Computer Vision
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Thursday 20 November
External validation of breast ultrasound segmentation models remains limited because internal train–test splits do not capture domain shifts across imaging systems, acquisition protocols, and patient populations. We introduce a novel multi-task framework for breast ultrasound segmentation and malignancy classification. Its central methodological advance is a differentiable morphology-to-malignancy bridge: lesion area, boundary roughness, compactness, and texture are computed from the predicted soft segmentation mask, aggregated with learned weights into a morphology-based malignancy score, and constrained to agree with the image-level classifier. To our knowledge, this is the first breast ultrasound framework to use BI-RADS-inspired morphology derived from its own soft segmentation output as an end-to-end consistency target for malignancy classification. It is also the first 2D B-mode multi-task study to report every directed external transfer among four independent datasets: training on each dataset and testing on the other three yields 12 source–target pairs, assessed with single models and five-fold ensembles. In matched comparisons across all pairs, the proposed single-model configuration outperforms dedicated single-task baselines in segmentation (DC: 0.764 vs. 0.740) and malignancy classification (AUC: 0.818 vs. 0.791). The ensemble achieves a mean external DC of 0.786 and is competitive with SAM-based segmentation methods using an EfficientNet-B7 encoder while also predicting malignancy. The learned morphology weights retain the same ordering across all four datasets, with boundary roughness receiving the greatest weight. These results establish the first complete four-dataset directed benchmark for joint 2D breast ultrasound segmentation and malignancy classification and demonstrate that clinically grounded morphological consistency improves both tasks under domain shift.
Computer Vision
InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer
Recently, the strong generalization ability of CLIP has facilitated open-vocabulary semantic segmentation, which labels pixels using arbitrary text. However, existing methods that fine-tune CLIP for segmentation on limited seen categories often lead to overfitting and degrade the pretrained vision-language alignment. To stabilize modality alignment during fine-tuning, we propose InfoCLIP, which leverages an information-theoretic perspective to transfer alignment knowledge from pretrained CLIP to the segmentation task. Specifically, this transfer is guided by two novel objectives grounded in mutual information. First, we compress the pixel-text modality alignment from pretrained CLIP to reduce noise arising from its coarse-grained local semantic representations learned under image-text supervision. Second, we maximize the mutual information between the alignment knowledge of pretrained CLIP and the fine-tuned model to transfer compact local semantic relations suited for the segmentation task. Extensive evaluations across various benchmarks validate the effectiveness of InfoCLIP in enhancing CLIP fine-tuning for open-vocabulary semantic segmentation, demonstrating its adaptability and superiority in asymmetric transfer.
Read the full abstract
Computer Vision
Click2Graph: Interactive Panoptic Video Scene Graphs from a Single Click
State-of-the-art Video Scene Graph Generation (VSGG) systems provide structured visual understanding but operate as closed, feed-forward pipelines with no ability to incorporate human guidance. In contrast, promptable segmentation models such as SAM2 enable precise user interaction but lack semantic or relational reasoning. We introduce Click2Graph, the first interactive framework for Panoptic Video Scene Graph Generation (PVSG) that unifies visual prompting with spatial, temporal, and semantic understanding. From a single user cue, such as a click or bounding box, Click2Graph segments and tracks the subject across time, autonomously discovers interacting objects, and predicts <subject, object, predicate> triplets to form a temporally consistent scene graph. Our framework introduces two key components: a Dynamic Interaction Discovery Module that generates subject-conditioned object prompts, and a Semantic Classification Head that performs joint entity and predicate reasoning. Experiments on the OpenPVSG benchmark demonstrate that Click2Graph establishes a strong foundation for user-guided PVSG, showing how human prompting can be combined with panoptic grounding and relational inference to enable controllable and interpretable video scene understanding.
