Papers

Artificial intelligence can support cultural heritage and digital humanities through large-scale retrieval and analysis of digitized collections. However, cultural heritage data are often distributed across institutions, constrained by ownership and access restrictions, and continuously evolving over time. Federated Continual Learning (FCL) is well suited to this setting, as it enables models to learn from distributed and sequential data without sharing raw collections. In this paper, we propose FedCurv-DR, a lightweight, regularisation-based FCL strategy. The method accumulates parameter-importance estimates across clients and experiences to protect learned knowledge, while updating them only at fixed intervals to minimize communication and computation overhead. We evaluate FedCurv-DR in a continual learning scenario using the WikiArt image dataset for genre classification with evolving styles, reporting performance, energy, and fairness metrics. Our results show that FedCurv- DR reduces forgetting and balances performance, fairness, and energy efficiency for sustainable AI in cultural heritage.

Streetscape quality has become a central concern in contemporary urban planning, particularly within the framework of the pedestrian-friendly 15-minute city, where walkability and public-space quality are increasingly recognized as key determinants of urban performance. However, assessing streetscape qualities across large suburban and peri-urban territories remains challenging due to the time and resource demands of conventional field surveys. This paper presents a planning-oriented assessment of streetscape qualities in the north-eastern periphery of Nice (France) using the latest release of SAGAI (Streetscape Analysis with Generative AI), an open-source workflow that leverages vision-language models (VLMs) for large-scale streetscape analysis from Google Street View imagery. The new release addresses limitations of the original framework through improved image acquisition, geographically consistent view generation, support for multiple VLM architectures, consensus-based inference, and an integrated analytical environment. The workflow is applied to several thousand street-level observations to evaluate qualities relevant to pedestrian-friendly urban environments: sidewalk presence, pedestrian entrance density, and vegetation. The resulting maps reveal that the desired streetscape qualities characterize only a fraction of today's suburban streetscapes, mainly in compact developments and traditional suburban faubourgs, while they are particularly lacking on residential hills. The analysis demonstrates the potential of contemporary VLMs to support urban diagnostics in extensive suburban territories where fieldwork would be prohibitively time-consuming. Beyond the case study, the paper illustrates how recent advances in vision-language models can contribute to evidence-based planning by enabling scalable, flexible, and interpretable assessments of urban public-space quality.

Preference optimization is a standard alignment method for generative models, yet extending it to continuous-time dynamics remains non-trivial. In flow matching, reward-driven updates modify transport trajectories without an inherent constraint to the pretrained data manifold and can move terminal samples off the pretrained support. We formalize this failure mode as manifold drift. Theoretically, we show that optimal flow matching recovers the terminal data distribution, whereas a preference update leaves the pretrained manifold whenever its induced terminal displacement has a nonzero normal component. As a remedy, we propose ThermoDPO, a temperature-controlled objective that anchors pairwise preference optimization on preferred samples. Across temperature regimes, this objective connects rejection sampling fine-tuning and FlowDPO and controls a pointwise reconstruction-based surrogate for manifold distance. To counteract diminished signals at low temperatures, we further introduce a weighted variant, ThermoDPO-weighted. On the main toy benchmark, ThermoDPO-weighted attains a StrictScore of 0.899, compared with 0.629 for FlowDPO and 0.857 for FlowDPO+RFT. On SD3.5-M at CFG = 4.5, it improves OCR by 47.5% and the average of four metrics by 16.0%.

Sparse view 3D reconstruction is commonly addressed with neural implicit surfaces or dense point-based representations such as Gaussian splatting. Surface-aware splatting methods improve extracted geometry through oriented primitives and regularization, while RadiosityGS incorporates differentiable light transport through a radiosity inspired finite-element surfel formulation. We propose a differentiable point rendering method based on opacity-bearing beta surfels. An opacity explicit adjoint light transport formulation provides gradients for surfel geometry and appearance parameters, allowing physically based light transport to constrain reconstruction. Across five synthetic objects reconstructed from ten posed views, our method achieves the lowest mean symmetric Chamfer distance among the evaluated baselines and reduces mean Chamfer distance by 28.5% relative to the strongest point-based baseline while using only 267 surfels on average, approximately ~161 fewer primitives. Directional Chamfer results further show improved accuracy and competitive completion relative to related point-based methods. These results show that, in the controlled direct illumination setting, compact beta surfels combined with transport-based optimization can recover surfaces without relying on the tens to hundreds of thousands of primitives used by the evaluated baselines.

