the spatial redundancy of exhaustive multi-view reasoning. To address these challenges, we propose MCM-VG, a novel framework that achieves robust zero-shot 3DVG by explicitly establishing Multiple Consistent 2D-3D Mappings. Instead of passively relying on noisy 3D segments, MCM-VG enforces 2D-3D consistency across three fundamental dimensions to achieve precise target localization and reliable reasoning. First, a Semantic Alignment module corrects category mismatches via LLM-driven query parsing and coarse-to-fine 2D-3D matching. Second, an Instance Rectification module leverages VLM-guided 2D segmentations to reconstruct missing targets, back-projecting these reliable visual priors to establish accurate 3D geometries. Finally, to eliminate spatial redundancy, a Viewpoint Distillation module clusters 3D camera directions to extract optimal frames. By pairing these optimal RGB frames with Bird's Eye View maps into concise visual prompt sets, we formulate the final target disambiguation as a multiple-choice reasoning task for Vision-Language Models. Extensive evaluations on ScanRefer and Nr3D benchmarks demonstrate that MCM-VG sets a new state-of-the-art for zero-shot 3D visual grounding. Remarkably, it achieves 62.0% and 53.6% in [email protected] and [email protected] on ScanRefer, outperforming previous baselines by substantial margins of 6.4% and 4.0%.

Point-Vision-Language Models promise to empower embodied agents with executable spatial reasoning, yet they frequently succumb to geometric hallucination where predicted 3D structures contradict the observed 2D reality. We identify a key cause of this failure not as a representation bottleneck but as a structural misalignment in reinforcement learning, where sparse geometric tokens are drowned out by noisy and broadcasted sequence-level rewards. To resolve this causal dilution, we propose Geometric Reward Credit Assignment, a framework that disentangles holistic supervision into field-specific signals and routes them exclusively to their responsible token spans. This mechanism transforms vague feedback into precise gradient updates and effectively turns generic policy optimization into targeted structural alignment. Furthermore, we internalize physical constraints via a Reprojection-Consistency term which serves as a cross-modal verifier to penalize physically impossible geometries. Validated on a calibrated benchmark derived from ShapeNetCore, our approach bridges the reliability gap by boosting 3D KPA from 0.64 to 0.93, increasing 3D bounding box intersection over union to 0.686, and raising reprojection consistency scores to 0.852. Crucially, these gains are achieved while maintaining robust 2D localization performance, marking a meaningful step from plausible textual outputs toward physically verifiable spatial predictions.

Large language models (LLMs) have recently been applied to 3D vision-language (3D-VL) tasks, which require spatial reasoning to identify target objects relative to anchors. Scene graphs are commonly employed to represent such relations, but reasoning over complete graphs incurs high token costs and computational inefficiencies, motivating the need for pruning. Existing pruning methods primarily rely on spatial proximity and often remove task-relevant relations, thereby undermining reliable spatial reasoning. To address these limitations, we derive a key requirement for scene graph pruning: preserving spatial relations that are most pertinent to the specific 3D-VL task. Guided by this insight, we propose the Conceptual-Adjacent Scene Graph Pruner (CAPruner). CAPruner integrates fuzzy semantic relevance with spatial proximity to estimate the importance of relations, enabling the selection of critical relations in a task-specific context. Moreover, to avoid costly relation-level annotations, CAPruner is trained by supervising the aggregated scores of each node's incident edges. Extensive experiments demonstrate that CAPruner effectively preserves relations essential for spatial reasoning, leading to substantial performance improvements of LLMs on 3D-VL tasks. Code is available at https://github.com/fz-zsl/CAPruner.

Vision-Language-Action (VLA) models drive next-generation autonomous systems, but training them requires scalable, high-quality annotations from complex environments. Current cloud pipelines rely on generic vision-language models (VLMs) that lack geometric reasoning and domain semantics due to their 2D image-text pretraining. To address this mismatch, we propose XEmbodied, a cloud-side foundation model that endows VLMs with intrinsic 3D geometric awareness and interaction with physical cues (e.g., occupancy grids, 3D boxes). Instead of treating geometry as auxiliary input, XEmbodied integrates geometric representations via a structured 3D Adapter and distills physical signals into context tokens using an Efficient Image-Embodied Adapter. Through progressive domain curriculum and reinforcement learning post-training, XEmbodied preserves general capabilities while demonstrating robust performance across 18 public benchmarks. It significantly improves spatial reasoning, traffic semantics, embodied affordance, and out-of-distribution generalization for large-scale scenario mining and embodied VQA.

