ICML 2026 Papers

We dream of a future where point clouds from all domains can come together to shape a single model that benefits them all. Toward this goal, we present Utonia, a first step toward training a single self-supervised point transformer encoder across heterogeneous domains, spanning remote sensing, outdoor LiDAR, indoor RGB-D sequences, object-centric CAD models, and point clouds lifted from RGB-only videos. Despite their distinct sensing geometries, densities, and priors, Utonia learns a consistent representation space that transfers across domains. This unification improves perception capability while revealing intriguing emergent behaviors that arise only when domains are trained jointly. Beyond perception, we observe that Utonia representations can also benefit embodied and multimodal reasoning: conditioning vision-language-action policies on Utonia features improves robotic manipulation, and integrating them into vision-language models yields gains on spatial reasoning. We hope Utonia can serve as a step toward foundation models for sparse 3D data, and support downstream applications in AR/VR, robotics, and autonomous driving.

Achieving pixel-level accurate segmentation of structural cracks across diverse scenarios remains a formidable challenge. Existing methods face significant bottlenecks in balancing crack topology modeling with computational efficiency, often failing to reconcile high segmentation quality with low resource demands. To address these limitations, we propose the Ultra-Compact Structure-Calibrated Vision RWKV (SCRWKV), a network that achieves high-precision modeling via a novel Structure-Field Encoder (SFE) backbone while maintaining linear complexity. The SFE integrates the Adaptive Multi-scale Cascaded Modulator (AMCM) to enhance texture representation and utilizes the Structure-Calibrated Insight Unit (SCIU) as its core engine. Specifically, the SCIU employs the Geometry-guided Bidirectional Structure Transformation (GBST) to capture topological correlations and integrates the Dynamic Self-Calibrating Decay (DSCD) into Dy-WKV to suppress noise propagation. Furthermore, we introduce a lightweight Cross-Scale Harmonic Fusion (CSHF) decoder to achieve precise feature aggregation. Systematic evaluations on multiple benchmarks characterized by complex textures and severe interference demonstrate that SCRWKV, with only 1.22M parameters, significantly outperforms SOTA methods. Achieving an F1 score of 0.8428 and mIoU of 0.8512 on the TUT dataset, the model confirms its robust potential for efficient real-world deployment. The code is available at https://github.com/zhxhzy/SCRWKV.

Test-time adaptation (TTA) has emerged as a promising paradigm for vision–language models (VLMs) to bridge the distribution gap between pre-training and test data. Recent works have focused on backpropagation-free TTA methods that rely on cache-based designs, but these introduce two key limitations. First, inference latency increases as the cache grows with the number of classes, leading to inefficiencies in large-scale settings. Second, suboptimal performance occurs when the cache contains insufficient or incorrect samples. In this paper, we present Prototype-Based Test-Time Adaptation (PTA), an efficient and effective TTA paradigm that uses a set of class-specific knowledge prototypes to accumulate knowledge from test samples. Particularly, knowledge prototypes are adaptively weighted based on the zero-shot class confidence of each test sample, incorporating the sample's visual features into the corresponding class-specific prototype. It is worth highlighting that the knowledge from past test samples is integrated and utilized solely in the prototypes, eliminating the overhead of cache population and retrieval that hinders the efficiency of existing TTA methods. This endows PTA with extremely high efficiency while achieving state-of-the-art performance on 15 image recognition benchmarks and 4 robust point cloud analysis benchmarks. For example, PTA improves CLIP’s accuracy from 65.64\% to 69.38\% on 10 cross-domain benchmarks, while retaining 92\% of CLIP’s inference speed on large-scale ImageNet-1K. In contrast, the cache-based TDA achieves a lower accuracy of 67.97\% and operates at only 50\% of CLIP’s inference speed.

3D Gaussian Splatting (3DGS) has been widely adopted for scene reconstruction, where training inherently constitutes a highly coupled and non-convex optimization problem. Recent works commonly incorporate geometric priors, such as LiDAR measurements, either for initialization or as training constraints, with the goal of improving photometric reconstruction quality. However, in large-scale outdoor scenarios, such geometric supervision is often spatially incomplete and uneven, which limits its effectiveness as a reliable prior and can even be detrimental to the final reconstruction. To address this challenge, we model partially observable geometry as a continuous energy field induced by geometric evidence and propose EnerGS. Rather than enforcing geometry as a hard constraint, EnerGS provides a soft geometric guidance for the optimization of Gaussian primitives, allowing geometric information to steer the optimization process without directly restricting the solution space. Extensive experiments on large-scale outdoor scenes demonstrate that, under both sparse multi-view and monocular settings, EnerGS consistently improves photometric quality and geometric stability, while effectively mitigating overfitting during 3DGS training. The codebase is publicly available at: https://github.com/ucla-mobility/EnerGS.

