多模态信息融合

Accurate LiDAR-camera calibration is essential for robust multi-modal perception. Targetless approaches avoid manual setup but remain limited by the scarcity of discriminative cross-modal features. Recent methods address this by reconstructing the scene within a differentiable model, enabling extrinsic optimization through dense photometric supervision. Among these, 3D Gaussian Splatting (3DGS) has been widely adopted as a geometric proxy that bridges LiDAR and camera within a single differentiable framework. However, since 3DGS was originally designed for novel view synthesis, existing methods tend to prioritize rendering quality, causing the proxy geometry to drift from the true LiDAR structure. We propose a framework that preserves the metric geometry of the Gaussian proxy by aggregating multi-view LiDAR observations for dense depth supervision and blocking photometric gradients from updating the Gaussian spatial parameters. We validate our method on public driving datasets, where it consistently outperforms existing targetless methods in calibration accuracy.

Leveraging Vision Foundation Models (VFMs) for camera-to-LiDAR knowledge distillation offers a promising solution to the scarcity of annotated data needed to represent the immense geometric and kinematic diversity of real-world autonomous driving (AD). However, current approaches typically treat VFMs as black-box teachers, relying exclusively on frame-wise feature similarity. Consequently, they do not fully exploit the teacher's layer-wise semantic structure and global context, as well as the rich spatiotemporal information inherent in LiDAR sequences. We propose HilDA, a self-supervised pretraining framework for LiDAR backbones that better captures the semantic what and geometric where needed for driving tasks. HilDA combines hierarchical distillation comprising multi-layer distillation for progressive semantic alignment and global context distillation for scene-level semantics, with a temporal occupancy diffusion objective promoting spatiotemporal consistency. Models pre-trained with HilDA achieve state-of-the-art results on cross-modal distillation benchmarks and outperform models trained via prior distillation approaches on 3D object detection, scene flow, and semantic occupancy prediction. Code available at: https://maxiuw.github.io/hilda.

Few-shot anomaly detection remains challenging due to limited training data. Multi-modal anomaly detection (MAD) offers a viable solution, leveraging 3D geometric cues to enrich 2D RGB representations and compensate for this scarcity. However, existing MAD methods apply spatially uniform feature processing, conflating stable macroscopic structures with high-frequency localized defect signals, exacerbating cross-modal misalignment and inflating false-positive rates. To overcome this, we present CMDS-AD, a Cross-Modal Dual-Stream Anomaly Detection framework. A LoRA-guided diffusion model generates diverse RGB samples to mitigate extreme data scarcity. For 3D normal augmentation, we employ a pre-trained diffusion model as a normal estimator. Crucially, this estimator inherently acts as a non-linear low-pass filter, directly extracting low-frequency normal representations from RGB inputs. This establishes an auxiliary estimated stream of purely low-frequency information, anchoring robust structural templates and assisting the uncompressed real stream, containing coupled high- and low-frequency components, to precisely isolate micro-defects. A Coordinate-Aware Hierarchical Feature Mapper adaptively aligns cross-modal semantics, while a multiplicative scoring mechanism filters modality-specific noise. Under the extreme 1-shot setting, CMDS-AD achieves absolute performance gains of 5.7% (I-AUROC) and 2.0% (AUPRO) on MVTec 3D-AD, alongside 7.7% and 5.6% improvements on EyeCandies, establishing a new state-of-the-art.

Despite significant progress in multi-modal Re-Identification (ReID), existing methods tend to emphasize low-frequency cues. Consequently, they focus on attributes such as color, illumination, and coarse appearance, while overlooking mid and high-frequency structures that encode geometric, textural, and identity-discriminative details. This imbalance leads to incomplete spectral representations and unstable cross-modal alignment. To overcome these limitations, we introduce FUSE, a frequency-domain framework that reformulates multi-modal ReID as a two-stage process of spectral disentanglement and energy alignment. The proposed Spectral Decomposition Module (SDM) adaptively partitions features into low, mid, and high-frequency subspaces, enabling hierarchical spectral modeling. The Cross-Modal Alignment Module (CAM) further enforces energy alignment and subspace complementarity across modalities via frequency-consistency regularization. In addition, FUSE incorporates learnable frequency modulation to enhance robustness under varying illumination and heterogeneous sensor conditions. Extensive experiments on RGBNT201, RGBNT100, and MSVR310 show that FUSE achieves 9.1\% mAP and 9.5\% Rank-1 improvements, establishing an interpretable frequency-domain paradigm for multi-modal representation learning.

