Probing Human-Machine Perceptual Alignment with Semantically Ambiguous Images
Yuqi Hu, Vasha DuTell, Ahna R. Girshick, Jennifer E. Corbett
AI 速览：该研究利用语义模糊图像作为探针，在视觉-语言嵌入空间中生成连续模糊谱，定量比较人类与机器分类器的感知决策边界与敏感度。
The classic duck-rabbit illusion reveals a fundamental property of perception: when visual evidence is ambiguous, a visual system must resolve competing interpretations. But do humans and machine classifiers resolve the same ambiguity in the same way? To explore this, we use semantically ambiguous images as probes of human-machine perceptual alignment. Our psychophysically-informed framework interpolates between concepts in vision-language embedding space to generate continuous spectra of ambiguous images, enabling direct comparison of human and machine perceptual decision boundaries and sensitivities. We find systematic differences in these boundaries: machine classifiers are shifted relative to both human observers and the midpoint of the synthesis continuum. Guidance scale affects both bias and sensitivity in humans and the machine classifiers tested. Controlled semantic ambiguity in generated images, combined with a psychophysical framework, can thus enable quantitative evaluation of human-machine perceptual alignment.
AI 速览：VitronEdit 提出一个统一框架，用共享序列表示和渐进式多模态训练，把图像与视频编辑知识迁移到数据稀缺的3D场景编辑。
Recent advances in unified visual editing have begun to consolidate image and video editing within a single model, while 3D scene editing remains largely separate and constrained by scarce paired training data. Given the rich image and video editing supervision now available and the common editing semantics shared across modalities, a natural question is whether this knowledge can be transferred to data-scarce 3D editing. We present VitronEdit, a universal framework for image, video, and 3D scene editing. VitronEdit adopts a shared sequence representation and progressive multimodal training to transfer editing knowledge across modalities. We further introduce geometry-aware post-training, which leverages a pretrained geometry reconstruction model to provide depth and camera-pose supervision. Surprisingly, applying geometric supervision only to 3D samples yields the best overall performance, while image and video editing also improve despite receiving no direct geometric supervision, suggesting that geometric regularization transfers through the shared backbone. Our analysis further shows that image and video training mainly transfers editing semantics to 3D, whereas 3D supervision primarily improves multi-view consistency. The project page: https://vitron-llm.github.io/VitronEdit/.
GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling
Kang He, Wenshuo Peng, Chuanhao Li, Zihui Gao, Xiaojie Xu, Zhengyuan Lin, Yuzhe Ding, Donghong Ji 等 10 位作者
AI 速览：作者构建了包含69.7K片段、1,655小时、约3.5亿帧的分钟级游戏视频数据集GameVerse，用于支撑长时程交互式世界模型训练。
Recent advances in interactive world models have made it possible to generate controllable, dynamic environments from action inputs. Yet current models struggle to maintain coherence beyond roughly one minute of rollout, a limitation rooted not in model capacity but in the scarcity of long-horizon training data. Existing gameplay video datasets typically consist of clips under ten seconds, with captions that describe whole clips in coarse and undifferentiated text, which is insufficient for controllable long-horizon generation. We address this with GameVerse, a minute-scale gameplay video dataset purpose-built for long-horizon interactive world modeling. GameVerse contains 69.7K clips spanning 1,655 hours and 349.6 million frames across diverse first- and third-person gameplay, including 1,358 hours of continuous two-minute sequences, an order of magnitude longer than prior datasets. Clips pass through a unified pipeline of scene-consistent segmentation, quality filtering, camera pose estimation, and event-based caption annotation. Each clip is paired with a temporally stable camera trajectory that remains coherent across minutes, together with captions that separate static scene context from dynamic foreground events and align to event boundaries rather than fixed time windows. Comprehensive analysis shows that GameVerse surpasses existing public datasets in scale, diversity, and annotation quality. Experiments further demonstrate that training on GameVerse substantially extends the temporal horizon of interactive world models.
