CVPR 2026 Papers

While multimodal large language models (MLLMs) have shown remarkable success across a wide range of tasks, long-form video understanding remains a significant challenge.In this study, we focus on video understanding by MLLMs.This task is challenging because processing a full stream of RGB frames is computationally intractable and highly redundant, as self-attention have quadratic complexity with sequence length.In this paper, we propose ReMoRa, a video MLLM that processes videos by operating directly on their compressed representations.A sparse set of RGB keyframes is retained for appearance, while temporal dynamics are encoded as a motion representation, removing the need for sequential RGB frames.These motion representations act as a compact proxy for optical flow, capturing temporal dynamics without full frame decoding.To refine the noise and low fidelity of block-based motions, we introduce a module to denoise and generate a fine-grained motion representation.Furthermore, our model compresses these features in a way that scales linearly with sequence length.We demonstrate the effectiveness of ReMoRa through extensive experiments across a comprehensive suite of long-video understanding benchmarks.ReMoRa outperformed baseline methods on multiple challenging benchmarks, including LongVideoBench, NExT-QA, and MLVU. Our project page is available at https://remora-v1rcm.kinsta.page/.

We present MeshFlow, a new method for compressing and generating artist-like 3D meshes. Current mesh generators often adopt Auto-Regressive (AR) next-token prediction, a natural choice given the discrete nature of mesh connectivity, which, however, scales poorly due to the inference cost being quadratic in mesh size. AR methods also require discretizing the vertex coordinates, which introduces quantization errors and can cause vertex collapse. To address these challenges, we introduce a Variational Autoencoder (VAE) that, supervised with a contrastive loss, represents both continuous vertex positions and discrete connectivity in a continuous latent space.This latent space is significantly more compact than prior token-based mesh representations. We then build a 3D generator based on a Rectified-Flow transformer, which generates all mesh vertices and edges in parallel. This model samples meshes 26xfaster than the fastest AR generator while also achieving state-of-the-art accuracy across standard mesh-generation metrics.

Color grading is central to High Dynamic Range (HDR) video production, shaping the perceptual tone, contrast, and luminance of content across diverse displays. However, evaluating HDR color grading quality is particularly difficult due to its semantic, content-dependent nature and the lack of large-scale annotated data. While pre-trained Vision-Language Models (VLMs) offer strong semantic priors and generalization ability, their exposure is limited to Standard Dynamic Range (SDR) data, making them poorly equipped to handle HDR photometry and perceptual nuances. We propose HDR-VLM, the first method to adapt a VLM to the HDR domain for perceptual quality assessment. Specifically, HDR-VLM employs a two-stage design: it first bridges the domain gap using a unified HLG-based encoding and progressive adaptation; then it aligns model assessments with noisy, multi-scale human preferences via reinforcement learning with curriculum-inspired rewards. Experiments on a real-world, production-sourced HDR dataset show that HDR-VLM not only outperforms existing quality assessment methods but also produces interpretable attribution rationales. These rationales offer actionable guidance for content creators, enhancing the reliability and transparency of automated HDR quality evaluation.

This work studies how latent space structure impacts the performance of Latent Diffusion Models (LDMs). We show that effective generation requires a latent space that is simultaneously locally smooth, enabling stable and reliable reconstruction, and globally dispersive, allowing the model to draw diverse and meaningful samples without collapsing into narrow regions of the latent space. However, existing approaches often emphasize smoothness, which may lead to concentrated latent regions and limited exploration of the broader space. To address these limitations, we propose Self-Organized Representation Learning (SORL), a bottom-up training paradigm inspired by self-organization in complex systems, where global structure emerges naturally from simple local interactions. The critical latent properties of smoothness and maximal dispersity are not explicitly imposed. Instead, SORL promotes these properties through two complementary local mechanisms: local attraction, which encourages coherent reconstructions among nearby latent codes, and local repulsion, which prevents latent codes from collapsing into dense clusters. Through their interaction, SORL induces a latent manifold that maintains both local smoothness and global dispersity, leading to improved reconstruction and generation.

