CVPR 2026 论文列表

The rapid proliferation of generative components, such as LoRAs, has created a vast but unstructured ecosystem. Existing discovery methods depend on unreliable user descriptions or biased popularity metrics, hindering usability. We present CARLoS, a large-scale framework for characterizing LoRAs without requiring additional metadata. Analyzing over 650 LoRAs, we employ them in image generation over a variety of prompts and seeds, as a credible way to assess their behavior. Using CLIP embeddings and their difference to a base-model generation, we concisely define a three-part representation: Direction, defining semantic shift; Strength, quantifying the significance of the effect; and Consistency, quantifying how stable the effect is. Using these representations, we develop an efficient retrieval framework that semantically matches textual queries to relevant LoRAs while filtering overly strong or unstable ones, outperforming textual baselines in automated and human evaluations. While retrieval is our primary focus, the same representation also supports analyses linking Strength and Consistency to legal notions of substantiality and volition, key considerations in copyright, positioning CARLoS as a practical system with broader relevance for LoRA analysis.

Recently, 3D Gaussian Splatting and its derivatives have achieved significant breakthroughs in large-scale scene reconstruction. However, how to efficiently and stably achieve high-quality geometric fidelity remains a core challenge. To address this issue, we introduce MetroGS, a novel Gaussian Splatting framework for efficient and robust reconstruction in complex urban environments. Our method is built upon a distributed 2D Gaussian Splatting representation as the core foundation, serving as a unified backbone for subsequent modules. To handle potential sparse regions in complex scenes, we propose a structured dense enhancement scheme that utilizes SfM priors and a pointmap model to achieve a denser initialization, while incorporating a sparsity compensation mechanism to improve reconstruction completeness. Furthermore, we design a progressive hybrid geometric optimization strategy that organically integrates monocular and multi-view optimization to achieve efficient and accurate geometric refinement. Finally, to address the appearance inconsistency commonly observed in large-scale scenes, we introduce a depth-guided appearance modeling approach that learns spatial features with 3D consistency, facilitating effective decoupling between geometry and appearance and further enhancing reconstruction stability. Experiments on large-scale urban datasets demonstrate that MetroGS achieves superior geometric accuracy, rendering quality, offering a unified solution for high-fidelity large-scale scene reconstruction. Project page: https://m3phist0.github.io/MetroGS.

Conventional monocular depth estimators suffer from visual ambiguities and nuisances. We demonstrate that language can improve the fidelity of estimates by providing additional information through text as a condition, thereby reducing the solution space for depth estimates. This conditional distribution is learned during text-to-image pre-training of diffusion models. To generate images under various viewpoints and layouts that reflect textual descriptions, the model implicitly encodes object shapes and their spatial relationships, comprising the 3-dimensional (3D) scene structure. We investigate the benefits of integrating text descriptions into the training and inference of the diffusion-based monocular depth estimators (MDE). We experiment with three different diffusion-based MDEs, namely Marigold, Lotus, and E2E-FT, and their variants. By training on HyperSim and Virtual KITTI, and evaluating on NYUv2, KITTI, ETH3D, ScanNet, and DIODE, we find that our strategy of integrating text into MDEs improves the overall accuracy of depth estimates, especially in small areas. The effect is also targeted in that improvements are more pronounced in specific regions described in the text. Naturally, this lends to iterative refinement of the depth estimate by providing additional descriptions of the 3D scene. Separately, we find that incorporating text can accelerate convergence of training and the inference diffusion trajectory.

Pixel-wise capabilities are essential for building interactive intelligent systems. However, pixel-wise multi-modal LLMs (MLLMs) remain difficult to scale due to complex region-level encoders, specialized segmentation decoders, and incompatible training objectives. To address these challenges, we present SAMTok, a discrete mask tokenizer that converts any region mask into two special tokens and reconstructs the mask from these tokens with high fidelity. By treating masks as a new language, SAMTok enables base MLLMs (such as the QwenVL series) to learn pixel-wise capabilities through standard next-token prediction and simple reinforcement learning, without architectural modifications and specialized loss design. SAMTok builds on SAM2 and is trained on 209M diverse masks using a mask encoder and residual vector quantizer to produce discrete, compact, and information-rich tokens. With 5M SAMTok-formatted mask understanding and generation data samples, QwenVL-SAMTok attains state-of-the-art or comparable results on region captioning, region VQA, grounded conversation, referring segmentation, scene graph parsing, and multi-round interactive segmentation. We further introduce a textual answer-matching reward that enables efficient reinforcement learning for mask generation, delivering substantial improvements on GRES and GCG benchmarks. Our results demonstrate a scalable and straightforward paradigm for equipping MLLMs with strong pixel-wise capabilities.

