Open-vocabulary semantic segmentation aims to partition an image into distinct semantic regions based on an open set of categories. Existing approaches primarily rely on image-level pre-trained vision-language models to perform this pixel-level task. In this paper, we propose SED, a simple yet effective encoder-decoder architecture for open-vocabulary semantic segmentation leveraging pre-trained vision-language models. SED consists of a hierarchical image encoder, a text encoder, and a gradual fusion decoder. The hierarchical image encoder and text encoder collaboratively generate a cost volume, which is progressively decoded by the gradual fusion decoder to produce segmentation results. In contrast to a plain encoder, the hierarchical encoder better captures image detail information while maintaining linear computational complexity with respect to input size. The gradual fusion decoder adopts a top-down structure to progressively integrate high-resolution features with the cost volume. Furthermore, a category early rejection strategy is introduced in gradual fusion decoder to filter out non-existent categories at different layers, significantly improving inference efficiency. Based on SED, we further introduce two modules, including non-label text embedding and additional category early rejection in the encoder. Moreover, we extend our method with minimal decoder modification for open-vocabulary video semantic segmentation. Extensive experiments on multiple datasets validate the effectiveness and efficiency of our proposed method. With ConvNeXt-B, our method achieves an mIoU of 34.9% on the ADE20 K with 150 classes (i.e., A-150) at an inference speed of 69 ms per image on a single A6000 GPU, and has an mIoU score of 40.2% on video segmentation dataset VSPW.

This paper reviews the NTIRE 2026 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a network that reduces one or several aspects, such as runtime, parameters, and FLOPs, while maintaining PSNR of around 26.90 dB on the DIV2K_LSDIR_valid dataset, and 26.99 dB on the DIV2K_LSDIR_test dataset. The challenge had 95 registered participants, and 15 teams made valid submissions. They gauge the state-of-the-art results for efficient single-image super-resolution.

Unified multimodal models can both understand and generate visual content within a single architecture. Existing models, however, remain data-hungry and too heavy for deployment on edge devices. We present Mobile-O, a compact vision-language-diffusion model that brings unified multimodal intelligence to a mobile device. Its core module, the Mobile Conditioning Projector (MCP), fuses vision-language features with a diffusion generator using depthwise-separable convolutions and layerwise alignment. This design enables efficient cross-modal conditioning with minimal computational cost. Trained on only a few million samples and post-trained in a novel quadruplet format (generation prompt, image, question, answer), Mobile-O jointly enhances both visual understanding and generation capabilities. Despite its efficiency, Mobile-O attains competitive or superior performance compared to other unified models, achieving 74

Diffusion Transformers (DiTs) power high-fidelity video world models but remain computationally expensive due to sequential denoising and costly spatio-temporal attention. Training-free feature caching accelerates inference by reusing intermediate activations across denoising steps; however, existing methods largely rely on a Zero-Order Hold assumption i.e., reusing cached features as static snapshots when global drift is small. This often leads to ghosting artifacts, blur, and motion inconsistencies in dynamic scenes. We propose \textbf{WorldCache}, a Perception-Constrained Dynamical Caching framework that improves both when and how to reuse features. WorldCache introduces motion-adaptive thresholds, saliency-weighted drift estimation, optimal approximation via blending and warping, and phase-aware threshold scheduling across diffusion steps. Our cohesive approach enables adaptive, motion-consistent feature reuse without retraining. On Cosmos-Predict2.5-2B evaluated on PAI-Bench, WorldCache achieves \textbf{2.3$\times$} inference speedup while preserving \textbf{99.4\%} of baseline quality, substantially outperforming prior training-free caching approaches. Our code can be accessed on \href{https://umair1221.github.io/World-Cache/}{World-Cache}.

Pre-trained video large language models excel at visual reasoning. However, they struggle when videos arrive with auxiliary streams, such as audio, depth map, or dense temporal evidence. In such a scenario, uniform fusion induces modality interference, allowing irrelevant channels to distract the model. To address this issue, we present a unified multimodal video understanding framework, named UniMVU, that performs instruction-aware fusion across video, audio, depth map, or any other modality inputs via two levels of dynamic gating: inner-modality gates emphasize salient regions within each modality, whereas modality-level gates re-weight whole streams; both are conditioned on the text instruction to adaptively balance modality importance. Our UniMVU combines cross-modal self-attention with instruction-driven inner-modality gating module and a modality-level gating module with control token; for time-aligned streams we further adopt a fast-to-slow fusion scheme that reduces redundancy. Across six benchmarks (AVQA, AVSD, Music-AVQA, ScanQA, SQA3D and MVBench), our UniMVU achieves consistent gains over static-fusion baselines achieving gains as high as 13.5 in terms of CIDEr metric. Further, our analysis shows that the gating mechanism aligns with the human-interpretable modality relevance, and ablations show the contributions of inner-modality and modality-level gating. Our UniMVU provides a simple, unified recipe for instruction-aware multimodal video understanding that scales to diverse modalities without hand-crafted fusion rules.