A precise state estimate is crucial for a tight feedback control that enables agile and near-obstacle flights of UAVs. The state-of-the-art methods fuse slow pose measurements with high-frequency inertial measurements to obtain a precise state estimate. However, the inertial measurements from the IMU onboard the UAV are degraded by vibrations from spinning propellers and the precision of the estimated state suffers. We propose a novel approach based on the preintegration of accelerations obtained from motor speeds. We show that the accelerations obtained in this manner can be used for state propagation on their own to achieve better precision without including the IMU. Further, we propose a factor composed of the preintegrated motor speeds that can be directly employed in factor graph optimization frameworks. We combine our factor with LiDAR measurements into the proposed Motor Angular Speed LiDAR Odometry (MAS-LO) algorithm for precise state estimation, which we open-source. Lastly, we evaluate the estimation precision against a state-of-the-art inertial algorithm LIO-SAM to show 28% improvement in position and 65% in velocity estimation accuracy, 14% lower measurement lag, and high robustness to wrong parameter values.

3D Gaussian Splatting (3DGS) has significantly boosted novel view synthesis and high-fidelity scene reconstruction, expanding the potential of 3DGS-based Visual Simultaneous Localization and Mapping (SLAM) methods. However, most existing systems fail to fully exploit the underlying structural information, which limits rendering quality and often leads to inconsistent maps. To address these limitations, we propose MMD-SLAM, a structure-enhanced Visual SLAM framework that leverages the Atlanta World (AW) assumption to guide a Multi-Meta Gaussian representation for photorealistic mapping. First, we introduce a point-line fusion strategy for pose optimization, where 3D line segments are incorporated to improve tracking robustness and provide additional constraints for mapping. Second, we design a Multi-Meta Gaussian representation with dominant directions, explicitly encoding structural priors from the AW hypothesis. Finally, we propose a Gaussian evolution strategy that adapts to scene geometry and incorporates structural cues into global optimization. Extensive experiments demonstrate that these innovations enable MMD-SLAM to achieve state-of-the-art performance in both tracking accuracy and mapping quality. e.g., our method achieves a 48.56% reduction in ATE RMSE on ScanNet and a 5.71% improvement in PSNR on Replica, compared with MonoGS.

Autonomous proximity operations, such as active debris removal and on-orbit servicing, require high-fidelity relative navigation solutions that remain robust in the presence of parametric uncertainty. Standard estimation frameworks typically assume that the target spacecraft's mass properties are known a priori; however, for non-cooperative or tumbling targets, these parameters are often unknown or uncertain, leading to rapid divergence in model-based propagators. This paper presents an augmented Unscented Kalman Filter (UKF) framework designed to jointly estimate the relative 6-DOF pose and the full inertia tensor of a non-cooperative target spacecraft. The proposed architecture fuses visual measurements from monocular vision-based Convolutional Neural Networks (CNN) with depth information from LiDAR to constrain the coupled rigid-body dynamics. By augmenting the state vector to include the six independent elements of the inertia tensor, the filter dynamically recovers the target's normalized mass distribution in real-time without requiring ground-based pre-calibration. To ensure numerical stability and physical consistency during the estimation of constant parameters, the filter employs an adaptive process noise formulation that prevents covariance collapse while allowing for the gradual convergence of the inertial parameters. Numerical validation is performed via Monte Carlo simulations, demonstrating that the proposed Augmented UKF enables the simultaneous convergence of kinematic states and inertial parameters, thereby facilitating accurate long-term trajectory prediction and robust guidance in non-cooperative deep-space environments.

Latent diffusion models (LDMs) enable efficient image-to-image translation but discard fine spatial details during compression, degrading downstream perception tasks. We identify two bottlenecks: the autoencoder, which loses spatial information, and the conditioning pathway, which further degrades the source signal through naive downsampling. We propose two lightweight, backbone-agnostic fixes: a Source-Conditioned Autoencoder (SCAE) that injects high-resolution source features into the decoder via skip connections, and a Learnable Guidance Encoder (LGE) that replaces naive downsampling with a learned conditioning signal. Evaluated on RGB-to-SWIR translation for driving scenes with two denoiser backbones (U-Net and DiT), our approach improves detection mAP by up to 2x over the latent diffusion baseline, with up to 3.4x gains on small objects (COCO-small, <32^2 px^2), while achieving state-of-the-art FID. We further show that FID and detection performance are poorly correlated, motivating multi-axis evaluation. Results generalise zero-shot to the public RASMD benchmark. We will publicly release test data with annotations, all checkpoints, and training code.

