CVPR 2026 论文列表

Positron Emission Tomography (PET) can be used for the early diagnosis of various brain disorders. However, the annotation of PET scans requires the involvement of specialized nuclear medicine experts, making accurately annotated PET data extremely scarce. MRI-based cross-modal domain adaptation methods can improve the brain disorder classification accuracy with sparsely labeled PET data. However, existing methods fail to balance the core requirements of domain discrepancy elimination and modality-specific discriminative information retention in cross-modal tasks. Forced alignment often undermines the core pathological discriminative features of both modalities, making it difficult to meet the collaborative optimization demands of cross-modal brain disorder classification. To address this, we propose a Dual-Stream feature Disentanglement and Alignment (DSDA) framework designed for collaborative optimization of cross-modal domain adaptation and brain disorder classification. This framework first dynamically evaluates and explicitly decouples the critical brain regions relevant to the classification task from the non-critical regions that preserve brain structural integrity. It then applies differential processing to the two types of brain regions: topology-weighted feature alignment for non-critical regions and high-confidence feature fusion for critical regions. This differential processing ensures that the model effectively aligns features while preserving key discriminative information. Extensive experimental results on various datasets (e.g., ADNI, AIBL, and PPMI) demonstrate the effectiveness of DSDA which helps achieve the state-of-the-art performance.

The integration of new modalities enhances the capabilities of multimodal large language models (MLLMs) but also introduces additional vulnerabilities. In particular, simple visual jailbreaking attacks can manipulate open-source MLLMs more readily than sophisticated textual attacks. However, these underdeveloped attacks exhibit extremely limited cross-model transferability, failing to reliably identify vulnerabilities in closed-source MLLMs. In this work, we analyse the loss landscape of these jailbreaking attacks and find that the generated attacks tend to reside in high-sharpness regions, whose effectiveness is highly sensitive to even minor parameter changes during transfer. To further explain the high-sharpness localisations, we analyse their feature representations in both the intermediate layers and the spectral domain, revealing an improper reliance on narrow layer representations and semantically poor frequency components. Building on this, we propose a Feature Over-Reliance CorrEction (FORCE) method, which guides the attack to explore broader feasible regions across layer features and rescales the influence of frequency features according to their semantic content. By eliminating non-generalizable reliance on both layer and spectral features, our method discovers flattened feasible regions for visual jailbreaking attacks, thereby improving cross-model transferability. Extensive experiments demonstrate that our approach effectively facilitates visual red-teaming evaluations against closed-source MLLMs.

Existing retrieval-augmented approaches for Dense Video Captioning (DVC) often fail to achieve accurate temporal segmentation aligned with true event boundaries, as they rely on heuristic strategies that overlook ground truth event boundaries.The proposed framework, STaRC, overcomes this limitation by supervising frame-level saliency through a highlight detection module. Note that the highlight detection module is trained on binary labels derived directly from DVC ground truth annotations without the need for additional annotation.We also propose to utilize the saliency scoresas a unified temporal signal that drives retrieval via saliency-guided segmentation and informs caption generation through explicit Saliency Prompts injected into the decoder.By enforcing saliency-constrained segmentation, our method produces temporally coherent segments that align closely with actual event transitions, leading to more accurate retrieval and contextually grounded caption generation. We conduct comprehensive evaluations on the YouCook2 and ViTT benchmarks, where STaRC achieves state-of-the-art performance across most of the metrics.