EarthScape: A Multimodal Benchmark for Geologic Mapping and Surface-Aware Learning under Geographic Domain Shift
Matthew A. Massey, Nusrat Munia, Abdullah-Al-Zubaer Imran
AI 速览：作者提出 EarthScape，一个融合航空影像、LiDAR 高程、多尺度地形衍生特征与上下文矢量数据的多模态基准，用于在地理域偏移下评估地质填图与地表感知学习。
Understanding natural Earth surface processes requires integrating topography, imagery, hydrology, and human infrastructure while remaining robust to geographic variation, yet few benchmarks support both challenges. We introduce EarthScape, a multimodal benchmark for geologic mapping and surface-aware learning under geographic domain shift. EarthScape combines aerial imagery, LiDAR-derived elevation, multi-scale terrain derivatives, and contextual vector data into 37 co-registered input channels per sample, together with pixel-level geologic masks. Its geographically separated regions share a common label space, enabling controlled evaluation of in-domain and cross-region generalization under realistic class imbalance and spatial complexity. Benchmark experiments show that engineered terrain representations transfer more robustly than raw elevation, while spatial support and multimodal terrain inputs strongly influence performance. Fusion effectiveness depends on backbone and evaluation domain, with more complex cross-attention providing no consistent advantage over simpler strategies. These representation trends extend across geospatial foundation models and semantic segmentation, while class-level results show that no single terrain feature or scale is optimal across geologic classes. Together, EarthScape provides a benchmark for studying representation design, multimodal fusion, and geographic robustness in surface-aware geospatial learning. Our source code is available at https://github.com/masseygeo/earthscape and the dataset at https://doi.org/10.13023/kgs.data.05.01.2025.
Learning Motion-Expressive 4D Gaussian Representations from Monocular Videos with Flow Splatting
Jinzhao Li, Miao Liu
AI 速览：提出具有时变均值与协方差的运动表达型4D高斯表示，并通过Flow Splatting渲染光流实现稠密运动监督，从单目视频重建动态3D场景。
Reconstructing dynamic 3D scenes from monocular videos remains challenging because limited observations provide insufficient motion constraints. Conventional 4D Gaussian representations model spatiotemporal appearance efficiently, but the restricted temporal evolution of each primitive makes complex nonlinear dynamics difficult to represent compactly. We propose a motion-expressive 4D Gaussian representation with time-varying means and covariances. By analytically differentiating Gaussian trajectories, we obtain Gaussian velocities and introduce Flow Splatting to render optical flow while accounting for camera motion, enabling dense motion supervision. This formulation jointly models scene appearance and motion within a unified set of 4D Gaussian primitives. We further introduce an initialization strategy based on the sampling theorem and a velocity consistency regularizer to stabilize optimization. Experiments on DAVIS and NVIDIA Dynamic Scenes demonstrate a favorable trade-off between reconstruction quality and efficiency under challenging monocular settings.
GUI-AC: Enhancing Continual Learning in GUI Agents
Can Lin, Wenjun Yang, Tao Feng, Hangjie Yuan, Dan Zhang, Yifan Zhu, Zhonghong Ou, Wen Chen 等 9 位作者
AI 速览：GUI-AC提出一种持续强化微调框架，通过优势与策略概率联合刻画grounding rollout并引入grounding certainty，以针对性优化探索与过度自信问题。
Graphical User Interfaces (GUIs) serve as the dominant medium for human-computer interaction, yet building GUI agents that generalize across the vast diversity of real-world interface environments, with the same flexibility and robustness that humans naturally exhibit, remains unsolved. Notably, GUI data are inherently non-stationary: the continual emergence of previously unseen interface instances (e.g., novel domains and resolutions) induces persistent distribution shifts, significantly impeding the continual learning of existing GUI agents. Reinforcement fine-tuning (RFT) has attracted considerable attention as a promising approach. Nevertheless, RFT exhibits pronounced instability in its grounding capability, where rollout outcomes are highly imbalanced and fixed clipping can suppress valuable exploration. More importantly, policy probability alone does not reveal the semantic role of a grounding prediction. To address these challenges, we propose GUI-AC, a continual RFT framework that jointly characterizes grounding rollouts through advantage and policy probability. This yields a four-region view of grounding behavior and enables targeted optimization of Exploration and Overconfidence. GUI-AC further introduces grounding certainty to support two core mechanisms: (i) Adaptive Advantage, which strengthens the negative correction for overconfident grounding failures; and (ii) Dynamic Clipping, which relaxes the upper clipping bound for exploratory grounding rollouts. Extensive experiments show that GUI-AC consistently outperforms state-of-the-art baselines. Code is available at https://anonymous.4open.science/r/GUI-AC-Code.
Structure is Supervision: Multiview Masked Autoencoders for Radiology
Sonia Laguna, Andrea Agostini, Alain Ryser, Samuel Ruiperez-Campillo, Irene Cannistraci, Moritz Vandenhirtz, Stephan Mandt, Nicolas Deperrois 等 12 位作者
AI 速览：提出MVMAE自监督框架，利用放射学检查的多视图结构进行跨视图对齐与掩码重建，并在低标签场景下通过报告文本辅助提升疾病分类性能。
Building robust medical machine learning systems requires pretraining strategies that exploit the intrinsic structure present in clinical data. We introduce Multiview Masked Autoencoder (MVMAE), a self-supervised framework that leverages the natural multi-view organization of radiology studies to learn view-invariant and disease-relevant representations. MVMAE combines masked image reconstruction with cross-view alignment, transforming clinical redundancy across projections into a powerful self-supervisory signal. We further extend this approach with MVMAE-V2T, which incorporates radiology reports as an auxiliary text-based learning signal to enhance semantic grounding while preserving fully vision-based inference. Evaluated on a downstream disease classification task on three large-scale public datasets, MIMIC-CXR, CheXpert, and PadChest, MVMAE consistently outperforms supervised and vision-language baselines. Furthermore, MVMAE-V2T provides additional gains, particularly in low-label regimes where structured textual supervision is most beneficial. Together, these results establish the importance of structural and textual supervision as complementary paths toward scalable, clinically grounded medical foundation models.
