Papers

App ratings are among the most significant indicators of the quality, usability, and overall user satisfaction of mobile applications. However, existing app rating prediction models are largely limited to textual data or user interface (UI) features, overlooking the importance of jointly leveraging UI and semantic information. To address these limitations, this study proposes a lightweight vision–language framework that integrates both mobile UI and semantic information for app rating prediction. The framework combines MobileNetV3 to extract visual features from UI layouts and DistilBERT to extract textual features. These multimodal features are fused through a gated fusion module with Swish activations, followed by a multilayer perceptron (MLP) regression head. The proposed model is evaluated using mean absolute error (MAE), root mean square error (RMSE), mean squared error (MSE), coefficient of determination (R2), and Pearson correlation. After training for 20 epochs, the model achieves an MAE of 0.1060, an RMSE of 0.1433, an MSE of 0.0205, an R2 of 0.8529, and a Pearson correlation of 0.9251. Extensive ablation studies further demonstrate the effectiveness of different combinations of visual and textual encoders. Overall, the proposed lightweight framework provides valuable insights for developers and end users, supports sustainable app development, and enables efficient deployment on edge devices.

We study how visual artifacts introduced by diffusion-based inpainting affect language generation in vision-language models. We use a two-stage diagnostic setup in which masked image regions are reconstructed and then provided to captioning models, enabling controlled comparisons between captions generated from original and reconstructed inputs. Across multiple datasets, we analyze the relationship between reconstruction fidelity and downstream caption quality. We observe consistent associations between pixel-level and perceptual reconstruction metrics and both lexical and semantic captioning performance. Additional analysis of intermediate visual representations and attention patterns shows that inpainting artifacts lead to systematic, layer-dependent changes in model behavior. Together, these results provide a practical diagnostic framework for examining how visual reconstruction quality influences language generation in multimodal systems.

Medical image segmentation plays a vital role in clinical decision-making, enabling precise localization of lesions and guiding interventions. Despite significant advances in segmentation accuracy, the black-box nature of most deep models has raised growing concerns about their trustworthiness in high-stakes medical scenarios. Current explanation techniques have primarily focused on classification tasks, leaving the segmentation domain relatively underexplored. We introduced an explanation model for segmentation task which employs the causal inference framework and backpropagates the average treatment effect (ATE) into a quantification metric to determine the influence of input regions, as well as network components, on target segmentation areas. Through comparison with recent segmentation explainability techniques on two representative medical imaging datasets, we demonstrated that our approach provides more faithful explanations than existing approaches. Furthermore, we carried out a systematic causal analysis of multiple foundational segmentation models using our method, which reveals significant heterogeneity in perceptual strategies across different models, and even between different inputs for the same model. Suggesting the potential of our method to provide notable insights for optimizing segmentation models. Our code can be found at https://github.com/lcmmai/PdCR.

What does it mean for a visual system to truly understand affordance? We argue that this understanding hinges on two complementary capacities: geometric perception, which identifies the structural parts of objects that enable interaction, and interaction perception, which models how an agent's actions engage with those parts. To test this hypothesis, we conduct a systematic probing of Visual Foundation Models (VFMs). We find that models like DINO inherently encode part-level geometric structures, while generative models like Flux contain rich, verb-conditioned spatial attention maps that serve as implicit interaction priors. Crucially, we demonstrate that these two dimensions are not merely correlated but are composable elements of affordance. By simply fusing DINO's geometric prototypes with Flux's interaction maps in a training-free and zero-shot manner, we achieve affordance estimation competitive with weakly-supervised methods. This final fusion experiment confirms that geometric and interaction perception are the fundamental building blocks of affordance understanding in VFMs, providing a mechanistic account of how perception grounds action.

