Energy-based predictive world models provide a powerful approach for multi-step visual planning by reasoning over latent energy landscapes rather than generating pixels. However, existing approaches face two major challenges: (i) their latent representations are typically learned in Euclidean space, neglecting the underlying geometric and hierarchical structure among states, and (ii) they struggle with long-horizon prediction, which leads to rapid degradation across extended rollouts. To address these challenges, we introduce GeoWorld, a geometric world model that preserves geometric structure and hierarchical relations through a Hyperbolic JEPA, which maps latent representations from Euclidean space onto hyperbolic manifolds. We further introduce Geometric Reinforcement Learning for energy-based optimization, enabling stable multi-step planning in hyperbolic latent space. Extensive experiments on CrossTask and COIN demonstrate around 3% SR improvement in 3-step planning and 2% SR improvement in 4-step planning compared to the state-of-the-art V-JEPA-2.

Camera calibration is fundamental to reliable geometric perception, yet classical approaches rely on dedicated targets, successful reconstruction, or dense view coverage, which casually captured imagery rarely satisfies. Recent learning-based single-image methods lift these requirements by exploiting visual cues, and extend calibration beyond intrinsics to gravity estimation. Yet in the common multi-view case, they predict each view independently and combine the estimates only afterwards, lacking full use of cross-view consistency. We bridge this gap with CalibAnyView, a framework that unifies single- and sparse multi-view calibration by enforcing that consistency inside the network: a transformer with cross-view attention predicts camera-model-agnostic perspective fields, followed by a multi-view optimization that fuses them into shared intrinsics and per-view gravity directions, covering camera models from pinhole to severely distorted lenses. To support this, we construct a large-scale in-the-wild multi-view video dataset spanning diverse camera models, dynamic scenes, realistic motion trajectories, and heterogeneous lens distortions. Extensive experiments show that CalibAnyView outperforms state-of-the-art methods in both sparse multi-view and single-view settings spanning pinhole to distorted optics.

Multimodal Large Language Models (MLLMs) have demonstrated strong cross-modal reasoning capabilities, yet their potential for vision-only tasks remains underexplored. We investigate MLLMs as training-free similarity estimators for instance-level image-to-image retrieval. Our approach prompts the model with paired images and converts next-token probabilities into similarity scores, enabling zero-shot re-ranking within large-scale retrieval pipelines. This design avoids specialized architectures and fine-tuning, leveraging the rich visual discrimination learned during multimodal pre-training. We address scalability by combining MLLMs with memory-efficient indexing and top-k candidate re-ranking. Experiments across diverse benchmarks show that MLLMs outperform task-specific re-rankers outside their native domains and exhibit superior robustness to clutter, occlusion, and small objects. Despite strong results, we identify failure modes under severe appearance changes, highlighting opportunities for future research. Our findings position MLLMs as a promising alternative for open-world large-scale image retrieval.

World Models (WMs) offer a promising mechanism for post-training Vision-Language-Action (VLA) policies by providing dynamics priors that improve generalization under task and scene variation. However, most WM-based post-training methods rely on pixel-space supervision, making policies sensitive to visual artifacts introduced by imperfect WM rollouts. We present World2Act, a latent-space post-training framework that transfers WM dynamics to the VLA policy without pixel-space supervision. World2Act operates in two stages: 1) it induces a shared video-action latent space by contrastively aligning WM-dynamics latents with action embeddings, and 2) it post-trains the VLA by guiding policy action representations toward WM-imagined dynamics rather than decoded pixels. Built on GR00T-N1.6, World2Act delivers absolute success-rate gains of up to +2.5

Depth priors are critical for maintaining accurate geometry in novel view synthesis, especially when input views are sparse and scenes are complex and room-scale. However, obtaining reliable depth under such conditions remains a significant challenge. In this work, we present a novel method that self-supervisedly adapts a pretrained video depth estimation network to each specific scene. This scene-specific adaptation enables high-fidelity depth estimation even under extreme view sparsity. Leveraging these accurate depth priors, we propose an efficient two-stage NeRF training pipeline with a density self-correction mechanism that mitigates the effects of depth errors without relying on explicit uncertainty modeling. Our approach not only enhances synthesis quality in sparse-view settings but also significantly accelerates neural radiance field (NeRF) training, outperforming existing methods in both fidelity and efficiency.