Video temporal grounding (VTG) takes an untrimmed video and a natural-language query as input and localizes the temporal moment that best matches the query. Existing methods rely on large, task-specific datasets requiring costly manual annotation. We introduce EvoGround, a framework of two coupled self-evolving agents, a proposer and a solver, that learn temporal grounding from raw videos without any task-specific annotations. The proposer generates query--moment pairs from raw videos, while the solver learns to ground them and feeds back signals that improve the proposer in return. Through this self-reinforcing reinforcement-learning loop, the two agents are initialized from the same backbone and mutually improve across iterations. Trained on 2.5K unlabeled videos, EvoGround matches or surpasses most fully supervised models across five VTG benchmarks, while emerging as a state-of-the-art fine-grained video captioner. We publicly release all resources at https://minjoong507.github.io/projects/EvoGround/.
Xuelin Qian, Ruiqi Wu, Zhongling Huang, Dingwen Zhang, Junwei Han
Lifelong Person Re-Identification (LReID) extends traditional ReID by requiring systems to continually learn from non-overlapping datasets across different times and locations, adapting to new identities while preserving knowledge of previous ones. Existing approaches, either rehearsal-free or rehearsal-based, still suffer from the problem of catastrophic forgetting since they try to cram diverse knowledge into one fixed model. To overcome this limitation, we introduce a novel framework AdalReID, that adopts knowledge adapters and a parameter-free auto-selection mechanism for lifelong learning. Concretely, we incrementally build distinct adapters to learn domain-specific knowledge at each step, which can effectively learn and preserve knowledge across different datasets. Meanwhile, the proposed auto-selection strategy adaptively calculates the knowledge similarity between the input set and the adapters. On the one hand, the appropriate adapters are selected for the inputs to process ReID, and on the other hand, the knowledge interaction and fusion between adapters are enhanced to improve the generalization ability of the model. Extensive experiments are conducted to demonstrate the superiority of our AdalReID, which significantly beats SOTAs by about 5\% and 3\% mAP on seen and unseen domains.
In this paper, we propose Concentrate and Concentrate (CaC), a coarse-to-fine anomaly reward model based on Vision-Language Models. During inference, it first conducts a global temporal scan to anchor anomalous time windows, then performs fine-grained spatial grounding within the localized interval, and finally derives robust judgments via structured spatiotemporal Chain-of-Thought reasoning. To equip the model with these capabilities, we construct the first large-scale generated video anomaly dataset with per-frame bounding-box annotations, temporal anomaly windows, and fine-grained attribution labels. Building on this dataset, we design a three-stage progressive training paradigm. The model initially learns spatial and temporal anchoring through single- and multi-frame supervised fine-tuning, and then is optimized by a reinforcement learning strategy based on two-turn Group Relative Policy Optimization (GRPO). Beyond conventional accuracy rewards, we introduce Temporal and Spatial IoU rewards to supervise the intermediate localization process, effectively guiding the model toward more grounded and interpretable spatiotemporal reasoning. Extensive experiments demonstrate that CaC can stably concentrate on subtle anomalies, achieving a 25.7% accuracy improvement on fine-grained anomaly benchmarks and, when used as a reward signal, CaC reduces generated-video anomalies by 11.7% while improving overall video quality.
We revisit the role of appearance modeling in 3D Gaussian Splatting (3DGS) and show that limited expressiveness in view-dependent reflectance is a key driver of representation redundancy. In standard 3DGS, low-order spherical harmonics (SH) are used, restricting the splats' ability to model high-frequency directional effects, which is typically compensated by increasing the number of splats. We propose \emph{NRF-GS: Neural Residual Fields for Gaussian Splatting}, a hybrid representation that replaces per-splat SH-bases with a shared neural residual field. Each Gaussian encodes a compact set of appearance features and a lambertian base color, while a lightweight \emph{global scene-level MLP} predicts view-dependent residuals conditioned on viewing direction, distance, and per-splat features. This formulation enhances directional reflectance modeling by combining diffuse per-splat reflectance representations with a shared global function for high-frequency details, enabling both higher expressiveness and parameter sharing across splats. Our key insight is that by accurately capturing high-frequency directional reflectance, especially in specular regions, the GS-representation becomes more expressive, reducing the need for geometrically redundant splats. As a result, NRF-GS achieves comparable or better rendering quality while reducing the number of Gaussians by up to 50\%, and produces visibly improved specular and high-frequency details.