Autonomous laparoscopic camera control must maintain a stable and safe surgical view under rapid tool-tissue interactions while remaining interpretable to surgeons. We present a strategy-grounded framework that couples high-level vision-language inference with low-level closed-loop control. Offline, raw surgical videos are parsed into camera-relevant temporal events (e.g., interaction, working-distance deviation, and view-quality degradation) and structured as attributed event graphs. Mining these graphs yields a compact set of reusable camera-handling strategy primitives, which provide structured supervision for learning. Online, a fine-tuned Vision-Language Model (VLM) processes the live laparoscopic view to predict the dominant strategy and discrete image-based motion commands, executed by an IBVS-RCM controller under strict safety constraints; optional speech input enables intuitive human-in-the-loop conditioning. On a surgeon-annotated dataset, event parsing achieves reliable temporal localization (F1-score 0.86), and the mined strategies show strong semantic alignment with expert interpretation (cluster purity 0.81). Extensive ex vivo experiments on silicone phantoms and porcine tissues demonstrate that the proposed system outperforms junior surgeons in standardized camera-handling evaluations, reducing field-of-view centering error by 35.26% and image shaking by 62.33%, while preserving smooth motion and stable working-distance regulation.

Diffusion models have achieved remarkable success in image and video generation tasks. However, the high computational demands of Diffusion Transformers (DiTs) pose a significant challenge to their practical deployment. While feature caching is a promising acceleration strategy, existing methods based on simple reusing or training-free forecasting struggle to adapt to the complex, stage-dependent dynamics of the diffusion process, often resulting in quality degradation and failing to maintain consistency with the standard denoising process. To address this, we propose a LEarnable Stage-Aware (LESA) predictor framework based on two-stage training. Our approach leverages a Kolmogorov-Arnold Network (KAN) to accurately learn temporal feature mappings from data. We further introduce a multi-stage, multi-expert architecture that assigns specialized predictors to different noise-level stages, enabling more precise and robust feature forecasting. Extensive experiments show our method achieves significant acceleration while maintaining high-fidelity generation. Experiments demonstrate 5.00x acceleration on FLUX.1-dev with minimal quality degradation (1.0% drop), 6.25x speedup on Qwen-Image with a 20.2% quality improvement over the previous SOTA (TaylorSeer), and 5.00x acceleration on HunyuanVideo with a 24.7% PSNR improvement over TaylorSeer. State-of-the-art performance on both text-to-image and text-to-video synthesis validates the effectiveness and generalization capability of our training-based framework across different models. Our code is available at https://github.com/caipeiliang2004/LESA.

While iterative stereo matching achieves high accuracy, its dependence on Recurrent Neural Networks (RNN) hinders edge deployment, a challenge underexplored in existing researches. We analyze iterative refinement and reveal that disparity updates are spatially sparse and temporally redundant. First, we introduce a progressive iteration pruning strategy that suppresses redundant update steps, effectively collapsing the recursive computation into a near-single-pass inference. Second, we propose a collaborative monocular prior transfer framework that implicitly embeds depth priors without requiring a dedicated monocular encoder, thereby eliminating its associated computational burden. Third, we develop FlashGRU, a hardware-aware RNN operator leveraging structured sparsity and I/O-conscious design, achieving a 7.28$\times$ speedup, 76.6% memory peak reduction and 80.9% global memory requests reduction over natvie ConvGRUs under 2K resolution. Our PipStereo enables real-time, high-fidelity stereo matching on edge hardware: it processes 320$\times$640 frames in just 75ms on an NVIDIA Jetson Orin NX (FP16) and 19ms on RTX 4090, matching the accuracy of large iterative based models, and our generalization ability and accuracy far exceeds that of existing real-time methods. Our embedded AI projects will be updated at: https://github.com/XPENG-Aridge-AI.

Recent advances in cross-modal few-shot adaptation treat visual-semantic alignment as a continuous feature transport problem via Flow Matching (FM). However, we argue that Euclidean-based FM overlooks fundamental limitations of flat geometry, where polynomial volume growth fails to accommodate diverse feature distributions, leading to severe path entanglement. To this end, we propose path-decoupled Hyperbolic Flow Matching (HFM), leveraging the Lorentz manifold's exponential expansion for trajectory decoupling. HFM structures the transport via two key designs: 1) Centripetal hyperbolic alignment: It constructs a centripetal hierarchy by anchoring textual roots, which pushes visual leaves to the boundary to initialize orderly flows. 2) Path-decoupled objective: It acts as a “semantic guardrail” rigidly confining trajectories within isolated class-specific geodesic corridors via step-wise supervision. Furthermore, we devise an adaptive diameter-based stopping to prevent over-transportation into the crowded origin based on the intrinsic semantic scale. Extensive ablations on 11 benchmarks have shown that HFM establishes a new state-of-the-art, consistently outperforming its Euclidean counterparts. Our codes and models will be released.