In this work, we propose the problem of localizing cameras and producing renders of a scene, given multiple images captured from ground/aerial/satellite viewpoints. We introduce a dataset called Sky2Ground, which contains synthetic/real images across all 3 viewpoints, along with camera parameters, and dense depth-maps/surface-normals. Recent works have shown that transformer-based nets like VGGT are capable of inferring scene-parameters in a single-forward pass. However, we formally reveal that simply fine-tuning such models reduces performance, and can't be solved simply by bruteforce-scaling. We find the culprit to be satellite images, which inject too much noise during the learning process. Therefore, we propose SkyNet to enable learning using satellite-images. SkyNet is a two-stream neural-net, with one stream explicitly processing satellite, and another processing all modalities together.We propose a restricted-attention mechanism, termed as `Masked-Satellite-Attention' which prevents ground/aerial images from interacting with satellite images. Further, our SkyNet is optimized with strategies inspired from curriculum-learning: sampling cameras which are far-away from each other during training. Extensive experiments on our Sky2Earth dataset reveal that SkyNet outperforms existing methods by 23% in terms of absolute performance. Our dataset, and code shall be made publicly available on huggingface.

Learning-based structure-from-motion methods such as ACE-Zero have demonstrated strong performance in estimating camera poses and scene coordinates from unordered image collections without requiring ground truth supervision. However, the lack of global and multi-view consistency constraints in ACE-Zero can lead to pose drift and misalignment, particularly in complex or ambiguous scenes. In this work, we propose a hybrid framework that integrates pose graph optimization (PGO) into ACE-Zero to refine camera poses and suppress incorrect refinements. We construct pose graphs directly from ACE-Zero outputs by extracting relative pose constraints from predicted scene coordinates. Furthermore, we introduce an uncertainty-aware optimization strategy by estimating confidence scores using geometric priors, including epipolar and optical flow consistencies across views. Our approach improves the robustness and accuracy of pose estimation, demonstrating that global geometric reasoning can effectively complement learning-based inference in structure-from-motion.

Motion transfer from the driving to the source portrait remains a key challenge in the portrait animation. Current diffusion-based approaches condition only on the driving motion, which fails to capture source-to-driving correspondences and consequently yields suboptimal motion transfer. Although flow estimation provides an alternative, predicting dense correspondences from 2D input is ill-posed and often yields inaccurate animation. We address this problem by introducing 3D flows, a learning-free and geometry-driven motion correspondence directly computed from parametric 3D head models. To integrate this 3D prior into diffusion model, we introduce 3D flow encoding to query potential 3D flows for each target pixel to indicate its displacement back to the source location. To obtain 3D flows aligned with 2D motion changes, we further propose depth-guided sampling to accurately locate the corresponding 3D points for each pixel. Beyond high-fidelity portrait animation, our model further supports user-specified editing of facial expression and head pose. Extensive experiments demonstrate the superiority of our method on consistent driving motion transfer as well as faithful source identity preservation.

Vision-Language models (VLMs) achieve strong performance on multimodal tasks but often fail at systematic visual reasoning, especially in inductive reasoning problems. Neuro-symbolic methods promise to address this by inducing interpretable logical programs from images, though they usually rely on rigid, domain-specific perception modules for this. We propose Vision-Language Programs (VLP), which combine the perceptual flexibility of VLMs with the systematic reasoning of symbolic program synthesis. Rather than embedding reasoning inside the VLM, VLP leverages the model to produce structured visual descriptions that are compiled into neuro-symbolic programs. The resulting programs execute directly on images, remain consistent with task constraints, and provide human-interpretable explanations that enable easy shortcut mitigation. Our experiments across synthetic and real-world datasets demonstrate that VLPs outperform both direct and structured prompting of VLMs, particularly on tasks that require complex logical reasoning.

Motion transfer has emerged as a promising direction for controllable video generation, yet existing methods largely focus on single-object scenarios and struggle when multiple objects require distinct motion patterns. In this work, we present FlexiMMT, the first implicit image-to-video (I2V) motion transfer framework that explicitly enables multi-object, multi-motion transfer. Given a static multi-object image and multiple reference videos, FlexiMMT independently extracts motion representations and accurately assigns them to different objects, supporting flexible recombination and arbitrary motion-to-object mappings. To address the core challenge of cross-object motion entanglement, we introduce a Motion Decoupled Mask Attention Mechanism that uses object-specific masks to constrain attention, ensuring that motion and text tokens only influence their designated regions. We further propose a Differentiated Mask Propagation Mechanism that derives object-specific masks directly from diffusion attention and progressively propagates them across frames efficiently. Extensive experiments demonstrate that FlexiMMT achieves precise, compositional, and state-of-the-art performance in I2V-based multi-object multi-motion transfer. Our project page is: https://ethan- li123.github.io/FlexiMMT_page/

