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.

Collaborative perception (CP) enhances scene understanding through multi-agent information sharing. While LiDAR-centric systems offer precise geometry, high costs and performance degradation in adverse weather necessitate multi-modal alternatives. Despite dense visual semantics and robust spatial measurements, the synergy between cameras and 4D radar remains underexplored in collaborative settings. This work introduces RC-GeoCP, the first framework to explore the fusion of 4D radar and images in CP. To resolve misalignment caused by depth ambiguity and spatial dispersion across agents, RC-GeoCP establishes a radar-anchored geometric consensus. Specifically, Geometric Structure Rectification (GSR) aligns visual semantics with geometry derived from radar to generate spatially grounded, geometry-consistent representations. Uncertainty-Aware Communication (UAC) formulates selective transmission as a conditional entropy reduction process to prioritize informative features based on inter-agent disagreement. Finally, the Consensus-Driven Assembler (CDA) aggregates multi-agent information via shared geometric anchors to form a globally coherent representation. We establish the first unified radar-camera CP benchmark on V2X-Radar and V2X-R, demonstrating state-of-the-art performance with significantly reduced communication overhead. Code will be released soon.

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.

Mapping the spatial distribution of species is essential for conservation policy and invasive species management. Species distribution models (SDMs) are the primary tools for this task, serving two purposes: achieving robust predictive performance while providing ecological insights into the driving factors of distribution. However, the increasing complexity of deep learning SDMs has made extracting these insights more challenging. To reconcile these objectives, we propose the first implementation of concept-based Explainable AI (XAI) for SDMs. We leverage the Robust TCAV (Testing with Concept Activation Vectors) methodology to quantify the influence of landscape concepts on model predictions. To enable this, we provide a new open-access landscape concept dataset derived from high-resolution multispectral and LiDAR drone imagery. It includes 653 patches across 15 distinct landscape concepts and 1,450 random reference patches, designed to suit a wide range of species. We demonstrate this approach through a case study of two aquatic insects, Plecoptera and Trichoptera, using two Convolutional Neural Networks and one Vision Transformer. Results show that concept-based XAI helps validate SDMs against expert knowledge while uncovering novel associations that generate new ecological hypotheses. Robust TCAV also provides landscape-level information, useful for policy-making and land management. Code and datasets are publicly available.

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.

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.

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.

Satellite communications face severe bottlenecks in supporting high-fidelity synchronized audiovisual services, as conventional schemes struggle with cross-modal coherence under fluctuating channel conditions, limited bandwidth, and long propagation delays. To address these limitations, this paper proposes an adaptive multimodal semantic transmission system tailored for satellite scenarios, aiming for high-quality synchronized audiovisual reconstruction under bandwidth constraints. Unlike static schemes with fixed modal priorities, our framework features a dual-stream generative architecture that flexibly switches between video-driven audio generation and audio-driven video generation. This allows the system to dynamically decouple semantics, transmitting only the most important modality while employing cross-modal generation to recover the other. To balance reconstruction quality and transmission overhead, a dynamic keyframe update mechanism adaptively maintains the shared knowledge base according to wireless scenarios and user requirements. Furthermore, a large language model based decision module is introduced to enhance system adaptability. By integrating satellite-specific knowledge, this module jointly considers task requirements and channel factors such as weather-induced fading to proactively adjust transmission paths and generation workflows. Simulation results demonstrate that the proposed system significantly reduces bandwidth consumption while achieving high-fidelity audiovisual synchronization, improving transmission efficiency and robustness in challenging satellite scenarios.

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.