Text-to-3D generation has advanced rapidly, yet state-of-the-art models, encompassing both optimization-based and feed-forward architectures, still face two fundamental limitations. First, they struggle with coarse semantic alignment, often failing to capture fine-grained prompt details. Second, they lack robust 3D spatial understanding, leading to geometric inconsistencies and catastrophic failures in part assembly and spatial relationships. To address these challenges, we propose VLM3D, a general framework that repurposes large vision-language models (VLMs) as powerful, differentiable {semantic and spatial critics}. Our core contribution is a {dual-query critic signal} derived from the VLM's "Yes/No" log-odds, which assesses both semantic fidelity and geometric coherence. We demonstrate the generality of this guidance signal across two distinct paradigms: (1) As a reward objective for optimization-based pipelines, VLM3D significantly outperforms existing methods on standard benchmarks. (2) As a test-time guidance module for feed-forward pipelines, it actively steers the iterative sampling process of SOTA native 3D models to correct severe spatial errors. VLM3D establishes a principled and generalizable path to inject the VLM's rich, language-grounded understanding of both semantics and space into diverse 3D generative pipelines.

3D visual grounding requires robust cross-modal representation to achieve fine-grained semantic alignment and precise geometric reasoning. However, most methods employ unimodal pre-trained encoders that transfer visual and linguistic knowledge independently, inducing domain shift and poor cross-modal alignment. Meanwhile, spatial modeling with handcrafted priors limits cross-modal geometric representation, struggling to capture complex object relations due to spectral bias. To address these challenges, we propose Text-Aware Feature Tuning (TFT) and Decomposed Spectral Geometry (DSG) to enhance cross-modal semantic representation. Specifically, TFT injects linguistic context into the visual hierarchy to mitigate domain shift and facilitate early cross-modal alignment. DSG employs a learnable Fourier basis and explicitly decomposes pairwise relations into symmetric and antisymmetric spectral components, allowing the model to capture high-frequency geometric details and direction-aware relations for precise spatial reasoning. Extensive experiments on ScanRefer, Nr3D and Sr3D validate the effectiveness of our method, demonstrating state-of-the-art performance with improvements of 2.05\% Acc@0.25 for 3DREC and 1.09\% mIoU for 3DRES on ScanRefer.

Open-vocabulary 3D scene understanding answers free-form text queries over reconstructed scenes. However, lifting dense 2D foundation-model embeddings into 3D Gaussian Splatting (3DGS) is still challenging. Existing 3DGS-based methods often average normalized embeddings in Euclidean space. This ignores their hyperspherical geometry and can cause feature collapse. They also distill supervision from all views equally, which amplifies occlusion noise and mixed-depth artifacts. We propose **Rh-3DGS**, a robust semantic 3DGS framework that uses reliability-aware distillation and manifold-consistent aggregation. **Visibility-Calibrated Distillation (VCD)** computes per-pixel reliability weights from rasterization statistics and down-weights ambiguous pixels. **Visibility-Weighted Fréchet Mean (VFM)** aggregates embeddings on the unit hypersphere with a Riemannian Huber objective for robust distillation. **Lightweight Consistency Contrast (LIC)** regularizes the 3D semantic field with neighborhood-based multi-positive contrast to improve local consistency and sharper boundaries. Experiments on three benchmarks show that Rh-3DGS is best on open-vocabulary segmentation, boundary quality, and view-consistent rendering.

