Joint-embedding predictive world models support planning through latent predictions, but unconstrained joint training can collapse distinct observations to identical embeddings. Two prominent strategies for avoiding collapse are to inherit pretrained features, as in DINO-WM, or to learn representations end-to-end with anti-collapse regularization, as in LeWorldModel (LeWM). Yet avoiding collapse does not ensure that latent distances distinguish outcomes in ways that matter for the task. In object manipulation, for example, success depends on the object's position and orientation relative to the goal. Such task-relevant state information can remain accurately decodable while barely influencing latent distance. The resulting planning cost may fail to reflect how close a predicted outcome is to the task goal. In this paper, we propose SCALE (State-CAlibrated Latent Embeddings), a method that correlates sampled pairwise latent distances with distances in task-relevant state space. Added to LeWM's existing objective, SCALE preserves its architecture, requires privileged state only during training, and adds no planning-time computation. We show that SCALE improves planning success over LeWM across manipulation and navigation tasks with multiple solvers and provide a comprehensive analysis of how SCALE reshapes representation geometry to support planning.
Vision-language models (VLMs) exhibit a striking paradox: they can generate executable code that reconstructs a 3D scene from geometric primitives with correct object counts, classes, and approximate positions, yet the same models fail at simpler spatial questions on the same image. We show that 3D geometric primitives (cubes, spheres, cylinders, expressed in executable code) serve as a powerful intermediate representation for spatial understanding, and exploit this through three contributions. First, we introduce SpatialBabel, a benchmark evaluating fourteen VLMs on primitive-based 3D scene reconstruction across six scene-code languages (programming languages and declarative formats for 3D primitive scenes), revealing that a single model's object-detection F1 can vary by up to 5.7× across languages. Second, we propose Code-CoT (Code Chain-of-Thought), a training-free inference strategy that routes spatial reasoning through primitive-based code generation. Code-CoT lifts the SpatialBabel-QA-Score by up to +6.4% on primitive scenes and real-photo CV-Bench-3D accuracy by +5.0% for VLMs with strong coding capabilities. Third, we propose S^3-FT (Self-Supervised Spatial Fine-Tuning), which self-supervisedly distills primitive spatial knowledge into general visual reasoning by parsing the model's own Three.js primitive-reconstructions into structured annotations and fine-tuning on the result, with no human labels and no teacher model. Training on primitive images alone, S^3-FT improves Qwen3-VL-8B by +4.6 to +8.6% on SpatialBabel-Primitive-QA, +9.7% on CV-Bench-2D, and +17% on HallusionBench; the recipe transfers across model families. These results establish geometric primitives in code as both a diagnostic and a transferable spatial vocabulary for VLMs. We will release all artifacts upon publication.
Generating high-quality 3D objects from textual descriptions remains a challenging problem due to high computational costs, the scarcity of 3D data, and the complexity of 3D representations. We introduce Geometry Image Diffusion (GIMDiffusion), a novel Text-to-3D model that utilizes geometry images to efficiently represent 3D shapes using 2D images, thereby avoiding the need for complex 3D-aware architectures. By integrating a Collaborative Control mechanism, we exploit the rich 2D priors of existing Text-to-Image models, such as Stable Diffusion, to achieve strong generalization despite limited 3D training data. This allows us to use only high-quality training data while retaining compatibility with guidance techniques such as IPAdapter. GIMDiffusion enables the generation of 3D assets at speeds comparable to current Text-to-Image models, without being restricted to manifold meshes during either training or inference. We simultaneously generate a UV unwrapping for the objects, consisting of semantically meaningful parts as well as internal structures, enhancing both usability and versatility.
We show that the task of synthesizing human motion conditioned on a set of key frames can be solved more accurately and effectively if a deep learning based interpolator operates in the delta mode using the spherical linear interpolator as a baseline. We empirically demonstrate the strength of our approach on publicly available datasets achieving state-of-the-art performance. We further generalize these results by showing that the $\Delta$-regime is viable with respect to the reference of the last known frame (also known as the zero-velocity model). This supports the more general conclusion that operating in the reference frame local to input frames is more accurate and robust than in the global (world) reference frame advocated in previous work. Our code is publicly available at https://github.com/boreshkinai/delta-interpolator.