Read the full abstract
Computer Vision
Automated Interpretable 2D Video Extraction from 3D Echocardiography
Although the heart has complex three-dimensional (3D) anatomy, conventional medical imaging with cardiac ultrasound relies on a series of 2D videos showing individual cardiac structures. 3D echocardiography is a developing modality that now offers adequate image quality for clinical use, with potential to streamline acquisition and improve assessment of off-axis features. We propose an automated method to select standard 2D views from 3D cardiac ultrasound volumes, allowing physicians to interpret the data in their usual format while benefiting from the speed and usability of 3D scanning. Applying a deep learning view classifier and downstream heuristics based on anatomical landmarks together with heuristics provided by cardiologists, we reconstruct standard echocardiography views. This approach was validated by three cardiologists in blinded evaluation (96% accuracy in 1,600 videos from 2 hospitals). The downstream 2D videos were also validated in their ability to detect cardiac abnormalities using AI echocardiography models (EchoPrime and PanEcho) as well as ability to generate clinical-grade measurements of cardiac anatomy (EchoNet-Measurement). We demonstrated that the extracted 2D videos preserve spatial calibration and diagnostic features, allowing clinicians to obtain accurate real-world interpretations from 3D volumes. We release the code and a dataset of 29 3D echocardiography videos https://github.com/echonet/3d-echo .
Read the full abstract
Computer Vision
Boosting Medical Visual Understanding From Multi-Granular Language Learning
Recent advances in image-text pretraining have significantly enhanced visual understanding by aligning visual and textual representations. Contrastive Language-Image Pretraining (CLIP) has played a pivotal role in multimodal learning. However, its focus on single-label, single-granularity alignment limits its effectiveness in complex domains such as medical imaging, where images often correspond to multiple high-level labels (e.g., disease categories) across different annotation granularities (e.g., diagnostic description, clinical explanation). To address this, we propose Multi-Granular Language Learning (MGLL), a contrastive learning framework designed to improve both multi-label and cross-granularity alignment. MGLL leverages structured multi-label supervision, integrates textual descriptions across granularities, and introduces soft-label supervision with point-wise constraints to enhance alignment. MGLL employs smooth Kullback-Leibler (KL) divergence to ensure cross-granularity consistency while maintaining computational efficiency as a plug-and-play module for vision-language models. Pretrained on our constructed large-scale multi-granular datasets and evaluated across multiple datasets, MGLL outperforms other state-of-the-art methods in downstream tasks. The code is available at https://github.com/HUANGLIZI/MGLL.
Read the full abstract
Wednesday 19 November
Computer Vision · Cross-listed from physics.geo-ph
Coarse-to-Fine Non-Rigid Registration for Side-Scan Sonar Mosaicking
Side-scan sonar mosaicking plays a crucial role in large-scale seabed mapping but is challenged by complex non-linear, spatially varying distortions due to diverse sonar acquisition conditions. Existing rigid or affine registration methods fail to model such complex deformations, whereas traditional non-rigid techniques tend to overfit and lack robustness in sparse-texture sonar data. To address these challenges, we propose a coarse-to-fine hierarchical non-rigid registration framework tailored for large-scale side-scan sonar images. Our method begins with a global Thin Plate Spline initialization from sparse correspondences, followed by superpixel-guided segmentation that partitions the image into structurally consistent patches preserving terrain integrity. Each patch is then refined by a pretrained SynthMorph network in an unsupervised manner, enabling dense and flexible alignment without task-specific training. Finally, a fusion strategy integrates both global and local deformations into a smooth, unified deformation field. Extensive quantitative and visual evaluations demonstrate that our approach significantly outperforms state-of-the-art rigid, classical non-rigid, and learning-based methods in accuracy, structural consistency, and deformation smoothness on the challenging sonar dataset.