Visual navigation using only a single camera and a topological map has recently become an appealing alternative to methods that require additional sensors and 3D maps. This is typically achieved through an image-relative approach to estimating control from a given pair of current observation and subgoal image. However, image-level representations of the world have limitations because images are strictly tied to the agent's pose and embodiment. In contrast, objects, being a property of the map, offer an embodiment- and trajectory-invariant world representation. In this work, we present a new paradigm of learning object-relative control that exhibits several desirable characteristics: a) new routes can be traversed without strictly requiring to imitate prior experience, b) the control prediction problem can be decoupled from solving the image matching problem, and c) high invariance can be achieved in cross-embodiment deployment for variations across both training-testing and mapping-execution settings. We propose a topometric map representation in the form of a relative 3D scene graph, which is used to obtain more informative object-level global path planning costs. We train a local controller, dubbed ObjectReact, conditioned directly on a high-level "WayObject Costmap" representation that eliminates the need for an explicit RGB input. We demonstrate the advantages of learning object-relative control over its image-relative counterpart across sensor height variations and multiple navigation tasks that challenge the underlying spatial understanding capability, e.g., navigating a map trajectory in the reverse direction. We further show that our sim-only policy is able to generalize well to real-world indoor environments. Project Page: https://object-react.github.io/

Existing RGB-based imitation learning approaches typically employ traditional vision encoders such as ResNet or ViT, which lack explicit 3D reasoning capabilities. Recent geometry-grounded vision models, such as VGGT , provide robust spatial understanding and are promising candidates to address this limitation. This work investigates the integration of geometry-aware visual representations into robotic manipulation. Our results suggest that incorporating the geometry-aware vision encoder into imitation learning frameworks, including ACT and DP, yields up to 6.5

We propose Hier-SLAM++, a comprehensive Neuro-Symbolic semantic 3D Gaussian Splatting SLAM method with both RGB-D and monocular input featuring an advanced hierarchical categorical representation, which enables accurate pose estimation as well as global 3D semantic mapping. The parameter usage in semantic SLAM systems increases significantly with the growing complexity of the environment, making scene understanding particularly challenging and costly. To address this problem, we introduce a novel hierarchical representation that encodes both semantic and geometric information in a compact form into 3D Gaussian Splatting, leveraging the capabilities of large language models (LLMs) as well as the 3D generative model. By utilizing the proposed hierarchical tree structure, semantic information is symbolically represented and learned in an end-to-end manner. We further introduce an advanced semantic loss designed to optimize hierarchical semantic information through both Intra-level and Inter-level optimizations. Additionally, we propose an improved SLAM system to support both RGB-D and monocular inputs using a feed-forward model. To the best of our knowledge, this is the first semantic monocular Gaussian Splatting SLAM system, significantly reducing sensor requirements for 3D semantic understanding and broadening the applicability of semantic Gaussian SLAM system. We conduct experiments on both synthetic and real-world datasets, demonstrating superior or on-par performance with state-of-the-art methods, while significantly reducing storage and training time requirements. Our project page is available at: https://hierslampp.github.io/

Visual navigation in robotics traditionally relies on globally-consistent 3D maps or learned controllers, which can be computationally expensive and difficult to generalize across diverse environments. In this work, we present a novel RGB-only, object-level topometric navigation pipeline that enables zero-shot, long-horizon robot navigation without requiring 3D maps or pre-trained controllers. Our approach integrates global topological path planning with local metric trajectory control, allowing the robot to navigate towards object-level sub-goals while avoiding obstacles. We address key limitations of previous methods by continuously predicting local trajectory using monocular depth and traversability estimation, and in-corporating an auto-switching mechanism that falls back to a baseline controller when necessary. The system operates using foundational models, ensuring open-set applicability without the need for domain-specific fine-tuning. We demonstrate the effectiveness of our method in both simulated environments and real-world tests, highlighting its robustness and deployability. Our approach outperforms existing state-of-the-art methods, offering a more adaptable and effective solution for visual navigation in open-set environments. The source code is made publicly available: https://github.com/podgorki/TANGO.

