Papers

Continuous sign language recognition (CSLR) is a key technology for accessibility, yet its development remains limited by the high cost of annotating continuous video streams. Active learning offers a path toward mitigating this cost, but standard acquisition functions are not designed for weakly aligned sign language videos, where sign executions are interleaved with rest poses, irregular pauses, sign-like motion, and temporally redundant frames. This temporal redundancy can undermine sample selection, as acquisition scores may be influenced by timesteps from regions that are not associated with the decoded gloss sequence, distorting the video's estimated informativeness. In this work, we show that modern CSLR models already contain a mechanism for identifying gloss-level temporal evidence: the CTC decoder. Although typically used only during inference, its alignment peaks indicate where the model localizes each predicted gloss in the feature sequence, providing a source of temporal structure for active learning acquisition functions at zero additional labeling cost. Thus, we introduce RAIDAL (Redundancy-Aware Information Density Active Learning), which repurposes the CTC decoder to restrict representation-based scoring to decoder-aligned gloss regions, rather than exposing the acquisition function to the entire unfiltered video. Across three datasets and two architectures, RAIDAL achieves its strongest data-efficiency gains over competing baselines in large-vocabulary, budget-limited settings, while remaining competitive in the smaller-vocabulary, large-budget setting. The code used in this work is publicly available at github.com/verlab/RAIDAL.

Multi-task biomedical classification requires models to generalize across disparate modalities and class distributions. We study 11 heterogeneous MedMNIST datasets using the harmonic mean of per-task macro-F1. We evaluate three backbones with task-specific linear heads. We identify a resolution domain shift between the MedMNIST API and evaluation environment. Resolving this inconsistency and optimizing architecture-specific regularization substantially improved performance. Our best configuration, a ConvNeXt-Tiny backbone with label smoothing, achieved a leaderboard harmonic-mean macro-F1 of 0.73294 in the Tensor Reloaded: Multi-Task MedMNIST competition, ranking sixth at the close of the official competition phase. Our implementation is publicly available at: https://github.com/GavrilStefan-Dorian/A-Shared-Backbone-Approach-for-Multi-Task-MedMNIST-Classification

The next generation of artificial intelligence systems will likely be natively temporal and multimodal in both inputs and outputs: able to converse, perceive, predict, reason, and synthesize through a shared world representation. Realizing this requires a temporal perceptual substrate integrating sensory streams, language, and structured outputs within a multimodal world model. We seek a generalist open-world perceptual system that represents biological forms, natural physical structures, and artifacts, and their interactions, as a coherent, temporally persistent process. The model should infer geometry, articulation, semantics, interaction structure, and uncertainty from raw multimodal streams; maintain identity through occlusion and viewpoint change; generalize across species, forms, mechanisms, and materials; and abstain or expand its ontology when encountering the unknown. The objective is a structured world state supporting understanding, prediction, counterfactual reasoning, and controllable synthesis. Recent work suggests that some cross-modal and reasoning-like capabilities can emerge from large-scale generative video pretraining, reminiscent of language-model scaling. Yet these capabilities are often accessed through language probes or expressed through photorealistic video, leaving explicit semantic, geometric, or temporal structure largely unexposed. This paper articulates an alternative and complementary paradigm: perception and synthesis as distinct conditionings within a shared Generalist Open-World Temporal Perception Architecture (GOWTPA). Recognition, structured prediction, and simulation arise as different conditionings of the same generative substrate, while reasoning and embodiment-specific policies build upon the resulting world state. This positions generalist temporal perception as a potential foundation layer for broader multimodal intelligence and physical AI.

Active mapping requires a robot to select camera viewpoints that efficiently reconstruct an unknown 3D scene. To reason about unobserved regions, recent systems use pretrained occupancy networks as world models that complete missing geometry. The predicted structure contributes to expected coverage gain and constrains feasible robot motion. Consequently, occupancy errors can change both what the robot chooses to explore and where it is able to move. We diagnose these effects by holding the planner fixed and varying only the occupancy representation provided to it. We consider planning without completion, with learned occupancy, with false positives removed by a ground truth oracle, with false negatives restored by an oracle, and with ground truth occupancy. Our experiments show that correcting false positives or false negatives alone does not consistently improve final coverage. This finding reveals a gap between occupancy accuracy and downstream planning performance. Ground truth occupancy provides a much larger improvement in coverage efficiency than in endpoint coverage, suggesting that planning and reachability remain important bottlenecks even when the geometric world model is accurate. Based on these findings, we introduce a dynamic filtering strategy that preserves predictions in unexplored space while suppressing repeatedly unsupported occupancy using online observations. Preliminary examples show that this strategy can redirect viewpoint selection toward reachable surfaces that would otherwise remain unobserved.