Automatic vision inspection holds significant importance in industry inspection. While multimodal large language models (MLLMs) exhibit strong language understanding capabilities and hold promise for this task, their performance remains significantly inferior to that of human experts. In this context, we identify two key challenges: (i) insufficient integration of anomaly detection (AD) knowledge during pre-training and (ii) the lack of technically precise and context-aware language generation for anomaly reasoning. To address these issues, we propose ADSeeker, an anomaly task assistant designed to enhance inspection performance through knowledge-grounded reasoning. ADSeeker first leverages a curated visual document knowledge base, SEEK-MVTec&VisA (SEEK-M&V), which we construct to address the limitations of existing resources that rely solely on unstructured text. SEEK-M&V includes semantic-rich descriptions and image-document pairs, enabling more comprehensive anomaly understanding. To effectively retrieve and utilize this knowledge, we introduce the Query Image-Knowledge Retrieval-Augmented Generation (Q2K RAG) framework. To further enhance the performance in zero-shot anomaly detection (ZSAD), ADSeeker leverages the Hierarchical Sparse Prompt mechanism and type-level features to efficiently extract anomaly patterns. Furthermore, to tackle the challenge of limited industry anomaly detection (IAD) data, we introduce the largest-scale AD dataset, Multi-type Anomaly (MulA), encompassing 72 multi-scale defect types across 26 categories. Extensive experiments show that our plug-and-play framework, ADSeeker, achieves state-of-the-art zero-shot performance on several benchmark datasets.

Pretrained Vision-Language Models (VLMs) like CLIP show promise in continual learning, but existing Few-Shot Class-Incremental Learning (FSCIL) methods assume homogeneous domains and balanced data distributions, limiting real-world applicability where data arises from heterogeneous disciplines with imbalanced sample availability and varying visual complexity. We identify Domain Gravity, a representational asymmetry where data imbalance across heterogeneous domains causes overrepresented or low-entropy domains to disproportionately influence the embedding space, leading to prototype drift and degraded performance on underrepresented or high-entropy domains. To address this, we introduce Cross-Discipline Variable Few-Shot Class-Incremental Learning (XD-VSCIL), a benchmark capturing real-world heterogeneity and imbalance where Domain Gravity naturally intensifies. We propose Hybrid Prototype Calibration (HyCal), a training-free method combining cosine similarity and Mahalanobis distance to capture complementary geometric properties--directional alignment and covariance-aware magnitude--yielding stable prototypes under imbalanced heterogeneous conditions. Operating on frozen CLIP embeddings, HyCal achieves consistent retention-adaptation improvements while maintaining efficiency. Experiments show HyCal effectively mitigates Domain Gravity and outperforms existing methods in imbalanced cross-domain incremental learning.

Video understanding with multimodal large language models (MLLMs) remains challenging due to the long token sequences of videos, which contain extensive temporal dependencies and redundant frames.Existing approaches typically treat MLLMs as passive recognizers, processing entire videos or uniformly sampled frames without adaptive reasoning.Recent agent-based methods introduce external tools, yet still depend on manually designed workflows and perception-first strategies, resulting in inefficiency on long videos. We present EVA, an Efficient Reinforcement Learning framework for End-to-End Video Agent, which enables planning-before-perception through iterative summary-plan-action-reflection reasoning.EVA autonomously decides what to watch, when to watch, and how to watch, achieving query-driven and efficient video understanding.To train such agents, we design a simple yet effective three-stage learning pipeline--comprising supervised fine-tuning (SFT), Kahneman-Tversky Optimization (KTO), and Group Relative Policy Optimization (GRPO)--that bridges supervised imitation and reinforcement learning.We further construct high-quality datasets for each stage, supporting stable and reproducible training.We evaluate EVA on six video understanding benchmarks, demonstrating its comprehensive capabilities. Compared with existing baselines, EVA achieves a substantial improvement of 6--12% over general MLLM baselines and a further 1--3% gain over prior adaptive agent methods.

Large Multimodal Models (LMMs) have shown remarkable success in visual understanding tasks. LMMs encode visual and textual inputs into tokens, which are then processed by Large Language Models (LLMs). However, the large number of visual tokens poses a major bottleneck for inference efficiency and memory usage. Reducing visual tokens is a promising training-free solution, but existing methods remain limited. Importance-based approaches suffer from poor generalization, are incompatible with kernel-level inference optimizations, and only consider information from a single modality. Diversity-based strategies typically focus on pairwise token redundancy and treat all tokens as equally important. Recent attempts to sequentially combine importance and diversity criteria still fail to address the intrinsic drawbacks of their underlying metrics. To address these limitations, we reformulate visual token reduction as an optimal subset selection problem jointly guided by two complementary objectives: informativeness and coverage. Informativeness is quantified through per-token intrinsic saliency and visual-textual alignment, while coverage is enforced via a volume-based subset selection criterion that ensures global representativeness in the visual feature space. This joint formulation effectively integrates visual saliency, cross-modal alignment, and global coverage in an end-to-end token selection process, yielding a computationally efficient, model-agnostic framework compatible with modern inference accelerators. Extensive experiments demonstrate that CoIn substantially reduces computation and memory cost while maintaining strong task performance.