Read the full abstract
Computer Vision · Cross-listed from cs.CL
CrossCheck-Bench: Diagnosing Compositional Failures in Multimodal Conflict Resolution
Multimodal Large Language Models are primarily trained and evaluated on aligned image-text pairs, which leaves their ability to detect and resolve real-world inconsistencies largely unexplored. In open-domain applications visual and textual cues often conflict, requiring models to perform structured reasoning beyond surface-level alignment. We introduce CrossCheck-Bench, a diagnostic benchmark for evaluating contradiction detection in multimodal inputs. The benchmark adopts a hierarchical task framework covering three levels of reasoning complexity and defines seven atomic capabilities essential for resolving cross-modal inconsistencies. CrossCheck-Bench includes 15k question-answer pairs sourced from real-world artifacts with synthetically injected contradictions. The dataset is constructed through a multi-stage annotation pipeline involving more than 450 expert hours to ensure semantic validity and calibrated difficulty across perception, integration, and reasoning. We evaluate 13 state-of-the-art vision-language models and observe a consistent performance drop as tasks shift from perceptual matching to logical contradiction detection. Most models perform well on isolated entity recognition but fail when multiple clues must be synthesized for conflict reasoning. Capability-level analysis further reveals uneven skill acquisition, especially in tasks requiring multi-step inference or rule-based validation. Additional probing shows that conventional prompting strategies such as Chain-of-Thought and Set-of-Mark yield only marginal gains. By contrast, methods that interleave symbolic reasoning with grounded visual processing achieve more stable improvements. These results highlight a persistent bottleneck in multimodal reasoning and suggest new directions for building models capable of robust cross-modal verification.
Read the full abstract
Computer Vision
TSRE: Channel-Aware Typical Set Refinement for Out-of-Distribution Detection
Out-of-Distribution (OOD) detection is a critical capability for ensuring the safe deployment of machine learning models in open-world environments, where unexpected or anomalous inputs can compromise model reliability and performance. Activation-based methods play a fundamental role in OOD detection by mitigating anomalous activations and enhancing the separation between in-distribution (ID) and OOD data. However, existing methods apply activation rectification while often overlooking channel's intrinsic characteristics and distributional skewness, which results in inaccurate typical set estimation. This discrepancy can lead to the improper inclusion of anomalous activations across channels. To address this limitation, we propose a typical set refinement method based on discriminability and activity, which rectifies activations into a channel-aware typical set. Furthermore, we introduce a skewness-based refinement to mitigate distributional bias in typical set estimation. Finally, we leverage the rectified activations to compute the energy score for OOD detection. Experiments on the ImageNet-1K and CIFAR-100 benchmarks demonstrate that our method achieves state-of-the-art performance and generalizes effectively across backbones and score functions.
Read the full abstract
Computer Vision
Upstream Probabilistic Meta-Imputation for Multimodal Pediatric Pancreatitis Classification
Pediatric pancreatitis is a progressive and debilitating inflammatory condition, including acute pancreatitis and chronic pancreatitis, that presents significant clinical diagnostic challenges. Machine learning-based methods also face diagnostic challenges due to limited sample availability and multimodal imaging complexity. To address these challenges, this paper introduces Upstream Probabilistic Meta-Imputation (UPMI), a light-weight augmentation strategy that operates upstream of a meta-learner in a low-dimensional meta-feature space rather than in image space. Modality-specific logistic regressions (T1W and T2W MRI radiomics) produce probability outputs that are transformed into a 7-dimensional meta-feature vector. Class-conditional Gaussian mixture models (GMMs) are then fit within each cross-validation fold to sample synthetic meta-features that, combined with real meta-features, train a Random Forest (RF) meta-classifier. On 67 pediatric subjects with paired T1W/T2W MRIs, UPMI achieves a mean AUC of 0.908 $\pm$ 0.072, a $\sim$5% relative gain over a real-only baseline (AUC 0.864 $\pm$ 0.061).
Read the full abstract
Computer Vision
Efficient Score Pre-computation for Diffusion Models via Cross-Matrix Krylov Projection
This paper presents a novel framework to accelerate score-based diffusion models. It first converts the standard stable diffusion model into the Fokker-Planck formulation which results in solving large linear systems for each image. For training involving many images, it can lead to a high computational cost. The core innovation is a cross-matrix Krylov projection method that exploits mathematical similarities between matrices, using a shared subspace built from “seed" matrices to rapidly solve for subsequent “target" matrices. Our experiments show that this technique achieves a 15.8% to 43.7% time reduction over standard sparse solvers. Additionally, we compare our method against DDPM baselines in denoising tasks, showing a speedup of up to 115$\times$. Furthermore, under a fixed computational budget, our model is able to produce high-quality images while DDPM fails to generate recognizable content, illustrating our approach is a practical method for efficient generation in resource-limited settings.