Modern stereo matching models fail when disparity crosses zero, with end-point error (EPE) rising by 4.6-37$\times$. Yet stereoscopic content, from cinema 3D to VR, routinely contains objects behind the zero-disparity plane (ZDP), corresponding to negative disparities. The blind spot cascades through datasets, architectures, and evaluation protocols, all of which inherit the non-negative geometry. Rectified parallel cameras place ZDP at infinity, so every finite depth yields $d=fB/z \ge 0$ by construction, and nothing within the standard pipeline can violate, or even measure, a negative disparity. To measure it, we propose ZDPShift, a benchmark of $21{,}495$ stereo pairs from seven cinematographer-authored open movies, each frame rendered at five zero-disparity-plane positions with dense signed ground truth. Six state-of-the-art image and video stereo matching models collapse once the plane moves. On identical scene content, FoundationStereo goes from $2.24$ px EPE to $75.33$px, with every backbone leaving roughly half of all pixels exceeding a three-pixel disparity error. What is missing, however, is not the underlying matching capability. % The capability itself, however, is already present. Training on supervision synthesized from SceneFlow, which adds no new data or parameters, keeps the error flat across the signed range. Training only the decoder, with the pretrained matching features frozen, performs comparably across all six backbones, with EPE jittering within $0.2$px. Thus, the pretrained features already extend to the negative regime they were never trained on, and only the output convention discarded it. Meanwhile, positive-regime accuracy on KITTI, Middlebury, ETH3D, and Sintel is largely preserved.

In this work, we comprehensively evaluate three popular feature-extraction paradigms in AI-based neuroimaging modeling: (1) computation of anatomical surfaces and volumes, (2) supervised learning with convolutional neural networks (CNNs), and (3) unsupervised pretraining of vision transformer (ViT) foundation models, followed by supervised finetuning. Our study is based on 18 publicly available datasets containing 3D structural T1-weighted MRI scans from approximately 80,000 participants across seven distinct clinical tasks. We observe that a linear model based on anatomical features matches the diagnostic performance of complex nonlinear features learned by sophisticated AI frameworks, including foundation models trained on thousands of scans. Conversely, CNNs and pretrained ViTs learn features that implicitly capture relevant anatomical information, bypassing the need for explicit feature extraction. Building upon these insights, we propose Anatomy Segmentation Pretraining (ASP), a novel method to incorporate anatomical information during foundation-model pretraining, which outperforms existing models in biological age estimation.

Automatic Pronunciation Assessment (APA) systems have achieved strong performance with transformer-based models and self-supervised speech representations. However, most methods rely only on acoustic signals and overlook temporal synchronization between speech and articulatory movements, limiting diagnostic feedback on timing mismatches important for L2 pronunciation training. We propose an interpretable audio-visual synchronization framework that explicitly models speech-lip temporal alignment through feature encoding, cross-attention fusion, lag estimation, stability quantification, and visualization. The framework introduces frame-level lag trajectories and a Lag Stability Index (LSI) to quantify synchronization robustness. We also interviewed 30 participants, including 10 instructors and 20 students with diverse first-language backgrounds, to assess its effectiveness. By transforming implicit alignment into interpretable representations, the framework connects automatic scoring with actionable Computer-Aided Pronunciation Training feedback. Datasets and supplemental materials are available at https://www.robots.ox.ac.uk/~vgg/data/lip_reading/.

Out-of-Distribution (OOD) detection remains a fundamental challenge for neural networks, whose predictions can be overconfident on inputs that deviate from the training distribution. Most post-hoc OOD detection methods derive scores from a single representation level (eg., logits or penultimate features) or combine multiple layers via depth selection or OOD-calibrated weighting. However, because OOD shifts are diverse, the most informative representation level can vary strongly across OOD types and domains, making fixed-layer choices and OOD-calibrated aggregation brittle. In this paper, we propose PRISM (Projected Representation with Intermediate-layer Subspace Modeling), a model-agnostic post-hoc OOD detection method that models a unified multi-layer feature representation rather than aggregating independently scored layers. PRISM fuses intermediate and deep features into a single hierarchical embedding, estimates an in-distribution (ID) principal subspace, and then combines two complementary signals: (i) a class-conditional Mahalanobis distance in the projected subspace and (ii) the residual energy orthogonal to the learned manifold. This simple design avoids OOD-tuned layer weighting while capturing both in-subspace semantic deviations and off-subspace anomalies. Across diverse benchmarks spanning natural images, medical imaging, and industrial visual inspection, PRISM achieves consistent state-of-the-art cross-domain OOD detection performance with a single default configuration across all evaluated domains and architectures. We further show that PRISM incurs minimal inference overhead, making it practical for real-world deployment.