Vision-Language Models (VLMs) have become indispensable for multimodal reasoning, yet their representations often encode and amplify demographic biases, resulting in biased associations and misaligned predictions in downstream tasks. Such behavior undermines fairness and distorts the intended alignment between vision and language. Recent post-hoc approaches attempt to mitigate bias by replacing the most attribute-correlated embedding coordinates with neutral values. However, our systematic analysis reveals three critical limitations of this coordinate-wise approach: feature entanglement, poor cross-dataset generalization, and incomplete bias removal. We find that bias is not localized to a few coordinates but is instead distributed across a few linear subspaces. To address these limitations, we propose Subspace Projection Debiasing (SPD), a geometrically principled framework that identifies and removes the entire subspace of linearly decodable bias while reinserting a neutral mean component to preserve semantic fidelity. Extensive experiments across zero-shot classification, text-to-image retrieval, and image generation validate the effectiveness of SPD: our method achieves more robust debiasing with an average improvement of 18.5% across four fairness metrics, while maintaining minimal loss in task performance compared to the best debiasing baseline.

Conventional whole slide image (WSI) analysis pipelines follow a two-stage process. First, an image encoder, such as a vision transformer (ViT), is used to perform batched offline feature extraction on a series of tiles cropped from the WSI. Second, a multiple instance learning (MIL) model is trained with slide-level labels to obtain task-specific slide embeddings. However, several limitations exist: strong reliance on pre-trained weights of the tile encoder, the absence of receptive fields from the original image, and a lack of task-independent WSI representations. An ideal improvement would be to develop an end-to-end pre-trained WSI model, but training it from scratch will face challenges such as high training costs and computational complexity. In this work, we deconstruct the key steps of ViT-based pathology image representation and propose a conversion strategy called E2E-ViT, which transforms a vanilla ViT into an end-to-end pre-trained WSI model without introducing additional parameters. E2E-ViT directly inputs the entire tissue region in WSIs to efficiently feed image sequences into the transformer backbone, achieving information interaction from the original receptive fields and generating slide features. Through multiple survival prediction tasks, we demonstrate that transformed pre-trained ViTs outperform two-stage MIL models and slide foundation models (SFM). Our work presents a new end-to-end learning paradigm that provides a promising direction for the next generation of computational pathology models.

Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a visual projector that maps the pixels into a sequence of tokens in its embedding space, so that images can be presented in essentially the same form as text. However, the language model has been optimized to operate on discrete, semantically meaningful tokens, while prevailing visual projectors transform an image into a long stream of continuous and highly correlated embeddings. This causes the visual tokens to behave differently from the word-like units that LLMs are originally trained to understand. We propose a novel Disentangled Visual Tokenization (DiVT) that clusters patch embeddings into coherent semantic units, so each token corresponds to a distinct visual concept instead of a rigid grid cell. DiVT further adapts its token budget to image complexity, providing an explicit accuracy compute trade-off modifying neither the vision encoder nor the language model. Across diverse multimodal benchmarks, DiVT matches or surpasses baselines with significantly fewer visual tokens, demonstrating robustness under limited token budgets, significantly reducing memory cost and latency while making visual inputs more compatible with LLMs. Our code is available at https://github.com/snuviplab/DiVT.

Audio-Visual Speech Recognition (AVSR) has achieved remarkable progress in offline conditions, yet its robustness in real-world video conferencing (VC) remains largely unexplored. This paper presents the first systematic evaluation of state-of-the-art AVSR models across mainstream VC platforms, revealing severe performance degradation caused by transmission distortions and spontaneous human hyper-expression. To address this gap, we construct MLD-VC, the first multimodal dataset tailored for VC, comprising 31 speakers, 22.79 hours of audio-visual data, and explicit use of the Lombard effect to enhance human hyper-expression. Through comprehensive analysis, we find that speech enhancement algorithms are the primary source of distribution shift, which alters the first and second formants of audio. Interestingly, we find that the distribution shift induced by the Lombard effect closely resembles that introduced by speech enhancement, which explains why models trained on Lombard data exhibit greater robustness in VC. Fine-tuning AVSR models on MLD-VC mitigates this issue, achieving an average 17.5% reduction in CER across several VC platforms. Our findings and dataset provide a foundation for developing more robust and generalizable AVSR systems in real-world video conferencing. MLD-VC is available at https://huggingface.co/datasets/nccm2p2/MLD-VC.

