CVPR 2026 Papers

Monocular 3D Object Detection has achieved impressive performance on densely annotated datasets. However, it struggles when only a fraction of objects are labeled due to the high cost of 3D annotation. This sparsely-annotated setting is common in real-world scenarios where annotating every object is impractical.To address this, we propose a novel framework for sparsely-annotated monocular 3D object detection with two key modules.First, we propose Road-Aware Patch Augmentation (RAPA), which leverages sparse annotations by augmenting segmented object patches onto road regions while preserving 3D geometric consistency. Second, we propose Prototype-Based Filtering (PBF), which generates high-quality pseudo-labels by filtering predictions through prototype similarity and depth uncertainty. PBF maintains global 2D RoI feature prototypes and selects pseudo-labels that are both feature-consistent with learned prototypes and have reliable depth estimates.Our training strategy combines geometry-preserving augmentation with prototype-guided pseudo-labeling to achieve robust detection under sparse supervision.Extensive results demonstrate the effectiveness of the proposed method. The source code will be publicly available.

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.

Audio-visual navigation enables embodied agents to navigate toward sound-emitting targets by leveraging both auditory and visual cues. However, most existing approaches rely on precomputed room impulse responses (RIRs) for binaural audio rendering, restricting agents to discrete grid positions and leading to spatially discontinuous observations. To establish a more realistic setting, we introduce Semantic Audio-Visual Navigation in Continuous Environments (SAVN-CE), where agents can move freely in 3D spaces and perceive temporally and spatially coherent audio-visual streams. In this setting, targets may intermittently become silent or stop emitting sound entirely, causing agents to lose goal information. To tackle this challenge, we propose MAGNet, a multimodal transformer-based model that jointly encodes spatial and semantic goal representations and integrates historical context with self-motion cues to enable memory-augmented goal reasoning. Comprehensive experiments demonstrate that MAGNet significantly outperforms state-of-the-art methods, achieving up to a 12.1% absolute improvement in success rate. These results also highlight its robustness to short-duration sounds and long-distance navigation scenarios. The code is available at https://github.com/yichenzeng24/SAVN-CE.

Despite remarkable progress, multimodal foundation models still exhibit surprising deficiencies in spatial intelligence. In this work, we explore scaling up multimodal foundation models to cultivate spatial intelligence within the SenseNova-SI family, built upon established multimodal foundations including visual understanding models (i.e., Qwen3-VL and InternVL3) and unified understanding and generation models (i.e., Bagel). We take a principled approach to constructing high-performing and robust spatial intelligence by systematically curating SenseNova-SI-8M: eight million diverse data samples under a rigorous taxonomy of spatial capabilities. SenseNova-SI demonstrates unprecedented performance across a broad range of spatial intelligence benchmarks: 68.8% on VSI-Bench, 43.3% on MMSI, 85.7% on MindCube, 54.7% on ViewSpatial, 47.7% on SITE, 63.9% on BLINK, 55.5% on 3DSR, and 72.0% on EmbSpatial, while maintaining strong general multimodal understanding (e.g., 84.9% on MMBench-En). More importantly, we analyze the impact of data scaling, discuss early signs of emergent generalization capabilities enabled by diverse data training, analyze the risk of overfitting and language shortcuts, present a preliminary study on spatial chain-of-thought reasoning, and validate the potential downstream application. All newly trained multimodal foundation models are publicly released.

High-quality pixel-level responses remain a major bottleneck for multimodal large language models (MLLMs) in regional perception. Existing approaches generally attach regression decoders to MLLM features, achieving strong grounding performance but compromising end-to-end design and increasing training costs. Researchers have applied parameter and data scaling to improve pure MLLMs' ability to generate pixel coordinates in natural language, yet the performance gains on grounding tasks remain markedly weaker than those in standard QA tasks. Our analysis shows the primary bottleneck is that conventional scaling fails to effectively enhance the key reasoning stage required for pixel-level regional perception. To address this, we propose R-Ground, a reasoning framework for MLLM-based grounding built upon a multimodal Monte Carlo Tree Search algorithm. R-Ground leverages structured reasoning actions, multimodal feature alignment scoring, and regional feature weighted voting to perform scaling at the designated reasoning stage. Extensive experiments demonstrate that R-Ground achieves effective reasoning scaling, enabling a 7B MLLM to match or even surpass a 72B model on the grounding task.