Near-Earth Objects (NEOs) can appear as faint streaks in long-exposure astronomical images. Detecting these streaks across diverse observatories requires methods that remain reliable despite differences in image quality, orientation, sky background, and noise. However, existing detectors are commonly evaluated using data from only one source, providing limited evidence of cross-source generalization. We introduce NEO-Bench, a multi-source benchmark containing 8,376 images from five astronomical-image datasets. The sources include the Hubble Space Telescope, a Stellina smart telescope, the United Arab Emirates Meteor Monitoring Network, a TETRA1 telescope using a Celestron C14 with Fastar, and the Roboflow Asteroid dataset. We converted the data to a common YOLO format, audited a sample of labels, and defined within-source and leave-one-source-out evaluation protocols. We evaluated four approaches: Hough, Radon, Gaussian PSF, and YOLO26L. Leave-one-source-out F1 decreased in 14 of 20 image-level method-source pairs and 13 of 20 IoU@0.50 localization pairs. Across the datasets categorized as medium or hard, F1 decreased in 11 of 12 image-level pairs and 9 of 12 localization pairs. These results show that cross-source performance remains inconsistent and that reliable generalization across astronomical imaging sources remains an open challenge. The benchmark, code, and data are publicly available.

Visual generation is evolving from generative models used through a single invocation into agentic control processes that can plan, select tools, inspect intermediate synthesized outputs, revise failures, and reuse prior experience. In most existing systems, the controller is an LLM or VLM, while visual generation models serve as tools or executors. However, existing work lacks a consistent criterion for determining when a generation system becomes agentic. Planning depth, tool use, multi-role collaboration, and reinforcement learning are often treated as evidence of agenticity, even though none of them necessarily determines which generation decisions the controller can make. We organize the field according to what the controller can directly control in the generation process. At L1 Conditioning Control, the controller prepares the input to a predetermined generator but does not control which visual operation is executed. At L2 Execution Control, it selects and invokes actual generation, editing, rendering, or other content-modifying operations. At L3 Outcome-Adaptive Control, it observes an intermediate outcome and uses that observation to change a subsequent operation within the current task. At L4 Experience-Adaptive Control, it retains experience from completed tasks and uses that experience to change decisions on future tasks. L0 Fixed Support separately denotes generators, editors, evaluators, reward models, benchmarks, and fixed pipelines without a deployed controller that makes generation-level decisions. These levels describe a progressively broader decision-making scope rather than model size, system complexity, output quality, tool or role count, or training method. Applying this framework across image, video, editing, 3D, world, slide, and user-interface generation reveals how controller capabilities have evolved and how their mechanisms are distributed across levels.

Latent visual reasoning aims to perform multimodal reasoning through hidden-state computation rather than explicit textual chains of thought. However, visual information being present in a latent state does not imply that the model actually relies on that state when producing its answer, especially when alternative image-conditioned paths remain available. We introduce Causal Visual Recurrent Reasoning (CVRR), which preserves pretrained visual competence while making recurrent computation the required image-conditioned path to prediction. CVRR initializes recurrence from the question hidden state after the pretrained vision-language model has incorporated the image, then repeatedly updates this state while re-reading the same fixed visual evidence. Before decoding, visual states and the original multimodal KV cache are removed so that only the final recurrent state carries image-conditioned information to the answer. Across the $V^*$, MMVP, BLINK, and MME-RealWorld-Lite benchmarks, CVRR retains strong performance under this strict interface, while compatible latent reasoners fail to recover comparable visual competence even when retrained under the same constraint. Causal interventions further show that predictions remain sensitive to recurrent content when the question is held fixed, and that persistent visual evidence causally revises the recurrent trajectory. These results distinguish latent informativeness from latent computation that is actually used for prediction.