Zero-shot image denoising has gained prominence in recent years, as it inherently relies on the intrinsic priors of images rather than learning from external data. Nevertheless, most existing methods either fail to fully exploit global priors, or do not properly preserve the fine-grained details governed by local priors. In this work, we propose a novel framework of pseudo sample generation for zero-shot denoising guided by local and global image priors. Specifically, we propose a well-crafted down-sampler based on gradient merging and grouping within a small window to generate down-sampled samples by exploiting spatial locality. Meanwhile, a global random sampler conditioned on a Gaussian distribution is devised to incorporate the nonlocal self-similarity of natural images. These two samplers build a new paradigm of pseudo sample generation powered by both local and global priors, which is termed as Zero-Shot Hybrid Prior-guided Denoising (ZS-HPD). Considering that noise is more likely to affect high-frequency details, we also present a simple yet effective loss that works in the Fourier domain and applies discriminative weights to distinct spectral bands. Numerous experiments on benchmark datasets have demonstrated the superiority of our ZS-HPD over existing advanced methods. The code of our ZS-HPD will be available at here.

This paper addresses the critical and underexplored challenge of long video understanding with low computational budgets.We propose LongVideo-R1, an active, reasoning-equipped multimodal large language model (MLLM) agent designed for efficient video context navigation, avoiding the redundancy of exhaustive search.At the core of LongVideo-R1 lies a reasoning module that leverages high-level visual cues to infer the most informative video clip for subsequent processing.During inference, the agent initiates traversal from top-level visual summaries and iteratively refines its focus, immediately halting the exploration process upon acquiring sufficient knowledge to answer the query.To facilitate training, we first extract hierarchical video captions from CGBench, a video corpus with grounding annotations, and guide GPT-5 to generate 33K high-quality chain-of-thought-with-tool trajectories. The LongVideo-R1 agent is fine-tuned upon the Qwen-3-8B model through a two-stage paradigm: supervised fine-tuning (SFT) followed by reinforcement learning (RL), where RL employs a specifically designed reward function to maximize selective and efficient clip navigation.Experiments on multiple long video benchmarks validate the effectiveness of name, which enjoys superior tradeoff between QA accuracy and efficiency. All curated data and source code are provided in the supplementary material and will be made publicly available.

Accurate metric depth is critical for autonomous driving perception and simulation, yet current approaches struggle to achieve high metric accuracy, multi-view and temporal consistency, and cross-domain generalization. To address these challenges, we present DriveMVS, a novel multi-view stereo framework that reconciles these competing objectives through two key insights: (1) Sparse but metrically accurate LiDAR observations can serve as geometric prompts to anchor depth estimation in absolute scale, and (2) deep fusion of diverse cues is essential for resolving ambiguities and enhancing robustness, while a spatio-temporal decoder ensures consistency across frames. Built upon these principles, DriveMVS embeds the LiDAR prompt in two ways: as a hard geometric prior that anchors the cost volume, and as soft feature-wise guidance fused by a triple-cue combiner. Regarding temporal consistency, DriveMVS employs a spatio-temporal decoder that jointly leverages geometric cues from the MVS cost volume and temporal context from neighboring frames. Experiments show that DriveMVS achieves state-of-the-art performance on multiple benchmarks, excelling in metric accuracy, temporal stability, and zero-shot cross-domain transfer, demonstrating its practical value for scalable, reliable autonomous driving systems. Code: https://github.com/Akina2001/DriveMVS.git.

Multimodal sentiment analysis requires integrating language, visual, and acoustic cues, yet these modalities are often noisy, incomplete, or contradictory, making fusion unreliable. Most existing methods assume uniformly trustworthy modalities and thus degrade when signals conflict. To address this, we propose CICA, a framework that couples Confidence-Aware Pretraining with Confidence-Informed Attention. In pretraining, each modality encoder learns to estimate the reliability of its own representation, producing both embeddings and confidence scores. These scores then guide a confidence-informed attention mechanism, which strengthens contributions from reliable modalities while suppressing noisy or conflicting ones, enabling adaptive fusion under varying signal conditions. CICA achieves state-of-the-art performance across four major benchmarks on MOSI, MOSEI, CH-SIMS, and CH-SIMSv2. It achieves MAE 0.630 and Corr 0.855 on MOSI, and MAE 0.489 and Corr 0.856 on MOSEI, significantly surpassing prior methods. Consistent improvements are also observed across Acc-7, Acc-2, and F1 metrics. Under noisy and missing-modality conditions, CICA maintains significantly more stable performance, indicating improved robustness and interpretability.

