CVPR 2026 Papers

Transformers are remarkably versatile, suggesting the existence of generic inductive biases beneficial across modalities. In this work, we explore a new way to instil such biases in vision transformers (ViTs) through pretraining on procedurally generated data devoid of visual or semantic content. We generate this data with simple algorithms such as formal grammars, so the results bear no relationship to either natural or synthetic images. We use this procedurally generated data to pretrain ViTs in a warm-up phase that bypasses their visual patch embedding mechanisms, thus encouraging the models to internalise abstract computational priors. When followed by standard image-based training, this warm-up significantly improves data efficiency, convergence speed, and downstream performance. On ImageNet-1K, for example, allocating just 1% of the training budget to procedural data improves final accuracy by over 1.7%. In terms of its effect on performance, 1% procedurally generated data is thus equivalent to 28% of the ImageNet-1K data. These findings suggest a promising path toward new data-efficient and domain-agnostic pretraining strategies.

Long video understanding is a key challenge that plagues the advancement of Multimodal Large language Models (MLLMs). In this paper, we study this problem from the perspective of visual memory mechanism, and proposed a novel and training-free approach, termed Flexible Memory (FlexMem). In principle, FlexMem aims to mimic human behavior of video watching, i.e., continually watching video content and recalling the most relevant memory fragments to answer the question. In this way, FlexMem can help MLLMs achieve video understanding of infinite lengths, unlike previous methods that process all video information at once and have input upper-limit. Concretely, FlexMem first consider the visual KV caches as the memory sources, and realize the effective memory transfer and writing via a dual-pathway compression design. Afterwards, FlexMem also explores different memory reading strategies for the diverse video understanding tasks, including the popular streaming one. To validate FlexMem, we apply it to two popular video-MLLMs, and conduct extensive experiments on five long video and one streaming video task. The experimental results show that on a single 3090 GPU, our FlexMem can achieve obvious improvements than existing efficient video understanding methods and process more than 1k frames, which also helps the base MLLMs achieve comparable or even better performance than SOTA MLLMs on some benchmarks, e.g. , GPT-4o and Gemini-1.5 Pro. Our code is released at: https://github.com/city1517/FlexMem.

Understanding animal species from multimodal data poses an emerging challenge at the intersection of computer vision and ecology.While recent biological models, such as BioCLIP, have demonstrated strong alignment between images and textual taxonomic information for species identification, the integration of the audio modality remains an open problem. We propose BioVITA, a novel visual-textual-acoustic alignment framework for biological applications. BioVITA involves (i) a training dataset, (ii) a representation model, and (iii) a retrieval benchmark. First, we construct a large-scale training dataset comprising 1.3 million audio clips and 2.3 million images, covering 14,133 species annotated with 34 ecological trait labels. Second, building upon BioCLIP2, we introduce a two-stage training framework to effectively align audio representations with visual and textual representations. Third, we develop a cross-modal retrieval benchmark that covers all possible directional retrieval across the three modalities (i.e., image-to-audio, audio-to-text, text-to-image, and their reverse directions), with three taxonomic levels: Family, Genus, and Species. Extensive experiments demonstrate that our model learns a unified representation space that captures species-level semantics beyond taxonomy, advancing multimodal biodiversity understanding. The project page is available at: https://dahlian00.github.io/BioVITA_Page/

Modern multi-label image classification models suffer from a critical reliance on spurious correlations, failing to learn the underlying causal mechanisms. Many causality-inspired methods are impractical, demanding box-level supervision that is rarely available in real-world datasets. Others rely on static confounder dictionaries, which are inherently inflexible and fail to capture complex biases or adapt to feature space changes during training. To address this, we present prototype-based causal intervention (ProCI), a novel framework that approximates the backdoor adjustment using only image-level supervision. It models confounders as learnable contextual prototypes engineered to represent class-wise co-occurring bias. These prototypes are learned dynamically within a stable memory and leveraged to construct sample-specific bias vectors for an adaptive feature adjustment, effectively counteracting spurious correlations. Experiments on MS-COCO, Pascal VOC, COCO-Stuff, and the challenging Sewer-ML dataset validate our approach. ProCI achieves competitive performance on standard benchmarks while setting a new state-of-the-art on the highly-confounded Sewer-ML. It outperforms the previous best model by a remarkable +5.44 points on the F2-CIW metric. These results demonstrate the effectiveness of our approach in mitigating complex real-world biases using only image-level supervision.