Recent progress in multimodal reasoning has enabled agents that can interpret imagery, connect it with language, and perform structured analytical tasks. Extending such capabilities to the remote sensing domain remains challenging, as models must reason over spatial scale, geographic structures, and multispectral indices while maintaining coherent multi-step logic. To bridge this gap, OpenEarthAgent introduces a unified framework for developing tool-augmented geospatial agents trained on satellite imagery, natural-language queries, and detailed reasoning traces. The training pipeline relies on supervised fine-tuning over structured reasoning trajectories, aligning the model with verified multistep tool interactions across diverse analytical contexts. The accompanying corpus comprises 14,538 training and 1,169 evaluation instances, with more than 100K reasoning steps in the training split and over 7K reasoning steps in the evaluation split. It spans urban, environmental, disaster, and infrastructure domains, and incorporates GIS-based operations alongside index analyses such as NDVI, NBR, and NDBI. Grounded in explicit reasoning traces, the learned agent demonstrates structured reasoning, stable spatial understanding, and interpretable behaviour through tool-driven geospatial interactions across diverse conditions. We report consistent improvements over a strong baseline and competitive performance relative to recent open and closed-source models.

Although the eye may appear static during fixation, it is in constant motion–transforming visual input into rich spatio-temporal streams of neuronal activity. These movements challenge the classical view that visual acuity derives from spatial sampling, suggesting that hyperacuity can emerge from precise temporal encoding. Here we show that artificial systems can exploit this principle using retina-like event-based (EB) sensing, a neuromorphic approach in which the sensor emits asynchronous spikes in response to luminance changes. Using an EB camera undergoing controlled “fixational” motion over tiny, pixelated images, we generated datasets in which recognition depends on sub-pixel information. We found that artificial neural networks trained on these spatio-temporal event streams relied crucially on the precise temporal information and outperformed conventional frame-based models. The learned representations also supported Vernier-style sub-pixel discrimination, demonstrating hyperacuity-like behavior in the artificial bio-mimetic system. These results show that active event-based sensing can use precise timing to recover spatial details that are unrecoverable from a static single frame. Together, these findings offer a new perspective on visual perception, open pathways for advancing neuromorphic engineering and energy-efficient AI vision systems, and provide a framework for testing hypotheses about biological vision. Unlike conventional frame-based vision, biomimetic event-based sensing preserves precise temporal information. The authors show that these timing signals can be exploited to recover spatial details from tiny images, enabling event-based vision to outperform frame-based approaches.

Modern Earth observation (EO) increasingly leverages deep learning to harness the scale and diversity of satellite imagery across sensors and regions. While recent foundation models have demonstrated promising generalization across EO tasks, many remain limited by the scale, geographical coverage, and spectral diversity of their training data, factors critical for learning globally transferable representations. In this work, we introduce TerraFM, a scalable self-supervised learning model that leverages globally distributed Sentinel-1 and Sentinel-2 imagery, combined with large spatial tiles and land-cover aware sampling to enrich spatial and semantic coverage. By treating sensing modalities as natural augmentations in our self-supervised approach, we unify radar and optical inputs via modality-specific patch embeddings and adaptive cross-attention fusion. Our training strategy integrates local-global contrastive learning and introduces a dual-centering mechanism that incorporates class-frequency-aware regularization to address long-tailed distributions in land cover. TerraFM achieves strong generalization on both classification and segmentation tasks, outperforming prior models on GEO-Bench and Copernicus-Bench. Our code and pretrained models will be publicly released.