Skeleton-based Video Anomaly Detection (VAD) offers a robust, privacy-preserving solution for identifying abnormal behaviors. To model the distribution of normal static and moving poses, recent methods train Energy-Based Models (EBMs) via Denoising Score Matching (DSM). However, directly injecting noise, required for training, into raw joint coordinates creates physically impossible poses, and this structural collapse severely worsens as the temporal window expands. To address this, we introduce STEP, a simple framework that utilizes Principal Component Analysis (PCA) to project pose sequences into a compact, whitened PC-space. Learning the data density within this well-behaved PC-space ensures that the injected noise translates into physically plausible variations, which allows the model to process longer video sequences without the performance collapse of raw coordinate baselines. Additionally, to mitigate inherent pose estimation inaccuracies arising from occlusions or motion blur, we integrate a sequence-level weighting mechanism based on the estimator's confidence scores. Operating at real-time computational efficiency, our simple and lightweight framework outperforms the previous skeleton-based state-of-the-art by 12.2% (90.1% AUROC) on the challenging UBnormal dataset and achieves highly competitive results by improving on the ShanghaiTech benchmark.

Recently, open-vocabulary 3D object detection (3D-OVD) has gained increasing attention for its ability to detect unseen objects in 3D scenes. Existing approaches typically adopt a two-stage pipeline that first discovers novel objects using foundation models and then trains a 3D-OVD model based on these discovered objects. Although effective, this pipeline often suffers from inaccurate localization and mismatched classification during the discovery stage, which subsequently limits the performance of the model training stage. To address these limitations, we advocate for improving both the reliability of novel object discovery and the robustness of model training, and propose an innovative framework. Specifically, for reliable discovery, our co-distillation strategy distills high-quality novel objects by applying Hungarian matching over a comprehensive score that incorporates geometric consistency, structural objectness, and semantic certainty. To enhance robust model training, we further propose a dual-guidance learning scheme, incorporating a scene-awareness-guided uncertainty regularization for the regression head and an LLM-guided hierarchical alignment for the classification head, effectively mitigating the negative effects of imprecise 3D bounding boxes and semantic ambiguity. Extensive experiments on SUN RGB-D and ScanNetV2 demonstrate that our method achieves significant performance gains over state-of-the-art approaches. Code is available at https://github.com/shangboyuan/Co-3DGT

Modern computer vision has enabled partial autonomy in robotic assembly manipulation. However, performing autonomous manipulation of a progressive assembly demands a more specific set of skills, in addition to perceiving the objects. Through a comparative analysis of research in the associated domains, we deduce that object-centric perception must advance towards learning assembly dependencies to predict meaningful actionable outputs for autonomous assembly manipulation. Subsequently, we present a 3D keypoint-based modular learning framework to learn assembly dependencies to infer actionable outputs given a RGB-D input of an assembly scene. We train and evaluate our trained network on an assembly pose estimation dataset and compare it against object-centric baselines with an augmented set of metrics for progressive assemblies.

Segmentation of curvilinear anatomical structures in 3D medical images remains challenging due to complex topology, severe class imbalance, weak contrast, and large variations in structure morphology. While deep learning approaches for 3D curvilinear segmentation have been proposed, they are often tailored to specific anatomies or modalities, limiting generalization across clinical settings and leaving room for improvement. Recent generative models have shown the benefits of iterative prediction for structured segmentation tasks, yet diffusion-based methods suffer from computationally expensive sampling, hindering their use on high-resolution 3D volumes. We present 3D-CurvSegFlow, a flow matching-based model for 3D curvilinear structure segmentation. The model learns a continuous transformation from a simple source distribution to the target vascular representation, enabling progressive refinement of complex curvilinear geometries with efficient inference. We evaluate our method on Three public challenging datasets covering distinct anatomies and modalities: portal vein, cerebral vessel, and coronary arteries. Using a common architecture and training strategy across all tasks, our method outperforms general-purpose and vessel-specific approaches, with strong preservation of thin branches and vascular continuity. This work not only advances the state-of-the-art in 3D curvilinear segmentation but also opens new avenues for efficient, generalizable, and clinically applicable methods in medical image analysis.

