CVPR 2026 论文列表

Humans constantly reason about 3D proximity, the relations between their body and surrounding objects, to guide perception and action in daily life. Whether multimodal large language models (MLLMs) can perform such embodied 3D reasoning remains unclear. To this end, we introduce EgoProx, a benchmark for egocentric 3D proximity reasoning. We organize our tasks along a cognitive chain, covering intention, exploration, exploitation, and chain-of-actions reasoning. We also design an agent based data engine that produces diverse and consistent QA pairs at scale. We benchmark prevailing MLLMs on EgoProx and conduct additional analyses with dataset specific and task specific instruction tuning. We observe large cross-domain gains, indicating that current MLLMs contain some spatial knowledge; however, they still struggle to effectively leverage it for spatial reasoning VQA.

We propose Delta Rectified Flow Sampling (DRFS), a novel inversion-free, path-aware editing framework within rectified flow models for text-to-image editing. DRFS is a distillation-based method that explicitly models the discrepancy between the source and target velocity fields in order to mitigate over-smoothing artifacts rampant in prior distillation sampling approaches. We further introduce a time-dependent shift term to push noisy latents closer to the target trajectory, enhancing the alignment with the target distribution. We theoretically demonstrate that disabling this shift recovers Delta Denoising Score (DDS), bridging score-based diffusion optimization and velocity-based rectified-flow optimization. Moreover, under rectified-flow dynamics, a linear shift schedule recovers the inversion-free method FlowEdit as a strict special case, yielding a unifying view of optimization and ODE editing. We conduct an analysis to guide the design of our shift term, and experimental results on the widely used PIE Benchmark indicate that DRFS achieves superior editing quality, fidelity, and controllability while requiring no architectural modifications. Code is available at https://github.com/Harvard-AI-and-Robotics-Lab/DeltaRectifiedFlowSampling.

We propose VIAFormer, a Voxel-Image Alignment transFormer model designed for Multi-view Conditioned Voxel Refinement--the task of repairing incomplete noisy voxels using calibrated multi-view images as guidance. Its effectiveness stems from a synergistic design: an Image Index that provides explicit 3D spatial grounding for 2D image tokens, a Correctional Flow objective that learns a direct voxel-refinement trajectory, and a Hybrid Stream Transformer that enables robust cross-modal fusion. Experiments show that VIAFormer establishes a new state of the art in correcting both severe synthetic corruptions and realistic artifacts on the voxel shape obtained from powerful Vision Foundation Models. Beyond benchmarking, we demonstrate VIAFormer as a practical and reliable bridge in real-world 3D creation pipelines, paving the way for voxel-based methods to thrive in large-model, big-data wave.

Current vision-language pre-training (VLP) paradigms excel at global scene understanding but struggle with instance-level reasoning due to global-only supervision. We introduce InstAP, an Instance-Aware Pre-training framework that jointly optimizes global vision-text alignment and fine-grained, instance-level contrastive alignment by grounding textual mentions to specific spatial-temporal regions. To support this, we present InstVL, a large-scale dataset (2 million images, 50,000 videos) with dual-granularity annotations: holistic scene captions and dense, grounded instance descriptions. On the InstVL benchmark, InstAP substantially outperforms existing VLP models on instance-level retrieval, and also surpasses a strong VLP baseline trained on the exact same data corpus, isolating the benefit of our instance-aware objective. Moreover, instance-centric pre-training improves global understanding: InstAP achieves competitive zero-shot performance on multiple video benchmarks, including MSR-VTT and DiDeMo. Qualitative visualizations further show that InstAP localizes textual mentions to the correct instances, while global-only models exhibit more diffuse, scene-level attention.

