ICML 2026 Papers

Human spatial understanding arises from jointly perceiving geometry and semantics, enabling consistent object identification and localization across viewpoints and time. Current video segmentation models depend on explicit object appearance memory banks for instance tracking, yet they remain vulnerable to large viewpoint changes and long-term occlusions. Leveraging the spatial consistency afforded by modern feed-forward 3D reconstruction models, we propose the Geometry Grounded Tracking Anything Model (G$^2$TAM), a unified framework for promptable instance tracking in 3D using only unordered RGB images or videos. G$^2$TAM employs spatially aligned geometric representations as implicit memory, ensuring stable instance identity and localization across frames and views. At its core is a cross-modal spatial encoder that integrates visual and textual prompts into a shared geometric space, enabling end-to-end spatial reconstruction and instance-consistent mask prediction. To support training and evaluation, we construct InsTrack, a large-scale dataset with a dedicated validation split for benchmarking. Extensive experiments show that G$^2$TAM delivers strong cross-view consistency, promptable instance spatial tracking, video object segmentation, and spatial reconstruction, establishing a foundation for interactive, geometry-grounded spatial reasoning.

Neural Signed Distance Functions (SDFs) excel at reconstructing watertight manifolds but fail on thin structures and open boundaries due to strict inside—outside constraints. Conversely, Unsigned Distance Fields (UDFs) accommodate general geometries but suffer from gradient singularities at the zero-level set, hindering optimization and extraction. We introduce Metric—Phase Fields (MPFs), a decoupled implicit representation that separates metric proximity from topological phase. Given an unoriented point cloud, MPFs learn (i) an unsigned metric field $r$ and (ii) a smooth phase field $\theta$, for which we derive a bounded phase indicator $P=\tanh(\beta\theta)$ that provides soft inside—outside cues where they are meaningful. We couple the two fields via a gated-metric formulation with a residual phase injection to obtain a signed implicit function with stable near-surface gradients. The phase coefficient $\beta$ is learnable, allowing MPFs to adaptively control the sharpness of the phase transition and the degree of saturation of the soft sign indicator. Experiments on both synthetic and scanned thin-shell and thin-plate shapes demonstrate that MPFs preserve thin and layered structures more faithfully than recent SDF-based methods, while also enabling more robust training and more reliable surface extraction than UDF-based approaches. Check out [MPFs-GitHub](https://github.com/JIAYI-Scarlett/ICML2026-MPF) for source code and test models.

Vision Transformers increasingly incorporate extra tokens beyond patch tokens—from class tokens for aggregation to register tokens for artifact mitigation. While effective for their intended purposes, these tokens typically lack semantic structure. We ask a more ambitious question: Can we design regularization constraints that transform extra tokens into disentangled representations, enabling them to decompose images into semantic parts (e.g., heads, bodies, legs) without explicit supervision? We propose XTRA, an intuitive yet powerful framework that augments Vision Transformers with dedicated ``factor tokens'' and enforces disentanglement via a novel Minimum Volume Constraint (MVC). A multi-stage aggregation process further enforces these factor tokens into semantically pure components, preventing token collapse that often occurs when training with MVC alone. On ImageNet-1K, XTRA achieves superior disentanglement (8.4× improvement in SEPIN@1 over DINOv2) while simultaneously improving representation quality: KNN accuracy improves by 5.8\% and linear-probe accuracy by 2.3\%.