For full-body avatars, modeling surface dynamics is crucial for overcoming the uncanny valley and achieving perceptual realism. Person-agnostic methods recover static 3D avatars from monocular images, videos, or text prompts, but their skeleton-driven animations lack realistic surface dynamics such as clothing wrinkles. In contrast, person-specific methods achieve high-quality rendering and realistic dynamics, but require expensive multi-view captures for each individual. Recent generalizable dynamic avatar methods struggle to embed surface dynamics, leading to either limited multi-view consistency or dynamic expressiveness. To this end, we propose AvatarDynamizer, a generative method that transforms an off-the-shelf static 3D avatar into a controllable, realistic, and multi-view-consistent 4D avatar. We introduce a novel texture-space surface-dynamics embedding and formulate avatar dynamics modeling as conditional texture generation. Our encoder–decoder representation embeds pose-dependent dynamics into dynamic texture maps, enabling compatibility with pre-trained video diffusion models while decoding them into 3D Gaussians for multi-view consistent rendering. Since existing datasets are limited in scale, sequence length, or motion diversity, we collect a large-scale multi-view dataset with long sequences covering diverse skeletal motions and surface dynamics. Experiments show that our method effectively animates static avatars with faithful surface dynamics and outperforms competing generalizable methods in visual fidelity, especially under limited dynamic training data.

Multi-view computer vision pipelines typically rely on accurate sparse keypoints and robust descriptors. While incorporating line features has shown clear benefits for matching and pose estimation, existing point-line approaches remain inefficient: they detect points and lines separately, use increasingly heavy networks, and depend on CPU-bound heuristics that hinder real-time performance. We introduce a Unified Efficient Points and Lines (UPAL) feature extractor that jointly extracts keypoints, line segments, and feature descriptors within a single lightweight architecture. A shared backbone provides common representations that feed different branches for point and line features. Line segments are recovered through an accelerated post-processing stage, an enhanced and highly efficient variant of the LSD algorithm. UPAL matches or exceeds state-ofthe-art performance in both point and line applications while significantly reducing computational cost, achieving, for instance, a 4x speedup and 10x smaller memory footprint over the ALIKED + DeepLSD pipeline. Code is publicly available at https://github.com/francois141/upal.

Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object compositions by leveraging knowledge of primitive concepts learned from seen compositions. Although recent works achieve impressive performance in CZSL by leveraging large vision-language models, they primarily rely on discriminative representations that may not explicitly preserve the structured relationships between primitive concepts and their compositions. Motivated by the recent success of diffusion-based classifiers and their competitive performance relative to discriminative models, we investigate whether intermediate diffusion representations can provide complementary cues for CZSL. To this end, we propose DIFFCZSL, a diffusion-augmented framework that injects generative priors from pre-trained diffusion models into CLIP-based CZSL pipelines. We extract intermediate diffusion representations and project them into the CLIP embedding space to provide auxiliary supervision on both image and text modalities. Through contrastive alignment between CLIP embeddings and diffusion features during training, our method encourages the embedding geometry toward richer composition-aware semantics, while introducing no additional cost at inference time. Extensive experiments on three public CZSL benchmarks demonstrate consistent improvements over strong CLIP-based baselines under both closed-world and open-world settings. Our results highlight the complementary strengths of generative diffusion representations and discriminative vision-language models for compositional generalization.

This paper presents a novel data-driven approach to camera-based autonomy for micro-drones in GPS-denied, radio-challenging indoor environments. The target application is disaster and emergency response, where micro-UAVs can provide rapid situational awareness in hazardous settings such as firefighting and chemical, biological, radiological, and nuclear (CBRN) incidents while reducing risk for human responders. When the communication link is lost, the micro-drone uses a learned yaw controller to autonomously navigate toward open space, preserving onboard sensor data that would otherwise be lost with the vehicle. A custom micro-drone equipped with a 360-degree camera was used to record diverse industrial, underground, and training scenarios representative of communication-denied field operations. We introduce a preprocessing pipeline that converts equirectangular 360-degree footage into planar front views and dynamically generates image-label pairs for AI training. We then train and compare multiple convolutional neural network variants that predict a continuous yaw command from a single monocular view. Evaluation on a held-out test set confirms the feasibility of the learned yaw-prediction approach. A semi-autonomous real-world test further demonstrates the practicality of the method while revealing key failure modes, particularly reflections and glare.