Synthesizing text-driven 3D human motion within realistic scenes requires learning both semantic intent ("walk to the couch") and physical feasibility (e.g., avoiding collisions). Current methods use generative frameworks that simultaneously learn high-level planning and low-level contact reasoning, and rely on computationally expensive 3D scene data such as point clouds or voxel occupancy grids. We propose SceMoS, a scene-aware motion synthesis framework that shows that structured 2D scene representations can serve as a powerful alternative to full 3D supervision in physically grounded motion synthesis. SceMoS disentangles global planning from local execution using lightweight 2D cues and relying on (1) a text-conditioned autoregressive global motion planner that operates on a bird's-eye-view (BEV) image rendered from an elevated corner of the scene, encoded with DINOv2 features, as the scene representation, and (2) a geometry-grounded motion tokenizer trained via a conditional VQ-VAE, that uses 2D local scene heightmap, thus embedding surface physics directly into a discrete vocabulary. This 2D factorization reaches an efficiency-fidelity trade-off: BEV semantics capture spatial layout and affordance for global reasoning, while local heightmaps enforce fine-grained physical adherence without full 3D volumetric reasoning. SceMoS achieves state-of-the-art motion realism and contact accuracy on the TRUMANS benchmark, reducing the number of trainable parameters for scene encoding by over 50%, showing that 2D scene cues can effectively ground 3D human-scene interaction.

Generative models have been shown to "memorize" certain training data, leading to verbatim or near-verbatim generating images, which may cause privacy concerns or copyright infringement. We introduce Guidance Using Attractive-Repulsive Dynamics (GUARD), a novel framework for memorization mitigation in text-to-image diffusion models. GUARD adjusts the image denoising process to guide the generation away from an original training image and towards one that is distinct from training data while remaining aligned with the prompt, guarding against reproducing training data, without hurting image generation quality. We propose a concrete instantiation of this framework, where the positive target that we steer towards is given by a novel method for (cross) attention attenuation based on (i) a novel statistical mechanism that automatically identifies the prompt positions where cross attention must be attenuated and (ii) attenuating cross-attention in these per-prompt locations. The resulting GUARD offers a surgical, dynamic per-prompt inference-time approach that, we find, is by far the most robust method in terms of consistently producing state-of-the-art results for memorization mitigation across two architectures and for both verbatim and template memorization, while also improving upon or yielding comparable results in terms of image quality.

The Local Climate Zone (LCZ) framework is commonly employed to represent urban form in morphological analyses despite its mapping predominantly relies on satellite imagery. Urban morphometrics, describing urban form via numerical measures of physical aspects and spatial relationships of its elements, offers another avenue. This study evaluates the ability of morphometric assessment to predict LCZs using a) a morphometric-based LCZ prediction, and b) a fusion-based LCZ prediction combining morphometrics with satellite imagery. We calculate 321 2D morphometric attributes from building footprints and street networks, covering their various properties at multiple spatial scales. Subsequently, we develop four classification schemes: morphometric-based prediction, baseline image-based prediction, and two techniques fusing morphometrics with imagery. We evaluate them across five sites. Results from the morphometric-based prediction indicate that the correspondence between 2D urban morphometrics and urban LCZ types is selective and inconsistent, rendering the efficacy of this method site-dependent. Nevertheless, it demonstrated that a much broader range of urban form properties is relevant for distinguishing LCZ types compared to standard parameters. Relative to the image-based baseline, the fusion yielded relatively distinct accuracy improvements for urban LCZ types at two sites; however, gains at the remaining sites were negligible or even slightly negative, suggesting that the benefits of fusion are modest and inconsistent. Collectively, these results indicate that the relationship between the LCZs and the measurable, visible aspects of urban form is tenuous, thus the LCZ framework should be used with caution in morphological studies.