Spatial reasoning, the ability to understand and interpret the 3D structure of the world, is a critical yet underdeveloped capability in Multimodal Large Language Models (MLLMs). Current methods predominantly rely on verbal descriptive tuning, which suffers from visual illiteracy, i.e., they learn spatial concepts through textual symbols alone, devoid of connection to their visual manifestations. To bridge this gap, this paper introduces MILO, an Implicit spatIaL wOrld modeling paradigm that simulates human-like spatial imagination. MILO integrates a visual generator to provide geometry-aware feedback, thereby implicitly grounding the MLLM's symbolic reasoning in perceptual experience. Complementing this paradigm, we propose RePE (Relative Positional Encoding), a novel encoding scheme that captures relative camera-pose transformations, offering superior performance over absolute coordinate systems. To support the training, we construct GeoGen, a large-scale Geometry-aware Generative dataset with approximately 2,241 videos and 67,827 observation-action-outcome triplets. Experiments demonstrate that our approach significantly enhances spatial reasoning capabilities across multiple baselines and benchmarks, offering a more holistic understanding of 3D space.

Grasp detection is a fundamental robotic task critical to the success of many industrial applications. However, current language-driven models for this task often struggle with cluttered images, lengthy textual descriptions, or slow inference speed. We introduce GraspMamba, a new language-driven grasp detection method that employs hierarchical feature fusion with Mamba vision to tackle these challenges. By leveraging rich visual features of the Mamba-based backbone alongside textual information, our approach effectively enhances the fusion of multimodal features. GraspMamba represents the first Mamba-based grasp detection model to extract vision and language features at multiple scales, delivering robust performance and rapid inference time. Intensive experiments show that GraspMamba outperforms recent methods by a clear margin. We validate our approach through real-world robotic experiments, highlighting its fast inference speed.

Current 3D Large Multimodal Models (3D LMMs) have shown tremendous potential in 3D-vision-based dialogue and reasoning. However, how to further enhance 3D LMMs to achieve fine-grained scene understanding and facilitate flexible human-agent interaction remains a challenging problem. In this work, we introduce 3D-LLaVA, a simple yet highly powerful 3D LMM designed to act as an intelligent assistant in comprehending, reasoning, and interacting with the 3D world. Unlike existing top-performing methods that rely on complicated pipelines—such as offline multi-view feature extraction or additional task-specific heads—3D-LLaVA adopts a minimalist design with integrated architecture and only takes point clouds as input. At the core of 3D-LLaVA is a new Omni Superpoint Transformer (OST), which integrates three functionalities: (1) a visual feature selector that converts and selects visual tokens, (2) a visual prompt encoder that embeds interactive visual prompts into the visual token space, and (3) a referring mask decoder that produces 3D masks based on text description. This versatile OST is empowered by the hybrid pretraining to obtain perception priors and leveraged as the visual connector that bridges the 3D data to the LLM. After performing unified instruction tuning, our 3D-LLaVA reports impressive results on various benchmarks. The code and model will be released at https://github.com/djiajunustc/3D-LLaVA.

3D Gaussians have recently emerged as an effective scene representation for real-time splatting and accurate novel-view synthesis, motivating several works to adapt multi-view structure prediction networks to regress per-pixel 3D Gaussians from images. However, most prior work extends these networks to predict additional Gaussian parameters – orientation, scale, opacity, and appearance – while relying almost exclusively on view-synthesis supervision. We show that a view-synthesis loss alone is insufficient to recover geometrically meaningful splats in this setting. We analyze and address the ambiguities of learning 3D Gaussian splats under self-supervision for pose-free generalizable splatting, and introduce G3Splat, which enforces geometric priors to obtain geometrically consistent 3D scene representations. Trained on RE10K, our approach achieves state-of-the-art performance in (i) geometrically consistent reconstruction, (ii) relative pose estimation, and (iii) novel-view synthesis. We further demonstrate strong zero-shot generalization on ScanNet, substantially outperforming prior work in both geometry recovery and relative pose estimation. Code and pretrained models are released on our project page (https://m80hz.github.io/g3splat/).