Diffusion-based stylization has advanced significantly, yet existing methods are limited to color-driven transformations, neglecting complex semantics and material details. We introduce StyleExpert, a semantic-aware framework based on Mixture of Experts (MoE).Our framework employs a unified style encoder, trained on our large-scale dataset of content-style-stylized triplets, to embed diverse styles into a consistent latent space. This embedding is then used to condition a similarity-aware gating mechanism, which dynamically routes styles to specialized experts within the MoE architecture. Leveraging this MoE architecture, our method adeptly handles diverse styles spanning multiple semantic levels, from shallow textures to deep semantics. Extensive experiments show that StyleExpert outperforms existing approaches in preserving semantics and material details, while generalizing to unseen styles.

Diffusion-based image-to-image (I2I) translation excels in high-fidelity generation but suffers from slow sampling in state-of-the-art Diffusion Bridge Models (DBMs), often requiring dozens of function evaluations (NFEs). We introduce DBMSolver, a training-free sampler that exploits the semi-linear structure of DBM's underlying SDE and ODE via exponential integrators, yielding highly-efficient 1st- and 2nd-order solutions. This reduces NFEs by up to 5X while boosting quality (e.g., FID drops 53% on DIODE at 20 NFEs vs. 2nd-order baseline). Experiments on inpainting, stylization, and semantics-to-image tasks across resolutions up to 256x256 show DBMSolver sets new SOTA efficiency-quality tradeoffs, enabling real-world applicability. Our code is publicly available at https://github.com/snumprlab/dbmsolver.

We present FlexTraj, a framework for image-to-video generation with flexible point trajectory control. FlexTraj introduces a unified point-based representation that encodes point with a temporally consistent trajectory ID, a segmentation ID, and an optional color channel for appearance cues, enabling both dense and sparse trajectory control. Instead of injecting trajectory conditions into the video generator through token concatenation or ControlNet, FlexTraj employs an efficient sequence-concatenation scheme that achieves faster convergence, stronger controllability, and efficient inference, while maintaining robustness under unaligned conditions. To train such a unified point trajectory-controlled video generator, FlexTraj adopts an annealing training strategy that gradually reduces reliance on complete supervision and aligned condition. Experimental results demonstrate that FlexTraj enables multi-granularity, alignment-agnostic trajectory control for video generation, supporting various applications such as motion cloning, drag-based image-to-video, motion interpolation, camera redirection, flexible action control and mesh animations.

Recent advances in multimodal large language models (MLLMs) have accelerated progress in domain-oriented AI, yet their development in geoscience and remote sensing (RS) remains constrained by distinctive challenges: wide-ranging disciplinary knowledge, heterogeneous sensor modalities, and a fragmented spectrum of tasks. To bridge these gaps, we introduce GeoMMBench, a comprehensive multimodal question-answering benchmark covering diverse RS disciplines, sensors, and tasks, enabling broader and more rigorous evaluation than prior benchmarks. Using GeoMMBench, we assess 36 open-source and proprietary large language models (LLMs), uncovering systematic deficiencies in domain knowledge, perceptual grounding, and reasoning--capabilities essential for expert-level geospatial interpretation. Beyond evaluation, we propose GeoMMAgent, a multi-agent framework that strategically integrates retrieval, perception, and reasoning through domain-specific RS models and tools. Extensive experimental results demonstrate that GeoMMAgent significantly outperforms standalone LLMs, underscoring the importance of tool-augmented agents for dynamically tackling complex geoscience and RS challenges.