X-Ray Computed Tomography (XCT) is a compelling tool in experimental mechanics, capable of non-destructively extracting information pertaining to the internal morphology of materials. For materials with random heterogeneous morphology such as concrete, such information is of particular relevance since it allows for studies of morphology-related behaviour and for predictive modelling. Nevertheless, XCT images require semantic segmentation for practical usage. Here, concrete poses a unique challenge due to the similar X-ray attenuation coefficients of aggregates and mortar, which result in low contrast between the two phases in the ensuing XCT images. As such, purely intensity-dependent semantic segmentation tools remain unfeasible. While vision transformers (ViTs) and convolutional neural networks (CNNs) are proven techniques for semantic segmentation in such challenging cases, they typically require labelled training data, which is often unavailable for concrete or resource-intensive to obtain, thereby limiting their relevance. To address this challenge, a self-annotation technique is presented here that leverages superpixel algorithms to identify perceptually similar local regions in an image and relates them to the global context by utilizing the receptive field of a CNN-based model. This enables the model to learn a global-local relationship in the images and facilitates the identification of semantically similar structures. When evaluated against manually annotated ground truth on out-of-distribution data, the proposed methodology consistently outperformed direct greyscale thresholding across all pertinent metrics, demonstrating improved discernibility between aggregates and mortar, and providing the most favourable balance of sensitivity and precision for aggregate-phase identification.

Video-language models (VLMs) are reshaping video querying services, bringing unified solutions to complex perception and reasoning tasks. However, deploying large VLMs in real-world systems remains challenging due to their high resource demands, and remote-based deployment often results in unacceptable response delays. Although small, locally deployable VLMs offer faster responses, they unavoidably fall short in accuracy. To reconcile this trade-off, we propose QuickGrasp, a responsive, quality of service (QoS)-aware system that bridges this gap through a local-first architecture with on-demand edge augmentation. Built upon the highly modular architecture of VLMs, QuickGrasp shares the vision representation across model variants to avoid redundant computation. To maximize system-wide efficiency, QuickGrasp introduces three key designs: accelerated video tokenization, query-adaptive edge augmentation, and delay-aware, accuracy-preserving vision token density configuration. We implement a prototype of QuickGrasp and evaluate it across multiple video understanding benchmarks. The results show that QuickGrasp matches the accuracy of large VLMs while achieving up to a 12.8x reduction in response delay. QuickGrasp represents a key advancement toward building responsive video querying services for open-world understanding that fully leverage the capabilities of VLMs.

Automated clinical decision support for clear aligner orthodontics faces a key challenge: bridging geometric perception (3D tooth segmentation) with clinical reasoning (biomechanical feasibility). We address this with OrthOAI, introducing three methodological contributions. First, sparse-supervision segmentation: a landmark-to-point-cloud synthesis protocol enables training from sparse anatomical annotations (6-8 points per tooth) instead of dense labels, combined with a clinically stratified loss mixing label-smoothed cross-entropy and a batch-adaptive Dice term for class imbalance. Second, knowledge-grounded constraint inference: biomechanical feasibility is modeled as a Constraint Satisfaction Problem over a domain ontology of tooth movements, encoding evidence-based per-stage limits as soft and hard constraints. Third, multi-criteria treatment evaluation: treatment quality is scored through a formal Multi-Criteria Decision Analysis framework using a weighted Additive Value Function grounded in clinical priority theory. On landmark-reconstructed point clouds from 3DTeethLand (MICCAI 2024), segmentation reaches 81.4% Tooth Identification Rate with 60,705 parameters. Ablations quantify the impact of each design choice. End-to-end inference runs in under 4 seconds on CPU. We also outline the gap between the current prototype-trained on synthetic ellipsoidal approximations-and clinical deployment, with a roadmap for validation. Code and weights are released.

Recent advances in Large Vision-Language Models (LVLMs) have shown strong potential for multi-modal radiological reasoning, particularly in tasks like diagnostic visual question answering (VQA) and radiology report generation. However, most existing approaches for 3D CT analysis largely rely on static, single-pass inference. In practice, clinical interpretation is a dynamic, tool-mediated workflow where radiologists iteratively review slices and use measurement, radiomics, and segmentation tools to refine findings. To bridge this gap, we propose CT-Flow, an agentic framework designed for interoperable volumetric interpretation. By leveraging the Model Context Protocol (MCP), CT-Flow shifts from closed-box inference to an open, tool-aware paradigm. We curate CT-FlowBench, the first large-scale instruction-tuning benchmark tailored for 3D CT tool-use and multi-step reasoning. Built upon this, CT-Flow functions as a clinical orchestrator capable of decomposing complex natural language queries into automated tool-use sequences. Experimental evaluations on CT-FlowBench and standard 3D VQA datasets demonstrate that CT-Flow achieves state-of-the-art performance, surpassing baseline models by 41% in diagnostic accuracy and achieving a 95% success rate in autonomous tool invocation. This work provides a scalable foundation for integrating autonomous, agentic intelligence into real-world clinical radiology.