Earth Observation (EO)-based agricultural monitoring is shifting from pixel-level spectral analysis toward representation-driven modeling, yet systematic evaluation of learned representations remains limited. Geospatial foundation models (FMs) generate high-dimensional embeddings encoding complex spatio-temporal land-surface properties, but their utility and interpretability for agricultural applications remain insufficiently understood. This study presents a representation-agnostic framework evaluating a 64-dimensional AlphaEarth embedding space against Sentinel-2 reflectance, NDVI phenology, and harmonic features across geometric separability, temporal dynamics, spatial robustness, and cross-regional generalisation using field-scale data from the Conterminous United States (CONUS; 2017-2023) and Northern India (2021). Traditional features achieve strong linear separability (Fisher ratio), while embeddings provide superior distribution-aware separation - Bhattacharyya and Mahalanobis distances up to an order of magnitude higher for spectrally similar pairs (e.g. Corn/Soybeans: 3.9 vs. 0.10). Embeddings uniquely capture multi-year crop rotation dynamics, yielding a separability ratio of 1.784, versus a maximum of 1.003 for all engineered features. Under spatially explicit validation, embeddings exhibit lower residual spatial autocorrelation of errors (mean Moran's $I \approx 0.17$), reducing reliance on geographic proximity. However, harmonic features show stronger cross-continental transferability (US $\to$ India Macro F1: 0.493 vs. 0.326 for embeddings), with NDVI showing a similar advantage. The combined feature space yields balanced performance. These findings reveal a trade-off between representational richness and cross-region transferability, providing a framework for feature selection in large-scale crop classification.
Yohann Perron, Guillaume Astruc, Nicolas Gonthier, Clement Mallet, Loic Landrieu
Vision Transformers (ViT) dominate computer vision. However, their reliance on rigid patch projectors hinders transfer to Earth Observation (EO), where input modalities, scales, and resolutions vary widely. We introduce UniverSat, a ViT-style backbone built around a Universal Patch Encoder that maps patches from arbitrary spatial, spectral, and temporal resolutions, and from both optical and non-optical sensors, into a shared embedding space with a shared set of weights. This enables training a single model on heterogeneous multimodal corpora via self-supervision, yielding robust, sensor-agnostic spatial features. We validate this approach with strong results across classification and segmentation on standard EO benchmarks from GeoBench, PANGEABench, and SpectralEarth. Our code and models are available at https://github.com/gastruc/UniverSat.
Facial micro-expressions are subtle, short-lived facial movements that reveal genuine human emotions. Despite the large advances in facial expression synthesis and animation, realistic micro-expressions remain challenging due to scarce annotated data and the extremely subtle nature of their motion. Existing dedicated micro-expression methods therefore often struggle with generation quality, robustness, and generalization. We present MEGMAG, a transferable framework for micro-expression generation via magnification that enables pretrained facial animation models to generate realistic micro-expressions without modifying or fine-tuning their backbones. The key idea is to transform subtle micro-expression dynamics into the domain of regular facial expressions, where pretrained animation models can effectively capture and transfer facial motion. A learnable Magnification Module amplifies subtle micro-expression dynamics, enabling a frozen facial animation backbone to transfer the amplified motion to a source identity without altering its original architecture or parameters. A DeMagnification Module then attenuates the generated motion to recover realistic micro-expression characteristics. This design allows MEGMAG to leverage diverse off-the-shelf facial animation models while remaining architecture-agnostic and fully transferable across backbones.