Colonoscopy is currently one of the most sensitive screening methods for colorectal cancer. This study investigates the frontiers of intelligent colonoscopy techniques and their prospective implications for multimodal medical applications. With this goal, we begin by assessing the current data-centric and model-centric landscapes through four tasks for colonoscopic scene perception, including classification, detection, segmentation, and vision-language understanding. Our assessment reveals domain-specific challenges and underscores the need for further multimodal research in colonoscopy. To address these gaps, we establish three foundational initiatives: a large-scale multimodal instruction tuning dataset ColonINST, a colonoscopy-designed multimodal language model ColonGPT, and a multimodal benchmark. To facilitate continuous advancements in this rapidly evolving field, we provide a public website for the latest updates: https://github.com/ai4colonoscopy/IntelliScope .

A significant research effort is focused on exploiting the outstanding capacities of pretrained diffusion models for image editing. Approaches either fine tune the model, or invert the image in the latent space of the pretrained model. However, they suffer from two problems: (i) unsatisfactory results in selected regions and unexpected changes in non-selected regions, and (ii) the need for careful text prompt editing: the prompt should include all visual objects in the input image. To address this, we propose two improvements: (i) only optimizing the input of the value linear network in the cross-attention layers is sufficiently powerful to reconstruct a real image, and (ii) attention regularization to preserve the object-like attention maps after reconstruction and editing, enabling accurate style editing without causing significant structural change. We further improve the editing technique used for the unconditional branch of classifier-free guidance as used by P2P. Extensive experimental prompt-editing results on a variety of images demonstrate qualitatively and quantitatively that our method has editing capabilities superior to those of existing and concurrent works. Our StyleDiffusion code is available at https://github.com/sen-mao/StyleDiffusion.

Customized text-to-video generation (CTVG) has recently witnessed great progress in generating tailored videos from user-specific text. However, most CTVG methods assume that personalized concepts remain static and do not expand incrementally over time. Additionally, they struggle with forgetting and concept neglect when continuously learning new concepts, including subjects and motions. To resolve the above challenges, we develop a novel Continual Customized Video Diffusion (CCVD) model, which can continuously learn new concepts to generate videos across various text-to-video generation tasks by tackling forgetting and concept neglect. To address catastrophic forgetting, we introduce a concept-specific attribute retention module and a task-aware concept aggregation strategy. They can capture the unique characteristics and identities of old concepts during training, while combining all subject and motion adapters of old concepts based on their relevance during testing. Besides, to tackle concept neglect, we develop a controllable conditional synthesis to enhance regional features and align video contexts with user conditions, by incorporating layer-specific region attention-guided noise estimation. Extensive experimental comparisons demonstrate that our CCVD outperforms existing CTVG models.

Unsupervised anomaly segmentation in multi-sequence MRI is a promising way to scale lesion screening, but existing reconstruction-based methods face three persistent issues: they fail to generalize across modalities, they depend on hand-crafted masking or paired translations, and they often require separate models with high inference cost. In this work, we take a stepwise approach to address these limitations. In the first stage, we fully finetune a diffusion model on healthy brain MRI slices pooled across T1, T2, and FLAIR, which produces anatomically consistent reconstructions. To further improve, we introduce a lightweight second stage where modality-specific LoRA adapters are trained on top of the pretrained diffusion backbone. A simple router automatically selects the right adapter for each input, effectively turning the system into a modality-aware, agentic-like framework. To further stabilize reconstructions, we incorporate a learnable latent-frequency mask that suppresses non-informative spectral components and preserves structural detail. This design allows the model to emphasize healthy anatomy while efficiently capturing modality-dependent contrasts. This two-stage strategy boosts Dice to 88% on BraTS2021 (FLAIR), achieving state-of-the-art performance. Experiments on BraTS2021, ISLES, and ATLAS datasets confirm that the approach consistently improves Dice and SSIM across all modalities, outperforming diffusion, masking, and cycle-based baselines, and offering a practical balance between accuracy and efficiency for clinical MRI anomaly detection. Source code is available at https://github.com/wafaalghallabi/mri-router.

Vision Transformer (ViT) has shown impressive performance in image restoration due to its ability to capture a large receptive field. However, its complexity grows quadratically with input resolution, limiting its applicability for high-resolution images. In contrast, Convolutional Neural Networks (CNNs) are computationally efficient but are constrained by their inherently local receptive fields, which limit their ability to capture long-range pixel relationships. To address these challenges, we propose StarIR, which possesses the efficiency of CNNs while also capturing a large receptive field, similar to Transformers. StarIR incorporates two key innovations: 1) a dual-domain representation learning framework, with one branch processing spatial details and the other focusing on mesoscale interactions in the frequency domain; and 2) a high-dimensional feature fusion mechanism, the Star operation, which fuses information from both domains through element-wise multiplication, thereby enhancing representational capacity without increasing network width and depth. Our Star operation is followed by a channel attention unit to facilitate global feature modeling and enhance channel-wise interactions. Building on our straightforward yet powerful design principles, StarIR achieves state-of-the-art performance across 21 datasets covering six single-degradation image restoration tasks. Furthermore, our model performs favorably against leading algorithms in two all-in-one settings and demonstrates robustness on two composite-degradation datasets. In addition, StarIR extends well to several domain-specific applications, including ultra-high-definition (UHD) imaging, remote sensing, medical imaging, and underwater image enhancement.