Document extraction is an important step before retrieval-augmented generation (RAG), knowledge bases, and downstream generative AI can work. It turns unstructured documents like PDFs and scans into structured text and layout-aware representations. We introduce NovaLAD, a comprehensive document parsing system that integrates two concurrent YOLO object detection models - element detection and layout detection - with rule-based grouping and optional vision-language enhancement. When a page image is sent in, the first thing that happens is that it goes through both models at the same time. The element model finds semantic content like the title, header, text, table, image, and so on, and the layout model finds structural regions like layout_box, column_group, multi_column, row_group, and so on. A key design decision is to first send an image or figure through an image classifier (ViT) that decides whether it is relevant or not. Only useful images are then submitted to the Vision LLM for title, summary, and structured information, which cuts down on noise and costs. NovaLAD is built for speed: it works on CPU, employs parallel execution for detection, classification, OCR, and conversion, and generates several forms, including structured JSON, Markdown, RAG-ready texts, and knowledge graphs. We test on the DP-Bench benchmark (upstage/dp-bench) and get 96.49% TEDS and 98.51% NID, which is better than both commercial and open-source parsers. This paper explains how to extract data, how the architecture works, how data flows, and how to make NovaLAD both accurate and usable without needing a GPU.

Accurate prediction of RNA-associated interactions is essential for understanding cellular regulation and advancing drug discovery. While Biological Large Language Models (BioLLMs) such as ESM-2 and RiNALMo provide powerful sequence representations, existing methods rely on static fusion strategies that fail to capture the dynamic, context-dependent nature of molecular binding. We introduce CrossLLM-Mamba, a novel framework that reformulates interaction prediction as a state-space alignment problem. By leveraging bidirectional Mamba encoders, our approach enables deep “crosstalk” between modality-specific embeddings through hidden state propagation, modeling interactions as dynamic sequence transitions rather than static feature overlaps. The framework maintains linear computational complexity, making it scalable to high-dimensional BioLLM embeddings. We further incorporate Gaussian noise injection and Focal Loss to enhance robustness against hard-negative samples. Comprehensive experiments across three interaction categories, RNA-protein, RNA-small molecule, and RNA-RNA demonstrate that CrossLLM-Mamba achieves state-of-the-art performance. On the RPI1460 benchmark, our model attains an MCC of 0.892, surpassing the previous best by 5.2%. For binding affinity prediction, we achieve Pearson correlations exceeding 0.95 on riboswitch and repeat RNA subtypes. These results establish state-space modeling as a powerful paradigm for multi-modal biological interaction prediction.

Medical image segmentation remains challenging due to limited annotations for training, ambiguous anatomical features, and domain shifts. While vision-language models such as CLIP offer strong cross-modal representations, their potential for dense, text-guided medical image segmentation remains underexplored. We present MedCLIPSeg, a novel framework that adapts CLIP for robust, data-efficient, and uncertainty-aware medical image segmentation. Our approach leverages patch-level CLIP embeddings through probabilistic cross-modal attention, enabling bidirectional interaction between image and text tokens and explicit modeling of predictive uncertainty. Together with a soft patch-level contrastive loss that encourages more nuanced semantic learning across diverse textual prompts, MedCLIPSeg effectively improves data efficiency and domain generalizability. Extensive experiments across 16 datasets spanning five imaging modalities and six organs demonstrate that MedCLIPSeg outperforms prior methods in accuracy, efficiency, and robustness, while providing interpretable uncertainty maps that highlight local reliability of segmentation results. This work demonstrates the potential of probabilistic vision-language modeling for text-driven medical image segmentation.