Read the full abstract
Computer Vision
BD-Net: Has Depth-Wise Convolution Ever Been Applied in Binary Neural Networks?
Recent advances in model compression have highlighted the potential of low-bit precision techniques, with Binary Neural Networks (BNNs) attracting attention for their extreme efficiency. However, extreme quantization in BNNs limits representational capacity and destabilizes training, posing significant challenges for lightweight architectures with depth-wise convolutions. To address this, we propose a 1.58-bit convolution to enhance expressiveness and a pre-BN residual connection to stabilize optimization by improving the Hessian condition number. These innovations enable, to the best of our knowledge, the first successful binarization of depth-wise convolutions in BNNs. Our method achieves 33M OPs on ImageNet with MobileNet V1, establishing a new state-of-the-art in BNNs by outperforming prior methods with comparable OPs. Moreover, it consistently outperforms existing methods across various datasets, including CIFAR-10, CIFAR-100, STL-10, Tiny ImageNet, and Oxford Flowers 102, with accuracy improvements of up to 9.3 percentage points.
Read the full abstract
Computer Vision
RB-FT: Rationale-Bootstrapped Fine-Tuning for Video Classification
Vision Language Models (VLMs) are becoming increasingly integral to multimedia understanding; however, they often struggle with domain-specific video classification tasks, particularly in cases with limited data. This stems from a critical rationale gap, where sparse domain data is insufficient to bridge the semantic distance between complex spatio-temporal content and abstract classification labels. We propose a two-stage self-improvement paradigm to bridge this gap without new annotations. First, we prompt the VLMs to generate detailed textual rationales for each video, compelling them to articulate the domain-specific logic. The VLM is then fine-tuned on these self-generated rationales, utilizing this intermediate supervision to align its representations with the nuances of the target domain. Second, conventional supervised fine-tuning (SFT) is performed on the task labels, achieving markedly higher effectiveness as a result of the model's pre-acquired domain reasoning. Extensive experiments on diverse datasets demonstrate that our method significantly outperforms direct SFT, validating self-generated rationale as an effective, annotation-efficient paradigm for adapting VLMs to domain-specific video analysis.
Read the full abstract
Computer Vision
AnyBox: Efficient Zero-Shot 9DoF Pose Estimation of Boxes for Robotic Manipulation
Recovering the 9D pose of objects, both their 6D pose and 3D dimensions, under clutter and occlusion is a core requirement for warehouse automation, logistics, and manufacturing. Model-based methods are accurate but assume an instance-specific CAD model for every object, which is costly to maintain as inventories change. Model-free and category-level methods relax this assumption, yet they remain vulnerable to the symmetry, weak texture, and heavy occlusion that characterize stacked storage boxes, and they ignore the strong structural priors such scenes provide. We present AnyBox, an efficient zero-shot framework that exploits the geometric regularity of boxes to jointly recover pose and dimensions from a single RGB-D observation. Starting from a canonical category template, AnyBox alternates between pose and scale estimation, using the discrepancy between the reprojected template and the observed mask to drive a binary search over box dimensions. Two lightweight components make this practical: a depth-consistency filter that rejects the implausible hypotheses induced by box symmetry, and an early-stopping rule that replaces the remaining search with a single closed-form update. On public benchmarks and an in-house warehouse dataset, AnyBox improves detection AP by up to 36 points, more than doubling the previous best, and approaches instance-level pipelines that have access to ground-truth CAD models. These gains transfer downstream, raising success by 28% on a cluttered robotic box-shelving task.