Large Language Models (LLMs) such as GPT-4, trained on huge amount of datasets spanning multiple domains, exhibit significant reasoning, understanding, and planning capabilities across various tasks. This study presents the first-ever work in Arabic language integration within the Vision-and-Language Navigation (VLN) domain in robotics, an area that has been notably underexplored in existing research. We perform a comprehensive evaluation of state-of-the-art multi-lingual Small Language Models (SLMs), including GPT-4o mini, Llama 3 8B, and Phi-3 medium 14B, alongside the Arabic-centric LLM, Jais. Our approach utilizes the NavGPT framework, a pure LLM-based instruction-following navigation agent, to assess the impact of language on navigation reasoning through zero-shot sequential action prediction using the R2R dataset. Through comprehensive experiments, we demonstrate that our framework is capable of high-level planning for navigation tasks when provided with instructions in both English and Arabic. However, certain models struggled with reasoning and planning in the Arabic language due to inherent limitations in their capabilities, sub-optimal performance, and parsing issues. These findings highlight the importance of enhancing planning and reasoning capabilities in language models for effective navigation, emphasizing this as a key area for further development while also unlocking the potential of Arabic-language models for impactful real-world applications.

By enabling capturing of 3D point clouds that reflect the geometry of the immediate environment, LiDAR has emerged as a primary sensor for autonomous systems. If a LiDAR scan is too sparse, occluded by obstacles, or too small in range, enhancing the point cloud scan by while respecting the geometry of the scene is useful for downstream tasks. Motivated by the explosive growth of interest in generative methods in vision, conditional LiDAR generation is starting to take off. This paper proposes a novel simultaneous diffusion sampling methodology to generate point clouds conditioned on the 3D structure of the scene as seen from multiple views. The key idea is to impose multi-view geometric constraints on the generation process, exploiting mutual information for enhanced results. Our method begins by recasting the input scan to multiple new viewpoints around the scan, thus creating multiple synthetic LiDAR scans. Then, the synthetic and input LiDAR scans simultaneously undergo conditional generation according to our methodology. Results show that our method can produce accurate and geometrically consistent enhancements to point cloud scans, allowing it to outperform existing methods by a large margin in a variety of benchmarks.

Vision-Language-Action (VLA) models have gained popularity for learning robotic manipulation tasks that follow language instructions. State-of-the-art VLAs, such as OpenVLA and π_0, were trained on large-scale, manually labeled action datasets collected through teleoperation. More recent approaches, including LAPA and villa-X, introduce latent action representations that enable unsupervised pretraining on unlabeled datasets by modeling abstract visual changes between frames. Although these methods have shown strong results, their large model sizes make deployment in real-world settings challenging. In this work, we propose LAWM, a model-agnostic framework to pretrain imitation learning models in a self-supervised way, by learning latent action representations from unlabeled video data through world modeling. These videos can be sourced from robot recordings or videos of humans performing actions with everyday objects. Our framework is designed to be effective for transferring across tasks, environments, and embodiments. It outperforms models trained with ground-truth robotics actions and similar pretraining methods on the LIBERO benchmark and real-world setup, while being significantly more efficient and practical for real-world settings.