Jorge L. Rodriguez, Victor Angulo Morales, Areej Alwahas, Mariana Elias Lara, Fida Mohammad Thoker, Kasper Johansen, Bernard Ghanem, Fernando T. Maestre 等 9 位作者
Foundation models offer a promising route to transferable remote sensing representations, but many current approaches depend on very large pretraining datasets and fixed sensor configurations, limiting their suitability for ecological and environmental applications, where observations often vary across platforms, spatial and spectral resolutions, and available modalities. We introduce FLORO, a multimodal geospatial foundation model designed to learn transferable representations from a small but highly diverse remote sensing corpus. FLORO is pretrained using masked autoencoding on a heterogeneous combination of Sentinel-1, Sentinel-2, SkySAT imagery, elevation, and UAV-derived data. To accommodate sensor variability, FLORO incorporates availability-aware inputs that indicate which spectral bands and auxiliary modalities are present in each sample, enabling a unified input space across heterogeneous sensor configurations. We evaluated FLORO on the PANGAEA benchmark under a frozen-encoder protocol across scene classification, segmentation, and regression tasks. Despite being pretrained on a smaller corpus than competing foundation models, FLORO achieved strong and stable transfer across optical, optical-SAR, and optical-elevation benchmarks spanning medium-resolution satellite, airborne, and ultra-high-resolution UAV imagery. FLORO obtained the second-best average segmentation performance across six PANGAEA benchmarks, the third-best average rank across three scene-classification benchmarks, and excelled in regression tasks, while qualitative results showed improved preservation of spatial structure in flood, urban, biomass, and canopy-height prediction settings. Overall, these results position FLORO as a practical framework for ecological and environmental monitoring under heterogeneous sensing conditions.
Xiangfei Sheng, Xiaofeng Pan, Leida Li, Qian Zhang, Biao Wang, Johan Wagemans, Weisi Lin
Aesthetic image cropping (AIC) aims to improve image composition and aesthetic quality by removing extraneous or distracting content. Over the past decade, AIC methods have evolved from specialized vision models to multimodal large language models(MLLMs). Reliable evaluation that reflects human preferences is essential for benchmarking AIC methods and guiding model optimization. However, the current AIC evaluation relies largely on geometry-based metrics such as intersection over union (IoU), as well as image aesthetic assessment(IAA) models. Although inconsistencies with human preferences have long been observed, the robustness and reliability of these evaluation criteria remain underexplored. To bridge this gap, we first construct CropBench, a large-scale benchmark comprising 106,995 human preference pairs for 1,019 images, with each candidate set containing the original image and candidate crops produced by 14 AIC methods. A systematic study on CropBench reveals that the existing criteria, ranging from IoU to off-the-shelf IAA assessment models, only exhibit limited alignment with human preferences. Building upon CropBench, we further propose CropReward, an MLLM-based reward model that evaluates a candidate crop by comparing with the original uncropped image and outputs a score indicating explicit aesthetic improvement or degradation relative to the original. In addition, we employ CropReward to construct CropReward-300k, the largest AIC dataset to date, and further develop CropAlign, a preference-aligned AIC model trained solely with CropReward supervision, without human-annotated crop boxes. Experimental results demonstrate that CropReward aligns with human preferences significantly better than AIC existing criteria. CropAlign also surpasses the state-of-the-art AIC methods, demonstrating the advantage of CropReward in guiding AIC model optimization.
Yuqiang Lin, Kehua Chen, Sam Lockyer, Arjun Yadav, Mingxuan Sui, Shucheng Zhang, Yan Shi, Bingzhang Wang 等 15 位作者
Traffic Anomaly Understanding (TAU) is important for traffic safety in Intelligent Transportation Systems. Recent vision-language models (VLMs) have shown strong capabilities in video understanding. However, progress on TAU remains limited due to the lack of benchmarks and task-specific methodologies. To address this limitation, we introduce Roundabout-TAU, a dataset constructed from real-world roundabout videos collected in collaboration with the City of Carmel, Indiana. The dataset contains 342 clips and is annotated with more than 2,000 question-answer pairs covering multiple aspects of traffic anomaly understanding. Building on this benchmark, we propose TAU-R1, a two-layer vision-language framework for TAU. The first layer is a lightweight anomaly classifier that performs coarse anomaly categorisation, while the second layer is a larger anomaly reasoner that generates detailed event summaries. To improve task-specific reasoning, we introduce a two-stage training strategy consisting of decomposed-QA-enhanced supervised fine-tuning followed by TAU-GRPO, a GRPO-based post-training method with TAU-specific reward functions. Experimental results show that TAU-R1 achieves strong performance on both anomaly classification and reasoning tasks while maintaining deployment efficiency. The dataset and code are available at: https://github.com/siri-rouser/TAU-R1
Ghosting artifacts are an open problem for popular multi-shot based high dynamic range (HDR) imaging. An effective solution is to capture two large-exposure-ratio (LER) standard dynamic range (SDR) images simultaneously via a single-shot. Brightness order reversal (BOR) artifacts are generated when the two LER images are directly fused together. It is crucial to interpolate an image with an exposure time in between the exposure times of two LER images. In this paper, a novel physics-guided diffusion model based exposure interpolation algorithm is proposed to address the BOR artifacts. An initial image is interpolated by a physics-driven component, and the residual high-frequency details are generated by a new diffusion model based component. The new diffusion model is based on the correlation analysis of generative models and includes a new predicted target to reduce the variation of the Pearson correlation between the noisy data and the target, as well as the amplification factor of the fitting error. Compared with existing neural augmented exposure interpolation algorithms on top of convolution neural networks, the proposed exposure interpolation algorithm has an inherent advantage to generate more high frequency information. Experiment results validate the proposed exposure interpolation algorithm.