Read the full abstract
Computer Vision
Automatic Uncertainty-Aware Synthetic Data Bootstrapping for Historical Map Segmentation
The automated analysis of historical documents, particularly maps, has drastically benefited from advances in deep learning and its success across various computer vision applications. However, most deep learning-based methods heavily rely on large amounts of annotated training data, which are typically unavailable for historical maps, especially for those belonging to specific, homogeneous cartographic domains, also known as corpora. Creating high-quality training data suitable for machine learning often takes a significant amount of time and involves extensive manual effort. While synthetic training data can alleviate the scarcity of real-world samples, it often lacks the affinity (realism) and diversity (variation) necessary for effective learning. By transferring the cartographic style of a historical map corpus onto modern vector data, we bootstrap an effectively unlimited number of synthetic historical maps suitable for tasks such as land-cover interpretation of a homogeneous historical map corpus. We propose an automatic deep generative approach and an alternative manual stochastic degradation technique to emulate the visual uncertainty and noise, also known as aleatoric uncertainty, commonly observed in historical map scans. To quantitatively evaluate the effectiveness and applicability of our approach, the bootstrapped training datasets were employed for domain-adaptive semantic segmentation on a homogeneous map corpus using a Self-Constructing Graph Convolutional Network, enabling a comprehensive assessment of the impact of our data bootstrapping methods.
Read the full abstract
Computer Vision
WALDO: Where Unseen Model-based 6D Pose Estimation Meets Occlusion
Accurate 6D object pose estimation is vital for robotics, augmented reality, and scene understanding. For seen objects, high accuracy is often attainable via per-object fine-tuning but generalizing to unseen objects remains a challenge. To address this problem, past arts assume access to CAD models at test time and typically follow a multi-stage pipeline to estimate poses: detect and segment the object, propose an initial pose, and then refine it. Under occlusion, however, the early-stage of such pipelines are prone to errors, which can propagate through the sequential processing, and consequently degrade the performance. To remedy this shortcoming, we propose four novel extensions to model-based 6D pose estimation methods: (i) a dynamic non-uniform dense sampling strategy that focuses computation on visible regions, reducing occlusion-induced errors; (ii) a multi-hypothesis inference mechanism that retains several confidence-ranked pose candidates, mitigating brittle single-path failures; (iii) iterative refinement to progressively improve pose accuracy; and (iv) series of occlusion-focused training augmentations that strengthen robustness and generalization. Furthermore, we propose a new weighted by visibility metric for evaluation under occlusion to minimize the bias in the existing protocols. Via extensive empirical evaluations, we show that our proposed approach achieves more than 5% improvement in accuracy on ICBIN and more than 2% on BOP dataset benchmarks, while achieving approximately 3 times faster inference.
Read the full abstract
Computer Vision
EfficientSAM3: Progressive Hierarchical Distillation for Video Concept Segmentation from SAM1, 2, and 3
The Segment Anything Model 3 (SAM3) advances visual understanding with Promptable Concept Segmentation (PCS) across images and videos, but its unified architecture (shared vision backbone, DETR-style detector, dense-memory tracker) remains prohibitive for on-device use. We present EfficientSAM3, a family of efficient models built on Progressive Hierarchical Distillation (PHD) that transfers capability from SAM3 to lightweight students in three stages: (1) Encoder Distillation aligns image features via prompt-in-the-loop training on SA-1B; (2) Temporal Memory Distillation replaces dense memory with a compact Perceiver-based module trained on SA-V to compress and retrieve spatiotemporal features efficiently; and (3) End-to-End Fine-Tuning refines the full pipeline on the official SAM3 PCS data to preserve concept-level performance. PHD yields a spectrum of student variants using RepViT, TinyViT, and EfficientViT backbones, enabling on-device concept segmentation and tracking while maintaining high fidelity to teacher behavior. We benchmark on popular VOS datasets, and compare with varies of releated work, achieing strong performance-efficiency trade-offs.
Read the full abstract
Computer Vision
UniFit: Towards Universal Virtual Try-on with MLLM-Guided Semantic Alignment
Image-based virtual try-on (VTON) aims to synthesize photorealistic images of a person wearing specified garments. Despite significant progress, building a universal VTON framework that can flexibly handle diverse and complex tasks remains a major challenge. Recent methods explore multi-task VTON frameworks guided by textual instructions, yet they still face two key limitations: (1) semantic gap between text instructions and reference images, and (2) data scarcity in complex scenarios. To address these challenges, we propose UniFit, a universal VTON framework driven by a Multimodal Large Language Model (MLLM). Specifically, we introduce an MLLM-Guided Semantic Alignment Module (MGSA), which integrates multimodal inputs using an MLLM and a set of learnable queries. By imposing a semantic alignment loss, MGSA captures cross-modal semantic relationships and provides coherent and explicit semantic guidance for the generative process, thereby reducing the semantic gap. Moreover, by devising a two-stage progressive training strategy with a self-synthesis pipeline, UniFit is able to learn complex tasks from limited data. Extensive experiments show that UniFit not only supports a wide range of VTON tasks, including multi-garment and model-to-model try-on, but also achieves state-of-the-art performance. The source code and pretrained models are available at https://github.com/zwplus/UniFit.