Multimodal large language models have demonstrated remarkable capabilities in 2D vision, motivating their extension to 3D scene understanding. Recent studies represent 3D scenes as 3D spatial videos composed of image sequences with depth and camera pose information, enabling pre-trained video-language models to perform 3D reasoning tasks. However, the large number of visual tokens in spatial videos remains a major bottleneck for efficient inference and context management. Existing pruning methods overlook the view consistency of spatial videos and the spatial diversity of the remaining tokens, which prevents them from effectively removing inter-frame redundancy and preserving scene completeness. In this paper, we propose Geo3DPruner, a Geometry-Guided 3D Visual Token Pruning framework. Geo3DPruner first models cross-frame relevance through geometry-aware global attention, and then performs a two-stage pruning process. The intra-voxel stage selects representative multi-view features within each voxel, while the inter-voxel stage preserves spatial diversity by selecting a globally distributed subset of voxels. Extensive experiments on multiple 3D scene understanding benchmarks demonstrate that Geo3DPruner retains over 90% of the original performance while pruning 90% of visual tokens, significantly outperforming existing text-guided and vision-guided pruning methods.

Accurate prognostication and risk estimation are essential for guiding clinical decision-making and optimizing patient management. While radiologist-assessed features from CT scans provide valuable indicators of disease severity and outcomes, interpreting such images requires expert knowledge, and translating rich visual information into textual summaries inevitably leads to information loss. In this work, we propose a vision-language framework for 3D CT image understanding that leverages large-scale open-sourced CT images paired with radiology reports through visual instruction tuning. This pre-training enables the model to learn clinically meaningful visual-textual representations, which can then be adapted to downstream survival prediction tasks. By incorporating a survival prediction head on top of the pre-trained model, our approach improves survival prediction from CT images and clinical data while generating clinically meaningful language responses to predefined questions. Experimental results demonstrate that our method outperforms baseline methods in survival prediction, particularly, when clinical data alone is less predictive. The code will be released upon acceptance.

Visual search in 3D environments requires embodied agents to actively explore their surroundings and acquire task-relevant evidence. However, existing visual search and embodied AI benchmarks, including EQA, typically rely on static observations or constrained egocentric motion, and thus do not explicitly evaluate fine-grained viewpoint-dependent phenomena that arise under unrestricted 5-DoF viewpoint control in real-world 3D environments, such as visibility changes caused by vertical viewpoint shifts, revealing contents inside containers, and disambiguating object attributes that are only observable from specific angles. To address this limitation, we introduce {E3VS-Bench}, a benchmark for embodied 3D visual search where agents must control their viewpoints in 5-DoF to gather viewpoint-dependent evidence for question answering. E3VS-Bench consists of 99 high-fidelity 3D scenes reconstructed using 3D Gaussian Splatting and 2,014 question-driven episodes. 3D Gaussian Splatting enables photorealistic free-viewpoint rendering that preserves fine-grained visual details (e.g., small text and subtle attributes) often degraded in mesh-based simulators, thereby allowing the construction of questions that cannot be answered from a single view and instead require active inspection across viewpoints in 5-DoF. We evaluate multiple state-of-the-art VLMs and compare their performance with humans. Despite strong 2D reasoning ability, all models exhibit a substantial gap from humans, highlighting limitations in active perception and coherent viewpoint planning specifically under full 5-DoF viewpoint changes.

With the rise of pre-trained models in the 3D point cloud domain for a wide range of real-world applications, adapting them to downstream tasks has become increasingly important. However, conventional full fine-tuning methods are computationally expensive and storage-intensive. Although prompt tuning has emerged as an efficient alternative, it often suffers from overfitting, thereby compromising generalization capability. To address this issue, we propose Prototypical Point-level Prompt Tuning (P$^3$T), a parameter-efficient prompt tuning method designed for pre-trained 3D vision-language models (VLMs). P$^3$T consists of two components: 1) Point Prompter, which generates instance-aware point-level prompts for the input point cloud, and 2) Text Prompter, which employs learnable prompts into the input text instead of hand-crafted ones. Since both prompters operate directly on input data, P$^3$T enables task-specific adaptation of 3D VLMs without sacrificing generalizability. Furthermore, to enhance embedding space alignment, which is key to fine-tuning 3D VLMs, we introduce a prototypical loss that reduces intra-category variance. Extensive experiments demonstrate that our method matches or outperforms full fine-tuning in classification and few-shot learning, and further exhibits robust generalization under data shift in the cross-dataset setting. The code is available at \textcolor{violet}{https://github.com/gyjung975/P3T}.