Capturing high-quality images from only a few detected photons is a fundamental challenge in computational imaging. Single-photon avalanche diode (SPAD) sensors promise high-quality imaging in regimes where conventional cameras fail, but raw quanta frames contain only sparse, noisy, binary photon detections. Recovering a coherent image from a burst of such frames requires handling alignment, denoising, and demosaicing (for color) under noise statistics far outside those assumed by standard restoration pipelines or modern generative models. We present an approach that adapts large text-to-image latent diffusion models to the photon-limited domain of quanta burst imaging. Our method leverages the structural and semantic priors of internet-scale diffusion models while introducing mechanisms to handle Bernoulli photon statistics. By integrating latent-space restoration with burst-level spatio-temporal reasoning, our approach produces reconstructions that are both photometrically faithful and perceptually pleasing, even under high-speed motion. We evaluate the method on synthetic benchmarks and new real-world datasets, including the first color SPAD burst dataset and a challenging Deforming (XD) video benchmark. Across all settings, the approach substantially improves perceptual quality over classical and modern learning-based baselines, demonstrating the promise of adapting large generative priors to extreme photon-limited sensing. Code at \href{https://github.com/Aryan-Garg/gQIR}{https://github.com/Aryan-Garg/gQIR}.

The rapid advancement of generative models has made the detection of AI-generated images a critical challenge for both research and society. Recent works have shown that most state-of-the-art fake image detection methods overfit to their training data and catastrophically fail when evaluated on curated hard test sets with strong distribution shifts. In this work, we argue that it is more principled to learn a tight decision boundary around the real image distribution and treat the fake category as a sink class. To this end, we propose SimLBR, a simple and efficient framework for fake image detection using Latent Blending Regularization (LBR). Our method significantly improves cross-generator generalization, achieving up to +24.85% accuracy and +69.62% recall on the challenging Chameleon benchmark. SimLBR is also highly efficient, training orders of magnitude faster than existing approaches. Furthermore, we emphasize the need for reliability-oriented evaluation in fake image detection, introducing risk-adjusted metrics and worst-case estimates to better assess model robustness. All code and models will be released on HuggingFace and GitHub.

Recent vision-language models (VLMs) such as CLIP demonstrate impressive cross-modal reasoning, extending beyond images to 3D perception. Yet, these models remain fragile under domain shifts, especially when adapting from synthetic to real-world point clouds. Conventional 3D domain adaptation approaches rely on heavy trainable encoders, yielding strong accuracy but at the cost of efficiency. We introduce CLIPoint3D, the first framework for few-shot unsupervised 3D point cloud domain adaptation built upon CLIP. Our approach projects 3D samples into multiple depth maps and exploits the frozen CLIP backbone, refined through a knowledge-driven prompt tuning scheme that integrates high-level language priors with geometric cues from a lightweight 3D encoder. To adapt task-specific features effectively, we apply parameter-efficient fine-tuning to CLIP's encoders and design an entropy-guided view sampling strategy for selecting confident projections. Furthermore, an optimal transport-based alignment loss and an uncertainty-aware prototype alignment loss collaboratively bridge source-target distribution gaps while maintaining class separability. Extensive experiments on PointDA-10 and GraspNetPC-10 benchmarks show that CLIPoint3D achieves consistent 3-16% accuracy gains over both CLIP-based and conventional encoder-based baselines. Project page: https://sarthakm320.github.io/CLIPoint3D.

The aesthetic quality of a scene depends strongly on camera viewpoint. Existing approaches for aesthetic viewpoint suggestion are either single-view adjustments, predicting limited camera adjustments from a single image without understanding scene geometry, or 3D exploration approaches, which rely on dense captures or prebuilt 3D environments coupled with costly reinforcement learning (RL) searches. In this work, we introduce the notion of 3D aesthetic field that enables geometry-grounded aesthetic reasoning in 3D with sparse captures, allowing efficient viewpoint suggestions in contrast to costly RL searches. We opt to learn this 3D aesthetic field using a feedforward 3D Gaussian Splatting network that distills high-level aesthetic knowledge from a pretrained 2D aesthetic model into 3D space, enabling aesthetic prediction for novel viewpoints from only sparse input views. Building on this field, we propose a two-stage search pipeline that combines coarse viewpoint sampling with gradient-based refinement, efficiently identifying aesthetically appealing viewpoints without dense captures or RL exploration. Extensive experiments show that our method consistently suggests viewpoints with superior framing and composition compared to existing approaches, establishing a new direction toward 3D-aware aesthetic modeling.