Reconstructing unified continuous dynamics from sparse, non-contiguous, and unpaired point cloud snapshots remains a fundamental challenge in spatiotemporal analysis for computer vision and developmental biology. Existing methods, including scene flow and Optimal Transport-based approaches, are limited either by explicit reliance on point-wise correspondences or by cumulative errors from frame-to-frame propagation and temporal discontinuity, and limited ability to model multi-attribute dynamics such as gene expression and population changes. We propose FlowCloud, a variational Neural Ordinary Differential Equation (Neural ODE) generative framework. FlowCloud aggregates information from all observed time points into a joint latent representation that initializes a Neural ODE $z(t)$ enabling continuous spatiotemporal evolution modeling while mitigating propagation-induced errors and preserving temporal consistency. Training is performed without predefined correspondences using a multi-faceted objective with complementary roles: Sinkhorn distance for global distribution alignment, Chamfer distance for local geometric consistency, trajectory regularization to encourage smooth and physically plausible dynamics, and supervised losses for multi-attribute prediction. Experiments on human motion and developmental biology datasets demonstrate improved interpolation accuracy and promising short-term extrapolation performance. By unifying geometry, attributes, and population dynamics within a continuous latent framework, FlowCloud offers a novel and robust solution for continuous dynamic reconstruction from unstructured spatiotemporal observations.

The smoothness of the transformer architecture has been extensively studied in the context of generalization, training stability, and adversarial robustness. However, its role in transfer learning remains poorly understood. In this paper, we analyze the ability of vision transformer components to adapt their outputs to changes in inputs, or, in other words, their *plasticity*. Defined as an average rate of change, it captures the sensitivity to input perturbation; in particular, a high plasticity implies a low smoothness. Our theoretical analysis and extensive experiments -- over $1,000$ finetuning runs on large-scale vision transformers -- showcase that this perspective provides principled guidance in choosing the components to prioritize during adaptation. A key takeaway for practitioners is that the high plasticity of the attention modules and feedforward layers consistently leads to better finetuning performance. Our findings depart from the prevailing assumption that smoothness is desirable, offering a novel perspective on transformers' functional properties. The code is available at \url{https://github.com/ambroiseodt/vit-plasticity}.

Recent works introduce Rotary Position Embeddings (RoPE) into vision transformers (ViTs) to enhance their extrapolation capability, i.e., maintaining performance when inference is conducted on higher resolution images. RoPE encodes positions via rotating phases whose change is controlled by frequency components. Strandard 2D RoPE does not generalize well to input resolution changes as it only applies axial frequencies separately along each individual axis. To solve this issue, Mix-RoPE combines xy‑axis frequencies, such that it can model position relations in diagonal direction. However, in practice, we observe that the learned 2D frequencies become anisotropic in their direction distributions due to the axial spectral bias in image features, limiting the extrapolation ability of ViTs. Motivated by this observation, we propose Compass‑RoPE. We replace the xy cartesian coordinates with a polar parameterization that explicitly decouples frequency scale and angle. By initializing the angle vectors uniformly over [0,2π), it ensures the isotropic direction coverage. Besides, we further introduce discrete Fourier transform (DFT) mixing for the angle vectors, allowing each transformed individual angle vector element to nest multipule angles and thus to enrich angular expressiveness. Extensive experiments on multi-resolution classification and dense prediction tasks show that our Compass-RoPE achieves more stable extrapolation performance under large-scale resolution changes.

We present Creat3r, an iterative next-best-view (NBV) selection framework for efficient, high-quality 3D reconstruction. Starting from a small seed set of image-pose pairs, Creat3r repeatedly selects the most informative next camera pose. After each pose is chosen, the corresponding image is acquired and added to the multi-view set to update a 3DGS reconstruction. To guide selection, Creat3r constructs an intermediate point cloud and estimates reconstruction reliability via a novel 3D confidence field, which is projected to candidate poses through Gaussian projection to produce 2D confidence and exploration maps. These maps balance exploitation of reliable regions and exploration of uncertain or unseen areas under computational constraints. Experiments with standard 3DGS show that Creat3r consistently outperforms baselines in novel view synthesis and surface reconstruction, achieving higher SSIM and F1 scores with fewer views.