Learning 3D scene geometry and semantics from images is a core challenge in computer vision and a key capability for autonomous driving. Since large-scale 3D annotation is prohibitively expensive, recent work explores self-supervised learning directly from sensor data without manual labels. Existing approaches either rely on 2D rendering consistency, where 3D structure emerges only implicitly, or on discretized voxel grids from accumulated lidar point clouds, limiting spatial precision and scalability. We introduce QueryOcc, a query-based self-supervised framework that learns continuous 3D semantic occupancy directly through independent 4D spatio-temporal queries sampled across adjacent frames. The framework supports supervision from either pseudo-point clouds derived from vision foundation models or raw lidar data. To enable long-range supervision and reasoning under constant memory, we introduce a contractive scene representation that preserves near-field detail while smoothly compressing distant regions.QueryOcc surpasses previous camera-based methods by 26% in semantic RayIoU on the self-supervised Occ3D-nuScenes benchmark while running at 11.6 FPS, demonstrating that direct 4D query supervision enables strong self-supervised occupancy learning.

Co-salient Object Detection (CoSOD) aims to segment salient objects that consistently appear across a group of related images. Despite the notable progress achieved by recent training-based approaches, they still remain constrained by the closed-set datasets and exhibit limited generalization. However, few studies explore the potential of Vision Foundation Models (VFMs) to address CoSOD, which demonstrate a strong generalized ability and robust saliency understanding. In this paper, we investigate and leverage VFMs for CoSOD, and further propose a novel training-free method, TF-SSD, through the synergy between SAM and DINO. Specifically, we first utilize SAM to generate comprehensive raw proposals, which serve as a candidate mask pool. Then, we introduce a quality mask generator to filter out redundant masks, thereby acquiring a refined mask set. Since this generator is built upon SAM, it inherently lacks semantic understanding of saliency. To this end, we adopt an intra-image saliency filter that employs DINO's attention maps to identify visually salient masks within individual images. Moreover, to extend saliency understanding across group images, we propose an inter-image prototype selector, which computes similarity scores among cross-image prototypes to select masks with the highest score. These selected masks serve as final predictions for CoSOD. Extensive experiments show that our TF-SSD outperforms existing methods (e.g., 13.7% gains over the recent training-free method). Codes are available at https://github.com/hzz-yy/TF-SSD.

Vision-language models (VLMs) struggle with 3D-related tasks such as spatial cognition and physical understanding, which are crucial for real-world applications like robotics and embodied agents. We attribute this to a modality gap between the 3D tasks and the 2D training of VLM, which led to inefficient retrieval of 3D information from 2D input. To bridge this gap, we introduce SandboxVLM, a simple yet effective framework that leverages abstract bounding boxes to encode geometric structure for VLMs. Specifically, we design a 3D Sandbox reconstruction and perception pipeline comprising four stages: generating multi-view priors with abstract control, proxy elevation, multi-view voting and clustering, and 3D-aware reasoning. Evaluated in zero-shot settings across multiple benchmarks and VLM backbones, our approach consistently improves spatial intelligence, achieving an 8.3% gain on SAT Real compared with baseline methods for instance. These results demonstrate that presenting VLMs with 3D abstractions substantially enhances their 3D reasoning ability without additional training, suggesting new possibilities for general-purpose embodied intelligence.

The integration of Vision-Language Models (VLMs) into autonomous driving promises to solve long-tail scenarios, but this paradigm faces the critical and unaddressed challenge of catastrophic forgetting. The very fine-tuning process used to adapt these models to driving-specific data simultaneously erodes their invaluable pre-trained world knowledge, creating a self-defeating paradox that undermines the core reason for their use. This paper provides the first systematic investigation into this phenomenon. We introduce a new large-scale dataset of 180K scenes, which enables the first-ever benchmark specifically designed to quantify catastrophic forgetting in autonomous driving. Our analysis reveals that existing methods suffer from significant knowledge degradation. To address this, we propose the Drive Expert Adapter (DEA), a novel framework that circumvents this trade-off by shifting adaptation from the weight space to the prompt space. DEA dynamically routes inference through different knowledge experts based on scene-specific cues, enhancing driving-task performance without corrupting the model's foundational parameters. Extensive experiments demonstrate that our approach not only achieves state-of-the-art results on driving tasks but also effectively mitigates catastrophic forgetting, preserving the essential generalization capabilities that make VLMs a transformative force for autonomous systems. Dataset and code will be released.