3D content inherently encompasses multi-modal characteristics and can be projected into different modalities (e.g., RGB images, RGBD, and point clouds). Each modality exhibits distinct advantages in 3D asset modeling: RGB images contain vivid 3D textures, whereas point clouds define fine-grained 3D geometries. However, most existing 3D-native generative architectures either operate predominantly within single-modality paradigms-thus overlooking the complementary benefits of multi-modality data-or restrict themselves to 3D structures, thereby limiting the scope of available training datasets. To holistically harness multi-modalities for 3D modeling, we present TriMM, the first feed-forward 3D-native generative model that learns from basic multi-modalities (e.g., RGB, RGBD, and point cloud). Specifically, 1) TriMM first introduces collaborative multi-modal coding, which integrates modality-specific features while preserving their unique representational strengths. 2) Furthermore, auxiliary 2D and 3D supervision are introduced to raise the robustness and performance of multi-modal coding. 3) Based on the embedded multi-modal code, TriMM employs a triplane latent diffusion model to generate 3D assets of superior quality, enhancing both the texture and the geometric detail. Extensive experiments on multiple well-known datasets demonstrate that TriMM, by effectively leveraging multi-modality, achieves competitive performance with models trained on large-scale datasets, despite utilizing a small amount of training data. Furthermore, we conduct additional experiments on recent RGB-D datasets, verifying the feasibility of incorporating other multi-modal datasets into 3D generation.

Retrieving fine-grained visual content based on user intent remains a challenge in multimodal systems. Although current Composed Image Retrieval (CIR) methods combine reference images with retrieval texts, they are constrained to image-level matching and cannot localize specific objects. To this end, we propose Composed Object Retrieval (COR), a new object-level retrieval task that retrieves target object(s) from candidate objects in a target image and grounds the retrieved result with pixel-level masks. Given a reference object, its mask, a target image, and a retrieval text describing the desired modification, COR requires models to perform composed visual-textual reasoning rather than relying on explicit category names. This setting introduces several challenges, including fine-grained compositional matching, negative-object filtering under visually similar distractors, and flexible single- or multi-object retrieval. We construct COR125K, the first large-scale COR benchmark, containing 125,541 retrieval triplets across 408 categories with base/novel splits for evaluating category-level generalization. We also present CORE, a unified end-to-end model that integrates reference region encoding, adaptive vision-text interaction, and region-level contrastive learning to align composed representations with target objects while suppressing background and distractors. Extensive experiments demonstrate that CORE significantly outperforms existing CIR-based pipelines and strong baselines in both base and novel categories, establishing a simple and effective foundation for fine-grained object-level multimodal retrieval. Code will be released publicly at https://github.com/wangtong627/COR.

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.

We present TerraMind, the first any-to-any generative, multimodal foundation model for Earth observation (EO). Unlike other multimodal models, TerraMind is pretrained on dual-scale representations combining both token-level and pixel-level data across modalities. On a token level, TerraMind encodes high-level contextual information to learn cross-modal relationships, while on a pixel level, TerraMind leverages fine-grained representations to capture critical spatial nuances. We pretrained TerraMind on nine geospatial modalities of a global, large-scale dataset. In this paper, we demonstrate that (i) TerraMind's dual-scale early fusion approach unlocks a range of zero-shot and few-shot applications for Earth observation, (ii) TerraMind introduces "Thinking-in-Modalities" (TiM) -- the capability of generating additional artificial data during finetuning and inference to improve the model output -- and (iii) TerraMind achieves beyond state-of-the-art performance in community-standard benchmarks for EO like PANGAEA. The pretraining dataset, the model weights, and our code are open-sourced under a permissive license.

Recent advances in multimodal foundation models unifying image understanding and generation have opened exciting avenues for tackling a wide range of vision-language tasks within a single framework. Despite progress, existing unified models typically require extensive pretraining and struggle to achieve the same level of performance compared to models dedicated to each task. Additionally, many of these models suffer from slow image generation speeds, limiting their practical deployment in real-time or resource-constrained settings. In this work, we propose Layerwise Timestep-Expert Flow-based Transformer (LaTtE-Flow), a novel and efficient architecture that unifies image understanding and generation within a single multimodal model. LaTtE-Flow builds upon powerful pretrained Vision-Language Models (VLMs) to inherit strong multimodal understanding capabilities, and extends them with a novel Layerwise Timestep Experts flow-based architecture for efficient image generation. LaTtE-Flow distributes the flow-matching process across specialized groups of Transformer layers, each responsible for a distinct subset of timesteps. This design significantly improves sampling efficiency by activating only a small subset of layers at each sampling timestep. To further enhance performance, we propose a Timestep-Conditioned Residual Attention mechanism for efficient information reuse across layers. Experiments demonstrate that LaTtE-Flow achieves strong performance on multimodal understanding tasks, while achieving competitive image generation quality with around 6x faster inference speed compared to recent unified multimodal models.