Single-shot exposure correction aims to map an arbitrarily degraded image—whether under-exposed, over-exposed, or a spatial mixture of both—to a well-exposed output from a single capture. We present AutoLumNet, a framework that decomposes this task into a global monotone tone curve and a bounded local residual, making the global component the locus of formal guarantees. The tone curve is parameterized as the normalized cumulative integral of a strictly positive density, ensuring strict monotonicity by construction rather than by penalty. We prove that this parameterization (i)~preserves the pairwise luminance ordering of all pixels and all spatial extrema unconditionally, and (ii)~is dense in the space of valid tone corrections, containing the one-dimensional optimal-transport map from the input to any target luminance distribution. A differentiable sorted-sample Wasserstein-2 objective drives the learned curve toward the OT optimum during training. Spatially varying effects that the global map provably cannot address—local shading, chrominance shifts, and clipped-region restoration—are handled by a bounded residual decoder with dual-branch convex fusion, for which we provide an explicit sufficient condition for local order preservation. Experiments on five benchmarks (MSEC, SICE, LCDP, LOL-v1, LOL-v2-real) show that AutoLumNet achieves state-of-the-art PSNR and SSIM across both under- and over-exposure regimes at 11.2\,ms per frame, and generalizes zero-shot to pure low-light benchmarks without retraining. To our knowledge, AutoLumNet is the first exposure-correction method to unite structural monotonicity, optimal-transport optimality, and bounded local adaptivity within a single trainable architecture. Code is available at https://github.com/kraihan/Autolumnet.

Medical image captioning is a technique that accelerates early-stage diagnostic workflows and enhances the interpretability of medical diagnostic AI systems. However, unlike general image captioning, clinically reliable captioning remains challenging due to grayscale-based modalities, subtle anatomical cues, specialized medical phrasing, and variations in data quality. Despite recent advances in large vision-language models, fluent outputs do not necessarily guarantee sufficient alignment with clinical concept spaces or evaluation criteria. To address this issue, we propose a framework that strengthens clinical alignment by separating and enhancing training-time alignment and inference-time alignment. We build a medical image captioning pipeline that integrates single/dual vision encoders based on BioMedCLIP and SigLIP2, a Q-Former, and a LLaMA-based decoder, and examine the contribution of auxiliary learning for UMLS concept/type prediction. At inference, we apply single-embedding-based reranking to select the best caption among candidates, while at training we introduce MedPAIR-SCST, which combines clinically relevant rewards to shift the generative distribution toward improved clinical alignment. Our experiments show that complementary visual representations with a multi-encoder design and concept-level auxiliary learning help preserve clinically meaningful information. Furthermore, inference-time reranking provides a practical way to improve semantic and clinical alignment without additional training, whereas MedPAIR-SCST goes beyond selection by directly improving the model's distribution to generate more consistent and clinically grounded captions. These findings suggest that jointly leveraging selection-based alignment and reinforcement-learning-based alignment can promote more trustworthy medical image captioning even in data-constrained settings.

Conventional convolutional kernels are typically defined on fixed discrete grids, limiting their ability to accommodate heterogeneous local structures. Existing adaptive operators improve flexibility but often couple geometric scale variation with content-dependent filtering, while incurring high computational cost from per-location kernel generation. To decouple geometric scale adaptation from content-dependent filtering while avoiding expensive per-location kernel generation, we propose Continuous Relative-scale KAN (Core-KAN), a relative-scale-conditioned continuous convolution operator. Core-KAN maps input features into a compact latent basis space and uses a lightweight scale controller to predict local scales relative to an exponential moving average reference. A KAN-based generator represents depth-wise kernel bases as continuous coordinate functions, allowing the operator to synthesize spatial filters at arbitrary resolutions rather than being confined to a fixed lattice. Instead of synthesizing independent kernels at every location, it constructs a compact bank of scale-conditioned kernel responses and interpolates them according to the predicted local scale map. An independent mixing controller further combines the interpolated basis responses based on local content, explicitly decoupling geometric scale adaptation from content-dependent filtering. Together with lightweight pointwise projections, this design forms a low-rank dynamic convolution that scales efficiently with kernel size and integrates readily into hierarchical vision backbones. Experiments across three representative vision tasks show Core-KAN consistently outperforms strong convolutional and dynamic-kernel baselines with only marginal parameter and computational overhead, offering an efficient, general framework for continuous, scale-adaptive convolution.