Visual Text Rendering (VTR) remains a critical challenge in text-to-image generation, where even advanced models frequently produce text with structural anomalies such as distortion, blurriness, and misalignment. However, we find that leading MLLMs and specialist OCR models largely fail to perceive these structural anomalies, creating a critical bottleneck for both VTR evaluation and RL-based optimization. As a result, even state-of-the-art generators (e.g., SeedDream4.0, Qwen-Image) still struggle to render structurally faithful text. To address this, we propose TextPecker, a plug-and-play structural anomaly perceptive RL strategy that mitigates noisy reward signals and works with any text-to-image generator. To enable this capability, we construct a recognition dataset with character-level structural-anomaly annotations and develop a stroke-editing synthesis engine to expand structural-error coverage. Experiments show that TextPecker consistently improves diverse text-to-image models; even on the well-optimized Qwen-Image, it significantly yields average gains of 4% in structural fidelity and 8.7% in semantic alignment for Chinese text rendering, establishing a new state-of-the-art in high-fidelity VTR. Our work fills a gap in VTR optimization, providing a foundational step towards reliable and structural faithful visual text generation.

Humans often resolve visual uncertainty by comparing an image with relevant examples, but ViTs lack the ability to identify which examples would improve their predictions. We present Task-Aligned Context Selection (TACS), a framework that learns to select paired examples which truly improve task performance rather than those that merely appear similar. TACS jointly trains a selector network with the task model through a hybrid optimization scheme combining gradient-based supervision and reinforcement learning, making retrieval part of the learning objective. By aligning selection with task rewards, TACS enables discriminative models to discover which contextual examples genuinely help. Across 18 datasets covering fine-grained recognition, medical image classification, and medical image segmentation, TACS consistently outperforms similarity-based retrieval, particularly in challenging or data-limited settings.

Pretrained vision encoders are widely used as frozen, black-box feature extractors, yet they often inherit spurious correlations that disproportionately harm underrepresented groups. We introduce PLD-Debias, a fully black-box debiasing framework that requires neither access to backbone parameters nor demographic annotations. Our method integrates three components: (1) Rank-Regularized Amplification, a lightweight adapter that exaggerates latent spurious directions; (2) Unsupervised Pseudo-Bias Induction, which clusters amplified features to infer high-fidelity proxy bias labels; and (3) Bias-Guided Refinement, combining supervised contrastive alignment with cluster-aware adaptive margins to purify representations and equalize decision boundaries. We theoretically show that these components jointly tighten a worst-group risk bound under spurious correlations. Empirically, PLD-Debias achieves state-of-the-art worst-group accuracy across CelebA, Waterbirds, and CMNIST, improving performance by 3-5 points over prior black-box methods while maintaining average accuracy. Remarkably, our pseudo-bias labels align with ground-truth bias annotations at over 90% fidelity, enabling oracle-level robustness without demographic supervision. Our results demonstrate that fairness and utility can be achieved through a plug-and-play classifier adapter for any frozen foundation model.