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 foundation models, but rely on static single-layer extractions. We identify that such an approach induces a task misalignment bias: the geometric features naturally evolve towards 3D pretraining objectives, which may contradict the heterogeneous spatial demands of MLLMs, rendering any single layer fundamentally insufficient. To resolve this, we propose GeoAlign, a novel framework that dynamically aggregates multi-layer geometric features to realign with the actual demands. GeoAlign constructs a hierarchical geometric feature bank and leverages the MLLM's original visual tokens as content-aware queries to perform layer-wise sparse routing, adaptively fetching the suitable geometric features for each patch. Extensive experiments on VSI-Bench, ScanQA, and SQA3D demonstrate that our compact 4B model effectively achieves state-of-the-art performance, even outperforming larger existing MLLMs.

Vision-language models have been key to the development of open-vocabulary 2D semantic segmentation. Lifting these models from 2D images to 3D scenes, however, remains a challenging problem. Existing approaches typically back-project and average 2D descriptors across views, or heuristically select a single representative one, often resulting in suboptimal 3D representations. In this work, we introduce a novel multiview transformer architecture that cross-attends across vision-language descriptors from multiple viewpoints and fuses them into a unified per-3D-instance embedding. As a second contribution, we leverage multiview consistency as a self-supervision signal for this fusion, which significantly improves performance when added to a standard supervised target-class loss. Our Cross-Attentive Multiview Fusion, which we denote with its acronym CAMFusion, not only consistently outperforms naive averaging or single-view descriptor selection, but also achieves state-of-the-art results on 3D semantic and instance classification benchmarks, including zero-shot evaluations on out-of-domain datasets.

3D layout generation and editing play a crucial role in Embodied AI and immersive VR interaction. However, manual creation requires tedious labor, while data-driven generation often lacks diversity. The emergence of large models introduces new possibilities for 3D scene synthesis. We present HOG-Layout that enables text-driven hierarchical scene generation, optimization and real-time scene editing with large language models (LLMs) and vision-language models (VLMs). HOG-Layout improves scene semantic consistency and plausibility through retrieval-augmented generation (RAG) technology, incorporates an optimization module to enhance physical consistency, and adopts a hierarchical representation to enhance inference and optimization, achieving real-time editing. Experimental results demonstrate that HOG-Layout produces more reasonable environments compared with existing baselines, while supporting fast and intuitive scene editing.

3D medical image analysis is of great importance in disease diagnosis and treatment. Recently, multimodal large language models (MLLMs) have exhibited robust perceptual capacity, strong cross-modal alignment, and promising generalizability. Therefore, they have great potential to improve the performance of medical report generation (MRG) and medical visual question answering (MVQA), which serve as two important tasks in clinical scenarios. However, due to the scarcity of 3D medical images, existing 3D medical MLLMs suffer from insufficiently pretrained vision encoder and inability to extract customized image features for different kinds of tasks. In this paper, we propose to first transfer a 2D MLLM, which is well trained with 2D natural images, to support 3D medical volumetric inputs while reusing all of its pre-trained parameters. To enable the vision encoder to extract tailored image features for various tasks, we then design a Text-Guided Hierarchical MoE (TGH-MoE) framework, which can distinguish tasks under the guidance of the text prompt. Furthermore, we propose a two-stage training strategy to learn both task-shared and task-specific image features. As demonstrated empirically, our method outperforms existing 3D medical MLLMs in both MRG and MVQA tasks. Our code will be released once this paper is accepted.

Spatial reasoning is a fundamental capability for embodied intelligence, especially for fine-grained manipulation tasks such as robotic assembly. Recent methods based on vision-language models (VLMs) largely rely on coarse 2D perception and struggle to perform accurate reasoning over complex 3D geometry. To address this limitation, we propose AssemLM, a spatial multimodal large language model for robotic assembly that integrates assembly manuals, point clouds, and textual instructions to predict task-critical 6D assembly poses with explicit geometric understanding. To bridge raw 3D perception and high-level linguistic reasoning, AssemLM employs a specialized point cloud encoder to extract fine-grained geometric and rotational features for accurate 3D spatial reasoning in assembly tasks. In addition, we introduce AssemBench, a large-scale benchmark for assembly-oriented spatial reasoning with over 900K multimodal samples and precise 6D pose annotations, extending evaluation from 2D grounding to full 3D geometric inference. Extensive experiments and real-robot evaluations demonstrate that AssemLM achieves state-of-the-art 6D pose reasoning performance and effectively supports fine-grained, multi-step assembly tasks in real-world settings. Code, models, and the AssemBench dataset will be made publicly available.