Remote sensing is increasingly relied upon to deliver actionable science for forest and wildfire risk management across large landscapes. Wall-to-wall, annually updated maps are a persistent need for effective forest management. Many planning systems and data collections combine disparate data sources with different purposes, vintages, and prediction quality, which leads to confounding behavior in operational planning systems. We introduce the VibrantForests framework, developed and applied to map forest attributes and provide a coherent foundation for effective forest and wildfire planning. VibrantForests includes a satellite-based forest structure model trained on lidar-derived samples and applied across the contiguous United States to concurrently generate estimates of canopy cover, canopy height, aboveground live tree biomass, basal area, and quadratic mean diameter at 10-meter resolution. We demonstrate predictive capability spanning the full spectrum of forest conditions ranging from sparse-canopy/low-biomass to dense-canopy/high-biomass. Results show that our model extends the range at which saturation is commonly encountered in comparable passive-sensor models, and reduces regression-to-mean behavior that commonly produces overestimation of forest attributes in small/sparse conditions and underestimation in large/dense conditions. The VibrantForests framework addresses a key limitation in large-area forest and wildfire planning by delivering coherent wall-to-wall estimates of management-relevant attributes at annual cadence and 10m resolution.

Unlike traditional remote sensing change detection that relies on predefined categories, Open-Vocabulary Change Detection (OVCD) identifies land cover changes flexibly using arbitrary text prompts. However, existing methods suffer from an inherent trade-off when modeling changes: instance-level comparison overlooks fine-grained semantic variations (e.g., partial building extensions), while direct pixel comparison proves unreliable, yielding unstable responses and boundary artifacts due to semantic ambiguity and spatial inconsistency. To this end, we propose an efficient training-free Reliability-Aware Open-Vocabulary Change Detection (ReA-OVCD) framework. It first derives candidate change regions from pixel-wise semantic discrepancies to ensure flexible and detailed localization. To ensure reliability, it subsequently introduces a collaborative refinement strategy to explicitly model change validity from both semantic and spatial perspectives. Specifically, we develop a Semantic Change Reasoning (SCR) module that reassesses changes by jointly analyzing distributional divergence and response variation, enabling the suppression of incidental inconsistencies while preserving reliable semantic shifts. In addition, a Boundary-aware Change Refinement (BCR) module is designed to mitigate artifacts stemming from boundary misalignment and uncertainty through validating whether candidate regions are supported by reliable interior pixels. Extensive experiments across multiple datasets (LEVIR-CD, WHU-CD, DSIFN, and SECOND) demonstrate that our method consistently outperforms state-of-the-art approaches, achieving $\mathrm{F}_{1}^{C}$ improvements of 2.13\% to 9.75\% with higher computational efficiency. The code is publicly available at \https://github.com/Funny0101/ReA-OVCD

Head and neck cancers (HNC) represent a significant global health burden, with accurate tumor delineation being essential for effective radiotherapy planning. The complexity of the oropharyngeal anatomy, combined with the heterogeneous appearance of tumors on imaging, makes manual segmentation time-intensive and subject to inter-observer variability. Beyond segmentation, predicting long-term clinical outcomes, such as recurrence-free survival (RFS), and determining human papillomavirus (HPV) status from noninvasive imaging, remain challenging yet clinically valuable goals. The HECKTOR 2025 challenge addresses these needs by establishing a comprehensive benchmark for automated HNC analysis using multimodal PET/CT imaging and electronic health records. Building on previous editions (2020-2022), this challenge features an expanded multi-institutional dataset comprising over 1,100 patients from 10 centers worldwide. Participants were tasked with three complementary objectives: (1) segmenting primary gross tumor volumes (GTVp) and metastatic lymph nodes (GTVn), (2) predicting recurrence-free survival, and (3) classifying HPV status. The challenge attracted 35 registered teams, with 15 final submissions evaluated on a held-out test set. Top-performing algorithms achieved a mean Dice similarity coefficient of 0.75 for segmentation, a concordance index of 0.66 for survival prediction, and a balanced accuracy of 0.56 for HPV classification. This paper presents a comprehensive analysis of the submitted methodologies, evaluates their performance across different lesion characteristics, and discusses their implications for clinical translation in automated oncology workflows and decision support systems.