While linear-complexity attention mechanisms offer a promising alternative to Softmax attention for overcoming the quadratic bottleneck, training such models from scratch remains prohibitively expensive. Inheriting weights from pretrained Transformers provides an appealing shortcut, yet the fundamental representational gap between Softmax and linear attention prevents effective weight transfer. In this work, we address this conversion challenge from two perspectives: architectural alignment and representational alignment. We identify Test-Time Training (TTT) as a linear-complexity architecture whose two-layer dynamic formulation is structurally aligned with Softmax attention, enabling direct inheritance of pretrained attention weights. To further align representational properties, including key shift-invariance and locality, we introduce key instance normalization and a lightweight locality enhancement module. We validate our approach by linearizing Stable Diffusion 3.5 and introduce SD3.5-T$^5$ (Transformer To Test Time Training). With only 1 hour of fine-tuning on 4×H20 GPUs, SD3.5-T$^5$ achieves comparable text-to-image quality to the fine-tuned Softmax model, while accelerating inference by 1.32× and 1.47× at 1K and 2K resolutions. Code is available at this URL: https://github.com/LeapLabTHU/Transformer-to-TTT.

Point cloud data, with its inherent geometric and topological structures, plays a critical role in 3D vision tasks. However, existing parameter-efficient fine-tuning (PEFT) methods predominantly focus on input token prompting, overlooking the intrinsic geometric information. To address this limitation, we propose TopAdapter, a novel PEFT framework that enhances geometric perception by injecting local topological information into pre-trained 3D vision models. TopAdapter leverages 0D, 1D, and 2D simplices from algebraic topology as fundamental building blocks, introducing two core modules: the Topology Injection module (ToInjection) and the Topology Transfer module (ToTransfer). ToInjection constructs multi-scale topological features using a simplex generator and dynamically fuses them with semantic features via a geometric controller, thereby enhancing geometric adaptability. ToTransfer propagates these topological primitives across Transformer layers, ensuring efficient transmission of geometric information. Extensive experiments demonstrate that TopAdapter outperforms existing PEFT methods, achieving performance comparable to full fine-tuning across various benchmarks.

Point cloud registration can be categorized into rigid and non-rigid settings depending on the motion characteristics of the underlying objects. Rigid alignment assumes a single global transformation under which corresponding points remain geometrically consistent across scales, whereas non-rigid alignment involves spatially varying deformations, where geometric similarity holds only locally and semantic correspondence dominates at larger scales. This multi-scale discrepancy creates an optimization gap that has made unified registration particularly challenging. To this end, we propose RGGT, a Generative-Prior-Guided Transformer that unifies rigid and non-rigid registration within a shared optimization space. Through coordinated design at the representation, architecture, and supervision levels, RGGT jointly captures local geometric details and global structural semantics: generative priors enrich point features with unified geometric-semantic cues; a Global-Self-Cross Attention module models long-range structure, local interaction, and bidirectional cross-shape reasoning; and a dual correspondence-reconstruction objective provides consistent supervision for both deformation types. Extensive experiments on rigid (ModelNet40, 3DMatch, KITTI) and non-rigid (4DMatch) benchmarks demonstrate that RGGT achieves state-of-the-art accuracy across both rigid and non-rigid settings within a single unified framework. Code is available at https://github.com/zhengcy-lambo/RGGT.

Voxel-based 3D object detectors typically discretize the spatial domain using a uniform Cartesian grid, which allocates the same voxel size to both near-range and far-range regions. However, this uniform discretization is suboptimal for small objects such as pedestrians and cyclists, as they occupy only a few voxels and thus struggle to capture fine-grained geometric details. Although increasing the global voxel resolution can alleviate this problem, it inevitably increases substantial memory consumption and computational cost. In this paper, we propose Radial Scaling Voxelization (RSV), a simple yet effective non-uniform discretization strategy that adaptively modulates the effective voxel size based on the radial distance from the LiDAR sensor. Unlike previous cylindrical or polar discretization schemes, RSV preserves the Cartesian grid topology by applying a continuous radial scaling function to the input coordinates before standard voxelization. This operation yields a near-high, far-unchanged resolution pattern, i.e., the effective voxel size becomes finer in near regions, where the geometric structures of small objects are difficult to capture, while remaining nearly unchanged in far regions to avoid unnecessary computational cost. Importantly, RSV is architecture-agnostic and can directly replace the discretization module in any voxel-based detector without modifying the backbone, network design, or training pipeline. Extensive experiments on the KITTI and nuScenes datasets demonstrate that integrating our RSV into several voxel-based baselines consistently enhances small-object detection performance, especially for the Pedestrian and Cyclist categories, while incurring only marginal additional computational overhead. Code is available at https://github.com/Zeoy2020/RadialScalingVoxelization.