Spatio-Temporal Video Grounding (STVG) aims to localize target objects in videos based on natural language descriptions. While Multimodal Large Language Models have shown promise, a significant gap remains between current models and real-world demands involving diverse objects and complex queries. We attribute this to limited benchmark scope, causing models to exhibit category bias, oversimplified reasoning, and poor linguistic robustness.To address these limitations, we introduce OmniGround, a comprehensive benchmark with 3,475 videos spanning 81 categories and complex real-world queries. We propose the Forward-Backward-Refinement (FBR) annotation pipeline for high-quality labels and DeepSTG, a systematic evaluation framework quantifying dataset quality beyond superficial statistics. Evaluations reveal performance average drops of 10.4% on complex real-world scenes, particularly with small/occluded objects and intricate spatial relations. Motivated by these, we propose PG-TAF, a training-free two-stage framework decomposing STVG into high-level temporal grounding and fine-grained spatio-temporal propagation. Experiments demonstrate PG-TAF achieves 25.6% and 35.6% improvements in m_tIoU and m_vIoU on OmniGround with consistent gains across four benchmarks.

The inherent semantic ambiguity of "many-to-many", where one video matches multiple texts and vice versa, aggravates the difficulty in text-video retrieval. The dominant deterministic embeddings only struggle to capture the mean semantics, while existing probabilistic methods fail to distinguish hard negatives for their imposing rigid uncertainty priors or ignoring the interaction between similarity and uncertainty. To this end, we propose a novel physics-inspired framework (GraviAlign) that decomposes the alignment of cross-modal semantic distributions into two orthogonal factors inspired by the Gravitational Force: (1) Semantic Attraction measuring gravitational alignment between distribution centers via uncertainty-derived "semantic mass" and "semantic distance"; (2) Geometric Overlap quantifying distribution intersection. Each factor has independent veto power to reject those matches with misalignment or poor overlap. Additionally, GraviAlign offers an efficient (O(D)), theoretically grounded alternative to intractable joint integrals. Extensive experiments on DiDeMo, MSR-VTT, and ActivityNet demonstrate our effectiveness and superiority, and solid ablation studies confirm the indispensability of two novel components.

Recent Large Vision-Language Models (LVLMs) have demonstrated remarkable performance across various multimodal tasks that require understanding both visual and linguistic inputs. However, object hallucination -- the generation of nonexistent objects in answers -- remains a persistent challenge. Although several approaches such as retraining and external grounding methods have been proposed to mitigate this issue, they still suffer from high data costs or structural complexity. Training-free methods such as Contrastive Decoding (CD) are more cost-effective, avoiding additional training or external models, but still suffer from long-term decay, where visual grounding weakens and language priors dominate as the generation progresses. In this paper, we propose First Logit Boosting (FLB), a simple yet effective training-free technique designed to alleviate long-term decay in LVLMs. FLB stores the logit of the first generated token and adds it to subsequent token predictions, effectively mitigating long-term decay of visual information. We observe that FLB (1) sustains the visual information embedded in the first token throughout generation, and (2) suppresses hallucinated words through the stabilizing effect of the "The" token. Experimental results show that FLB significantly reduces object hallucination across various tasks, benchmarks, and backbone models. Notably, it causes negligible inference overhead, making it highly applicable to real-time multimodal systems. Code is available at https://github. com/jiwooha20/FLB

Vision foundation models trained via multi-teacher distillation offer a promising path toward unified visual representations, yet the learning dynamics and data efficiency of such approaches remain underexplored. In this paper, we systematically study multi-teacher distillation for vision foundation models and identify key factors that enable training at lower computational cost. We introduce SigLino, an efficient family of agglomerative vision foundation models that distill knowledge from SigLIP2 and DINOv3 simultaneously into Dense and Mixture-of-Experts students. We show that (1) our Asymmetric Relation-Knowledge Distillation loss preserves the geometric properties of each teacher while enabling effective knowledge transfer, (2) token-balanced batching that packs varying-resolution images into sequences with uniform token budgets stabilizes representation learning across resolutions without sacrificing performance, (3) hierarchical clustering and sampling of training data--typically reserved for self-supervised learning--substantially improves sample efficiency over random sampling for multi-teacher distillation, and (4) the resulting representations transfer effectively to early-fusion Grounding-VLMs, outperforming models trained from scratch. By combining these findings, we curate OpenLVD200M, a 200M-image corpus that demonstrates superior efficiency for multi-teacher distillation. Instantiated in a Mixture-of-Experts, our SigLino-MoE initializes an early-fusion Grounding-VLM that replaces the conventional ViT-LLM stack, demonstrating improved performance compared to a model trained from scratch. We release OpenLVD200M and distilled checkpoints.