Generating high-resolution 3D CT volumes with fine details remains challenging due to substantial computational demands and optimization difficulties inherent to existing generative models. In this paper, we propose the Pixel-Level Residual Diffusion Transformer (PRDiT), a scalable generative framework that synthesizes high-quality 3D medical volumes directly at voxel-level. PRDiT introduces a two-stage training architecture comprising 1) a local denoiser in the form of an MLP-based blind estimator operating on overlapping 3D patches to separate low-frequency structures efficiently, and 2) a global residual diffusion transformer employing memory-efficient attention to model and refine high-frequency residuals across entire volumes. This coarse-to-fine modeling strategy simplifies optimization, enhances training stability, and effectively preserves subtle structures without the limitations of an autoencoder bottleneck. Extensive experiments conducted on the LIDC-IDRI and RAD-ChestCT datasets demonstrate that PRDiT consistently outperforms state-of-the-art models, such as HA-GAN, 3D LDM and WDM-3D, achieving significantly lower 3D FID, MMD and Wasserstein distance scores.

Whole-slide images (WSIs) are widely used for computational cancer prognosis. However, most existing methods primarily focus on in-domain performance and fail to generalize across clinical centers. This limitation stems from their reliance on pixel-derived representations that are highly susceptible to domain-specific artifacts caused by staining protocols and scanner hardware. We hypothesize that high-level pathology semantics, such as tumor grade and micro-environmental architecture, provide a domain-invariant semantic representation that mirrors the robust diagnostic logic of human pathologists. Therefore, we propose a Semantic-Anchored Evidential Fusion Survival (SAEFS) framework, where SAEFS derives semantic anchors from WSIs via Visual Question Answering (VQA), employs a dual-stream WSI evidence extraction architecture, uses Dirichlet-based Subjective Logic to model uncertainty, and fuses semantic and visual evidence through a cautious conjunction rule to avoid overconfident fusion from correlated sources. Trained exclusively on one source domain and evaluated zero-shot across four unseen domains, SAEFS consistently outperforms state-of-the-art models both in prediction accuracy and reliability, improving the average C-index by 10.2%. Quantitative analyses further show that VQA-derived semantic features exhibit significantly lower cross-center divergence than pixel-derived features, highlighting their robustness for cross-center clinical applications.

Multi-view imaging, such as mammography and chest radiography, is a standard component of clinical practice. However, medical images are often unregistered and contain view-specific artifacts or irrelevant background cues that can obscure diagnostically relevant findings. Many existing methods directly fuse per-view representations, allowing such irrelevant content to contaminate the fused embedding and reducing robustness under varying view configurations. We propose OTCHA, a confidence-aware latent hub token alignment module based on optimal transport (OT) that refines patch tokens before fusion for multi-view classification. OTCHA introduces a set of learnable latent hub tokens shared across views. For each view, we compute an OT plan between patch tokens and hub tokens that jointly considers feature similarity and geometry, and augment the OT formulation with token-conditional dustbins to enable partial matching and discard irrelevant tokens. The resulting transport plan provides token-wise matching confidence, which gates hub-mediated message passing and weights a novel optimal-transport-based representation alignment loss to stabilize refinement. Experiments on three multi-view medical image datasets demonstrate consistent improvements over competing baselines across diverse anatomies and view configurations. Our code is available at https://github.com/labhai/OTCHA.

Alzheimer's disease (AD) is a fatal disorder that destroys memory and cognitive skills in the elderly population. Most treatments for AD are effective in the early stage, leading to an increasing demand for early AD diagnosis. AD diagnosis increasingly relies on multimodal data such as clinical assessments, structural Magnetic Resonance Imaging (MRI), and Positron Emission Tomography (PET) imaging. However, MRI and PET acquisition remain costly and not universally accessible, making full-modality inference impractical in real-world clinical workflows. We propose ProMUSE, a Progressive Multi-modal Uncertainty Guided Staged Evidential Network that adaptively determines when additional modalities are necessary, helping reduce the overall cost of data acquisition while maintaining accuracy. ProMUSE first performs evidential classification using low-cost clinical data and quantifies uncertainty via a Dirichlet-based subjective logic model. When uncertainty exceeds a learned threshold, ProMUSE progressively incorporates MRI or PET features, fusing modality-wise belief and uncertainty through Dempster-Shafer theory to obtain a calibrated multimodal prediction. This staged acquisition strategy enables accurate diagnosis while minimizing reliance on expensive imaging. Experiments on ADNI, AIBL, and OASIS across CN-AD, CN-MCI, and MCI-AD tasks demonstrate that ProMUSE achieves competitive or superior accuracy compared to full-modality baselines while reducing MRI/PET usage by 50-90%, yielding substantial cost savings. These results highlight ProMUSE as a practical, uncertainty-aware, and resource-efficient solution for real-world AD screening.