We present Layered Ray Intersections (LaRI), a fully supervised method for occluded geometry reasoning from a single image. Unlike conventional depth estimation, which is limited to visible surfaces, LaRI predicts multiple surfaces intersected by the camera rays using layered point maps. Compared to the existing approaches that leverage neural implicit representations or iterative refinement, LaRI achieves complete scene reconstruction in one feed-forward pass, enabling efficient and view-aligned geometric reasoning to underpin both object-level and scene-level tasks. We further propose to predict the ray stopping index, which identifies valid intersecting pixels and layers from LaRI's output. To better underpin and evaluate this task, we build an annotation pipeline using rendering engines, construct annotations for five public datasets, including synthetic and real-world data covering 3D objects and scenes. As a generic method, LaRI's performance is validated in object-level and scene-level reconstruction tasks.

Reconstructing 3D scenes using 3D Gaussian Splatting (3DGS) from sparse views is an ill-posed problem due to insufficient information, often resulting in noticeable artifacts. While recent approaches have sought to leverage generative priors to complete information for under-constrained regions, they struggle to generate content that remains consistent with input observations. To address this challenge, we propose GSFixer, a novel framework designed to improve the quality of 3DGS representations reconstructed from sparse inputs. The core of our approach is the reference-guided video restoration model, built upon a DiT-based video diffusion model trained on paired artifact 3DGS renders and clean frames with additional reference-based conditions. Considering the input sparse views as references, our model integrates both 2D semantic and 3D geometric features of reference views extracted from the visual geometry foundation model, enhancing the semantic coherence and 3D consistency when fixing artifact novel views. Furthermore, we introduce a reference-guided trajectory sampling strategy that ensures both angular coverage and view quality, further enhancing reconstruction fidelity. Considering the lack of suitable benchmarks for 3DGS artifact restoration evaluation, we present DL3DV-Res which contains artifact frames rendered using low-quality 3DGS. Extensive experiments demonstrate our GSFixer outperforms current state-of-the-art methods in 3DGS artifact restoration and sparse-view 3D reconstruction. Project page: https://github.com/GVCLab/GSFixer.

Recent progress in large-scale self-supervised learning has improved dense geometric prediction, but it remains unclear whether such scaling yields inference-time physical plausibility checks. We propose Scrambled Edges, a controlled counterfactual that injects salient edge-like cues while violating surface continuity, illumination coherence, and occlusion ordering. With energy-matched and structure-matched controls, we isolate the effect of unsupported edge evidence from high-frequency energy and edge sparsity. Across CNN/ViT/SSL depth predictors on NYU Depth v2 and KITTI, Scrambled Edges induce up to 3.2× larger deviation from clean predictions than energy-matched noise. The resulting Geometric Collapse propagates globally: even with oracle knowledge of the corrupted region, output-level repair recovers only 47%, with substantial error outside the mask. These findings provide controlled behavioral evidence that current dense predictors lack reliable mechanisms to quarantine physically unsupported edge cues, motivating explicit plausibility scoring and selective cue integration.

Alignment plays a fundamental role in many machine learning problems, such as multi-network analysis, multimodal learning, and point cloud registration. Recent works increasingly leverage optimal transport (OT) for distributional alignment, whose effectiveness largely depends on sparse supervision that is hard or costly to obtain in practice. Existing works, however, largely overlook how to actively acquire high-quality supervision to improve their alignment performance under OT frameworks. In this paper, we propose a principled active alignment framework for optimal transport alignment called AvAtar. We quantify the informativeness of a candidate by measuring its gradient-based impact on the global alignment result, computed as the gradient propagation from the global alignment result to all possible supervisions of the candidate through the entropy-regularized OT formulation. While differentiating through OT is challenging given its constrained nature, we leverage the adjoint-state method to reformulate the computation to a linear system solvable by the conjugate gradient method with linear complexity and guaranteed convergence. By encoding the global alignment result via effective utility functions, AvAtar is applicable to general alignment problems under the OT framework. Extensive experiments on three representative alignment tasks demonstrate the effectiveness, scalability, and generalizability of the proposed AvAtar.