Read the full abstract
Computer Vision · Cross-listed from eess.IV
UniUltra: Interactive Parameter-Efficient SAM2 for Universal Ultrasound Segmentation
The Segment Anything Model 2 (SAM2) demonstrates remarkable universal segmentation capabilities on natural images. However, its performance on ultrasound images is significantly degraded due to domain disparities. This limitation raises two critical challenges: how to efficiently adapt SAM2 to ultrasound imaging while maintaining parameter efficiency, and how to deploy the adapted model effectively in resource-constrained clinical environments. To address these issues, we propose UniUltra for universal ultrasound segmentation. Specifically, we first introduce a novel context-edge hybrid adapter (CH-Adapter) that enhances fine-grained perception across diverse ultrasound imaging modalities while achieving parameter-efficient fine-tuning. To further improve clinical applicability, we develop a deep-supervised knowledge distillation (DSKD) technique that transfers knowledge from the large image encoder of the fine-tuned SAM2 to a super lightweight encoder, substantially reducing computational requirements without compromising performance. Extensive experiments demonstrate that UniUltra outperforms state-of-the-arts with superior generalization capabilities. Notably, our framework achieves competitive performance using only 8.91% of SAM2's parameters during fine-tuning, and the final compressed model reduces the parameter count by 94.08% compared to the original SAM2, making it highly suitable for practical clinical deployment. The source code is available at https://github.com/xq141839/UniUltra.
Read the full abstract
Computer Vision
RoMa v2: Harder Better Faster Denser Feature Matching
Dense feature matching aims to estimate all correspondences between two images of a 3D scene and has recently been established as the gold standard due to its high accuracy and robustness. However, existing dense matchers still fail or perform poorly for many hard real-world scenarios, and high-precision models are often slow, limiting their applicability. In this paper, we attack these weaknesses on a wide front through a series of systematic improvements that together yield a significantly better model. In particular, we construct a novel matching architecture and loss, which, combined with a curated diverse training distribution, enables our model to solve many complex matching tasks. We further make training faster through a decoupled two-stage matching-then-refinement pipeline, and at the same time, significantly reduce refinement memory usage through a custom CUDA kernel. Finally, we leverage the recent DINOv3 foundation model along with multiple other insights to make the model more robust and unbiased. In our extensive set of experiments, we show that the resulting novel matcher sets a new state-of-the-art, being significantly more accurate than its predecessors. Code is available at https://github.com/Parskatt/romav2
Read the full abstract
Computer Vision
GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization
Current research on agentic visual reasoning enables deep multimodal understanding but primarily focuses on image manipulation tools, leaving a gap toward more general-purpose agentic models. In this work, we revisit the geolocalization task, which requires not only nuanced visual grounding but also web search to confirm or refine hypotheses during reasoning. Since existing geolocalization benchmarks fail to meet the need for high-resolution imagery and the localization challenge for deep agentic reasoning, we curate GeoBench, a benchmark that includes photos and panoramas from around the world, along with a subset of satellite images of different cities to rigorously evaluate the geolocalization ability of agentic models. We also propose GeoVista, an agentic model that seamlessly integrates tool invocation within the reasoning loop, including an image-zoom-in tool to magnify regions of interest and a web-search tool to retrieve related web information. We develop a complete training pipeline for it, including a cold-start supervised fine-tuning (SFT) stage to learn reasoning patterns and tool-use priors, followed by a reinforcement learning (RL) stage to further enhance reasoning ability. We adopt a hierarchical reward to leverage multi-level geographical information and improve overall geolocalization performance. Experimental results show that GeoVista surpasses other open-source agentic models on the geolocalization task greatly and achieves performance comparable to closed-source models such as Gemini-2.5-flash and GPT-5 on most metrics.