Max Kahl, Sebastian Stricker, Lisa Hutschenreiter, Florian Bernard, Carsten Rother, Bogdan Savchynskyy
Multi-graph matching is a fundamental problem in computer vision. Our work is motivated by a challenging application in bioimaging, where dozens or even hundreds of 3D microscopy images of worms must be brought into correspondence. Existing datasets do not cover this large-scale regime, and virtually all existing methods are inapplicable because they assume a complete or dense problem setting. To support further research, our first contribution is a new large-scale dataset based on problem instances from bioimaging. Our second contribution is a comprehensive analysis of the two main multi-graph matching paradigms: direct and permutation synchronization-based formulations. We argue, in part by proof, that practical large-scale methods must explicitly address problem sparsity and incompleteness. Since standard permutation synchronization approaches fail in this setting, we further introduce a sparse permutation synchronization paradigm. Our final contribution is GREEDA, a general method for sparse and incomplete problems that can be instantiated across cost orders and paradigms. While our paper focuses on objective functions up to quadratic order, GREEDA is inherently generalizable to arbitrary orders. On larger, sparse instances, GREEDA outperforms competing methods in both objective value and runtime. For example, for moderately sized problems based on 30 worm images GREEDA produces a high-quality solution within 2 minutes, whereas competitors require at least an hour and yield far worse results. On smaller dense problems, GREEDA remains on par with leading methods while being an order of magnitude faster.
Detector confidence is often used to decide whether a robot needs another view of a target. We test this signal against detector-free visibility from geometry segmentation. In controlled clutter, Grounding DINO confidence remains nearly constant as target visibility falls from all scenes to one in eight. OWLv2 and SAM 3 retain positive correlations with visibility, but all three detectors lose target-instance localization under heavy occlusion. Grounding DINO reports a hidden target present in about nine of ten scenes by detecting same-category distractors. Consequently, confidence understates the benefit of additional views ($8$ versus $88$ percentage points). In a $40$-scene localization comparison, additional-view selection and fusion increase target localizability from $5\%$ to $100\%$. Experiments cover nine categories, two simulators, and real video. On DAVIS, confidence correlates positively with visible area, yet $99\%$ of occluded frames yield a detection and $94\%$ of those detections miss the tracked target. These results distinguish category presence from target visibility and motivate target-grounded evaluation of active perception.
Aoxiang Fan, Corentin Dumery, Nicolas Talabot, Pascal Fua
Computing accurate geometry from multi-view images is a fundamental problem in computer vision. Recent feed-forward (FF) models jointly estimate 3D geometry and camera parameters, but they typically suffer from geometry distortion caused by reconstruction ambiguity, even when ground-truth camera parameters are supplied. In this paper, we study the multi-view stereo (MVS) problem with known camera parameters and propose a novel approach that bridges conventional MVS and FF methods. Rather than casting MVS as a sequence-to-one mapping that predicts depth only for a single reference view, we reformulate it as a sequence-to-sequence task, akin to FF models, that jointly predicts geometry for all input views. We introduce a global transformer-based architecture with two components that explicitly exploit camera-induced priors: ray-map embeddings that inject camera parameters into image patch tokens, making the transformer camera-aware, and a unified global cost volume that replaces conventional per-view cost volumes to jointly capture 3D structure across all views. Extensive experiments on multiple public benchmarks show our approach achieves state-of-the-art performance, surpassing both MVS and FF reconstruction baselines.
Parameter-efficient finetuning (PEFT) and probing enable adaptation of foundation models using only a small number of trainable parameters. This makes these techniques attractive for video understanding where annotation and computation are expensive. However, video PEFT has focused on adapting image-pretrained models, while standard PEFT methods can also be applied to video representations. These settings are rarely compared and both confine temporal reasoning to a single component of the model, leaving open how temporal context should be distributed across backbone, PEFT, and probe. In this work, we provide a systematic study of model adaptation strategies for video understanding. We evaluate methods across appearance-focused, motion-focused and spatially dense settings, with a particular emphasis on scenarios with limited data where parameter efficiency is most beneficial. Our results provide new insights into PEFT and probing across task types and demonstrate the importance of temporal context allocation for effective video adaptation.