Flow-based generative methods offer a simple and effective framework for high-fidelity generation, yet pretrained flow models are rarely used in their vanilla conditional form: in image generation, samples without guidance often appear diffuse and lack fine-grained detail. Existing guidance techniques such as classifier-free guidance (CFG) improve fidelity but reduce sample diversity. We introduce Momentum Guidance (MG), a guidance method that improves sample quality by extrapolating the current velocity away from an exponential moving average of past velocities along the ODE trajectory, while preserving the standard one-evaluation-per-step cost. MG provides gains beyond CFG, improving the precision-recall Pareto frontier. Experiments demonstrate the effectiveness of MG across benchmarks. On ImageNet-256, MG improves FID by 36.54% without CFG and 25.42% with CFG on average across sampling settings, attaining an FID of 1.553 at 16 sampling steps. Evaluations on large flow-based models, including Stable Diffusion 3 and FLUX.1-dev, further confirm improvements across standard metrics.

AI video generation is evolving rapidly. For video generators to be useful for applications ranging from robotics to film-making, they must consistently produce realistic videos. However, evaluating the realism of generated videos remains a largely manual process – requiring human annotation or bespoke evaluation datasets which have restricted scope. Here we develop an automated evaluation framework for video realism which captures both semantics and coherent 3D structure and which does not require access to a reference video. Our method, 3DSPA, is a 3D spatiotemporal point autoencoder which integrates 3D point trajectories, depth cues, and DINO semantic features into a unified representation for video evaluation. 3DSPA models how objects move and what is happening in the scene, enabling robust assessments of realism, temporal consistency, and physical plausibility. Experiments show that 3DSPA reliably identifies videos which violate physical laws, is more sensitive to motion artifacts, and aligns more closely with human judgments of video quality and realism across multiple datasets. Our results demonstrate that enriching trajectory-based representations with 3D semantics offers a stronger foundation for benchmarking generative video models, and implicitly captures physical rule violations. The code and pretrained model weights will be available at https://github.com/TheProParadox/3dspa_code.

Full-Reference image quality assessment (FR IQA) is important for image compression, restoration and generative modeling, yet current neural metrics remain slow and vulnerable to adversarial perturbations. We present BiRQA, a compact FR IQA metric model that processes four fast complementary features within a bidirectional multiscale pyramid. A bottom-up attention module injects fine-scale cues into coarse levels through an uncertainty-aware gate, while a top-down cross-gating block routes semantic context back to high resolution. To enhance robustness, we introduce Anchored Adversarial Training, a theoretically grounded strategy that uses clean "anchor" samples and a ranking loss to bound pointwise prediction error under attacks. On five public FR IQA benchmarks BiRQA outperforms or matches the previous state of the art (SOTA) while running ~3x faster than previous SOTA models. Under unseen white-box attacks it lifts SROCC from 0.30-0.57 to 0.60-0.84 on KADID-10k, demonstrating substantial robustness gains. To our knowledge, BiRQA is the only FR IQA model combining competitive accuracy with real-time throughput and strong adversarial resilience.

In this study, we present an end-to-end pipeline capable of converting drone-captured video streams into high-fidelity 3D reconstructions with minimal latency. Unmanned aerial vehicles (UAVs) are extensively used in aerial real-time perception applications. Moreover, recent advances in 3D Gaussian Splatting (3DGS) have demonstrated significant potential for real-time neural rendering. However, their integration into end-to-end UAV-based reconstruction and visualization systems remains underexplored. Our goal is to propose an efficient architecture that combines live video acquisition via RTMP streaming, synchronized sensor fusion, camera pose estimation, and 3DGS optimization, achieving continuous model updates and low-latency deployment within interactive visualization environments that supports immersive augmented and virtual reality (AR/VR) applications. Experimental results demonstrate that the proposed method achieves competitive visual fidelity, while delivering significantly higher rendering performance and substantially reduced end-to-end latency, compared to NeRF-based approaches. Reconstruction quality remains within 4-7% of high-fidelity offline references, confirming the suitability of the proposed system for real-time, scalable augmented perception from aerial platforms.