Read the full abstract
Computer Vision · Cross-listed from cs.RO
In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data
Egocentric videos are a valuable and scalable data source to learn manipulation policies. However, due to significant data heterogeneity, most existing approaches utilize human data for simple pre-training, which does not unlock its full potential. This paper first provides a scalable recipe for collecting and using egocentric data by categorizing human data into two categories: in-the-wild and on-task alongside with systematic analysis on how to use the data. We first curate a dataset, PHSD, which contains over 1,000 hours of diverse in-the-wild egocentric data and over 20 hours of on-task data directly aligned to the target manipulation tasks. This enables learning a large egocentric language-conditioned flow matching policy, Human0. With domain adaptation techniques, Human0 minimizes the gap between humans and humanoids. Empirically, we show Human0 achieves several novel properties from scaling human data, including language following of instructions from only human data, few-shot learning, and improved robustness using on-task data. Project website: https://xiongyicai.github.io/In-N-On/
Read the full abstract
Computer Vision
Think Visually, Reason Textually: Vision-Language Synergy in ARC
Abstract reasoning from minimal examples remains a core unsolved problem for frontier foundation models such as GPT-5 and Grok 4. These models still fail to infer structured transformation rules from a handful of examples, which is a key hallmark of human intelligence. The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) provides a rigorous testbed for this capability, demanding conceptual rule induction and transfer to novel tasks. Most existing methods treat ARC-AGI as a purely textual reasoning task, overlooking the fact that humans rely heavily on visual abstraction when solving such puzzles. However, our pilot experiments reveal a paradox: naively rendering ARC-AGI grids as images degrades performance due to imprecise rule execution. This leads to our central hypothesis that vision and language possess complementary strengths across distinct reasoning stages: vision supports global pattern abstraction and verification, whereas language specializes in symbolic rule formulation and precise execution. Building on this insight, we introduce two synergistic strategies: (1) Vision-Language Synergy Reasoning (VLSR), which decomposes ARC-AGI into modality-aligned subtasks; and (2) Modality-Switch Self-Correction (MSSC), which leverages vision to verify text-based reasoning for intrinsic error correction. Extensive experiments demonstrate that our approach yields up to a 4.33% improvement over text-only baselines across diverse flagship models and multiple ARC-AGI tasks. Our findings suggest that unifying visual abstraction with linguistic reasoning is a crucial step toward achieving generalizable, human-like intelligence in future foundation models. Source code is released at https://github.com/InternLM/ARC-VL.
Read the full abstract
Computer Vision
First Frame Is the Place to Go for Video Content Customization
What role does the first frame play in video generation models? Traditionally, it's viewed as the spatial-temporal starting point of a video, merely a seed for subsequent animation. In this work, we reveal a fundamentally different perspective: video models implicitly treat the first frame as a conceptual memory buffer that stores visual entities for later reuse during generation. Leveraging this insight, we show that it's possible to achieve robust and generalized video content customization in diverse scenarios, using only 20-50 training examples without architectural changes or large-scale finetuning. This unveils a powerful, overlooked capability of video generation models for reference-based video customization.