Image fusion aims to integrate complementary information from multiple source images to produce a more informative and visually consistent representation, benefiting both human perception and downstream vision tasks. Despite recent progress, most existing fusion methods are designed for specific tasks (i.e., multi-modal, multi-exposure, or multi-focus fusion) and struggle to effectively preserve source information during the fusion process. This limitation primarily arises from task-specific architectures and the degradation of source information caused by deep-layer propagation. To overcome these issues, we propose UniFusion, a unified image fusion framework designed to achieve cross-task generalization. First, leveraging DINOv3 for modality-consistent feature extraction, UniFusion establishes a shared semantic space for diverse inputs. Second, to preserve the understanding of each source image, we introduce a reconstruction-alignment loss to maintain consistency between fused outputs and inputs. Finally, we employ a bilevel optimization strategy to decouple and jointly optimize reconstruction and fusion objectives, effectively balancing their coupling relationship and ensuring smooth convergence. Extensive experiments across multiple fusion tasks demonstrate UniFusion's superior visual quality, generalization ability, and adaptability to real-world scenarios.

Recent generative models have shown strong performance in generating diverse 3D assets from 2D images, a fundamental research topic in computer vision and graphics. However, these models still struggle to generate voluminous 3D assets when the input is a flat image that provides limited 3D cues. We introduce REVIVE 3D, a two-stage, plugand-play pipeline for generating voluminous 3D assets from flat images. In Stage 1, we construct an Inflated Prior by inflating the foreground silhouette to recover global volume and superimposing part-aware details to capture local structure. In Stage 2, 3D Latent Refinement injects Gaussian noise into the Inflated Prior's latent and then denoises it, using the prior's geometric cues to leverage the backbone's pretrained 3D knowledge. Furthermore, our framework supports image-conditioned 3D editing. To quantify volume and surface flatness, we propose Compactness and Normal Anisotropy. We validate Compactness and Normal Anisotropy through a user study, showing that these metrics align with human perception of volume and quality. We show that REVIVE 3D achieves state-of-the-art performance on a challenging flat image dataset, based on extensive qualitative and quantitative evaluations.

Next-scale prediction paradigm visual autoregressive (VAR) models have demonstrated significant potential for image super-resolution. However, their practical application is constrained by a rigid, size-specific design. This limitation stems from their reliance on memorizing fixed, absolute scaling schedules, which necessitates a distinct model for each target resolution. We introduce DVAR, a Dynamic Visual AutoRegressive framework that overcomes this fundamental bottleneck. Instead of memorizing these rigid schedules, DVAR learns a canonical scaling dynamic. This dynamic effectively decouples the logic of relative scaling from the absolute target size, thereby preserving a single set of proportions between generative steps that can be applied uniformly to any size. Furthermore, we introduce a dynamic sampling scheduler to mitigate the teacher-forcing problem with negligible computational overhead. By leveraging the geometric proximity of visual tokens in the codebook, it efficiently simulates the model's predictive error distribution to bridge the training-inference gap. To our knowledge, DVAR is the first framework to grant VAR models size-flexibility, breaking their one-to-one dependency on a fixed resolution. Extensive evaluations demonstrate that DVAR achieves superior visual quality over existing Real-ISR methods, proving that a flexible, purely autoregressive approach is a viable path to state-of-the-art image super-resolution. Code is available at https://github.com/YuZheng9/DVAR.