Intraoperative bleeding in laparoscopic surgery causes rapid obscuration of the operative field to hinder the surgical process and increases the risk of postoperative complications. Intelligent detection of bleeding areas can quantify the blood loss to assist decision-making, while locating bleeding points helps surgeons quickly identify the source of bleeding and achieve hemostasis in time to improve surgical success rates. To fill the benchmark gap, we first construct a real-world laparoscopic surgical bleeding detection dataset, named SurgBlood, comprising 5,330 frames from 95 surgical video clips with bleeding region and point annotations. Accordingly, we develop a dual-task synergistic online detector called BlooDet, enabling simultaneous detection of bleeding regions and points in laparoscopic surgery. The baseline embraces a dual-branch bidirectional guidance design based on Segment Anything Model 2. The mask branch detects bleeding regions through adaptive edge and point prompt embeddings, while the point branch leverages mask memory to induce bleeding point memory modeling and captures point motion direction via inter-frame optical flow. By coupled bidirectional guidance, our framework explores spatial-temporal correlations while exploiting memory modeling to infer current bleeding status. Extensive experiments indicate that our method outperforms 13 counterparts in bleeding detection. Code and data are available at https://github.com/PJLallen/SurgBlood.

We introduce C-GenReg, a training-free framework for 3D point cloud registration that leverages the complementary strengths of world-scale generative priors and registration-oriented Vision Foundation Models (VFMs). Current learning-based 3D point cloud registration methods struggle to generalize across sensing modalities, sampling differences, and environments. Hence, C-GenReg augments the geometric point cloud registration branch by transferring the matching problem into an auxiliary image domain, where VFMs excel, using a World Foundation Model to synthesize multi-view-consistent RGB representations from the input geometry. This generative transfer preserves spatial coherence across source and target views without any fine-tuning. From these generated views, a VFM pretrained for finding dense correspondences extracts matches. The resulting pixel correspondences are lifted back to 3D via the original depth maps. To further enhance robustness, we introduce a "Match-then-Fuse" probabilistic cold-fusion scheme that combines two independent correspondence posteriors, that of the generated-RGB branch with that of the raw geometric branch. This principled fusion preserves each modality's inductive bias and provides calibrated confidence without any additional learning. C-GenReg is zero-shot and plug-and-play: all modules are pretrained and operate without fine-tuning. Extensive experiments on indoor (3DMatch, ScanNet) and outdoor (Waymo) benchmarks demonstrate strong zero-shot performance and superior cross-domain generalization. For the first time, we demonstrate a generative registration framework that operates successfully on real outdoor LiDAR data, where imagery is unavailable.

In this work, we introduce LLaDA-V, a purely diffusion-based Multimodal Large Language Model (MLLM) that integrates visual instruction tuning with masked diffusion models, representing a departure from the autoregressive paradigms dominant in current multimodal approaches. Built upon LLaDA, a representative large language diffusion model, LLaDA-V incorporates a vision encoder and MLP connector that projects visual features into the language embedding space, leveraging diffusion language models' bidirectional attention to capture spatial relationships in visual data more effectively than causal, sequential processing. Our empirical investigation reveals several intriguing results: First, LLaDA-V demonstrates promising multimodal performance despite its language model being weaker on purely textual tasks than counterparts like LLaMA3-8B and Qwen2-7B. When trained on the same instruction data, LLaDA-V is highly competitive with LLaMA3-V across multimodal tasks and shows promising data scaling behavior on several benchmarks. It also narrows the performance gap to Qwen2-VL, suggesting the effectiveness of its architecture for multimodal tasks. Second, LLaDA-V achieves state-of-the-art performance in multimodal understanding compared to existing purely diffusion-based MLLMs. Our findings suggest that large language diffusion models show promise in multimodal contexts and warrant further investigation. To facilitate future research, we open-source LLaDA-V together with its training and evaluation code at https://github.com/ML-GSAI/LLaDA-V.