Learning motion latents for robotic manipulation heavily relies on extracting motion patterns from visual sequences, yet effective action abstractions require understanding three-dimensional geometric transformations. Here, we introduce GeoMoLa (Geometry-Aware Motion Latents), which learns discrete motion latent codes by predicting how point clouds evolve during manipulation rather than reconstructing visual observations. This four-dimensional objective – spatial geometry changing through time – forces latent representations to encode actual physical motion rather than appearance patterns. GeoMoLa achieves state-of-the-art performance using only single-view RGB-D input, while existing methods require multi-view reconstruction, succeeding across diverse manipulation benchmarks. Our ablations reveal that geometric prediction is the key to driving performance, quantitatively validating that manipulation depends on spatial understanding. Furthermore, the learned codes exhibit effective motion abstraction: applying them to novel scenes produces physically consistent transformations regardless of visual context. Our real-world experiments also confirm this robustness capability, achieving robust manipulation with minimal demonstrations in cluttered environments where geometric reasoning determines success. Thus, we demonstrate that effective motion latents for robot control can better emerge from understanding motion through its three-dimensional effects rather than pixel-level patterns.

The generation of immersive and navigable 3D environments is increasingly prevalent with the growing adoption of virtual reality and 3D content. However, recent methods face a fundamental limitation: they cannot produce 3D worlds that simultaneously (i) are navigable over long-range spatial extents and (ii) cover the complete omnidirectional field of view ($360^\circ$ horizontally and $180^\circ$ vertically). To address this challenge, we introduce SphericalDreamer, a method for generating fully immersive and long-range 3D outdoor environments from textual prompts. Our approach is built on the generation of multiple panoramic images, which are subsequently lifted into 3D and fused together while maintaining visual and geometric consistency. SphericalDreamer produces highly detailed, fully immersive 3D environments, while substantially improving scale and navigability compared to prior approaches.

We present ReflFlow, a novel framework for high-fidelity rendering of dynamic specular scenes by addressing two key challenges: precise reflection direction estimation and physically accurate modeling. To achieve this, we propose a Residual Material-Augmented 2D Gaussian Splatting representation that models dynamic geometry and material properties, allowing accurate reflection ray computation. Furthermore, we introduce a Dynamic Environment Gaussian and a hybrid rendering pipeline that decomposes rendering into diffuse and specular components, enabling physically informed specular synthesis via rasterization and ray tracing. Finally, we devise a coarse-to-fine training strategy to improve optimization stability and promote physically meaningful decomposition. Extensive experiments on dynamic scene benchmarks demonstrate that ReflFlow outperforms prior methods quantitatively and qualitatively, producing sharper and more realistic specular reflections in complex dynamic environments.

Consumer-level applications require fast optimization of 3D Gaussian Splatting (3DGS) with high-fidelity novel view rendering. However, existing 3DGS acceleration approaches still incur substantial computation on redundant pixels while sacrificing fine details. In this paper, we present TurboGS, an error-guided training framework that accelerates 3DGS by concentrating optimization on perceptually informative pixels. TurboGS is built upon four core components: (1) a tile-wise sparse pixel sampling, which, driven by multi-view reconstruction errors during training, prioritizes challenging regions and skips well-reconstructed ones to avoid redundant gradient computation; (2) a tile-wise structure-aware loss with sparse Normalized Cross-Correlation, which provides sparse yet effective supervision to preserve fine details and stabilize training; (3) an error-driven Gaussian density control strategy, which dynamically allocates model capacity and removes redundant primitives; and (4) a tailored hybrid optimizer that couples Hessian-informed updates with Adam moment damping to stabilize and improve convergence under sparse supervision. Experiments on standard benchmarks demonstrate that TurboGS can deliver on par or superior rendering quality within 100 seconds (up to 10x training speedup over vanilla 3DGS).