Progress in object detection benchmarks is stagnating. It is limited not by architectures but by the inability to distinguish model improvements from label noise. To restore trust in benchmarking the field requires rigorous quantification of annotation consistency to ensure the reliability of evaluation data. However, standard statistical metrics fail to handle the instance correspondence problem inherent to vision tasks. Furthermore, validating new agreement metrics remains circular because no objective ground truth for agreement exists. This forces reliance on unverifiable heuristics. We propose K\alphaLOS, a unified meta-algorithm that generalizes the "Localization First" principle to standardize dataset quality evaluation. By resolving spatial correspondence before assessing agreement, our framework transforms complex spatio-categorical problems into nominal reliability matrices. Unlike prior heuristic implementations, K\alphaLOS employs a principled, data-driven configuration; by statistically calibrating the localization parameters to the inherent agreement distribution, it generalizes to diverse tasks ranging from bounding boxes to volumetric segmentation or pose estimation. This standardization enables granular diagnostics beyond a single score. These include annotator vitality, collaboration clustering, and localization sensitivity. To validate this approach, we introduce a novel and empirically derived noise generator. Where prior validations relied on uniform error assumptions, our controllable testbed models complex and non-isotropic human variability. This provides evidence of the metric's properties and establishes K\alphaLOS as a robust standard for distinguishing signal from noise in modern computer vision benchmarks.

We propose a federated framework for training diffusion models on decentralized and private datasets. The method learns a shared generative model alongside personalized client models, allowing clients to benefit from cross-client structure while ensuring that the shared model cannot reproduce any client's data on its own. We provide formal differential privacy guarantees for each client and establish utility bounds for conditional generation under a Gaussian mixture model, showing that collaboration improves sample quality relative to private non-collaborative training. Experiments on CIFAR-10, Colorized MNIST, and CelebA support these results: the method generates high-fidelity samples, improves performance on minority and underrepresented classes, and maintains strong protection against membership inference, memorization, and reconstruction attacks.

YOLO detectors are known for their fast inference speed, yet training them remains unexpectedly time-consuming due to their exhaustive pipeline that processes every training image in every epoch, even when many images have already been sufficiently learned. This stands in clear contrast to the efficiency suggested by the "You Only Look Once" philosophy. This naturally raises an important question: Does YOLO really need to see every training image in every epoch? To explore this, we propose an Anti-Forgetting Sampling Strategy (AFSS) that dynamically determines which images should be used and which can be skipped during each epoch, allowing the detector to learn more effectively and efficiently. Specifically, AFSS measures the learning sufficiency of each training image as the minimum of its detection recall and precision, and dynamically categorizes training images into easy, medium, or hard levels accordingly. Easy training images are sparsely resampled during training in a continuous review manner, with priority given to those that have not been used for a long time to reduce redundancy and prevent forgetting. Moderate training images are partially selected, prioritizing recently unused ones and randomly choosing the rest from unselected images to ensure coverage and prevent forgetting. Hard training images are fully sampled in every epoch to ensure sufficient learning. The learning sufficiency of each training image is periodically updated, enabling detectors to adaptively shift its focus toward the informative training images over time while progressively discarding redundant ones. On widely used natural image detection benchmarks (MS COCO 2017 and PASCAL VOC 2007) and remote sensing detection datasets (DOTA-v1.0 and DIOR-R), AFSS achieves more than 1.43x training speedup for YOLO-series detectors while also improving accuracy.

Large 3D reconstruction models have revolutionized the 3D content generation field, enabling broad applications in virtual reality and gaming. Just like other large models, large 3D reconstruction models suffer from hallucinations as well, introducing structural outliers (e.g., odd holes or protrusions) that deviate from the input data. However, unlike other large models, hallucinations in large 3D reconstruction models remain severely underexplored, leading to malformed 3D-printed objects or insufficient immersion in virtual scenes. Such hallucinations majorly originate from that existing methods reconstruct 3D content from sparsely generated multi-view images which suffer from large viewpoint gaps and discontinuities. To mitigate hallucinations by eliminating the outliers, we propose Dehallu3D for 3D mesh generation. Our key idea is to design a balanced multi-view continuity constraint to enforce smooth transitions across dense intermediate viewpoints, while avoiding over-smoothing that could erase sharp geometric features. Therefore, Dehallu3D employs a plug-and-play optimization module with two key constraints: (i) adjacent consistency to ensure geometric continuity across views, and (ii) adaptive smoothness to retain fine details. We further propose the Outlier Risk Measure (ORM) metric to quantify geometric fidelity in 3D generation from the perspective of outliers. Extensive experiments show that Dehallu3D achieves high-fidelity 3D generation by effectively preserving structural details while removing hallucinated outliers.