Large multimodal models are increasingly used as the reasoning core of embodied agents operating in 3D environments, yet they remain prone to hallucinations that can produce unsafe and ungrounded decisions. Existing inference-time hallucination mitigation methods largely target 2D vision-language settings and do not transfer to embodied 3D reasoning, where failures arise from object presence, spatial layout, and geometric grounding rather than pixel-level inconsistencies. We introduce 3D-VCD, the first inference-time visual contrastive decoding framework for hallucination mitigation in 3D embodied agents. 3D-VCD constructs a distorted 3D scene graph by applying semantic and geometric perturbations to object-centric representations, such as category substitutions and coordinate or extent corruption. By contrasting predictions under the original and distorted 3D contexts, our method suppresses tokens that are insensitive to grounded scene evidence and are therefore likely driven by language priors. We evaluate 3D-VCD on the 3D-POPE and HEAL benchmarks and show that it consistently improves grounded reasoning without any retraining, establishing inference-time contrastive decoding over structured 3D representations as an effective and practical route to more reliable embodied intelligence.

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in 2D visual tasks but still struggle to understand physical space in real-world visual streams. Recently, feed-forward geometric foundation models that implicitly extract geometric priors from visual inputs have offered a promising direction. However, many existing geometry-aware MLLMs extract features from a single deep encoder layer and perform one-shot fusion at the language-model input, potentially overlooking complementary information across geometric encoder layers, limiting access to fine-grained geometric cues, and hindering progressive cross-modal adaptation. To address these limitations, we propose GUIDE (Geometric Unrolling Inside MLLM Early-layers), a progressive framework for integrating geometric priors. GUIDE samples and aligns multi-level features from the geometric encoder and sequentially injects them into the early layers of the MLLM. This design enables the MLLM to continuously access multi-granularity geometric cues and progressively integrate them with visual representations during layer-wise semantic abstraction. GUIDE further introduces a dual context-aware gating mechanism at both the token and layer levels, selectively regulating geometric information to reduce redundant injection and interference with pretrained representations. Extensive experiments on spatial reasoning and 3D scene understanding benchmarks, including VSI-Bench, ScanRefer, and Scan2Cap, validate the effectiveness and cross-task applicability of GUIDE. Our 5B and 9B models achieve average scores of 71.5 and 72.1 on VSI-Bench, respectively.

Recent advances in Multimodal Large Language Models (MLLMs) have expanded reasoning capabilities into 3D domains, enabling fine-grained spatial understanding. However, the substantial size of 3D MLLMs and the high dimensionality of input features introduce considerable inference overhead, which limits practical deployment on resource constrained platforms. To overcome this limitation, this paper presents Efficient3D, a unified framework for visual token pruning that accelerates 3D MLLMs while maintaining competitive accuracy. The proposed framework introduces a Debiased Visual Token Importance Estimator (DVTIE) module, which considers the influence of shallow initial layers during attention aggregation, thereby producing more reliable importance predictions for visual tokens. In addition, an Adaptive Token Rebalancing (ATR) strategy is developed to dynamically adjust pruning strength based on scene complexity, preserving semantic completeness and maintaining balanced attention across layers. Together, they enable context-aware token reduction that maintains essential semantics with lower computation. Comprehensive experiments conducted on five representative 3D vision and language benchmarks, including ScanRefer, Multi3DRefer, Scan2Cap, ScanQA, and SQA3D, demonstrate that Efficient3D achieves superior performance compared with unpruned baselines, with a +2.57% CIDEr improvement on the Scan2Cap dataset. Therefore, Efficient3D provides a scalable and effective solution for efficient inference in 3D MLLMs. The code is released at: https://github.com/sol924/Efficient3D