Brain MRIs are routinely acquired as multiple complementary sequences with unique contrast weighting, including T1-weighed imaging (T1w) anatomic and fluid-sensitive T2-weighted (T2w) contrasts. However, methods for learning unified representations across the multitude of MRI contrast mechanisms at health-system scale are lacking. In this study, we introduce Neuro-JEPA, a sparse multimodal neuroimaging foundation model that combines a latent predictive objective with a Mixture-of-Experts architecture to encode brain MRI across core T1w, T2w, and fluid-suppressed FLAIR imaging (FLAIR). We further provide a systematic methodological study of architectural, masking, objective, and sparsity design choices beneficial for robust neuroimaging multimodal representation learning. Neuro-JEPA was pretrained on 1,551,862 scans from 428,647 studies after modality-specific preprocessing with data curation across three core structural brain MRI sequences. We evaluated the learned representations across clinical and research settings, including 25 tasks from three health systems: NYU Langone, NYU Long Island, and Massachusetts General Hospital, and 22 tasks from 12 public datasets, covering unimodal, multimodal and cross-domain evaluation configurations. Across these benchmarks, existing neuroimaging foundation models showed inconsistent gains over a simple convolutional neural network (CNN) baseline, whereas Neuro-JEPA achieved stronger and more consistent performance across all evaluated settings. These results establish a scalable methodological framework for multimodal neuroimaging representation learning and highlight the need for foundation model evaluation protocols that include simple baselines, clinically heterogeneous cohorts and controlled multimodal comparisons.

With 890,000 annual new cases globally, head and neck squamous cell carcinoma has one of the highest recurrence rates among solid malignancies. Although frozen section analysis is the standard of care for intraoperative margin assessment, accurately relocating detected positive margins on the resection bed remains challenging due to imprecise alignment between resected specimens and their resection bed, compounded by post-resection mucosal tissue shrinkage. We present a biomechanics-driven deformable registration framework that corrects post-resection tissue deformation to provide intraoperative guidance. Our approach registers 3D specimen meshes to intraoperative resection bed point clouds using a deformable registration approach based on regularized Kelvinlet basis functions. The registration matches surface point clouds, fiducial landmarks, and boundary contour constraints that directly penalize perpendicular distance-to-agreement between specimen and resection bed boundaries. Across nine specimens from skin, buccal mucosa, and tongue sites, the overall mean target registration error was $11.11 \pm 4.07$ mm using rigid registration, which decreased to $8.20 \pm 2.68$ mm (26.19\% reduction) using deformable registration without contour constraint. The proposed contour-constrained deformable registration further reduced the error to $5.62 \pm 2.28$ mm, a 49.41\% reduction relative to rigid registration. We observed the largest reduction in the most clinically challenging tongue specimens. We also performed a systematic two-stage parameter search to characterize the relative importance of surface alignment, fiducial correspondences, contour constraint, and strain energy regularization. This search revealed that contour weighting dominates registration accuracy for tissue types with large lateral deformation, while the algorithm operates over a broad range of parameter combinations.

Automated cardiac interpretation in resource-constrained settings (RCS) is often hindered by poor-quality echocardiographic imaging, limiting the effectiveness of downstream diagnostic models. While super-resolution (SR) techniques have shown promise in enhancing magnetic resonance imaging (MRI) and computed tomography (CT) scans, their application to echocardiography-a widely accessible but noise-prone modality-remains underexplored. In this work, we investigate the potential of deep learning-based SR to improve classification accuracy on low-quality 2D echocardiograms. Using the publicly available CAMUS dataset, we stratify samples by image quality and evaluate two clinically relevant tasks of varying complexity: a relatively simple Two-Chamber vs. Four-Chamber (2CH vs. 4CH) view classification and a more complex End-Diastole vs. End-Systole (ED vs. ES) phase classification. We apply two widely used SR models-Super-Resolution Generative Adversarial Network (SRGAN) and Super-Resolution Residual Network (SRResNet), to enhance poor-quality images and observe significant gains in performance metric-particularly with SRResNet, which also offers computational efficiency. Our findings demonstrate that SR can effectively recover diagnostic value in degraded echo scans, making it a viable tool for AI-assisted care in RCS, achieving more with less.