Continual Generalized Category Discovery (C-GCD) seeks to incrementally discover new categories from unlabeled data and memorize old categories' knowledge, fostering model adaptability in real-world scenarios. Especially, the unlabeled data is from both old and new classes, requiring the model to recognize previously learned classes while discovering. In response, recent efforts focus on devising specific frameworks and various anti-forgetting strategies, striving for a typical stability-plasticity trade-off. Unlike previous studies, in this work, we first revisit these methods and identify that most of these methods over-protect old classes, hampering the accurate discovery of novel ones. To address this challenge, we introduce the Decouple Your Discovery and Memory (DYDM), a dual-branch architecture that decouples the discovery of new classes and the memorization of old classes. The discovery branch is focused on accurately recognizing new classes, while the memory branch consolidates all identified categories in a recursive manner and functions as the inference branch. Importantly, benefiting from the strong knowledge retention ability of the memory branch, the discovery branch can facilitate the recognition of novel classes from the unlabeled data, achieving a win-win outcome between plasticity and stability. Extensive experiments on various datasets and settings demonstrate the superiority of our approach, achieving leads of up to 9.87%, 7.30%, 3.18%, and 8.25%. Furthermore, our framework can integrate with existing approaches, consistently enhancing their performance.

Self-attention with separate pre- and post-projections can be a universal approximator (on compact domains) under mild conditions. Yet we observe a striking gap: an attention-only Transformer (w/o FFN layers) exhibits a marked accuracy drop relative to its standard interleaved attention--FFN baseline. We term this the weak-independence challenge of attention. We study this through a new conceptual lens, Selection-as-Nonlinearity (SaN), which interprets effective nonlinearity as directed, cost-constrained selection, offering a coherent account of attention as context-gated activation. In this joint game-decision view, attention performs a resource-constrained cooperative allocation over values: each query distributes a unit-mass weight budget over shared values to optimize representational utility, under a normalizer (e.g., \mathrm softmax ), and guided by context-derived scores (e.g., q-k similarities). SaN interprets weak-independence as a structural tension: the value weights almost cannot simultaneously attain the decoupled per-query (row-wise) and the per-value (column-wise) optimums under shared budgets, thereby limiting attention's stand-alone capacity. Guided by SaN, we introduce CSaN, an interpretable, efficient attention compensation paradigm with two key insights: 1) hierarchical budget calibration, re-allocate row budgets via inter-query correction signals; and 2) public-private cooperation, enhancing the public attention pathway with a per-token private value pathway to decouple conflicting demands. CSaN is evaluated on various vision benchmarks and demonstrates remarkable gains across popular Transformer families (Swin, ViT, Hiera), enabling models to rival much heavier same-family counterparts ~2xas large.

Large-scale video-language pretraining enables strong generalization across multimodal tasks but often incurs prohibitive computational costs. Although recent advances in masked visual modeling help mitigate this issue, they still suffer from two fundamental limitations: severe visual information loss under high masking ratios and temporal information leakage caused by inter-frame correlations. To address these challenges, we propose ClusterSTM, a Cluster-Wise Spatio-Temporal Masking strategy for efficient video-language pretraining. ClusterSTM first performs intra-frame clustering to partition visual tokens into multiple semantically independent clusters, then conducts cluster-wise masking by retaining the token with the highest temporal density within each cluster. Our masking strategy ensure that the retained tokens capture holistic video content while exhibit strong temporal correlation. Additionally, we introduce a video-text relevance reconstruction objective that aligns high-level multimodal semantics beyond conventional visual reconstruction. Extensive experiments across multiple benchmarks demonstrate that ClusterSTM achieves superior performance on video-text retrieval, video question answering, and video captioning tasks, establishing a new state-of-the-art among efficient video-language models.