Pretraining 3D encoders through alignment with Contrastive Language-Image Pre-training (CLIP) has emerged as a promising direction for learning generalizable representations for 3D scene understanding. In this paper, we propose UniScene3D, a transformer-based framework that learns unified 3D scene representations from multi-view RGB-Pointmap inputs by leveraging the priors of a pretrained 2D foundation model. For robust RGB-Pointmap representation learning, we introduce cross-view geometric alignment and grounded view alignment to enforce geometric and semantic consistency across views. Extensive low-shot and task-specific fine-tuning on viewpoint grounding, scene retrieval, scene classification, and 3D visual question answering demonstrates state-of-the-art performance. These results establish UniScene3D as an effective framework for unified 3D scene understanding. Project page: https://yebulabula.github.io/UniScene3D/

Recent advancements in open-vocabulary 3D scene understanding heavily rely on 3D Gaussian Splatting (3DGS) to register vision-language features into 3D space. However, we identify two critical limitations in these approaches: the spatial ambiguity arising from unstructured, overlapping Gaussians which necessitates probabilistic feature registration, and the multi-level semantic ambiguity caused by pooling features over object-level masks, which dilutes fine-grained details. To address these challenges, we present a novel framework that leverages Sparse Voxel Rasterization (SVRaster) as a structured, disjoint geometry representation. By regularizing SVRaster with monocular depth and normal priors, we establish a stable geometric foundation. This enables a deterministic, confidence-aware feature registration process and suppresses the semantic bleeding artifact common in 3DGS. Furthermore, we resolve multi-level ambiguity by exploiting the emerging dense alignment properties of the AM-RADIO foundation model, avoiding the computational overhead of hierarchical training methods. Our approach achieves state-of-the-art performance on Open Vocabulary Point Cloud Understanding, and highly competitive results on 3D and 2D Object Retrieval benchmarks.

Indoor 3D scenes are ultimately meant to be used: an embodied agent should be able to navigate, reach objects, and complete diverse activities. Yet whether a given scene actually supports these activities for a specific agent profile is rarely verified. Existing evaluations of indoor 3D scenes typically focus on visual quality and semantic plausibility. In contrast, the feasibility of an activity depends on geometric, agent-specific constraints such as reach, clearance, and navigable space availability. These properties are not captured by visual plausibility metrics, and, as we show, VLMs, which are increasingly used to reason about 3D scenes, often fail to determine action feasibility in a single shot. We present SceneTeract, a verification interface that separates semantic action understanding from physical feasibility. Given a scene, an activity, and an embodied agent profile, we decompose the activity into atomic actions on scene objects. Explicit geometric checks then decide whether each step is executable and return a diagnostic trace explaining failures. In synthetic indoor scenes, SceneTeract reveals widespread functional and accessibility failures across diverse agent profiles. Moreover, when benchmarked against our verification, we find that existing VLMs systematically over-predict action feasibility, highlighting limited awareness of embodied functional constraints. In response, we post-train a lightweight VLM with verifier feedback, improving its assessment of physical feasibility. Although trained only on renders of synthetic scenes, we demonstrate that scene understanding improvements also generalize to real-world scenes. We will release our verification suite, benchmark labels, and diagnostic trace datasets.

Vision-language models (VLMs) have been widely adopted for 3D question answering (3D QA). In typical pipelines, visual tokens extracted from multiple viewpoints are concatenated with language tokens and jointly processed by a large language model (LLM) for inference. However, aggregating multi-view observations inevitably introduces severe token redundancy, leading to an overly large visual token set that significantly hinders inference efficiency under constrained token budgets. Visual token pruning has emerged as a prevalent strategy to address this issue. Nevertheless, most existing pruners are primarily tailored to 2D inputs or rely on indirect geometric cues, which limits their ability to explicitly retain semantically critical objects and maintain sufficient spatial coverage for robust 3D reasoning. In this paper, we propose SeGPruner, a semantic-aware and geometry-guided token reduction framework for efficient 3D QA with multi-view images. Specifically, SeGPruner first preserves semantically salient tokens through an attention-based importance module (Saliency-aware Token Selector), ensuring that object-critical evidence is retained. It then complements these tokens with spatially diverse ones via a geometry-guided selector (Geometry-aware Token Diversifier), which jointly considers semantic relevance and 3D geometric distance. This cooperation between saliency preservation and geometry-guided diversification balances object-level evidence and global scene coverage under aggressive token reduction. Extensive experiments on ScanQA and OpenEQA demonstrate that SeGPruner substantially improves inference efficiency, reducing the visual token budget by 91% and inference latency by 86%, while maintaining competitive performance in 3D reasoning tasks.