In multimodal video reasoning, reinforcement learning-based methods typically rely on simplistic and inflexible reasoning-length control strategies that fail to adapt to the model's evolving competence. This mismatch may suppress necessary exploration at early stages, while encouraging redundant reasoning and inefficient decoding once the model becomes more competent. In this paper, we propose CARE, a competence-aware reward shaping framework for adaptive reasoning length optimization in multimodal reasoning. Specifically, CARE maintains a smoothed competence estimate via an exponential moving average of pass rates, and uses it to route training into progressive stages that shift the reward preference from exploration-oriented long-form reasoning to efficiency-oriented concise reasoning. To avoid conflating verbosity with intrinsic task complexity, CARE further normalizes reasoning effort with batch-level statistics, and introduces a posterior amplifier to strengthen reward signals for unexpectedly strong performance on historically difficult samples. The proposed mechanism is seamlessly integrated into the GRPO training pipeline and incurs no additional inference-time overhead. Extensive experiments on multiple video reasoning and general video understanding benchmarks demonstrate that CARE consistently improves reasoning accuracy, stabilizes reinforcement learning, and significantly enhances token efficiency. Moreover, CARE exhibits a characteristic inverted-U trajectory of reasoning length during training, and yields shorter yet more informative reasoning traces at convergence, indicating effective adaptive allocation of reasoning budget. We provide the source code for our proposed CARE framework and experiments at https://github.com/1Pansy/Video-CARE.

Concept Bottleneck Models (CBMs) enhance the interpretability of deep learning networks by aligning the features extracted from images with natural concepts. However, existing CBMs are constrained in their ability to generalize beyond a fixed set of predefined classes and the risk of non-concept information leakage, where predictive signals outside the intended concepts are inadvertently exploited. In this paper, we propose Multimodal Concept Bottleneck Model (MM-CBM) to address these issues and extend CBMs into CLIP. MM-CBM utilizes dual Concept Bottleneck Layers (CBLs) to align both the image and text embeddings into interpretable features. This allows us to perform new vision tasks like zero-shot classification or image retrieval in an interpretable way. Compared to existing methods, MM-CBM achieves up to 51.26% accuracy improvement on average across four standard benchmarks. Our method maintains high accuracy, staying within ~5% of black-box performance while offering greater interpretability.

Visual tokens enter Large Language Models (LLMs) as raw, foreign signals. How they are transformed into meaningful representations and interact with the language space depends entirely on the integration architecture. Whether by treating visual tokens as in-context prompts within the input sequence or injecting them directly into the LLM's intermediate layers. A controlled comparison and understanding of how these architectural choices affect visual information and its internal transformation to integrate with the LLM remains underexplored. We provide a fair comparison by evaluating in-context and layer-wise injection VLM integration paradigms under identical training conditions across single image, multi-image, and video benchmarks. In doing so, we uncover a hidden evolution where visual tokens enter the LLM as disguised visual context, raw representations lacking linguistic structure, but are progressively reshaped depending on the integration paradigm, each capturing fundamentally different frequency characteristics of the visual signal. We show that this evolution inside the LLM determines what visual features the VLM can utilize effectively, how visual representations align with the language space, and ultimately how each paradigm performs across different tasks. We further demonstrate that attention allocation alone is insufficient, and that performance is driven by the quality of visual representations at each layer.

Multimodal Large Language Models (MLLMs) often lose track of the right image regions during fine-grained spatial reasoning, because a textual query rarely carries any explicit geometric anchor into the pixel domain. Prevailing remedies either rewire the model's weights or pad the prompt with verbose instructions, yet neither reliably pins the language to the correct visual coordinates without eroding the backbone's general competence. We introduce Timage, a paradigm that recasts multimodal understanding as an alignment problem solved at the input: the query is drawn, as a typeset overlay, onto the image itself. The placement and appearance of this overlay are produced by a Constrained Schrödinger Bridge (cSB), an entropic optimal-transport sampler that factorizes layout synthesis into two coupled stochastic stages. The first stage, Region Search, transports noise toward query-aligned image zones while obeying a hard occlusion barrier that protects salient foreground content; the second stage, Appearance Shaping, sizes the glyphs through an ``ink-budget'' regularizer so that the rendered text stays legible and visually balanced. The resulting overlay behaves as an explicit attention beacon that channels the model's focus along spatial semantics. On the VMCBench suite, Timage paired with a modest 7B backbone clearly overtakes far larger proprietary systems as well as parameter-tuned baselines. The study positions deliberate input reconstruction as a powerful, architecture-neutral lever for strengthening multimodal reasoning.