To prevent the adoption of aesthetically polished but pedagogically flawed AI content, we study a video authoring pipeline featuring two layers of structured refusal. The first layer empowers educators to iteratively reshape AI scripts based on multimedia learning theory, while the second employs automated metrics to flag violations in instructional coherence and narrative-visual synchronization. While neither layer is exhaustive, their synergy ensures that principled resistance–the act of deferring AI output until it meets rigorous standards–becomes a catalyst for higher quality. Evaluation combining a study with 23 educators across 3 topics and automated metrics across 7 topics drawn from established science and philosophy curricula shows that both layers independently improve the same instructional dimensions, suggesting that thoughtful resistance and generative AI are not opposites but partners.

Trustworthy multimodal fusion in clinical settings requires handling incomplete and heterogeneous modality subsets across institutions, where privacy constraints prohibit centralized data sharing. Federated learning (FL) mitigates data-sharing constraints but suffers from client-specific missing modalities, where institutions possess incomplete multimodal subsets, degrading fusion quality and segmentation performance. While FL and weak supervision have been studied separately, their joint use with image-level labels under heterogeneous missing modalities remains unaddressed. We propose MOSAIC, the first modality-agnostic federated framework for weakly supervised binary tumor segmentation under client-specific missing modalities. We introduce a client-specific modality-alignment module that fuses available channels into a shared latent space without prior knowledge of modality identity, a spectral prototype alignment loss that reconciles cross-client distribution shift using compact non-invertible frequency-domain statistics, and a dedicated federated refinement network that denoises the resulting CAM pseudo-labels into accurate masks, breaking the accuracy ceiling of weak supervision. Experiments on three multi-institutional brain tumor benchmarks (FeTS2022, BraTS-MEN, and BraTS-SSA) demonstrate significant improvements over all image, box, and point-supervised baselines, approaching fully supervised accuracy using only image-level labels and reaching 0.84 Dice on FeTS2022. Dynamic new client addition enables previously unseen institutions to join an already-trained federation within 0.01-0.04 Dice without retraining. Code is available at https://github.com/Tarun2201/MOSAIC.

Existing optimal transport (OT) models primarily seek an OT map or plan between distributions by minimizing a prescribed transport cost or distortion. However, minimizing transport cost or distortion alone may fail to identify a geometrically meaningful transformation between the two distributions. To address this limitation, this paper proposes a novel coupled OT framework that leverages a small number of annotated landmarks to guide the recovery of an underlying deformation governing the distribution transformation. The coupled OT framework integrates the optimization of the transport plan and the deformation field into a unified model, where the landmark-guided deformation field and the cost-driven transport plan are coupled through a mutual-consistency constraint. As a result, the deformation is jointly determined by the annotated landmarks and cost-driven distribution matching. The proposed framework provides a principled connection between landmark-based registration and transport-based distribution matching, enabling the recovery of transport maps from sparse geometric supervision. We establish the well-definedness of the proposed model in a general variational setting and develop a finite-element-based numerical algorithm for computation whose convergence properties are systematically analyzed. The practical effectiveness of the proposed approach is verified in shape matching.

Fast and accurate segmentation of Acute Ischemic Stroke (AIS) lesions is essential for stroke prognosis and treatment planning. Non-contrast CT (NCCT), the first-line imaging modality for diagnosing ischemic infarcts, exhibits subtle infarct contrast, making manual delineation slow and labor-intensive. Motivated by this, and by the clinical practice of comparing brain hemispheres to localize infarcts, we propose a two-stage, nnU-Net-compatible 3D segmentation method. The first stage corrects head tilt to align each scan to its true anatomical mid-sagittal plane; the second applies a novel Asymmetric Feature Extraction (AsymFeX) module, comparing each voxel to its true contralateral counterpart within a local 3 x 3 x 3 neighborhood via cross-hemispheric attention, feature disparity estimation, and dual-scale gating to capture both large and small infarcts. On AISD, our method achieves 0.6796 Dice, 23.53 mm HD95, and 7.69 mL AVD, significantly outperforming existing state-of-the-art methods, with clinically relevant volumetric analysis at the 70 mL thrombolysis-eligibility threshold. Proof-of-concept evaluation on ATLAS v2.1 and ISLES'24 demonstrates that the same symmetry-driven design generalizes across imaging modalities and stroke time points without architectural changes, further supported by an uncertainty analysis assessing reliability under clinical deployment. Code is publicly available at https://github.com/biomedia-lab/AIS-detection.