Recent unified models have made remarkable strides in generating high-quality images, yet they consistently fail on reasoning-intensive tasks, i.e., solving mazes, assembling tangrams. Intriguingly, we find that vision-language models (VLMs) and large language models (LLMs) can accurately solve these tasks, but cannot generate the corresponding images because they lack a structured visual output interface. This reveals that the core bottleneck is not reasoning capacity, but the lack of a structured interface to translate high-level reasoning into precise visual output. To bridge this gap, we propose using code-structured visual hints (i.e., SVG/HTML) overlays that explicitly encode reasoning steps directly on the image plane. Accordingly, we develop an automatic data construction pipeline that can generate high-quality code-structured hints for existing datasets and train a unified model called Hint2Gen based on FLUX.1 Kontext to condition its generation on such hints. Furthermore, to comprehensively evaluate the effectiveness of our approach, we introduce Reason2Gen, a benchmark comprising 4,000 samples spanning 20 categories across 7 core dimensions, including path connectivity, spatial assembly, etc. Extensive experiments demonstrate that even simply providing such hints as extra inputs--without any retraining--boosts their performance. And our model significantly outperforms all leading open-source/closed-source methods on reasoning-aware generation and editing across all the dimensions.

Large vision-language models (VLMs) still struggle with reliable 3D spatial reasoning, a core capability for embodied and physical AI systems. This limitation arises from their inability to capture fine-grained 3D geometry and spatial relationships. While recent efforts have introduced multi-view geometry transformers into VLMs, they typically fuse only the deep-layer features from vision and geometry encoders, discarding rich hierarchical signals and creating a fundamental bottleneck for spatial understanding. To overcome this, we propose SpatialStack, a general hierarchical fusion framework that progressively aligns vision, geometry, and language representations across the model hierarchy. Moving beyond conventional late-stage vision-geometry fusion, SpatialStack stacks and synchronizes multi-level geometric features with the language backbone, enabling the model to capture both local geometric precision and global contextual semantics. Building upon this framework, we develop VLM-SpatialStack, a model that achieves state-of-the-art performance on multiple 3D spatial reasoning benchmarks. Extensive experiments and ablations demonstrate that our multi-level fusion strategy consistently enhances 3D understanding and generalizes robustly across diverse spatial reasoning tasks, establishing SpatialStack as an effective and extensible design paradigm for vision-language-geometry integration in next-generation multimodal physical AI systems.

Existing hand-object interactions (HOI) methods are largely limited to rigid objects, while 4D reconstruction methods of articulated objects generally require pre-scanning the object or even multi-view videos. It remains an unexplored but significant challenge to reconstruct 4D human-articulated-object interactions from a single monocular RGB video. Fortunately, recent advancements in foundation models present a new opportunity to address this highly ill-posed problem. To this end, we introduce ArtHOI, an optimization-based framework that integrates and refines priors from multiple foundation models. Our key contribution is a suite of novel methodologies designed to resolve the inherent inaccuracies and physical unreality of these priors. In particular, we introduce an Adaptive Sampling Refinement (ASR) method to optimize object's metric scale and pose for grounding its normalized mesh in world space. Furthermore, we propose a Multimodal Large Language Model (MLLM) guided hand-object alignment method, utilizing contact reasoning information as constraints of hand-object mesh composition optimization. To facilitate a comprehensive evaluation, we also contribute two new datasets, ArtHOI-RGBD and ArtHOI-Wild. Extensive experiments validate the robustness and effectiveness of our ArtHOI across diverse objects and interactions. Project: https://arthoi-reconstruction.github.io.

Physical AI aims to develop models that can perceive and predict real-world dynamics; yet, the extent to which current multi-modal large language models and video generative models support these abilities is insufficiently understood. We introduce Physical AI Bench (PAI-Bench), a unified and comprehensive benchmark that evaluates perception and prediction capabilities across video generation, conditional video generation, and video understanding, comprising 2,808 real-world cases with task-aligned metrics designed to capture physical plausibility and domain-specific reasoning. Our study provides a systematic assessment of recent models and shows that video generative models, despite strong visual fidelity, often struggle to maintain physically coherent dynamics, while multi-modal large language models exhibit limited performance in forecasting and causal interpretation. These observations suggest that current systems are still at an early stage in handling the perceptual and predictive demands of Physical AI. In summary, PAI-Bench establishes a realistic foundation for evaluating Physical AI and highlights key gaps that future systems must address.