Sliced optimal transport (SOT), or sliced Wasserstein (SW) distance, is widely recognized for its statistical and computational scalability. In this work, we further enhance computational scalability by proposing the first method for estimating SW from sample streams, called streaming sliced Wasserstein (Stream-SW). To define Stream-SW, we first introduce a streaming estimator of the one-dimensional Wasserstein distance (1DW). Since the 1DW has a closed-form expression, given by the integral of the absolute difference between the quantile functions of the compared distributions, we leverage quantile approximation techniques for sample streams to define a streaming 1DW estimator. By applying the streaming 1DW to all projections, we obtain Stream-SW. The key advantage of Stream-SW is its low memory complexity while providing theoretical guarantees on the approximation error. We demonstrate that Stream-SW achieves a more accurate approximation of SW than random subsampling, with lower memory consumption, when comparing Gaussian distributions and mixtures of Gaussians from streaming samples. Additionally, we conduct experiments on point cloud classification, point cloud gradient flows, and streaming change point detection to further highlight the favorable performance of the proposed Stream-SW.

3D hierarchical semantic segmentation (3DHS) is crucial for embodied intelligence that demands the coarse-to-fine grained and multi-hierarchy understanding of 3D scenes. 3DHS tasks can be addressed by multi-label learning, but facing two issues: I) learning multiple labels for each point with a shared model can lead to multi-hierarchy conflicts in cross-hierarchy optimization, and II) the class imbalance issue is inevitable across multiple hierarchies of 3D scenes, making the model easily be dominated by major classes. To address these issues, we propose a novel multi-label learning with contrastive cluster self-supervision framework for 3DHS. Specifically, we propose a late-decoupled multi-label learning 3DHS network which employs decoupled decoders with the coarse-to-fine hierarchical consistency guidance. This late-decoupled model architecture can mitigate the underfitting and overfitting conflicts among multiple hierarchies and also constrain the class imbalance problem within each individual hierarchy. Moreover, we introduce a 3DHS-oriented contrastive cluster self-supervision learning method, which learns cluster-wise point cloud features with contrastive loss and produces self-supervised information to enhance the class-imbalance segmentation. Extensive experiments on multiple datasets and backbones demonstrate that our approach promotes the multi-hierarchy balance and mitigates the class imbalance issue in 3DHS tasks.

While LiDAR NeRFs excel in static environments, synthesizing dynamic scenes remains challenging as moving objects break multi-view consistency, causing conflicting supervision and ghosting artifacts across frames. Existing methods typically suffer from optimization difficulty from the start, struggling to disentangle valid geometry from motion noise when initial motion priors are unreliable. To address this, we propose MAC-NeRF, a novel LiDAR NeRF framework enhanced by motion-aware curriculum learning for high-fidelity dynamic scene synthesis. First, we propose Rectified Temporal Consistency to resolve motion-induced supervision conflicts. By filtering out erroneous supervision via forward-backward geometric verification, it creates a curriculum that prioritizes trustworthy temporal correspondences before handling challenging motions. Second, we propose Confidence-Modulated Frequency Regularization (CMFR) to eliminate geometric ambiguity. It adaptively modulates the frequency regularization bandwidth, progressively transitioning from strict low-frequency constraints for artifact suppression to full-spectrum modeling for fine-grained detail preservation. Extensive experiments on KITTI-360 and nuScenes demonstrate that MAC-NeRF significantly outperforms state-of-the-art methods in rendering quality.

State-of-the-art single-image 3D reconstruction methods often rely on complex hybrid architectures and loss functions (e.g., MoGe), or necessitate compressing geometry into latent spaces (e.g., GeometryCrafter) to leverage pre-trained latent diffusion models. In this work, we demonstrate that such architectural overhead and intricate loss formulations are unnecessary. We introduce a minimalist pixel-space Diffusion Transformer built on a plain ViT, which operates directly on raw 3D point map patches and is conditioned on image tokens from a pre-trained DINOv3. Unlike existing latent diffusion-based approaches, we train our diffusion backbone entirely from scratch, eliminating the need for point map tokenizers. We show that this streamlined approach yields results superior to complex latent-based diffusion models while remaining significantly simpler than hybrid alternatives. Notably, our model produces sharper geometric structures and achieves significantly better results on highly ambiguous regions, such as transparent objects.