Brain tumor segmentation from multimodal MRI relies on complementary evidence across four imaging sequences, yet one or more modalities may be unavailable because of acquisition cost, protocol variation, scan failure, or patient condition. Existing work has explored reconstruction, knowledge transfer, and direct feature fusion, but leaves open whether missing-modality fusion should change with representation level. High-resolution lateral features retain spatial detail, whereas compressed bottleneck features encode semantic and inter-modality context. We therefore hypothesize that fusion should be conditioned jointly on modality availability and feature hierarchy. We propose the Level-Aware Availability-Conditioned Spatial-Semantic Fusion Network (LASSNet), which contains two level-specialized modules. Hierarchical Availability-Conditioned Fusion (HACF) constructs four lateral representations using count-normalized aggregation of available modalities, mask-conditioned channel modulation, and local 3D refinement. Tri-Scale Relational-Spatial Fusion (TriRSF) models relations among available modality descriptors and spatial context across multiple bottleneck resolutions, followed by cross-scale aggregation and availability-conditioned global spatial attention. A shared coarse-to-fine decoder starts from TriRSF semantics and progressively injects HACF features, without reconstructing missing inputs. Across all 15 non-empty modality configurations, LASSNet obtains mean Dice scores of 76.7% and 83.2% over WT, TC, and ET on BraTS2019 and BraTS2023, respectively.

Accurate 3D brain tumour segmentation from multi-modal Magnetic Resonance Imaging (MRI) is essential for clinical diagnosis and treatment planning. Existing brain tumour segmentation methods often suffer from heavy computational demands, while current lightweight architectures frequently lack the capacity to maintain segmentation fidelity in complex tumour regions. To address these issues, we propose a novel ultra-lightweight framework (Uni-Light) that achieves high-fidelity segmentation with substantially reduced computational overhead. It combines multi-scale convolutions with an uncertainty-aware knowledge distillation scheme that directs the student model toward hard-to-classify regions, complemented by a Signed Distance Field boundary loss for geometric constraints. Experimental results on BraTS2023-GLI and MSD-BTS datasets demonstrate that Uni-Light reduces parameters by 97.56%, floating-point operations (FLOPs) by 73.03%, and inference memory footprint by 81.58%, while surpassing the state-of-the-art model by an average of 1.47% in Dice score, offering a highly competitive trade-off between segmentation accuracy and computational efficiency in resource-constrained clinical settings. This work also advances data engineering for medical imaging by demonstrating that teacher model uncertainty can be exploited as a data-driven supervisory signal, re-prioritising the training data distribution without requiring additional annotation.

We present B2TFPose, a training-free zero-shot method for 6DoF pose estimation of unseen objects from RGB images. Using a single frozen DINOv3 vision transformer as its only pretrained component within the pose estimation pipeline, B2TFPose extracts dense patch-level features that generalize across the synthetic-to-real domain gap without any task-specific fine-tuning, revisiting the classical local feature matching paradigm through the lens of large-scale self-supervised foundation models. Three contributions advance the training-free state of the art. A geodesic non-maximum suppression strategy retrieves a viewpoint-diverse template set for coarse-to-fine correspondence matching. Render-guided Re-Correspondence (RRC) synthesizes object-specific views at the estimated pose and re-establishes dense 2D-3D correspondences to sharpen the initial estimate without additional learned parameters. A multi-mask hypothesis selection strategy jointly scores competing segmentation candidates to resolve segmentation ambiguity. On the seven core datasets of the BOP Benchmark, B2TFPose achieves 40.7 mean AR without refinement and 56.4 with refinement, establishing state-of-the-art performance among training-free RGB methods and outperforming trained counterparts including GigaPose and GenFlow, at competitive inference speed.

Meshes remain the most practical representation for geometry reasoning and integration into graphics pipelines, yet existing reconstruction methods struggle to produce high-quality meshes. Most state-of-the-art approaches initially learn an intermediate representation (NeRF/3DGS) and treat mesh extraction as a post-processing step, which often leads to oversmoothed surfaces or poor quality meshes with excessive triangle counts.Existing mesh-native optimization methods alleviate some of these issues but suffer from fixed-resolution discretizations and unstable optimization behavior. In this paper, we introduce an adaptive mesh-based optimization framework and a practical mesh rendering technique to address these challenges. Our representation combines an optimizable Delaunay-triangulated tetrahedral grid with a multi-resolution hash grid. The former is refined through point pruning and insertion, while the latter provides latent features for SDF/appearance value predictions. We use volumetric rendering to bootstrap a coarse geometry while leveraging mesh-based rendering for recovering fine-grained details. Additionally, we propose a differentiable, rasterization-based depth-offset rendering formulation, reducing geometric artifacts and improving reconstruction quality. Our method significantly outperforms existing mesh optimization approaches across a variety of object-centric benchmarks while being competitive with state-of-the-art NeRF/3DGS methods.