Unlocking the spatial intelligence of multimodal large language model (MLLMs) is crucial for understanding and interacting with the 3D world. Prevailing approaches typically inject spatial priors via external tools, which impose significant inference overhead, or rely on latent feature distillation, which remains uninterpretable and lacks fine-grained geometric constraints. To address these issues, we propose SpatialSV, a framework designed to internalize robust 3D spatial awareness within MLLMs while simultaneously offering inherent interpretability. Deviating from passive feature imitation, SpatialSV employs task-oriented visual supervision, compelling the model to actively lift its 2D visual features into explicit 3D representations, including depth maps, camera poses, and point clouds. Crucially, this 2D-to-3D lifting process provides a transparent window into the model's representations: the resulting 3D reconstructions serve as an intuitive proxy for visualizing and diagnosing the quality of the model's intrinsic spatial knowledge. Extensive experiments across multiple models and benchmarks demonstrate the effectiveness of SpatialSV in enhancing and interpreting MLLMs' spatial intelligence. Furthermore, the framework exhibits strong generalization in semi-supervised settings, validating its potential to leverage unlabeled visual data for scalable, interpretable spatial representation learning.

Recently, vision-language models (VLMs) have made significant progress in 3D scene understanding, driving advances in applications such as embodied intelligence and robotic vision. However, existing approaches typically either rely directly on explicit 3D inputs (e.g., point clouds or RGB-D sequences), or introduce an additional 3D geometry encoder to derive 3D-aware visual tokens from 2D images. Such designs structurally decouple 3D geometric perception from the rich 2D semantics learned via vision-language pre-training, hindering the development of a unified 3D vision-language representation. In this work, we propose Occ-VLM, a novel framework for 3D scene understanding that operates purely on posed RGB images and employs a single 2D vision encoder. Specifically, Occ-VLM reconstructs 3D scene occupancy as an auxiliary geometric prior, which is utilized to spatially associate foreground 2D tokens with 3D space. These tokens are then decoded by a Large Language Model (LLM) for unified scene understanding. Extensive experiments demonstrate that Occ-VLM achieves both accurate geometric perception and robust vision-language reasoning: it attains state-of-the-art performance on multi-view occupancy prediction, while performing on par with 3D-input VLMs on 3D Visual Question Answering (VQA) and 3D dense captioning benchmarks.

Audio editing aims to modify specific content in an existing audio clip according to a natural language instruction while preserving the remaining acoustic content. Despite the remarkable progress of diffusion models, existing training-based editing methods mainly rely on the local inductive biases and cross-attention interaction in convolutional U-Net backbones, which often hinder long-range semantic alignment and precise understanding and localization of instructions. In contrast, diffusion transformers provide stronger global modeling and multimodal fusion, but existing editing architectures usually adopt a simple stack of MMDiT and DiT blocks. Applying joint attention over concatenated audio and text tokens in all blocks results in quadratic complexity with respect to token length. To balance editing performance and efficiency, we propose a hybrid two-stage diffusion transformer architecture for instruction-guided audio editing based on rectified flow matching. It performs joint attention over audio and text tokens to establish coarse semantic alignment at low-resolution stage, then switches to alternating joint-attention and cross-attention blocks to refine editing details at high-resolution stage. This coarse-to-fine strategy enables efficient and accurate instruction-guided audio editing. Experiments show that the proposed framework achieves notable performance gains on challenging editing tasks involving overlapping audio events and complex instructions, while substantially improving editing efficiency with a compact model.

Occlusion-robust scene recovery remains a major challenge in computational imaging, particularly in natural environments where dense foreground vegetation severely limits visibility. We propose a vision-reasoning-guided light field occlusion removal framework that combines the visibility recovery capability of light field integration (LFI) with the semantic reasoning capacity of vision-language models (VLMs). Multi-view observations are first integrated via LFI to suppress foreground occlusions and produce an initial visibility-enhanced representation. A VLM is then incorporated as a conditional semantic prior to restore degraded structures and recover fine details, guided by the observed measurements. To improve recovery consistency and reduce hallucination artifacts, we introduce a multi-sample fusion strategy that aggregates multiple generated hypotheses into a unified estimate. Experimental results on synthetic and real-world datasets demonstrate state-of-the-art performance, achieving the highest average SSIM across four synthetic light field benchmark scenes (4-Syn) and strong generalization across structured and unstructured acquisition settings. These results highlight the effectiveness of combining physical imaging constraints with vision-language reasoning for robust perception under severe occlusion, with applicability to search-and-rescue and exploratory robotic navigation.