Visual Autoregressive (AR) models generate images by predicting discrete tokens that are decoded by a visual tokenizer.Despite demonstrating strong overall image generation ability, they still underperform on text rendering with blur strokes and disrupt letter shapes. In this work, we trace this limitation to the visual tokenizer, which struggles to reconstruct fine-grained detail.Improving the tokenizer is straightforward but expensive, as it necessitates retraining both the tokenizer and the AR model.Can we improve text rendering performance of AR models without retraining the existing tokenizer and AR model? To achieve this, we propose the Residual Decoder Adapter(\method) that upgrades an existing tokenizer post-hoc without changing its token space. Specifically, it refines the decoder output of the visual tokenizer by introducing two novel components: (i) a paired codebook that shares the token distribution with the original one; (ii) a parallel branch to learn the tiny differences (residual) between the reconstructed image and the ground-truth images in the pixel space. This residual design allows us to enhance the tokenizer non-invasively while preserving compatibility with prior AR models. \method substantially improves text rendering significantly by a large margin. For instance, we boost finetuned Janus-Pro OCR accuracy rises from 24.52% to 58.26% (TextVisionBlend), from 12.75% to 36.81% (StyledTextSynth) on competitive TextAtlas benchmark. Codes will be released.

Language-guided photo retouching aims to adjust color and tone while preserving geometry and texture. Recently, diffusion-based retouching shows a superior visual quality, but often struggles with both fidelity issues due to its generative nature and efficiency because of its iterative sampling process.In this work, we propose an efficient and fidelity-preserving retouching method using bilateral space manipulation, which is both compact and content-decoupled. Specifically, instead of directly editing pixels or image latents, our model predicts a low-resolution bilateral grid of affine transforms, which are sliced using a learned guidance map and then applied to the full-resolution image. This approach yields both high fidelity and improved efficiency.To retain strong priors of a pretrained generative model, we distill a multi-step diffusion model into our bilateral grid framework using Variational Score Distillation, complemented by a prompt alignment loss to guide instruction-following behavior. Additionally, we introduce a new benchmark and evaluate our method across multiple dimensions: fidelity, instruction following, and efficiency.Compared to the latest retouch methods, like Gemini-2.5-Flash (Nano-Banana), our method can avoid content drift, significantly improve latency, and generate visually pleasing edits, while maintaining a high level of fidelity.

Although normalization layers have long been viewed as indispensable components of deep learning architectures, the recent introduction of Dynamic Tanh (DyT) has demonstrated that alternatives are possible. The point-wise function DyT constrains extreme values for stable convergence and reaches normalization-level performance; this work seeks further for function designs that can surpass it. We first study how the intrinsic properties of point-wise functions influence training and performance. Building on these findings, we conduct a large-scale search for a more effective function design. Through this exploration, we introduce \mathrm Derf (x) = \mathrm erf (\alpha x + s), where \mathrm erf (x) is the rescaled Gaussian cumulative distribution function, and identify it as the most performant design. Derf outperforms LayerNorm, RMSNorm, and DyT across a wide range of domains, including visual recognition and generation, speech representation, and DNA sequence modeling. Our analysis also suggests that the performance gains of Derf largely stem from its improved generalization rather than stronger fitting capacity. Its simplicity and stronger performance make Derf a practical choice for normalization-free Transformer architectures.

Standard deep learning models for image segmentation cannot guarantee topology accuracy, failing to preserve the correct number of connected components or structures. This, in turn, affects the quality of the segmentations and compromises the reliability of the subsequent quantification analyses. Previous works have proposed to enhance topology accuracy with specialized frameworks, architectures, and loss functions. However, these methods are often cumbersome to integrate into existing training pipelines, they are computationally very expensive, or they are restricted to structures with tubular morphology. We present SCNP, an efficient method that improves topology accuracy by penalizing the logits with their poorest-classified neighbor, forcing the model to improve the prediction at the pixels' neighbors before allowing it to improve the pixels themselves. We show the effectiveness of SCNP across 13 datasets, covering different structure morphologies and image modalities, and integrate it into three frameworks for semantic and instance segmentation. Additionally, we show that SCNP can be integrated into several loss functions, making them improve topology accuracy. Our code can be found at https://jmlipman.github.io/SCNP-SameClassNeighborPenalization.