Deep learning models are well known to be susceptible to backdoor attacks, and text-to-image generation models are no exception. When a specific trigger is embedded in the input, a backdoored model can be manipulated to perform attacker-defined malicious behaviors, such as generating harmful or inappropriate images. Existing backdoor attacks on text-to-image generation models are largely limited to dirty-label attacks, where misaligned image-caption pairs are injected into the training data. While effective in controlled settings, such methods are often easily detectable, limiting their practicality in realistic applications. To address this limitation, we propose the first clean-label backdoor attack for text-to-image generative models, which preserves semantic consistency within poisoned image-caption pairs to evade detection. We design a dual-modality manipulation strategy that injects nearly imperceptible noise into images while embedding a composite semantic text trigger. The text trigger combines synonym substitution and syntactic restructuring, enabling stealthy yet effective backdoor implantation without compromising the visual-textual alignment. Experimental results demonstrate that our method achieves high attack success while effectively preserving model utility and evading mainstream defenses, including commercial content filters.

Compositional video generation aims to synthesize multiple instances with diverse appearance and motion. However, current approaches mainly focus on binding semantics, neglecting to understand diverse motion categories specified in prompts. In this paper, we propose a motion factorization framework that decomposes complex motion into three primary categories: motionlessness, rigid motion, and non-rigid motion. Specifically, our framework follows a planning before generation paradigm. (1) During planning, we reason about motion laws on the motion graph to obtain frame-wise changes in the shape and position of each instance. This alleviates semantic ambiguities in the user prompt by organizing it into a structured representation of instances and their interactions. (2) During generation, we modulate the synthesis of distinct motion categories in a disentangled manner. Conditioned on the motion cues, guidance branches stabilize appearance in motionless regions, preserve rigid-body geometry, and regularize local non-rigid deformations. Crucially, our two modules are model-agnostic, which can be seamlessly incorporated into various diffusion model architectures. Extensive experiments demonstrate that our framework achieves impressive performance in motion synthesis on real-world benchmarks. Code is available at https://github.com/ZixuanWang0525/MF-CVG.

Instruction-based video editing promises to democratize content creation, yet its progress is severely hampered by the scarcity of large-scale, high-quality training data. We introduce Ditto, a holistic framework designed to tackle this fundamental challenge. At its heart, Ditto features a novel data generation pipeline that fuses the creative diversity of a leading image editor with an in-context video generator, overcoming the limited scope of existing models. To make this process viable, our framework resolves the prohibitive cost-quality trade-off by employing an efficient, distilled model architecture augmented by a temporal enhancer, which simultaneously reduces computational overhead and improves temporal coherence. Finally, to achieve full scalability, this entire pipeline is driven by an intelligent agent that crafts diverse instructions and rigorously filters the output, ensuring quality control at scale. Using this framework, we invested over 12,000 GPU-days to build Ditto-1M, a new dataset of one million high-fidelity video editing examples. We trained our model, Editto, on Ditto-1M with a curriculum learning strategy. The results demonstrate superior instruction-following ability and establish a new state-of-the-art in instruction-based video editing.

Recent advancements in image customization exhibit a wide range of application prospects due to stronger customization capabilities. However, since we humans are more sensitive to faces, a significant challenge remains in preserving consistent identity while avoiding identity confusion with multi-reference images, limiting the identity scalability of customization models. To address this, we present UMO, a Unified Multi-identity Optimization framework, designed to maintain high-fidelity identity preservation and alleviate identity confusion with scalability. With multi-to-multi matching paradigm, UMO reformulates multi-identity generation as a global assignment optimization problem and unleashes multi-identity consistency for existing image customization methods generally. To facilitate the training of UMO, we develop a customization dataset with multi-reference images, consisting of both synthesised and real parts. Additionally, we propose a new metric to measure identity confusion. Extensive experiments demonstrate that UMO not only improves identity consistency significantly, but also reduces identity confusion on several image customization methods, setting a new state-of-the-art among open-source methods along the dimension of identity preserving. Code and model: https://github.com/bytedance/UMO.