Nuclei instance segmentation is fundamental to quantitative pathology. Yet high-accuracy methods mostly build on large vision transformers (ViTs) or heavy convolutional backbones, whose parameter count and compute cost hinder deployment in clinical and edge settings. We present NucShare, a lightweight model whose shared decoder handles nuclear pixel segmentation, horizontal-vertical distance, and classification through learnable transposed convolutions for upsampling and three lightweight heads, using 37% of independent decoders' parameters with no loss in accuracy. Output-level distillation then transfers knowledge from NucShare-T (UNI2-h) to NucShare-S (ConvNeXt V2-Tiny), reducing 690.5M parameters to 34.7M. On PanNuke they reach mPQ 0.524 and 0.519, above the prior best CFR-SAM-H at 0.511, and NucShare-S surpasses HoVer-Net and Mask R-CNN by 5.6 and 15.0 points; on zero-shot MoNuSeg it attains bPQ 0.668 against CFR-SAM-H's 0.662. Code: https://github.com/L-iMeng-L/Newidea
Shuijin Lin, Shaozhen Yan, Tuo Liu, Haifeng Wang, Chunfeng Lian, Jie Lu, Jianhua Ma, Lin Xie
The biological definition of Alzheimer's disease (AD) relies on multi-modal neuroimaging, yet the clinical utility of positron emission tomography (PET) is limited by cost and radiation exposure, hindering early screening at preclinical or prodromal stages. While generative models offer a promising alternative by synthesizing PET from magnetic resonance imaging (MRI), achieving subject-specific precision remains a primary challenge. Here, we introduce DIReCT$++$, a Domain-Informed ReCTified flow model for synthesizing multi-tracer PET from MRI combined with fundamental clinical information. Our approach integrates a 3D rectified flow architecture to capture complex cross-modal and cross-tracer relationships with a domain-adapted vision-language model (BiomedCLIP) that provides text-guided, personalized generation using clinical scores and imaging knowledge. Extensive evaluations on multi-center datasets demonstrate that DIReCT$++$ not only produces synthetic PET images ($^{18}$F-AV-45 and $^{18}$F-FDG) of superior fidelity and generalizability but also accurately recapitulates disease-specific patterns. Crucially, combining these synthesized PET images with MRI enables precise personalized stratification of mild cognitive impairment (MCI), advancing a scalable, data-efficient tool for the early diagnosis and prognostic prediction of AD. The source code will be released on https://github.com/ladderlab-xjtu/DIReCT-PLUS.
In this work, we present a method and two large-scale datasets for Script-Driven Multimodal Video Summarization. The proposed method, SD-MVSum, builds on our earlier SD-VSum method for script-driven video summarization. SD-VSum considered the relevance of a provided script, which outlines the desired content of the summary, only with the visual content of the video. SD-MVSum takes into account, in addition to the visual modality, the relevance of the script with the spoken content (i.e., the audio transcript) of the video. The dependence between each considered pair of data modalities, i.e., script-video and script-transcript, is modeled using a new weighted cross-modal attention mechanism. This mechanism explicitly exploits the semantic similarity between the paired modalities in order to promote the parts of the full-length video with the highest relevance to the script. Furthermore, we extend two large-scale datasets for script-driven (S-VideoXum) and generic (MrHiSum) video summarization, to make them suitable for training and evaluation of script-driven multimodal video summarization methods. Experimental comparisons document the competitiveness of the proposed SD-MVSum method against other SotA approaches for script-driven and generic video summarization. Our new method and extended datasets are available at: https://github.com/IDT-ITI/SD-MVSum.
Yiqi Nie, Fei Wang, Junjie Chen, Kun Li, Yudi Cai, Dan Guo, Chenglong Li, Meng Wang
Multimodal Emotional Reappraisal (MER) aims to shift affective interpretation by rewriting and editing a situation without altering its underlying semantic context. Despite advances in controllable editing and sentiment transfer, MER remains challenging under coupled multimodal constraints, especially in internet memes where images, embedded text, and layout jointly encode affective meaning. To bridge this gap, we present MER-Bench, a systematic benchmark for MER on image-text memes, containing over 3,000 real-world memes with fine-grained annotations for emotion transformation and structure-preserving multimodal editing. MER-Bench spans diverse visual, textual, and structural settings and is paired with a structured MLLM-as-a-Judge evaluation suite, comprising eight fine-grained metrics and three aggregated objectives for emotional alignment, content fidelity, and transformation strength. Extensive evaluation of 14 advanced multimodal models reveals that: (1) current models struggle to jointly balance affect, semantics, structure, and text; (2) strong visual editing does not imply effective MER, with poor embedded text rendering and affect-aware rewriting remaining key bottlenecks. Our results identify MER as a critical capability gap in current multimodal generation systems and highlight affective image-text reasoning as a key challenge for future work. Project Page: https://github.com/one-seven17/MER-Bench
Normalizing flows (NFs) provide exact likelihoods and deterministic invertible sampling, but have historically lagged behind diffusion models for large-scale image generation. We identify a key obstacle: NFs are required to learn a single invertible transport over the full ambient space, making them highly sensitive to high-dimensional representations. This leads to a semantic-capacity mismatch in modern visual representation spaces, where semantic information is compact but encoded in overcomplete features. We propose SRC-Flow, which introduces a Semantic Representation Compressor (SRC) to compact high-dimensional RAE features into a low-dimensional semantic space before flow modeling and preserve reconstruction through the frozen RAE decoder. This compact space reduces the modeling burden of NFs and enables effective likelihood-based generation in semantic representation space. We further adopt constant noise regularization tailored to the fixed unconditional bijection learned by flows. On ImageNet 256x256 and 512x512, SRC-Flow achieves state-of-the-art generation quality among normalizing flow methods, with gFID scores of 1.65 and 2.07 under classifier-free guidance, while retaining exact likelihood computation in the compact semantic representation space and deterministic invertible sampling at the flow level. Codes and models will be released in the future.