Self-supervised pretraining on remote sensing imagery typically treats all samples as equally informative, despite large variability in geographic and visual structure. We propose a curriculum learning strategy for self-supervised Earth observation that ranks samples by geographic isolation, a label-free proxy derived entirely from geolocation metadata already present in geospatial datasets, requiring no image decoding, no model feedback, and no manual annotation. Unlike visual complexity proxies, it scales as O(D log D) with dataset size D and is well-defined for both contrastive and reconstructive objectives. We integrate the proposed measure into MoCoV2 and MAE pretraining and evaluate across three downstream tasks from CopernicusBench (BigEarthNet, DFC-2020, LCZ). Our curriculum reaches baseline final-epoch performance using as few as 20% of the training budget (MAE) and at most 40% (MoCo) of the training budget, and improves final downstream performance by up to +5 mAP on BigEarthNet, with gains of 1-5 points across benchmarks, matching visual-complexity curricula while reducing pre-computation cost by more than 140x (4 s vs. 568 s on SSL4EO). A CKA and effective-rank analysis further reveals that curriculum-trained encoders develop higher-dimensional, more uniformly utilized embedding spaces throughout training.

We describe our entry to the PhysAI Dynamic 4D Reconstruction Challenge, which placed third of 27 teams at 0.58356 APD on the final leaderboard, without a single gradient update. This was not the plan: of thirteen fine-tuning configurations of a pre-trained 4D backbone, twelve degraded the challenge score, and eleven of those twelve improved local validation at the same time. We trace this inversion to the structure of the benchmark: only 25% of the evaluation set belongs to the data variant released for training, so updates that fit the available data damage the pre-trained features the remaining 75% relies on. Our system therefore freezes the backbone and spends its budget at inference time, fusing three decoding configurations – temporal stride-3, horizontal-flip test-time augmentation, and dense stride-1 – under a convex weighting. The ensemble recovers +0.041 APD over the frozen baseline, more than any training run achieved, at zero training cost.

Multimodal LLMs can see a document, but they often can't read it reliably. Small text, tables, visual cues, and topological elements still trip them up under direct visual inference, even when the page is already sitting in the model's context. Most document-VQA systems treat perception as fixed: they encode the page once, ask the question, and answer from whatever the model happened to extract in that single fast pass. We think document VQA needs slower, more deliberate perception: rather than answering from one fixed encoding, the model should spend a bit of extra compute at inference time working out what to look at next, and only then answer. We build this into Q-Guide, a small agent that reads a question, works out what evidence it is still missing, and calls targeted tool(s) to recover it—reading text where text is needed, zooming in where detail is needed, or grounding a region where position matters. On DocVQA2026 and Manga109, Q-Guide outperforms both direct prompting and recent multi-agent document systems ($65.0\%$ vs.\ $40.0\%$ on DocVQA2026, $32.4\%$ vs.\ $24.4\%$ on Manga109), and the improvement holds across three Claude backbones (Opus 4.6, Sonnet 4.6, and Opus 4.5). We find that accuracy scales with the perception budget—most of the gain appears within two to three deliberate rounds—and that the gain comes from directing perception to the right place, not from complex control logic: adding planners, routers, or multiple collaborating agents does not help.

Full-cycle biventricular geometry is essential for characterizing cardiac function. However, dense and temporally consistent 3D+t biventricular meshes are not routinely available, whereas end-diastolic (ED) anatomy can often be obtained reliably. We therefore investigate full-cycle biventricular motion synthesis from a single ED mesh. This task is challenging because cardiac deformation is spatially heterogeneous and phenotype dependent, while conventional global generative models often obscure localized motion patterns. In this study, we propose a region-specific and phenotype-adaptive framework that integrates motion-informed functional parcellation with conditional latent flow. A functional partition learned from reconstructed motion organizes the ventricular surface into regions with coherent dynamics and enables topology-aware regional feature exchange. A phenotype-conditioned rectified-flow model subsequently maps the ED anatomy to full-cycle motion latents through fine-grained conditioning and prototype-routed motion adapters. An optional control branch further incorporates available motion descriptors for controllable synthesis. Experiments on ACDC, M&Ms, and M&Ms-2 demonstrate consistent improvements in geometric accuracy and functional fidelity. Under ED-only synthesis, our method achieves biventricular ASSD, HD95, and vRMSE of \(1.49\pm0.34\)~mm, \(3.77\pm1.06\)~mm, and \(3.31\pm1.03\)~mm, respectively, outperforming all competing methods. Complementary functional and robustness evaluations further demonstrate that the synthesized sequences preserve physiologically plausible ventricular dynamics and generalize across cohorts and disease phenotypes. The code will be released publicly upon acceptance of the manuscript for publication.