We introduce Talk2Move, a reinforcement learning (RL) based diffusion framework for text-instructed spatial transformation of objects within scenes. Spatially manipulating objects in a scene through natural language poses a challenge for multimodal generation systems. While existing text-based manipulation methods can adjust appearance or style, they struggle to perform object-level geometric transformations--such as translating, rotating, or resizing objects--due to scarce paired supervision and pixel-level optimization limits. Talk2Move employs Group Relative Policy Optimization (GRPO) to explore geometric actions through diverse rollouts generated from input images and lightweight textual variations, removing the need for costly paired data. A spatial reward guided model aligns geometric transformations with linguistic description, while off-policy step evaluation and active step sampling improve learning efficiency by focusing on informative transformation stages. Furthermore, we design object-centric spatial rewards that evaluate displacement, rotation, and scaling behaviors directly, enabling interpretable and coherent transformations.Experiments on curated benchmarks demonstrate that Talk2Move achieves precise, consistent, and semantically faithful object transformations, outperforming existing text-guided editing approaches in both spatial accuracy and scene coherence.

This paper introduces a novel unsupervised approach for image deblurring that utilizes a simple process for training data collection, thereby enhancing the applicability and effectiveness of deblurring methods. Our technique does not require meticulously paired data of blurred and corresponding sharp images; instead, it uses unpaired blurred and sharp images of similar scenes to generate pseudo-ground truth data by leveraging a dense matching model to identify correspondences between a blurry image and reference sharp images. Thanks to the simplicity of the training data collection process, our approach does not rely on existing paired training data or pre-trained networks, making it more adaptable to various scenarios and suitable for networks of different sizes, including those designed for low-resource devices. We demonstrate that this novel approach achieves state-of-the-art performance, marking a significant advancement in the field of image deblurring.

High-resolution image editing is essential for professional and creative applications, yet existing multimodal diffusion-based editors remain computationally inefficient and constrained to relatively low resolutions. Current approaches redundantly process the entire image canvas or rely on large-scale high-resolution datasets, resulting in substantial training and inference costs. We introduce **HierEdit**, a region-aware hierarchical diffusion framework designed for efficient and scalable high-resolution image editing. Our method first performs edits on a low-resolution proxy using an off-the-shelf editing model to generate a reference and to localize the modified regions. A hierarchical local-window diffusion model (**Local-Window MMDiT**) that refines only edited regions within the original high-resolution image, while reusing the unaltered regions as conditioning inputs. The low-resolution proxy further provides structural guidance and intermediate denoising supervision (**Inference Acceleration**) , ensuring consistent global semantics and stable generation without the need for full-resolution attention computation. This targeted and hierarchical design enables fast, high-fidelity editing of images up to 4K resolution without requiring any specialized high-resolution training data. Extensive experiments demonstrate that **HierEdit** achieves competitive visual quality on commodity-resolution datasets while significantly accelerating inference and extending seamlessly to ultra-high-resolution 4K editing.

We present Lynx, a high-fidelity model for personalized video synthesis from a single input image. Built on an open-source Diffusion Transformer (DiT) foundation model, Lynx introduces two lightweight adapters to ensure identity fidelity. The ID-adapter employs a Perceiver Resampler to convert ArcFace-derived facial embeddings into compact identity tokens for conditioning, while the Ref-adapter integrates dense VAE features from a frozen reference pathway, injecting fine-grained details across all transformer layers through cross attention. These modules collectively enable robust identity preservation while maintaining temporal coherence and visual realism. Through evaluation on a curated benchmark of 40 subjects and 20 unbiased prompts, which yielded 800 test cases, Lynx has demonstrated superior face resemblance, competitive prompt following, and strong video quality, thereby advancing the state of personalized video generation. Code and models will be released publicly upon publication.