Image-to-Video (I2V) generation represents a frontier in content creation, where models synthesize dynamic visual sequences by jointly reasoning from both image and text prompts. This multimodal grounding enables diverse controllability over video attributes. However, it is precisely this capability that introduces a critical security blind spot: by exploiting the interplay between visual and textual cues, attackers can launch multimodal jailbreak attacks that severely compromise output security. Despite the increasing implementation of security mechanisms in real-world I2V systems, such cross-modal threats remain unexplored. Existing attack methods remain confined to single-modal settings, relying solely on isolated text or image perturbations, which severely limits their effectiveness. To bridge this gap, we propose Runaway Evil, the first multimodal jailbreaking framework for I2V models with dynamic evolutionary capability. Built on a Strategy-Tactic-Action paradigm, our framework exhibits self-amplifying attack through three core components: (1) a strategy-aware command unit that enables the attack to self-evolve its strategies through reinforcement learning-driven strategy customization and large language model (LLM)-based strategy exploration; (2) a multimodal tactical planning unit that generates synergistic text jailbreak instructions and image tampering guidelines based on the selected strategies; and (3) an tactical action Unit executes and evaluates the coordinated attacks. This self-evolving architecture allows the framework to continuously adapt and intensify its attack strategies without human intervention. Extensive experiments demonstrate that Runaway Evil achieves state-of-the-art attack success rates on commercial I2V models, such as Open-Sora 2.0 and CogVideoX. This work provides a critical tool for probing and mitigating multimodal vulnerabilities, laying a foundation for building more robust video generation systems. The code is available at: https://github.com/DeepSota/RunawayEvil.

Cardiovascular disease (CVD) diagnosis relies heavily on electrocardiograms (ECGs). However, most existing self-supervised uni-modal methods suffer from limited representational capacity, while multi-modal frameworks are hindered by coarse-grained semantic alignment across modalities, thus restricting their generalizability in clinical settings. To address these limitations, we propose TAMER, a Tri-modal contrastive Alignment and Multi-scale Embedding Refinement framework that jointly models ECG recordings, spectrograms, and diagnostic reports. TAMER is composed of three key components: First, the tri-modal feature encoding and projection (TFEP) module employs modality-specific encoders to extract global and local features from ECG recordings, spectrograms, and diagnostic reports, and projects them into latent spaces. Then, the global-local temporal-spectral alignment (GLTSA) module captures complementary rhythm- and wave-level characteristics via contrastive alignment and attentive interaction between temporal and spectral modalities. Finally, the report-aware alignment and refinement (RAAR) module performs diagnostic-level alignment and wave-level refinement with clinical reports, enabling semantic enrichment of ECG representations.Extensive experiments on three public ECG datasets demonstrate that TAMER achieves state-of-the-art zero-shot classification performance (AUC: 81.2%) and strong cross-domain generalization (AUC: 83.1%), outperforming existing uni-modal and multi-modal baselines methods.The source code is available at https://github.com/zhouxw12345/TAMER.

3D Gaussian Splatting (3DGS) enables high-quality novel view synthesis, motivating interest in generating higher-resolution renders than those available during training. A natural strategy is to apply super-resolution (SR) to low-resolution (LR) input views, but independently enhancing each image introduces multi-view inconsistencies, leading to blurry renders. Prior methods attempt to mitigate these inconsistencies through learned neural components, temporally consistent video priors, or joint optimization on LR and SR views, but all uniformly apply SR across every image. In contrast, our key insight is that close-up LR views may contain high-frequency information for regions also captured in more distant views, and that we can use the camera pose relative to scene geometry to inform where to add SR content. Building from this insight, we propose SplatSuRe, a method that selectively applies SR content only in undersampled regions lacking high-frequency supervision, yielding sharper and more consistent results. Across Tanks & Temples, Deep Blending and Mip-NeRF 360, our approach surpasses baselines in both fidelity and perceptual quality. Notably, our gains are most significant in localized foreground regions where higher detail is desired.