Deep learning is developing rapidly and handling common computer vision tasks well. It is time to pay attention to more complex vision tasks, as model size, knowledge, and reasoning capabilities continue to improve. In this paper, we introduce and review a family of complex tasks, termed Concealed Dense Prediction (CDP), which has great value in agriculture, industry, etc. CDP's intrinsic trait is that the targets are concealed in their surroundings, thus fully perceiving them requires fine-grained representations, prior knowledge, auxiliary reasoning, etc. The contributions of this review are three-fold: (i) We introduce the scope, characteristics, and challenges specific to CDP tasks and emphasize their essential differences from generic vision tasks. (ii) We develop a taxonomy based on concealment counteracting to summarize deep learning efforts in CDP through experiments on three tasks. We compare 25 state-of-the-art methods across 12 widely used concealed datasets. (iii) We discuss the potential applications of CDP in the large model era and summarize 6 potential research directions. We offer perspectives for the future development of CDP by constructing a large-scale multimodal instruction fine-tuning dataset, CvpINST, and a concealed visual perception agent, CvpAgent.

When a model produces a correct solution under reinforcement learning with verifiable rewards (RLVR), every token receives the same reward signal regardless of whether it was a decisive reasoning step or a grammatical filler. A natural fix is to condition the model on the correct answer as a teacher, identifying tokens it would have generated differently had it known the answer. Prior work shows this either corrupts training by leaking the answer into the gradient, or produces a weak signal that cannot distinguish decisive steps from filler, since both look equally surprising relative to the model's baseline. We propose Contrastive Evidence Policy Optimization (CEPO), which asks a sharper question at every token: not just "does the correct answer favor this token?" but "does the correct answer favor it while the wrong answer disfavors it?" A token satisfying both is a genuine reasoning step; one satisfying neither is filler. The wrong-answer teacher is constructed from rejected rollouts already in the training batch, incurring no additional sampling cost. We prove CEPO inherits all structural safety guarantees of the prior state of the art while strictly sharpening credit at decisive tokens, with the improvement vanishing exactly at filler positions. Empirically, CEPO achieves 43.43

Salient object detection (SOD) and camouflaged object detection (COD) are related but distinct binary mapping tasks, each involving multiple modalities that share commonalities while maintaining unique characteristics. Existing approaches often rely on complex, task-specific architectures, leading to redundancy and limited generalization. Our previous work, VSCode, introduced a generalist model that effectively handles four SOD tasks and two COD tasks. VSCode leveraged VST as its foundation model and incorporated 2D prompts within an encoder-decoder framework to capture domain and task-specific knowledge, utilizing a prompt discrimination loss to optimize the model. Building upon the proven effectiveness of our previous work VSCode, we identify opportunities to further strengthen generalization capabilities through focused modifications in model design and optimization strategy. To unlock this potential, we propose VSCode-v2, an extension that introduces a Mixture of Prompt Experts (MoPE) layer to generate adaptive prompts. We also redesign the training process into a two-stage approach: first learning shared features across tasks, then capturing specific characteristics. To preserve knowledge during this process, we incorporate distillation from our conference version model. Furthermore, we propose a contrastive learning mechanism with data augmentation to strengthen the relationships between prompts and feature representations. VSCode-v2 demonstrates balanced performance improvements across six SOD and COD tasks. Moreover, VSCode-v2 effectively handles various multimodal inputs and exhibits zero-shot generalization capability to novel tasks, such as RGB-D Video SOD.