We address the task of Vision-Language Navigation in Continuous Environments (VLN-CE) under the zero-shot setting. Zero-shot VLN-CE is particularly challenging due to the absence of expert demonstrations for training and minimal environment structural prior to guide navigation. To confront these challenges, we propose a Constraint-Aware Navigator (CA-Nav), which reframes zero-shot VLN-CE as a sequential, constraint-aware sub-instruction completion process. CA-Nav continuously translates sub-instructions into navigation plans using two core modules: the Constraint-Aware Sub-instruction Manager (CSM) and the Constraint-Aware Value Mapper (CVM). CSM defines the completion criteria for decomposed sub-instructions as constraints and tracks navigation progress by switching sub-instructions in a constraint-aware manner. CVM, guided by CSM's constraints, generates a value map on the fly and refines it using superpixel clustering to improve navigation stability. CA-Nav achieves the state-of-the-art performance on two VLN-CE benchmarks, surpassing the previous best method by 12% and 13% in Success Rate on the validation unseen splits of R2R-CE and RxR-CE, respectively. Moreover, CA-Nav demonstrates its effectiveness in real-world robot deployments across various indoor scenes and instructions.

For a complete comprehension of multi-person scenes, it is essential to go beyond basic tasks like detection and tracking. Higher-level tasks, such as understanding the interactions and social activities among individuals, are also crucial. Progress towards models that can fully understand scenes involving multiple people is hindered by a lack of sufficient annotated data for such high-level tasks. To address this challenge, we introduce Social-MAE, a simple yet effective transformer-based masked autoencoder framework for multi-person human motion data. The framework uses masked modeling to pre-train the encoder to reconstruct masked human joint trajectories, enabling it to learn generalizable and data efficient representations of motion in human crowded scenes. Social-MAE comprises a transformer as the MAE encoder and a lighter-weight transformer as the MAE decoder which operates on multi-person joints' trajectory in the frequency domain. After the reconstruction task, the MAE decoder is replaced with a task-specific decoder and the model is fine-tuned end-to-end for a variety of high-level social tasks. Our proposed model combined with our pre-training approach achieves the state-of-the-art results on various high-level social tasks, including multi-person pose forecasting, social grouping, and social action understanding. These improvements are demonstrated across four popular multi-person datasets encompassing both human 2D and 3D body pose.

Imitation learning has unlocked the potential for robots to exhibit highly dexterous behaviours. However, it still struggles with long-horizon, multi-object tasks due to poor sample efficiency and limited generalisation. Existing methods require a substantial number of demonstrations to cover possible task variations, making them costly and often impractical for real-world deployment. We address this challenge by introducing oriented affordance frames, a structured representation for state and action spaces that improves spatial and intracategory generalisation and enables policies to be learned efficiently from only 10 demonstrations. More importantly we show how this abstraction allows for compositional generalisation of independently trained sub-policies to solve long-horizon, multi-object tasks. To seamlessly transition between sub-policies, we introduce the notion of self-progress prediction, which we directly derive from the duration of the training demonstrations. We validate our method across three real-world tasks, each requiring multi-step, multi-object interactions. Despite the small dataset, our policies generalise robustly to unseen object appearances, geometries, and spatial arrangements, achieving high success rates without reliance on exhaustive training data. Video demonstration can be found on our project page: https://affordance-policy.github.io/.

We propose Hier-SLAM, a semantic 3D Gaussian Splatting SLAM method featuring a novel hierarchical categorical representation, which enables accurate global 3D semantic mapping, scaling-up capability, and explicit semantic label prediction in the 3D world. The parameter usage in semantic SLAM systems increases significantly with the growing complexity of the environment, making it particularly challenging and costly for scene understanding. To address this problem, we introduce a novel hierarchical representation that encodes semantic information in a compact form into 3D Gaussian Splatting, leveraging the capabilities of large language models (LLMs). We further introduce a novel semantic loss designed to optimize hierarchical semantic information through both inter-level and cross-level optimization. Furthermore, we enhance the whole SLAM system, resulting in improved tracking and mapping performance. Our Hier-SLAM outperforms existing dense SLAM methods in both mapping and tracking accuracy, while achieving a 2x operation speed-up. Additionally, it achieves on-par semantic rendering performance compared to existing methods while significantly reducing storage and training time requirements. Rendering FPS impressively reaches 2,000 with semantic information and 3,000 without it. Most notably, it showcases the capability of handling the complex real-world scene with more than 500 semantic classes, highlighting its valuable scaling-up capability. The open-source code is available at https://github.com/LeeBY68/Hier-SLAM.