Despite recent progress in 3D visual grounding, existing methods still struggle with three core challenges: 1) cross-modal misalignment that prevents textual cues from being reliably delivered to visual representations, 2) intra-class confusion arising from insufficient understanding of fine-grained expression cues, and 3) geometric reasoning errors caused by inaccurate aggregation of spatially relevant visual features. We propose EG-3DVG, a unified framework that addresses these issues through an expression and geometry aware grounding decoder. The decoder integrates two complementary attention modules--position-guided expression cross-attention (PECA) for reliable text-vision alignment and geometry-aware masked attention (GMA) for selective aggregation of geometry-consistent visual cues. To further distinguish semantically similar instances, we introduce expression-aware contrastive learning (ECL), which strengthens the alignment between the target object token and expression-relevant words. Extensive experiments on ScanRefer and SR3D/NR3D demonstrate that EG-3DVG achieves state-of-the-art performance in both 3D bounding box localization and mask prediction, validating the effectiveness of our geometry- and expression-aware design.

We introduce MOMO, the first multi-sensor foundation model for Mars remote sensing. MOMO uses model merge to integrate representations learned independently from three key Martian sensors (HiRISE, CTX, and THEMIS), spanning resolutions from 0.25 m/pixel to 100 m/pixel. Central to our method is our novel Equal Validation Loss (EVL) strategy, which aligns checkpoints across sensors based on validation loss similarity before fusion via task arithmetic. This ensures models are merged at compatible convergence stages, leading to improved stability and generalization. We train MOMO on a large-scale, high-quality corpus of 12 million samples curated from Mars orbital data and evaluate it on 9 downstream tasks from Mars-Bench. MOMO achieves better overall performance compared to ImageNet pre-trained, earth observation foundation model, sensor-specific pre-training, and fully-supervised baselines. Particularly on segmentation tasks, MOMO shows consistent and significant performance improvement. Our results demonstrate that model merging through an optimal checkpoint selection strategy provides an effective approach for building foundation models for multi-resolution data. The model weights, pretraining code, pretraining data, and evaluation code are available at: github.com/kerner-lab/MOMO.

Automatically extracting chemical structures from documents is essential for the large-scale analysis of the literature in chemistry. Automatic pipelines have been developed to recognize molecules represented either in figures or in text independently. However, methods for recognizing chemical structures from multimodal descriptions (Markush structures) lag behind in precision and cannot be used for automatic large-scale processing. In this work, we present MarkushGrapher-2, an end-to-end approach for the multimodal recognition of chemical structures in documents. First, our method employs a dedicated OCR model to extract text from chemical images. Second, the text, image, and layout information are jointly encoded through a Vision-Text-Layout encoder and an Optical Chemical Structure Recognition vision encoder. Finally, the resulting encodings are effectively fused through a two-stage training strategy and used to auto-regressively generate a representation of the Markush structure. To address the lack of training data, we introduce an automatic pipeline for constructing a large-scale dataset of real-world Markush structures. In addition, we present IP5-M, a large manually-annotated benchmark of real-world Markush structures, designed to advance research on this challenging task. Extensive experiments show that our approach substantially outperforms state-of-the-art models in multimodal Markush structure recognition, while maintaining strong performance in molecule structure recognition. Code, models, and datasets will be released publicly.

Vision-language models like CLIP have achieved remarkable progress in cross-modal representation learning, yet suffer from systematic misclassifications among visually and semantically similar categories. We observe that such confusion patterns are not random but persistently occur between specific category pairs, revealing the model's intrinsic bias and limited fine-grained discriminative ability. To address this, we propose CAPT, a Confusion-Aware Prompt Tuning framework that enables models to learn from their own misalignment. Specifically, we construct a Confusion Bank to explicitly model stable confusion relationships across categories and misclassified samples. On this basis, we introduce a Semantic Confusion Miner (SEM) to capture global inter-class confusion through semantic difference and commonality prompts, and a Sample Confusion Miner (SAM) to retrieve representative misclassified instances from the bank and capture sample-level cues through a Diff-Manner Adapter that integrates global and local contexts. To further unify confusion information across different granularities, a Multi-Granularity Difference Expert (MGDE) module is designed to jointly leverage semantic- and sample-level experts for more robust confusion-aware reasoning. Extensive experiments on 11 benchmark datasets demonstrate that our method significantly reduces confusion-induced errors while enhancing the discriminability and generalization of both base and novel classes, successfully resolving 50.72 percent of confusable sample pairs. Code will be released at https://github.com/greatest-gourmet/CAPT.