Patryk Bartkowiak, Dominik Michels, Sören Pirk, Wojciech Pałubicki
Distilled text-to-image models generate images quickly, but classifiers trained on those images can perform substantially worse than classifiers trained on images from their slower base models. We adapt released distilled generators to produce better training data while retaining fast generation. We fit a low-rank update to the student's first prediction so that it reaches an intermediate state produced by its unguided base, then disable the update and let the unchanged student finish generation. The base supplies training targets and is absent at inference. Guided targets and shorter jumps give classifiers lower accuracy in our ablations, showing why the state used for supervision matters. Across three generator families, the adapted images train better classifiers than images from the released students. With class-name templates at full ImageNet-1k scale, ResNet-50 top-1 rises from 8.4% to 34.2% for FLUX.2-klein and from 12.7% to 32.1% for SD-Turbo, using two and three denoiser evaluations per image, respectively. Fixed adapters also improve results on additional classes, fine-grained datasets, and other learner architectures and training recipes. Template-based adaptation remains useful against richer-prompt alternatives, while the benefit of combining adaptation with LLM generation prompts depends on the generator. Adapting a single generation step makes fast generators substantially more useful for training visual models.
Wenlin Chen, Mingtian Zhang, Jiajun He, Zijing Ou, José Miguel Hernández-Lobato, Bernhard Schölkopf, David Barber
Score-based distillation methods train one-step diffusion models in two stages: they first train a teacher score model, then distill it into a one-step student model. However, this distillation process can introduce bias from two sources: errors in the teacher score model and student score estimate. We propose DiffRatio, a new approach for training one-step diffusion models without teacher supervision based on a density-ratio formulation that connects score-based distribution matching and GAN-style adversarial training. Instead of using a teacher score model to provide training targets, DiffRatio directly learns a log density ratio between the student and data distributions across diffusion time steps. As a pre-trained score model is only used to initialize the one-step generator and does not supervise training, this design simplifies the training pipeline, mitigates gradient estimation bias, and reduces the size of auxiliary networks. The learned density ratio can be used as a verifier, enabling a principled inference-time parallel scaling method that further improves sample quality without external rewards or extra sequential computation. DiffRatio achieves strong one-step generation results on CIFAR-10 and ImageNet (64x64 and 512x512), outperforming most teacher-supervised distillation methods.
Hansheng Chen, Jan Ackermann, Minseo Kim, Gordon Wetzstein, Leonidas Guibas
Flow-based generation in high-dimensional pixel spaces is difficult because velocity prediction requires modeling high-dimensional noise, even when data has strong low-rank structure. We present Asymmetric Flow Modeling (AsymFlow), a rank-asymmetric velocity parameterization that restricts noise prediction to a low-rank subspace while keeping data prediction full-dimensional. From this asymmetric prediction, AsymFlow analytically recovers the full-dimensional velocity, leaving the network architecture and the standard flow-matching training and sampling procedures unchanged. On ImageNet 256$\times$256, AsymFlow achieves a leading 1.57 FID, outperforming prior DiT/JiT-like pixel diffusion models by a large margin. AsymFlow also provides the first-ever route for finetuning pretrained latent flow models into pixel-space models: aligning the low-rank pixel subspace to the latent space gives a seamless initialization that preserves the latent model's high-level semantics and structure, so finetuning mainly improves low-level mismatches rather than relearning pixel generation. We show that the pixel AsymFlow model finetuned from FLUX.2 klein 9B establishes a new state of the art for pixel-space text-to-image generation, beating its latent base on HPSv3, DPG-Bench, and GenEval while qualitatively showing substantially improved visual realism.