Large vision-language models (LVLMs) have achieved remarkable progress in video understanding and reasoning. Despite extensive studies on text- and image-based jailbreaks, video jailbreaks against LVLMs remain largely unexplored. Existing video jailbreak methods mainly manipulate textual content embedded in videos, while overlooking how such information is organized over time. Our analysis reveals that jailbreak effectiveness depends not only on the semantics of textual information but also on its temporal presentation, including duration and timing-slot allocation. Motivated by this finding, we use subtitles, which are common in real-world videos and allow semantic content to be presented under precise temporal control without appearing visually intrusive, as a natural attack medium. Based on this insight, we propose TempJail, a black-box video-based jailbreak framework that constructs query-aligned dialogue-style subtitle sequences and optimizes their temporal scheduling to exploit temporal vulnerabilities in LVLMs and elicit responses that satisfy the harmful intent of the source query. Extensive experiments on four representative LVLMs and two datasets demonstrate that TempJail achieves the highest attack success rate across all evaluated model–dataset settings, outperforming the strongest baseline by 53 and 18 percentage points in dataset-averaged ASR on GPT-5 and Gemini 3.5-Flash, respectively.

Vision-language-model-based embodied agents can complete instructed tasks but often violate safety constraints in the process, a problem recently framed as interactive safety. Training such agents to act safely is difficult, since safety and task success are distinct objectives, and safety arises only at a small number of safety-critical steps within a trajectory. Standard supervision is insufficient: imitating safe trajectories teaches behavior without explaining why it is safe, and contrasting arbitrary safe and unsafe trajectories mixes the safety signal with unrelated differences. We propose SafeBranch, a framework that aligns an embodied actor on safety through branch pairs constructed from the actor's own unsafe rollouts via environment rollback. SafeBranch rolls each unsafe rollout back to the safety-critical step that caused the violation, queries the actor for a safe alternative, and pairs the original action with the alternative so that the two branches differ only at that step. The trained actor acts safely at deployment with no critic in the loop. On IS-Bench, SafetyALFRED, and out-of-distribution variants with unseen tasks and objects, it improves safe task completion, achieving roughly ten times more safe successes than the untrained baseline on the unseen-object variant. Project page: https://github.com/98hyunse/SafeBranch.

The typical training process of a multimodal large language model (MLLM) involves adapting both the language model backbone and the projector between the backbone and a modality-specific encoder. We ask whether fine-tuning the backbone of an MLLM is necessary to adapt it to a new modality. Through experiments on 3D MLLMs, we find that training only the projector is sufficient to achieve strong multimodal performance relative to existing baseline models and our jointly trained MLLMs with the same encoder and backbone. We also show that joint training leads to undesirable drift in existing capabilities of the language model, which projector-only training avoids by definition. Furthermore, projector-only training has approximately twice the training sample throughput of joint training. We validate our findings across different language model backbones via 3D classification and captioning benchmarks as well as standard benchmarks evaluating language, vision, and spatial reasoning capabilities.

Streaming video understanding requires models to causally update state as video arrives and organize growing history into semantic units that can evolve, persist, and be recalled under bounded computation and memory. This challenge is pronounced in live soccer commentary, where a system must describe completed events, summarize recent play, recall earlier events, or remain silent using only information available before each utterance. We present StreamSoccer, an event-driven system that uses event memory as its intermediate representation. A fixed-budget active memory integrates the stream; completed event states are retained locally and consolidated into retrievable historical records. A unified generator uses current, recent, and historical context to produce three commentary modes, while a rule-assisted scheduler selects a mode or silence. Unlike streaming video-language models organized around frames, visual tokens, or caches, and soccer-commentary methods based on predefined clips or output timestamps, StreamSoccer explicitly models event lifecycles. We construct a three-track streaming soccer commentary dataset and a layered evaluation protocol. At common reference anchors, StreamSoccer obtains CIDEr scores of 38.62, 23.96, and 17.39 for current-event, recent-window, and historical-memory commentary, ranking first on the current-event and historical-memory tracks and second on recent-window. Controlled ablations show that local completed events improve all tracks and that the full system performs best on all three. Across 174 raw-video runs on 58 matches, per-minute RTF p95 ranges from 0.10 to 0.22 without sustained growth with match history. These results indicate that event memory supports streaming soccer commentary across temporal scopes while controlling long-history computation.