The Visual Geometry Grounded Transformer (VGGT) marks a significant leap forward in 3D scene reconstruction, as it is the first model that directly infers all key 3D attributes (camera poses, depths, and dense geometry) jointly in one pass. However, this joint inference mechanism requires global attention layers that perform all-to-all attention computation on tokens from all views. For reconstruction of large scenes with long-sequence inputs, this causes a significant latency bottleneck. In this paper, we propose head-wise temporal merging (HTTM), a training-free 3D token merging method for accelerating VGGT. Existing merging techniques merge tokens uniformly across different attention heads, resulting in identical tokens in the layers' output, which hinders the model's representational ability. HTTM tackles this problem by merging tokens in multi-head granularity, which preserves the uniqueness of feature tokens after head concatenation. Additionally, this enables HTTM to leverage the spatial locality and temporal correspondence observed at the head level to achieve higher merging ratios with lower merging costs compared to existing methods. Thus, HTTM achieves up to 7x acceleration with negligible performance drops in a GPU-based inference.

Despite the remarkable progress of Multimodal Large Language Models (MLLMs) in 2D vision-language tasks, their application to complex 3D scene manipulation remains underexplored. In this paper, we bridge this critical gap by tackling three key challenges in 3D object arrangement task using MLLMs. First, to address the weak visual grounding of MLLMs, which struggle to link programmatic edits with precise 3D outcomes, we introduce an MCP-based API. This shifts the interaction from brittle raw code manipulation to more robust, function-level updates. Second, we augment the MLLM's 3D scene understanding with a suite of specialized visual tools to analyze scene state, gather spatial information, and validate action outcomes. This perceptual feedback loop is critical for closing the gap between language-based updates and precise 3D-aware manipulation. Third, to manage the iterative, error-prone updates, we propose a collaborative multi-agent framework with designated roles for planning, execution, and verification. This decomposition allows the system to robustly handle multi-step instructions and recover from intermediate errors. We demonstrate the effectiveness of our approach on a diverse set of 25 complex object arrangement tasks, where it significantly outperforms existing baselines.

Face Anti-Spoofing (FAS) typically depends on a single visual modality when defending against presentation attacks such as print attacks, screen replays, and 3D masks, resulting in limited generalization across devices, environments, and attack types. Meanwhile, Multimodal Large Language Models (MLLMs) have recently achieved breakthroughs in image-text understanding and semantic reasoning, suggesting that integrating visual and linguistic co-inference into FAS can substantially improve both robustness and interpretability. However, the lack of a high-quality vision-language multimodal dataset has been a critical bottleneck. To address this, we introduce FaceCoT (Face Chain-of-Thought), the first large-scale Visual Question Answering (VQA) dataset tailored for FAS. FaceCoT covers 14 spoofing attack types and enriches model learning with high-quality CoT VQA annotations. Meanwhile, we develop a caption model refined via reinforcement learning to expand the dataset and enhance annotation quality. Furthermore, we introduce a CoT-Enhanced Progressive Learning (CEPL) strategy to better leverage the CoT data and boost model performance on FAS tasks. Extensive experiments demonstrate that models trained with FaceCoT and CEPL outperform state-of-the-art methods on multiple benchmark datasets.