Natural-language queries about 3D environments become actionable when responses are verifiable and metric. Verifiability requires explicit grounding to the referred 3D region, while metric answers report physical measurements in real-world units (e.g., size, thickness, clearance, and distance). Existing 3D large multimodal models (LMMs) approaches remain limited: conversational systems typically respond without explicit 3D grounding, while 3D grounding models are not designed for interactive, metric-aware dialogue. In this paper, we present Ground3D-LMM, a unified model that takes a point cloud and an optional RGB image as input and supports 3D spatial conversation with (i) point-grounded responses and (ii) metric numeric outputs at both object and part granularity, including multi-object queries. To evaluate this intersection of grounding and measurement, we define the 3D Grounded Measurement task, which requires predicting the referred 3D region and the corresponding metric quantities in real-world units. We introduce a large-scale dataset built on ScanNet and ScanNet++ datasets with dense object and part annotations and roughly 2.5M question-answer pairs spanning eight tasks, along with a manually verified test set. Extensive experiments on multiple datasets and tasks show that our proposed Ground3D-LMM model provides a strong baseline for grounded, metric-aware 3D conversational understanding. Our dataset and model are publicly available.

Reference Audio-Visual Segmentation (Ref-AVS) tasks challenge models to precisely locate sounding objects by integrating visual, auditory, and textual cues. Existing methods often lack genuine semantic understanding, tending to memorize fixed reasoning patterns. Furthermore, jointly training for reasoning and segmentation can compromise pixel-level precision. To address these issues, we introduce AURORA, a novel framework designed to enhance genuine reasoning and language comprehension in reference audio-visual segmentation. We employ a structured Chain-of-Thought (CoT) prompting mechanism to guide the model through a step-by-step reasoning process and introduce a novel segmentation feature distillation loss to effectively integrate these reasoning abilities without sacrificing segmentation performance. To further cultivate the model's genuine reasoning capabilities, we devise a further two-stage training strategy: first, a “corrective reflective-style training" stage utilizes self-correction to enhance the quality of reasoning paths, followed by reinforcement learning via Group Reward Policy Optimization (GRPO) to bolster robustness in challenging scenarios. Experiments demonstrate that AURORA achieves state-of-the-art performance on Ref-AVS benchmarks and generalizes effectively to unreferenced segmentation.

Custom diffusion models (CDMs) have garnered significant interest owing to their remarkable capacity for generating personalized concepts. However, the majority of CDMs unrealistically presume that the user's collection of personalized concepts is static and incapable of incremental growth over time. Furthermore, they exhibit significant catastrophic forgetting and concept neglect of previously learned concepts when incrementally learning a sequence of new ones. To resolve the above challenges, we develop a novel Continually Customizable Diffusion Model (CCDM), enabling users to perform concept-incremental versatile customization. Specifically, we design an attribute-decoupled LoRA (AD-LoRA) module and a relevance-guided AD-LoRA aggregation strategy to mitigate catastrophic forgetting. They can preserve concept-specific attributes of each task and leverage beneficial inter-task correlations to enhance the continual learning of new customization tasks. Additionally, to address the challenge of concept neglect, we propose a controllable regional context synthesis strategy that performs multi-concept composition in alignment with user-provided conditions. This strategy enhances the overall consistency in multi-concept synthesis by guaranteeing semantic independence between user-defined regions and their smooth boundary transitions. Experiments show our CCDM exhibits significant improvements over baseline methods.

Magnetic Resonance Imaging (MRI) interpretation is fundamental to clinical decision-making, requiring radiologists to integrate multi-view anatomical planes across sequential timepoints while precisely localizing interval changes. However, existing vision-language benchmarks remain confined to single-timepoint, single-view interpretation, failing to capture the temporal-spatial reasoning essential to radiologic practice. We introduce the Time-Aware Multi-View MRI Benchmark, an evaluation framework unifying multi-view anatomical input, temporal reasoning across longitudinal scans, and structured localization guidance. The benchmark comprises 3,920 expert-verified question-answer pairs derived from 890 patients across over 3,200 longitudinal MRI timepoints, drawn from seven clinical cohorts covering glioblastoma, neurodegeneration, vestibular schwannoma, and brain metastases, in open-ended, multiple-choice, and binary formats, requiring models to identify anatomical regions of maximal change, characterize progression across sequences and views, and provide structured guidance specifying boundaries, imaging features, and confounders. Experiments across 16 vision-language models reveal moderate temporal alignment but systematic failure on change direction recognition and volumetric quantification, while multi-view inputs improve spatial localization yet degrade temporal reasoning in compact architectures. Our benchmark provides a systematic framework for evaluating progression tracking, interval change localization, and temporal ordering, which are essential for clinical deployment. Code, evaluation splits, and the dataset are available at: https://github.com/wafaAlghallabi/Time-Aware-MRI.