AI companions are envisioned as always-on assistants that support users in daily life. With this regard, we introduce BuddyVQA, a benchmark for companion-style question answering (QA) on egocentric streaming video. BuddyVQA contains 21.6K questions linked to 6K highlight moments across 1,012 long, egocentric videos. It features two key characteristics that are common in daily first-person QA assistance but are largely overlooked in existing VideoQA benchmarks: ego-deictic expressions and interactively chained questions (e.g., "Where is it?", "How to get there?"). These require models to infer a user's in-situation intent by resolving visual pronouns in the context of egocentric visual and QA contents, with both grounded in a long-form streaming setting. To tackle the challenges, we propose MyBuddy, a companion-style QA assistant that highlights a multimodal chain-of-thought reasoning mechanism to infer the final answer based on the historical QA and visual content. An additional question filter and multi-level memory are designed to facilitate efficient QA and visual information retrieval under streaming QA settings. Experiments show that MyBuddy significantly enhances the performance of foundation models on BuddyVQA. Moreover, these gains generalize to other streaming and common video QA benchmarks, demonstrating the applicability and effectiveness of our approach. Our code and dataset are available at https://github.com/QHUni/BuddyVQA

Diffusion Transformers (DiTs) achieve strong video generation quality, but their dense spatiotemporal self-attention scales quadratically with sequence length and quickly becomes the dominant inference bottleneck. Sparse low-rank hybrids alleviate this cost by combining a local sparse branch with a global compressed branch. In video DiTs equipped with 3D Rotary Position Embeddings (RoPE), the global branch faces a structural compatibility issue: when RoPE is applied before a nonlinear feature map, the rotation and nonlinearity generally do not commute, making it difficult to keep a query-independent linear summary while preserving relative rotary geometry. Existing work often sidesteps this issue by replacing genuine cross-token global aggregation with coordinate-conditioned surrogates or learnable absolute positional modules. These compromises can be effective, but they approximate relative decay from absolute coordinates and introduce extra positional parameters. We propose RoLA, a rotary-positioned low-rank linear-attention branch that keeps genuine cross-token aggregation while remaining compatible with a reusable linear summary. The design applies RoPE outside the nonlinear low-rank feature map and reuses a truncated subset of the pre-trained rotary schedule matched to the low-rank bottleneck. This yields a linear-time low-rank global branch with relative positional behavior by design and no additional positional parameters; the full sparse–low-rank module still includes the fixed-sparsity sparse branch. Experiments on open-source video DiTs show that the resulting method remains competitive in generation quality at 90% sparsity while achieving 2.63$\times$ end-to-end inference speedup on Wan2.1-14B (720p, 81 frames, measured on an NVIDIA H100 GPU).

Chain-of-thought (CoT) may often look plausible, yet it may not faithfully reflect the model's decision-making process. While methods for measuring the faithfulness of CoTs for textual inputs have been increasingly introduced, using these methods for visual inputs is not straightforward. In this work, we adapt the family of counterfactual methods for measuring CoT faithfulness, namely the Counterfactual Test (CT) and Correlational Counterfactual Test (CCT), to visual inputs, and call them vCT and vCCT, respectively. Using vCT and vCCT, we benchmark eight recent open-source Vision Language Models (VLMs) on two datasets. Our analysis shows that CoTs do not reliably track visual evidence that influences model predictions: they may omit the removed object even when its removal causes a large prediction shift, yet mention it when the shift is small. We further find that Predict-then-Explain explanations align more strongly with perturbation-induced probability shifts than pre-answer CoTs, while binary vCT scores are often nearly saturated. We also include a reconstruction control, in which images pass through the same editing pipeline without object removal, and find that the main object-removal intervention induces larger shifts than reconstruction alone. We construct and release Counter-SNLI-VE and Counter-A-OKVQA, two datasets of image pairs that differ by a single object.