Reference-based diffusion stylization requires separating target geometry from transferable appearance. Existing tuning-based methods often rely on aligned content-style-target triplets or auxiliary visual encoders, which increases data cost and can transfer unintended scene structure from the style reference. We propose SEFS (Style-Encoder-Free Stylization), a style-encoder-free conditioning framework for diffusion transformers. SEFS forms style tokens from stochastic low-resolution crops of single training images. This crop bottleneck preserves local appearance statistics such as palette, stroke, texture, and material, while reducing access to global layout cues. Target content is encoded by edge and segmentation cues and fused with the noisy latent through parameter-efficient trainable projections. We add style-to-denoising re-normalization for token-statistic alignment and cross-block skip fusion for spatial detail. SEFS trains on unpaired single images; the frozen diffusion VAE is used only to place image conditions in the latent space. On artistic stylization benchmarks, SEFS improves content consistency and leakage diagnostics while retaining reference-style affinity, and ablations support the crop-resolution, re-normalization, and skip-fusion choices. The code of SEFS will be made publicly available.

Reliable underwater robotic perception remains difficult because optical imagery degrades under turbidity, wavelength-dependent attenuation, low illumination, scattering, and blur. Although sonar provides complementary information that is less affected by optical visibility, prior visual-sonar research has largely focused on feature alignment and nominal detection performance. We investigate cross-modal robustness as visual reliability deteriorates and assess whether pretrained visual foundation-model representations can be complemented by sonar under severe degradation. We use frozen DINOv2 as the visual encoder and construct a controlled five-level benchmark ranging from clean to extreme visual conditions. We compare conventional visual detection, frozen foundation-model representations, sonar context, fixed multimodal fusion, clean-trained adaptive gating, and degradation-aware gated fusion. Our method trains the fusion mechanism across the full range of degradation while keeping the visual and sonar encoders frozen, allowing modality contributions to adapt without fine-tuning the pretrained backbone. Under extreme combined degradation, the DINOv2 baseline achieves 0.4610 balanced accuracy, while degradation-aware visual-sonar fusion reaches 0.6152, a 33.5% relative improvement. The learned sonar contribution increases from 14.2% under clean conditions to 41.3% under extreme degradation, demonstrating adaptive redistribution of cross-modal reliance. Fusion provides the largest gains under severe turbidity and blur, whereas color attenuation alone yields little additional benefit. These results show that foundation-model representations remain valuable but insufficient under severe information loss, and that explicitly adapting fusion to modality reliability can improve robust underwater multimodal perception.

Sparse keypoint extraction and matching underpin core tasks in geometric computer vision, including structure-from-motion, visual SLAM, augmented reality, and medical image registration. Learning robust local feature representations, however, typically requires accurate camera poses or depth supervision, which are often unavailable in real-world settings. Reinforcement learning (RL) has recently emerged as a promising alternative, requiring only the information if two images show the same scene or not. However, existing RL formulations such as RIPE rely on coarse binary rewards and carefully constructed negative training pairs, limiting training stability and descriptor discriminability. In this paper, we revisit RL-based keypoint learning and propose a reward that fully exploits the geometric consistency signal, deriving both reward and penalty from a single positive pair without contrasting against negatives. This richer signal provides sufficient supervisory contrast to learn discriminative detectors and descriptors from positive image pairs alone, enabling representation learning under extremely limited supervision. Furthermore, we show that the same RL objective can be extended to the matching stage by adapting LightGlue, raising AUC@5 on MegaDepth1500 from 56.58 to 59.65 and enabling weakly-supervised training of the full sparse matching pipeline from image pairs with partial visual overlap. We validate our approach on established benchmarks, demonstrating competitive results compared to fully-supervised methods. We further show that the method can be even trained on low texture medical video sequences, where camera poses are usually unavailable and standard SfM pipelines often fail. Code and data are available at https://github.com/fraunhoferhhi/RIPEpp .