Multimodal Large Language Models (MLLMs) show great potential in medical tasks, but their elicited confidence often misaligns with actual accuracy, potentially leading to misdiagnosis or overlooking correct advice. This study presents the first comprehensive analysis of the relationship between accuracy and confidence in medical MLLMs. It proposes a novel method that combines Multi-Strategy Fusion-Based Interrogation (MS-FBI) with auxiliary expert LLM assessment, aiming to improve confidence calibration in Medical Visual Question Answering (VQA). Experiments demonstrate that our method reduces the Expected Calibration Error (ECE) by an average of 40\% across three Medical VQA datasets, significantly enhancing MLLMs' reliability. The findings highlight the importance of domain-specific calibration for MLLMs in healthcare, offering a more trustworthy solution for AI-assisted diagnosis.

Non-invasive brain-computer interfaces exhibit significant performance degradation when moving from controlled laboratory stimuli to real-world natural images. This degradation occurs because conventional multimodal contrastive representation learning models focus exclusively on optimizing geometric distance alignment, thereby failing to account for semantic consistency and inter-subject variability in neural representation and selective attention. As a result, these models are prone to producing spurious zero-shot matches. To address these limitations, we propose SUP-MCRL, a unified framework integrating three collaborative mechanisms: (1) a Semantic-entity Aware Visual Encoder (SAVE) that learns spatial attention to extract semantic content without relying on pre-trained saliency models; (2) a Unified EEG Enhancer (UEE) that employs multi-scale atrous convolutions and inter-band attention for adaptive cross-subject robustness; and (3) a Prototype-based Progressive Augmenter (PPA) that maintains an EMA-updated pseudo-feature pool to prevent representation collapse. Zero-shot experiments on the THINGS-EEG achieve 66.0%/91.9% (Top-1/Top-5) intra-subject and 24.0%/52.9% LOSO accuracy, significantly surpassing state-of-the-art methods and demonstrating that structured alignment supervision is key to overcoming the limitations of cross-modal decoding. Code is available at https://github.com/NZWANG/SUP-MCRL.

Video world models are moving toward preserving an observed world under controllable camera and object motion while allowing its environmental state to change. Yet these controls remain isolated, and weather generation typically relies on a source video or reconstructed scene that already specifies future structure. We study a first-frame-anchored source-to-state setting, where the model starts from a single image and follows explicit camera and object controls and an optional weather instruction, then generates a video that either preserves the source world or transfers it to a target weather state. To address these challenges, we first build HoloStateData, a state video dataset that turns diverse videos into unified control samples for camera, object, and weather supervision. Second, we introduce Holo-World, a unified controllable video world model that jointly controls scene from a single image. Its Unified Scene Adapter factorizes world preservation and weather transfer into distinct parameter subspaces, using rendered background, geometry buffers, and object controls to maintain controlled scene structure while modeling weather-dependent appearance and particle effects. Additionally, Scene-Weather Decomposed CFG guides scene and weather residuals separately, strengthening target weather effects without over-amplifying the full condition. Quantitative and qualitative experiments demonstrate that Holo-World maintains precise camera and object control with consistent scene structure while transferring scenes into diverse target weather state, outperforming video-to-video weather editing baselines on weather-state generation. Our project page is available at \url{https://xiangchenyin.github.io/Holo-World/}.

Makeup transfer models enable fun augmented reality (AR) experiences as well as virtual try-on (VTO) for online makeup shopping. While recent state-of-the-art diffusion based solutions such as Stable-Makeup dramatically improve the accuracy and realism of makeup transfer, they still face limitations in identity and skin color preservation, making production-level VTO for makeup shopping unrealistic. In this work, we propose MakeupMirror, a diffusion-based approach to makeup transfer that makes significant progress towards preserving facial features and skin tone. We introduce several technical innovations over Stable-Makeup: (1) integration of facial geometry conditioning with ControlNets to maintain facial fidelity; (2) region-specific makeup transfer control to enable precise makeup application across facial regions such as skin, eyes and lips; (3) skin tone-based makeup transfer modulation that prevent skin tone alteration in cross-subject transfer scenarios; and (4) integration of a Levenberg-Marquardt Langevin sampler to speed up inference while maintaining generation quality. Our experiments on CPM-Real, Makeup Wild, and (herein newly collected, more diverse) MakeupSelfies datasets show that MakeupMirror improves relative facial recognition similarity by +60%, reduces relative skin tone difference by -50% over Stable-Makeup, with a latency of 0.7s, while achieving expert acceptance rate of 94% across core facial identity preservation criteria.