Glaucoma is a progressive optic neuropathy characterized by irreversible damage to the optic nerve, making timely diagnosis critical to prevent permanent vision loss. Although deep learning has demonstrated promising performance in automated glaucoma detection, existing approaches often overlook feature refinement, suffer from class imbalance, and rely on individual classifiers that limit prediction robustness. To address these challenges, this paper proposes a hybrid glaucoma detection framework that integrates attention-enhanced deep feature extraction with heterogeneous ensemble learning. Specifically, deep representations are extracted using InceptionV3 and subsequently refined by incorporating the Convolutional Block Attention Module (CBAM) to enhance discriminative retinal features. To improve classification robustness, the extracted features are classified using multiple machine learning models together with Single-Level Ensemble (SLE) and Double-Level Ensemble (DLE) strategies, while SMOTE combined with Tomek Links (SMOTE+TL) is employed to alleviate class imbalance. Furthermore, a systematic comparison of handcrafted, deep, and attention-enhanced deep feature representations is conducted. Experimental evaluation on two public retinal fundus datasets demonstrates that deep feature-based methods consistently outperform handcrafted feature-based methods, while the proposed attention-enhanced framework achieves the best overall performance. Furthermore, Grad-CAM visualizations confirm that the proposed model focuses on clinically relevant retinal regions, providing interpretable evidence on the model's prediction process.

Diffusion-based models enable monocular geometry estimation, yet their pixel-space precision is limited by a shared, under-studied error source: VAE reconstruction degradation. The 8x spatial compression in the VAE encoder-decoder degrades surface normals at object boundaries; even encoding and decoding ground-truth normals introduces 1.3–8.5{\deg} of mean angular error (MAE), with edge MAE reaching 2.8x the global MAE. We present TransNormal-2, a FLUX.2-based rectified-flow framework with single-step deterministic inference that addresses this degradation on both sides of the VAE decoder: in how latent predictions are supervised during training, and in how decoded normals are corrected at inference. First, geometry-aware pixel-space losses, including inverse rendering self-consistency, von~Mises-Fisher angular loss, and wavelet edge-aware regularization, complement latent MSE by enforcing spherical normal geometry and diffuse image-formation cues after VAE decoding. Second, a lightweight Geometric Refinement Module (GRM) applies an RGB-guided residual correction to reduce boundary-localized decoding errors without freely rewriting the coarse prediction. On general-scene benchmarks, TransNormal-2 matches or exceeds MoGe-2 on all eight reported metrics while using only 1.4% as many task-specific normal annotations. The gains are clearest for transparent objects, reducing MAE by 4.2{\deg} on ClearGrasp and 3.1{\deg} on ClearPose over the strongest prior baselines. Code will be released at https://longxiang-ai.github.io/TransNormal-2.

Although multimodal Large Language Models (MLLMs) excel in diverse tasks, their scalability remains limited by the memory and computational overhead of KV cache storage. Recent KV cache eviction approaches incorporate a cosine similarity-based diversity metric with importance metrics to selectively retain critical key-value pairs. However, cosine similarity involves normalization that discards magnitude information, and it often yields uniformly high similarity values across layers due to the anisotropy property of hidden representations. In our study ECOKV, we rigorously deconstruct the capabilities of existing diversity metrics. Moving beyond simple measurement, we propose a geometry-aware composite metric that jointly leverages Euclidean distance and cosine similarity to capture token diversity from complementary perspectives. Furthermore, we use these two metrics to estimate the redundancy level of each attention head, allowing adaptive weighting between diversity and importance scores during token selection. Finally, we demonstrate that the observation window commonly employed to preserve recent tokens can be substantially reduced, thereby allocating more cache capacity to informative tokens and yielding consistent improvements. Extensive experiments demonstrate that ECOKV achieves state-of-the-art performance under various compression ratios and can be seamlessly integrated with existing KV cache eviction methods. We further analyze the relationship between importance and diversity, and examine redundancy patterns across layers and attention heads.

Accurate aerodynamic prediction is critical for designing fuel-efficient and safe transportation systems such as aircraft and automobiles, yet traditional computational fluid dynamics (CFD) simulations remain computationally expensive and expertise-intensive, severely limiting their use in iterative design and real-time analysis. Existing deep learning surrogates suffer from two major limitations: (i) they are evaluated on datasets with narrow flow-condition ranges, leaving their performance under complex flow conditions undemonstrated; (ii) they treat global flow conditions as a single vector injected uniformly across all surface points, ignoring that different geometric regions experience distinct local flow phenomena, which degrades prediction accuracy under complex flow conditions. To address these limitations, we propose the Flow State Attention Network (FSAN). FSAN separately encodes point cloud and flow conditions, then partitions the geometry into multiple flow states via learnable soft assignments, and uses flow features to update these state representations, which in turn influence point cloud features through state changes. This enables fine-grained, state-specific interaction between geometry and flow information. Extensive experiments on two well-recognized aerodynamic benchmarks demonstrate that FSAN achieves the highest accuracy among the methods compared in this work at a higher computational cost. On Emmi-Wing, FSAN reduces the Relative L2 (REL-L2) error by over 20% compared to the strongest baseline (Transolver), and on DrivAerNet++, it achieves a 10% reduction compared to the strongest baseline (AdaField). These results establish FSAN as a promising neural surrogate on public benchmarks with diverse flow conditions and geometries.