Although depth-assisted scene flow estimation has advanced rapidly, mainstream dense frameworks (e.g., RAFT-3D) still rely primarily on 2D feature correlations to optimize 3D motion fields, which hinders their ability to exploit 3D structural priors effectively and consequently limits robustness in complex scenes. We present SEA-Flow3D, a simple, efficient, and accurate framework for dense scene flow estimation. At its core lies a Spatial Vector Sampling (SVS) module that jointly samples 3D coordinates and correlation volumes within the local neighborhood of matched points, producing a direction-aware correlation representation with explicit spatial vectors and providing strong geometric guidance for subsequent optimization. Following the simplicity-and-efficiency principle, SEA-Flow3D adopts a RAFT-style multi-scale recurrent refinement architecture, integrating an RNN-based optimizer with context-guided upsampling to achieve higher accuracy with fewer iterations. Extensive experiments on KITTI and Sintel demonstrate that SEA-Flow3D achieves state-of-the-art performance while maintaining remarkable efficiency and a lightweight design. Code page: https://github.com/HanLingsgjk/SEAFLOW3D.

Large Vision-Language Models (LVLMs) have advanced multimodal learning but face high computational cost issues due to the input of large number of visual tokens, motivating token pruning to improve inference efficiency.The key challenge lies in identifying which tokens are truly important.Most existing approaches rely on attention- or similarity-based criteria to estimate token importance.However, they inherently suffer from certain limitations, such as being task-agnostic and exhibiting positional bias.In this work, we explore a new perspective on token importance assignment based on token transitions in LVLMs, where token transitions are defined as the changes in token representations occurring as they propagate through the model's modules.We observe that the transition of token representations provides a meaningful signal of semantic information.Based on this insight, we propose TransPrune, a training-free and efficient token pruning method.Specifically, TransPrune progressively prunes tokens by assessing their importance through a combination of Token Transition Variation (TTV), which measures changes in both the magnitude and direction of token representations; as well as Instruction-Guided Attention (IGA), which measures how strongly the instruction attends to visual tokens via attention.Extensive experiments on various LVLM architectures, such as LLaVA-v1.5, LLaVA-Next and Qwen2.5-VL, demonstrate that TransPrune maintains comparable multimodal performance while reducing inference TFLOPs by more than half. The code is available at https://github.com/liaolea/TransPrune.

Success in generative modeling across language, image, and video demonstrates that large, well-curated datasets are the key driver for building capable models. 3D Human motion, however, has lagged behind, constrained by an unsatisfying choice between small, high-fidelity motion capture datasets and large-scale in-the-wild collections dominated by static or low-quality sequences.We introduce RoMo, a rich, large-scale, carefully curated dataset of in-the-wild human motions that resolves these tradeoffs. To ensure quality, we introduce a taxonomy-aware filtering pipeline that aggressively removes static and artifact-prone sequences. Every sequence is annotated with detailed captions and organized by a novel three-level semantic taxonomy. This hierarchical structure provides the first benchmark for fine-grained, per-category evaluation, revealing model strengths and weaknesses obscured by global metrics. We demonstrate that models trained on RoMo achieve state-of-the-art fidelity and diversity while gaining a superior understanding of complex, subtle text prompts. Finally, we release the Motion Toolbox to standardize metrics, data conversion, and visualization, establishing a foundation for reproducible and interpretable motion generation research.

Understanding high-resolution (HR) images remains a critical challenge for multimodal large language models (MLLMs). Recent approaches leverage vision-based retrieval-augmented generation (RAG) to retrieve query-relevant crops from HR images, improving understanding capacity of MLLMs. However, this paradigm often leads to object fragmentation, resulting in semantic bias and incomplete retrieval, while also introducing false positives from irrelevant background patches. To address these issues, we propose Multi-resolution Retrieval-Detection (MRD), a training-free framework that enhances HR image understanding from both local and global perspectives. Locally, MRD enforces cross-scale semantic consistency via multi-resolution semantic fusion to mitigate single-resolution bias and alleviate object fragmentation. Globally, it integrates open-vocabulary object detection (OVD) as localization priors within a unified framework. Extensive experiments across multiple MLLMs on HR image benchmarks demonstrate that MRD achieves state-of-the-art (SOTA) performance on both single-object and multi-object understanding tasks. Code will be available at: https://github.com/yf0412/MRD.