Estimating the 3D pose of unseen objects from a single image remains a fundamental yet challenging problem in computer vision, especially under a CAD model-free setting.Pioneering attempts address this issue by matching templates generated through Novel View Synthesis (NVS), which essentially aims to learn the geometric transformation from a reference to a target view. While promising, these methods can only approximate this transformation under pixel-level supervision, as the starting orientation remains undefined. In the absence of explicit geometric constraints to verify the correctness of the predicted transformation, existing methods often synthesize novel views with geometry-distorted structures or severely blurred local textures, leading to unreliable template matching and suboptimal pose estimation results. To this end, we propose OrienPose, a novel object pose estimation framework via orientation-aware NVS from a single image. Specifically, we introduce the Orientation-Aware Guidance, which explicitly injects object orientation cues into the reference latent embedding to enhance orientation awareness during viewpoint transformation. We also introduce an orientation consistency loss that supervises viewpoint transformation at the geometric level, establishing sufficient supervision for explicit and geometry-consistent transformation guidance beyond pixel-level similarity. This loss justifies estimating the reference orientation rather than using its ground-truth pose, thereby ensuring the alignment of coordinate domains between the injected and supervised priors. Extensive experiments demonstrate that OrienPose achieves state-of-the-art performance in single-view unseen object pose estimation and impressive robustness to image degradations. Our code is available at https://github.com/pubyLu/OrienPose.

Open-vocabulary semantic segmentation (OVSS) aims to segment arbitrary category regions in images using open-vocabulary prompts, necessitating that existing methods possess pixel-level vision-language alignment capability. Typically, this capability involves computing the cosine similarity, ie, logits, between visual and linguistic features, and minimizing the distribution discrepancy between the logits and the ground truth (GT) to generate optimal logits that are subsequently used to construct segmentation maps, yet it depends on time-consuming iterative training or model-specific attention modulation. In this work, we propose a more direct approach that eschews the logits-optimization process by directly deriving an analytic solution for the segmentation map. We posit a key hypothesis: the distribution discrepancy encodes semantic information; specifically, this discrepancy exhibits consistency across patches belonging to the same category but inconsistency across different categories. Based on this hypothesis, we directly utilize the analytic solution of this distribution discrepancy as the semantic maps. In other words, we reformulate the optimization of the distribution discrepancy as deriving its analytic solution, thereby eliminating time-consuming iterative training, freeing us from model-specific attention modulation, and achieving state-of-the-art performance on eight benchmark datasets.

The rapid development of large vision-language model (VLM) has greatly promoted the research of GUI agent. However, GUI agents still face significant challenges in handling long-horizon tasks. First, single-agent models struggle to balance high-level capabilities and low-level execution capability, facing prevalent issues of responsibility coupling and capability conflicts. Second, agents lack awareness of the task state, leading to progress loss in long-horizon tasks. To address these challenges, we propose a staged execution-feedback reinforcement learning algorithm. Unlike training a unified policy model, we focus on training high-level scheduling models. Specifically, we propose and train two agents: a Coordinator, responsible for the strategic planning and task decomposition; and a State Tracker, responsible for context compression and information management to maintain the task's state and coherence. Based on this, we built the Coordinator-Executor-State Tracker (CES) multi-agent framework, which can be integrated with any low-level Executor model, assisting the Executor in solving long-horizon tasks through task scheduling and state management. Experiments on long-horizon task benchmarks demonstrate that CES significantly enhances the system's planning and state management capabilities. Furthermore, analysis confirms that our trained high-level scheduling module is a generalizable, plug-and-play module that significantly enhances the long-horizon capabilities of various Executors.

Large vision-language models (LVLMs) have shown remarkable capabilities in visual-language understanding. Despite their success, LVLMs still suffer from generating hallucinations in complex generation tasks, leading to inconsistencies between visual inputs and generated content. To address this issue, some approaches have introduced inference-time interventions, such as contrastive decoding, to reduce overreliance on language priors. However, these approaches overlook hallucinations stemming from position bias and spurious inter-modality correlations. In this paper, we propose a Cross-Modal Attention Calibration (CMAC) method to mitigate hallucinations in LVLMs in a training-free manner. In this method, we design an Inter-Modality Decoding (IMD) module to alleviate hallucination by a novel contrastive decoding mechanism. IMD masks the value vectors associated with significant cross-modal attention weights as distortion, which addresses both uni-modality overreliance and misleading inter-modality correlations. Additionally, a Cross-Modal Position Calibration (CMPC) module shrinks the position gap of image tokens, alleviating the position bias in cross-modal attention. Experimental results on diverse hallucination benchmarks validate the superiority of our method over existing state-of-the-art techniques in reducing hallucinations for LVLM. Our code will be available.