Video foundation models increasingly rely on large-scale pretraining data, yet the end-to-end data pipelines behind them remain largely closed and difficult to inspect or reuse. Researchers seeking to understand how video data recipes affect model pretraining often need to build substantial infrastructure before testing even a focused hypothesis. We present VIDAFORGE, an open research infrastructure that represents a video data recipe as an executable five-stage workflow from raw videos to training datasets. A decision in this workflow can be varied to construct alternative datasets while preserving how every sample was produced. To demon strate this research workflow, we compare data recipes with different coverage and quality in early from-scratch pretraining of Wan 2.1 and V-JEPA 2.1. Across both learning objectives, the broader-coverage recipe achieves the highest downstream benchmark scores, while loss-based evaluation favors different recipes. This study demonstrates how VidaForge connects data-recipe choices to downstream model performance. We further release VIDAFORGE-3M, containing 3.14 million scene level clips totaling 6,475 hours, with fine-grained annotations and curation signals for video data-recipe research.

Annotators routinely disagree on laughter boundaries and subtle chuckles, yet temporal laughter localization typically evaluates against a single reference annotation. We show that this disagreement is structured rather than random noise. Re-annotating the SMILE-Temporal benchmark (672 videos, 1,683 events) with 3-5 annotators per video (alpha = 0.757), we find systematic patterns: disagreement is 1.73 times larger at offsets than onsets, far more common for chuckles than full laughs (77% vs. 20%), and predictable from event attributes (AUC = 0.831). Evaluating against a single annotator breaks down under this structure: system scores shift by 0.246 F1 depending on the chosen ground truth, correctly ranking systems only 69.7% of the time (vs. 80% against all annotators). We propose a disagreement-calibrated evaluation that scores predictions against the full annotator distribution using conformally calibrated tolerance bands (wider at offsets, 0.727s, than onsets, 0.5s). The per-annotator annotations and analysis code are available at https://github.com/WSCSports/MTLLFM-temporal-laughter-localization.

All-in-one medical image restoration seeks to recover heterogeneous clinical images with a single model, but PET, CT, and MRI differ substantially in degradation statistics, anatomical contrast, and output-space bias. A fully shared network can entangle modality-specific residual errors, whereas separate modality-specific networks sacrifice the practical advantages of unified deployment. We therefore recast all-in-one restoration as a question of where limited adaptation should be placed: policy selection, feature execution, or output calibration. We propose MARR, a compact restoration framework that constrains multi-modality adaptation into degradation-aware policy routing, modality-private residual execution, and image-domain residual correction without requiring degradation labels or separate modality-specific models. The policy branch forms a routing prompt from input statistics, latent content, and modality identity, and uses it only as a control signal. Prompt-gated modality-private adapters then perform lightweight residual refinement at intermediate decoder stages, while zero-initialized modality-specific output heads calibrate the final image-domain residual without perturbing the initial shared prediction. On an all-in-one PET, CT, and MRI restoration benchmark, MARR outperforms thirteen methods re-trained under the same protocol, achieving PSNR values of 37.34 dB, 33.85 dB, and 32.09 dB on PET, CT, and MRI, respectively, and the best modality-average PSNR of 34.43 dB. The code is publicly available at https://github.com/CHB-learner/MARR.

An image-augmentation pipeline must deliver a complete batch before a model can use it. We compare seven input paths from five libraries, starting with RGB JPEG files and ending with a synchronized CUDA float16 batch. We manually matched transformation recipes and parameters across libraries to make the workloads as comparable as possible. The experiment uses 57 selected recipes, a batch size of 256, and one NVIDIA L4 machine. Throughput and peak process GPU memory are recorded together in 759 measurements. On the 11 recipes shared by all paths, DALI and AlbumentationsX have median throughputs of 5,029 and 4,679 images/s, with median peak GPU memory of 2,086 and 1,852 MiB. Broader pairwise comparisons favor AlbumentationsX on 26/26 TorchVision recipes, 50/51 Kornia recipes, and 25/26 Pillow recipes. DALI is faster than AlbumentationsX on all 22 shared recipes, with a median throughput ratio of 1.18x. A separate census reports coverage of the 118 entries in a selected AlbumentationsX RGB catalog. The study measures input preparation at fixed settings; it does not measure model training, numerical equivalence, or the best attainable configuration of each library. Benchmark code: https://github.com/albumentations-team/benchmark.