Computational pathology has advanced rapidly in recent years, driven by domain-specific image encoders and growing interest in using vision-language models to answer natural-language questions about diseases. Yet, the core problem behind pathology question-answering remains unsolved, considering that a gigapixel slide contains far more information than necessary for a given question. Pathologists naturally navigate tissue and morphology complexity by scanning broadly, and zooming in selectively according to the clinical questions. Current models, in contrast, rely on uniform patch sampling or broad attention maps, often attending equally to irrelevant regions while overlooking key visual evidence. In this work, we try to bring models closer to how humans actually examine slides. We propose a question-guided, tissue-aware, and coarse-to-fine retrieval framework, HistoSelect, that consists of two key components: a group sampler that identifies question-relevant tissue regions, followed by a patch selector that retrieves the most informative patches within those regions. By selecting only the most informative patches, our method becomes significantly more efficient: reducing visual token usage by 70% on average, while improving accuracy across three pathology QA tasks. Evaluated on 356,000 question-answer pairs, our approach outperforms existing methods and produces answers grounded in interpretable, pathologist-consistent regions. Our results suggest that bringing human-like search and attention patterns into WSI reasoning is a promising direction for building practical and reliable pathology VLMs. Code is available at https://github.com/winston52/HistoSelect.

The rapid growth of AI-generated imagery has blurred the boundary between real and synthetic content, raising practical concerns for digital integrity. Vision-language models (VLMs) can provide natural language explanations, but standard one-pass classifiers often miss subtle artifacts in high-quality synthetic images and offer limited grounding in the pixels. We propose Locate-Then-Examine (LTE), a two-stage VLM-based forensic framework that first localizes suspicious regions and then re-examines these crops together with the full image to refine the real vs. AI-generated verdict and its explanation. LTE explicitly links each decision to localized visual evidence through region proposals and region-aware reasoning. To support training and evaluation, we introduce TRACE, a dataset of 20,000 real and high-quality synthetic images with region-level annotations and automatically generated forensic explanations, constructed by a VLM-based pipeline with additional consistency checks and quality control. Across TRACE and multiple external benchmarks, LTE achieves competitive accuracy and improved robustness while providing human-understandable, region-grounded explanations suitable for forensic deployment.

Time-intensive performance evaluations significantly impede progress in Neural Architecture Search (NAS). To address this, neural predictors leverage surrogate models trained on proxy datasets, allowing for direct performance predictions for new architectures.However, these predictors often exhibit poor generalization due to their limited ability to capture intricate relationships among various architectures. In this paper, we propose HyperNAS, a novel neural predictor paradigm for enhancing architecture representation learning. HyperNAS consists of two primary components: a global encoding scheme and a shared hypernetwork. The global encoding scheme is devised to capture the comprehensive macro-structure information, while the shared hypernetwork serves as an auxiliary task to enhance the investigation of inter-architecture patterns. To ensure training stability, we further develop a dynamic adaptive multi-task loss to facilitate personalized exploration on the Pareto front. Extensive experiments across five representative search spaces, including ViTs, demonstrate the advantages of HyperNAS, particularly in few-shot scenarios. For instance, HyperNAS strikes new state-of-the-art results, with 97.60% top-1 accuracy on CIFAR-10 and 82.4% top-1 accuracy on ImageNet, using at least 5.0xfewer samples.

Caching-based acceleration methods have recently driven significant progress in efficient video generation with diffusion models. However, we identify a critical limitation when directly applying these acceleration techniques to auto-regressive video diffusion models, which generate long videos by sequentially synthesizing segments conditioned on historical context. In such settings, any approximation errors introduced by acceleration tend to propagate and accumulate over time, resulting in severe error accumulation and progressive degradation of video quality. To address this challenge, we propose ARCache, the first training-free caching-based acceleration framework specifically designed for auto-regressive video diffusion models. ARCache improves both the timing and quality of caching through two key components. First, History-Guided Cache (HGC) leverages historical information to adaptively schedule caching for each segment, enabling more accurate and efficient cache utilization. Second, Enhanced Residual Correction (ERC) adaptively refines the residual trajectory for subsequent segments, effectively mitigating error accumulation while introducing minimal computational overhead. Extensive experiments on FramePack-F1, SkyReels-V2, and auto-regressive world model Matrix-Game demonstrate that ARCache achieves state-of-the-art acceleration and visual fidelity.