The increasing scale and complexity of modern model parameters underscore the importance of pre-trained models. However, deployment often demands architectures of varying sizes, exposing limitations of conventional pre-training and fine-tuning. To address this, we propose SWEET, a self-supervised framework that performs constraint-based pre-training to enable scalable initialization in vision tasks. Instead of pre-training a fixed-size model, we learn a shared weight template and size-specific weight scalers under Tucker-based factorization, which promotes modularity and supports flexible adaptation to architectures with varying depths and widths. Target models are subsequently initialized by composing and reweighting the template through lightweight weight scalers, whose parameters can be efficiently learned from minimal training data. To further enhance flexibility in width expansion, we introduce width-wise stochastic scaling, which regularizes the template along width-related dimensions and encourages robust, width-invariant representations for improved cross-width generalization. Extensive experiments on classification, detection, segmentation and generation tasks demonstrate the state-of-the-art performance of SWEET for initializing variable-sized vision models.

Three-dimensional (3D) reasoning segmentation aims at segmenting target objects based on text instructions and 3D spatial cues. Recent efforts in 3D reasoning leverage Multimodal Large Language Models (MLLMs) to bridge the gap between text and 3D data. However, since MLLMs are primarily trained on text-image pairs, directly adapting them to unstructured 3D point clouds often fails to capture implicit semantic intent and reliably localize objects. This paper introduces TVDRNet to address these challenges. Inspired by Active Vision theory, where humans selectively choose optimal viewpoints to better observe targets, TVDRNet employs a differentiable renderer to simulate this active process in 3D perception. By using text instructions as supervision to optimize intrinsic and extrinsic rendering parameters, the TVDRNet identifies the optimal viewpoints for observing the 3D scene, and therefore learning 'where to look' based on what the text instruction 'asked to find'. This process generates informative, task-relevant 2D images that are compatible with MLLMs. TVDRNet comprises: (1) the AVPL module, establishing a learnable mapping from semantics to optimal rendering parameters; and (2) the MGL module, fusing multi-modalities via semantic grouping to guide mask generation. Experiments show TVDRNet achieves the state-of-the-art performance in 3D reasoning segmentation (Reason3D, Instruct3D) and 3D visual grounding (ScanRefer) benchmarks.

Entropic optimal transport (EOT) via Sinkhorn iterations is widely used in modern machine learning, yet GPU solvers remain inefficient at scale. Tensorized implementations suffer quadratic HBM traffic from dense $n\times m$ interactions, while existing online backends avoid storing dense matrices but still rely on generic tiled map-reduce reduction kernels with limited fusion. We present **FlashSinkhorn**, an IO-aware EOT solver for squared Euclidean cost that rewrites stabilized log-domain Sinkhorn updates as row-wise LogSumExp reductions of biased dot-product scores, the same normalization as transformer attention. This enables FlashAttention-style fusion and tiling: fused Triton kernels stream tiles through on-chip SRAM and update dual potentials in a single pass, substantially reducing HBM IO per iteration while retaining linear-memory operations. We further provide streaming kernels for transport application, enabling scalable first- and second-order optimization. On A100 GPUs, FlashSinkhorn achieves up to $32\times$ forward-pass and $161\times$ end-to-end speedups over state-of-the-art online baselines on point-cloud OT, improves scalability on OT-based downstream tasks. For reproducibility, we release an open-source implementation at https://github.com/ot-triton-lab/flash-sinkhorn.

Point clouds provide a compact and expressive representation of 3D objects, and have recently been integrated into multimodal large language models (MLLMs). However, existing methods primarily focus on static objects, while understanding dynamic point cloud sequences remains largely unexplored. This limitation is mainly caused by the lack of large-scale cross-modal datasets and the difficulty of modeling motions in spatio-temporal contexts. To bridge this gap, we present 4DPC$^2$hat, the *first* MLLM tailored for dynamic point cloud understanding. To this end, we construct a large-scale cross-modal dataset 4DPC$^2$hat-200K via a meticulous two-stage pipeline consisting of topology-consistent 4D point construction and two-level captioning. The dataset contains over 44K dynamic object sequences, 700K point cloud frames, and 200K curated question–answer (QA) pairs, supporting inquiries about counting, temporal relationship, action, spatial relationship, and appearance. At the core of the framework, we introduce a Mamba-enhanced temporal reasoning MLLM to capture long-range dependencies and dynamic patterns among a point cloud sequence. Furthermore, we propose a *failure-aware* bootstrapping learning strategy that iteratively identifies model deficiencies and generates targeted QA supervision to continuously strengthen corresponding reasoning capabilities. Extensive experiments demonstrate that our 4DPC$^2$hat significantly improves action understanding and temporal reasoning compared with existing models, establishing a strong foundation for 4D dynamic point cloud understanding.