Recent advancements in deep learning allow robotic agents to interact with dynamic and unstructured environments. Of special interest is the integration of physico-geospatial world knowledge into such systems, either by using physics-aware machine learning models, knowledge graphs to model relationships or spatio-temporal and logical reasoning. In the present work, we introduce an approach to augment the output of pre-trained, unmodified VLMs used for scene interpretation by integrating semantic descriptions, OpenStreetMap building data and street information with positional, temporal and metric information obtained from our sensory systems, fusing this information using LLMs. We apply this concept to an outdoor recording within a university campus, achieving an F1-Score of 0.83 in the task of grounding buildings and 0.64 for path surface grounding on our pilot evaluation set. The results demonstrate the conceptual capability of the proposed solution to deliver physico-geospatial grounded natural language descriptions. Code and results are available at https://datahub.rz.rptu.de/hstr-csrl-public/publications/physico-geospatial-grounded-scene-interpretation

Object-centric video models represent scenes with slots, yet exposed geometry can vary in meaning with appearance. In Invariant Slot Attention (ISA), explicit position and scale can disagree with the decoded center and extent; edits can yield unexpected motion or resizing, and replacing appearance can shift geometry. GeoCo-SAVi promotes geometric authority and semantic alignment. Its spatially equivariant, object-wise decoder makes position and scale effective commands: changing them moves or resizes the rendered support. Factual position alignment ties position to the decoded center, and normalized attention overlap discourages duplicate allocation. Appearance transplantation aligns geometry semantics across objects, so recipient geometry governs layout while donor appearance supplies shape. On Obj3D, GeoCo-SAVi matches ISA reconstruction, reduces latent-position-to-decoded-centroid error by nearly 90%, and reduces appearance-induced size variation while producing the expected translation and scale responses. On 250 MOVi-C videos, it improves reconstruction and instance grouping over both same-protocol references, and video editing over STAITUS. GeoCo-SAVi transforms explicit geometry into compositional control, making both position and scale more readable and editable. Project page: https://GeoCo-SAVi.github.io/.

Western blot (WB) images are widely used as key evidence in biomedical research. Recent scientific misconduct cases reveal that WB imagery is increasingly fabricated, making WB forensics a major concern for research integrity. However, while the progress of forensic detection techniques often relies on advances in forgery-generation techniques, the development of WB forensic techniques has been hindered by the lack of standardized appearance attribute definitions, image datasets, and controllable generation frameworks for WB imagery. To address this limitation, we present a controllable WB image synthesis framework, named GAN-Blot, for generating realistic synthetic WB images. We introduce a formulation that decomposes a WB image into a structure component and a style-reference component, enabling independent control over local protein-band geometry and the global visual appearance of a synthetic WB image. GAN-Blot integrates a dual-path autoencoding design with several style-alignment loss terms to enable implicit control over structure-style synthesis without predefined semantic appearance attributes. We further contribute a synthetic WB dataset containing more than 46K images and propose four evaluation protocols for controllable WB synthesis. Extensive experiments show that GAN-Blot can generate WB images with high fidelity in both protein-band structure and visual style. Under blind inspection, the generated images can fool domain experts and are not reliably distinguished from authentic WB images by existing detectors and screening platforms. These results demonstrate their utility as challenging controlled cases for validating and developing WB forensic methods.

In recent years, diffusion stochastic differential equation (SDE) inversion and inversion-free methods have become prevalent for training-free image editing, as they can achieve faithful reconstruction without tuning. However, existing approaches remain inefficient, exhibit limited plasticity, and struggle to accurately preserve unedited regions. To address these issues, we propose MIEdit, a training-free editing framework based on SDE inversion. MIEdit introduces a predictor-corrector multi-history-step scheme to achieve superior editing quality with fewer steps. We further mitigate heterogeneity and conflict between the multi-conditioned noise residuals and gradient terms during sampling, improving stability and editing plasticity under large edits. MIEdit also includes Inversion-Time Automatic Semantic Angle Masking (IASM); it leverages classifier-free guidance to automatically generate semantic angle masks during inversion and applies them throughout the sampling process for regional constraints, without extra user inputs. We additionally construct EditEval++ (30 fine-grained tasks, 1,000+ image-text-mask triplets) for comprehensive evaluation; experiments show that MIEdit outperforms state-of-the-art techniques. Project page: https://whywwwzzzg.github.io/MIEdit/.