Lesion detection, symptom tracking, and visual explainability are central to real-world medical image analysis, yet current medical Vision-Language Models (VLMs) still lack mechanisms that translate their broad knowledge into clinically actionable outputs. To bridge this gap, we present Medic-AD, a clinically oriented VLM that strengthens these three capabilities through a stage-wise framework. First, learnable anomaly-aware tokens (Ano) encourage the model to focus on abnormal regions and build more discriminative lesion centered representations. Second, inter-image difference tokens (Diff) explicitly encode temporal changes between studies, allowing the model to distinguish worsening, improvement, and stability in disease burden. Finally, a dedicated explainability stage trains the model to generate heatmaps that highlight lesion-related regions, offering clear visual evidence that is consistent with the model's reasoning. Through our staged design, Medic-AD steadily boosts performance across anomaly detection, symptom tracking, and anomaly segmentation, achieving state-of-the-art results compared with both closed source and medical-specialized baselines. Evaluations on real longitudinal clinical data collected from real hospital workflows further show that Medic-AD delivers stable predictions and clinically faithful explanations in practical patient-monitoring and decision-support workflows.

In many real-world applications of non-rigid shape matching, the shapes are subject to topological noise (i.e. varying genus). In this paper, we propose a novel formulation based on Markov Random Fields (MRF) that can handle these cases with topological noise. The solutions to our optimisation problem can be approximated efficiently using the alpha expansion algorithm, which comes with theoretical approximation guarantees. In particular, we cast non-rigid 3D shape matching as a multi-labelling problem in which each triangle of the source shape is assigned a label that represents the matching to a specific surface element on the target shape. We propose a novel pairwise term that imposes that our matching prefers solutions in which neighbouring triangles on the source shape remain close on the target shape. Further, by exploiting the specific structure of our label space, we show that the alpha expansion algorithm can be customised to achieve significant speed-ups, while maintaining its approximation guarantees. We evaluate our method on various shape matching datasets including settings in which shapes have topological artefacts.

Diffusion-based real-world image super-resolution (Real-ISR) methods have demonstrated impressive performance. To achieve efficient Real-ISR, many works employ Variational Score Distillation (VSD) to distill a pre-trained stable-diffusion (SD) model for one-step SR with a fixed timestep. However, since SD performs different generative priors at different timesteps, a fixed timestep is difficult for these methods to fully leverage the generative priors in SD, leading to suboptimal performance. To address this issue, we propose a Time-Aware one-step Diffusion Network for Real-ISR (TADSR). We first introduce a Time-Aware VAE Encoder, which projects the same image into different latent features based on timesteps. Through joint dynamic variation of timesteps and latent features, the student model can better align with the input pattern distribution of the pre-trained SD, thereby enabling more effective utilization of SD's generative capabilities. To better activate the generative prior of SD at different timesteps, we propose a Time-Aware VSD loss that bridges the timesteps of the student model and those of the teacher model, thereby producing more consistent generative prior guidance conditioned on timesteps. Additionally, though utilizing the generative prior in SD at different timesteps, our method can naturally achieve controllable trade-offs between fidelity and realism by changing the timestep. Experimental results demonstrate that our method achieves both state-of-the-art performance and controllable SR results with only a single step. The source code is released at https://github.com/zty557/TADSR

Knowledge distillation establishes a learning paradigm that leverages both data supervision and teacher guidance. However, determining the optimal balance between learning from data and learning from the teacher is challenging, as some samples may be noisy while others are subject to teacher uncertainty. This motivates the need for adaptively balancing data and teacher supervision. We propose Beta-weighted Knowledge Distillation (Beta-KD), an uncertainty-aware distillation framework that adaptively modulates how much the student relies on teacher guidance. Specifically, we formulate teacher-student learning from a unified Bayesian perspective and interpret teacher supervision as a Gibbs prior over student activations. This yields a closed-form, uncertainty-aware weighting mechanism and supports arbitrary distillation objectives and their combinations. Extensive experiments are conducted on multimodal VQA benchmarks by distilling a student Vision-Language Model from a large teacher VLM. The results demonstrate that Beta-KD consistently outperforms existing knowledge distillation methods. Code is available at https://github.com/Jingchensun/beta-kd.