Vision-language models (VLMs) are powerful but remain opaque black boxes. We introduce the first framework for transparent circuit tracing in VLMs to systematically analyze multimodal reasoning. By utilizing transcoders, attribution graphs, and attention-based methods, we uncover how VLMs hierarchically integrate visual and semantic concepts. We reveal that distinct visual feature circuits can handle mathematical reasoning and support cross-modal associations. Validated through feature steering and circuit patching, our framework proves these circuits are causal and controllable, laying the groundwork for more explainable and reliable VLMs.

Inverse problems in imaging are ill-posed, leading to infinitely many solutions consistent with the measurements due to the non-trivial null-space of the sensing matrix. Common image priors promote solutions on the general image manifold, such as sparsity, smoothness, or score function. However, as these priors do not constrain the null-space component, they can bias the reconstruction. Thus, we aim to incorporate meaningful null-space information in the reconstruction framework. Inspired by smooth image representation on graphs, we propose Graph-Smooth Null-Space Representation (GSNR), a mechanism that imposes structure only into the invisible component. Particularly, given a graph Laplacian, we construct a null-restricted Laplacian that encodes similarity between neighboring pixels in the null-space signal, and we design a low-dimensional projection matrix from the $p$-smoothest spectral graph modes (lowest graph frequencies). This approach has strong theoretical and practical implications: i) improved convergence via a null-only graph regularizer, ii) better coverage, how much null-space variance is captured by $p$ modes, and iii) high predictability, how well these modes can be inferred from the measurements. GSNR is incorporated into well-known inverse problem solvers, e.g., PnP, DIP, and diffusion solvers, in four scenarios: image deblurring, compressed sensing, demosaicing, and image super-resolution, providing consistent improvement of up to 4.3 dB over baseline formulations and up to 1 dB compared with end-to-end learned models in terms of PSNR.

The Sun is observed in unprecedented detail, enabling studies of its activity on very small spatiotemporal scales. However, the large volume of data collected by our telescopes cannot be fully analyzed with conventional methods. Popular machine learning methods identify general trends from observations, but tend to overlook unusual events due to their low frequency of occurrence. We study the applicability of unsupervised probabilistic methods to efficiently identify rare events in multidimensional solar observations and optimize our computational resources to the study of these extreme phenomena. We introduce Inspectorch, an open-source framework that utilizes flow-based models: flexible density estimators capable of learning the multidimensional distribution of solar observations. Once optimized, it assigns a probability to each sample, allowing us to identify unusual events. We apply this approach by applying it to observations from the Hinode Spectro-Polarimeter, the Interface Region Imaging Spectrograph, the Microlensed Hyperspectral Imager at Swedish 1-m Solar Telescope, the Atmospheric Imaging Assembly on board the Solar Dynamics Observatory and the Extreme Ultraviolet Imager on board Solar Orbiter. We find that the algorithm assigns consistently lower probabilities to spectra that exhibit unusual features. For example, it identifies profiles with very strong Doppler shifts, uncommon broadening, and temporal dynamics associated with small-scale reconnection events, among others. As a result, Inspectorch demonstrates that density estimation using flow-based models offers a powerful approach to identifying rare events in large solar datasets. The resulting probabilistic anomaly scores allow computational resources to be focused on the most informative and physically relevant events. We make our Python package publicly available at https://github.com/cdiazbas/inspectorch.

We present N4MC, the first 4D neural compression framework to efficiently compress time-varying mesh sequences by exploiting their temporal redundancy. Unlike prior neural mesh compression methods that treat each mesh frame independently, N4MC takes inspiration from inter-frame compression in 2D video codecs, and learns motion compensation in long mesh sequences. Specifically, N4MC converts consecutive irregular mesh frames into regular 4D tensors to provide a uniform and compact representation. These tensors are then condensed using an auto-decoder, which captures both spatial and temporal correlations for redundancy removal. To enhance temporal coherence, we introduce a transformer-based interpolation model that predicts intermediate mesh frames conditioned on latent embeddings derived from tracked volume centers, eliminating motion ambiguities. Extensive evaluations show that N4MC outperforms state-of-the-art in rate-distortion performance, while enabling real-time decoding of 4D mesh sequences. The implementation of our method is available at: https://github.com/frozzzen3/N4MC.