Even when told to "do nothing," modern diffusion models subtly alter their output relative to the input they are supposed to preserve. We call this effect No-Op Drift. We introduce the Drift Kernel K_M(sigma), defined as the expected perceptual deviation induced when running a diffusion model at noise strength sigma under a null instruction. Using 120,000 baseline samples (30,000 per model across SD15, SD21, SDXL, and InstructPix2Pix) and 9,600 ablation samples (four strengths, null versus strict copy prompts), we show that variance-driven diffusion models follow a quadratic form K_M(sigma) approximately equal to k_M sigma^2 plus c_M, with aggregate R^2 equal to 0.97. We derive this scaling from first principles via a Taylor expansion of the decoder, yielding k_M equal to Tr(J_D J_D^T), which depends only on the decoder Jacobian and not on prompts. To validate mechanistic structure, we construct synthetic decoders that reproduce the two regimes seen in practice: quadratic variance-driven drift and flat, high-variance edit-driven drift. We show that prompt wording has negligible effect (less than 17 percent coefficient difference), proving that drift is structural and not prompt-induced. We release NoOp-Bench, a benchmark with 10,000 inputs and full code for reproducible kernel estimation. Additional proofs, ablations, LPIPS and CLIP metrics, and extended visualizations appear in the Supplementary Material.

Neuronal morphology encodes critical information about circuit function, development, and disease, yet current methods analyze topology or graph structure in isolation. We introduce GraPHFormer, a multimodal architecture that unifies these complementary views through CLIP-style contrastive learning. Our vision branch processes a novel three-channel persistence image encoding unweighted, persistence-weighted, and radius-weighted topological densities via DINOv2-ViT-S. In parallel, a TreeLSTM encoder captures geometric and radial attributes from skeleton graphs. Both project to a shared embedding space trained with symmetric InfoNCE loss, augmented by persistence-space transformations that preserve topological semantics. Evaluated on six benchmarks (BIL-6, ACT-4, JML-4, N7, M1-Cell, M1-REG) spanning self-supervised and supervised settings, GraPHFormer achieves state-of-the-art performance on five benchmarks, significantly outperforming topology-only, graph-only, and morphometrics baselines. We demonstrate practical utility by discriminating glial morphologies across cortical regions and species, and detecting signatures of developmental and degenerative processes. Code: https://github.com/Uzshah/GraPHFormer

Existing methods following the integrated hard-regression or decoupling optimization paradigms exhibit limited fusion performance under complex degradations. To address these paradigm-level shortcomings, we propose ReCoFuse, an ultra-robust image fusion framework based on restorative multi-modal diffusion reciprocal coupling. ReCoFuse redefines the relationship between information restoration and integration, deriving a novel reciprocal coupling optimization paradigm through their mutual reinforcement. It first constructs two restoration branches using diffusion modules (DiM) to capture modality-specific restoration priors. Then, time-aware cross-modal integration modules (TIM) are introduced as a bridge to couple restoration and integration, embedded at each DiM sampling timestep to aggregate multi-modal information. The aggregated variable not only feeds back to each restoration branch to enhance degradation removal via cross-modal complementarity, but also generates high-quality fused images that comprehensively represent the scene. Moreover, an alternating regularization mechanism is designed to iteratively optimize DiM and TIM along the gradient path, ensuring effective collaboration between restoration and integration. Extensive experiments show that ReCoFuse achieves state-of-the-art performance under challenging degradations such as low light, haze, noise, low contrast, and stripes. The code is publicly available at https://github.com/HaoZhang1018/ReCoFuse.