3D Gaussian Splatting (3DGS) is a powerful technique for creating high-fidelity 3D assets. However, the widespread sharing and iterative modification of 3DGS models across digital platforms create pressing challenges for intellectual property protection and forensic traceability. To address this, we propose GaussTrace, a novel framework for constructing directed provenance graphs for 3DGS models. GaussTrace formulates provenance analysis as an evidence-based reasoning problem. It builds upon attribute-wise statistical profiling of 3DGS parameters to capture intrinsic properties. Moreover, we introduce hypothesis-driven editing simulations of common operations to provide auxiliary evidence for plausible transformation pathways. These statistical and simulated cues jointly enable a Large Language Model (LLM) to perform structured Chain-of-Thought (CoT) reasoning, yielding directional provenance inferences and explainable edge reasons. Experimental results demonstrate that GaussTrace effectively constructs evolutionary relationships among diverse 3DGS models, delivering accurate, interpretable, and robust provenance graphs without requiring model training or access to editing histories. Project page: https://haolianghan.github.io/GaussTrace.

Geometry-aware generative models and novel view synthesis approaches have shown strong potential in visual fidelity and consistency. In parallel, equivariant representation learning has emerged as a powerful framework for constructing latent spaces where analytically known group transformations could act directly, capturing geometric structure in data and enhancing both interpretability and generalization in novel view synthesis. However, we identify that existing approaches often suffer from latent misalignment, a discrepancy between the intended group action and the actually required transformations in the latent space. Consequently, the learned latents often fail to consistently preserve the equivariant relations imposed by the underlying group symmetry. To address this, we propose Residual Latent Flow, a flow-based framework that corrects the misaligned latents, thereby improving compliance with the underlying equivariance relation. Our comprehensive experiments show that our method significantly reduces latent misalignment and improves novel view synthesis quality, under rotation groups SO(n).

Open-vocabulary 3D instance segmentation is a core capability for robotics and AR/VR, but prior methods trade one bottleneck for another: multi-stage 2D+3D pipelines aggregate foundation-model outputs at hundreds of seconds per scene, while pseudo-labeled end-to-end approaches rely on fragmented masks and external region proposals. We present SpaCeFormer, a proposal-free space-curve transformer that runs in 0.12–0.30 seconds per scene across standard benchmarks, 2–3 orders of magnitude faster than multi-stage 2D+3D pipelines. We pair it with SpaCeFormer-3M, the largest open-vocabulary 3D instance segmentation dataset (3.0M multi-view-consistent captions over 604K instances from 7.4K scenes) built through multi-view mask clustering and multi-view VLM captioning; it reaches **21× higher mask recall** than prior single-view pipelines (54.3% vs 2.5% at IoU>0.5). SpaCeFormer combines spatial window attention with Morton-curve serialization for spatially coherent features, and uses a RoPE-enhanced decoder to predict instance masks directly from learned queries without external proposals. On ScanNet200 we achieve 11.1 zero-shot mAP, a 2.8× improvement over the prior best proposal-free method; on ScanNet++ and Replica, we reach 22.9 and 24.1 mAP, surpassing all prior methods including those using multi-view 2D inputs.

A common assumption in representation learning is that globally well-distributed embeddings support robust and generalizable representations. This focus has shaped both training objectives and evaluation protocols, implicitly treating global geometry as a proxy for representational competence. While global geometry effectively encodes which elements are present, it is often insensitive to how they are composed. We investigate this limitation by testing the ability of geometric metrics to predict compositional binding across 21 vision encoders. We find that standard geometry-based statistics exhibit near-zero correlation with compositional binding. In contrast, functional sensitivity, as measured by the input-output Jacobian, reliably tracks this capability. We further provide an analytic account showing that this disparity arises from objective design, as existing losses explicitly constrain embedding geometry but leave the local input-output mapping unconstrained. These results suggest that global embedding geometry captures only a partial view of representational competence and establish functional sensitivity as a critical complementary axis for modeling composite structure.