Read the full abstract
Computer Vision
Hyperspectral Image Classification using Spectral-Spatial Mixer Network
This paper introduces SS-MixNet, a lightweight and effective deep learning model for hyperspectral image (HSI) classification. The architecture integrates 3D convolutional layers for local spectral-spatial feature extraction with two parallel MLP-style mixer blocks that capture long-range dependencies in spectral and spatial dimensions. A depthwise convolution-based attention mechanism is employed to enhance discriminative capability with minimal computational overhead. The model is evaluated on the QUH-Tangdaowan and QUH-Qingyun datasets using only 1% of labeled data for training and validation. SS-MixNet achieves the highest performance among compared methods, including 2D-CNN, 3D-CNN, IP-SWIN, SimPoolFormer, and HybridKAN, reaching 95.68% and 93.86% overall accuracy on the Tangdaowan and Qingyun datasets, respectively. The results, supported by quantitative metrics and classification maps, confirm the model's effectiveness in delivering accurate and robust predictions with limited supervision. The code will be made publicly available at: https://github.com/mqalkhatib/SS-MixNet
Read the full abstract
Computer Vision
MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping
Mixture-of-Experts (MoE) Multimodal large language models (MLLMs) excel at vision-language tasks, but they suffer from high computational inefficiency. To reduce inference overhead, expert skipping methods have been proposed to deactivate redundant experts based on the current input tokens. However, we find that applying these methods-originally designed for unimodal large language models (LLMs)-to MLLMs results in considerable performance degradation. This is primarily because such methods fail to account for the heterogeneous contributions of experts across MoE layers and modality-specific behaviors of tokens within these layers. Motivated by these findings, we propose MoDES, the first training-free framework that adaptively skips experts to enable efficient and accurate MoE MLLM inference. It incorporates a globally-modulated local gating (GMLG) mechanism that integrates global layer-wise importance into local routing probabilities to accurately estimate per-token expert importance. A dual-modality thresholding (DMT) method is then applied, which processes tokens from each modality separately, to derive the skipping schedule. To set the optimal thresholds, we introduce a frontier search algorithm that exploits monotonicity properties, cutting convergence time from several days to a few hours. Extensive experiments for 3 model series across 13 benchmarks demonstrate that MoDES far outperforms previous approaches. For instance, when skipping 88% experts for Qwen3-VL-MoE-30B-A3B-Instruct, the performance boost is up to 10.67% (97.33% vs. 86.66%). Furthermore, MoDES significantly enhances inference speed, improving the prefilling time by 2.16$\times$ and the decoding time by 1.26$\times$. Our code is available at https://github.com/ModelTC/MoDES.
Read the full abstract
Computer Vision
MF-GCN: A Multi-Frequency Graph Convolutional Network for Tri-Modal Depression Detection Using Eye-Tracking, Facial, and Acoustic Features
Depression is a prevalent global mental health disorder, characterised by persistent low mood and anhedonia. However, it remains underdiagnosed because current diagnostic methods depend heavily on subjective clinical assessments. To enable objective detection, we introduce a gold standard dataset of 103 clinically assessed participants collected through a tripartite data approach which uniquely integrated eye tracking data with audio and video to give a comprehensive representation of depressive symptoms. Eye tracking data quantifies the attentional bias towards negative stimuli that is frequently observed in depressed groups. Audio and video data capture the affective flattening and psychomotor retardation characteristic of depression. Statistical validation confirmed their significant discriminative power in distinguishing depressed from non depressed groups. We address a critical limitation of existing graph-based models that focus on low-frequency information and propose a Multi-Frequency Graph Convolutional Network (MF-GCN). This framework consists of a novel Multi-Frequency Filter Bank Module (MFFBM), which can leverage both low and high frequency signals. Extensive evaluation against traditional machine learning algorithms and deep learning frameworks demonstrates that MF-GCN consistently outperforms baselines. In binary classification, the model achieved a sensitivity of 0.96 and F2 score of 0.94. For the 3 class classification task, the proposed method achieved a sensitivity of 0.79 and specificity of 0.87 and siginificantly suprassed other models. To validate generalizability, the model was also evaluated on the Chinese Multimodal Depression Corpus (CMDC) dataset and achieved a sensitivity of 0.95 and F2 score of 0.96. These results confirm that our trimodal, multi frequency framework effectively captures cross modal interaction for accurate depression detection.
Read the full abstract
Computer Vision
VisPlay: Self-Evolving Vision-Language Models from Images
Reinforcement learning (RL) provides a principled framework for improving Vision-Language Models (VLMs) on complex reasoning tasks. However, existing RL approaches often rely on human-annotated labels or task-specific heuristics to define verifiable rewards, both of which are costly and difficult to scale. We introduce VisPlay, a self-evolving RL framework that enables VLMs to autonomously improve their reasoning abilities using large amounts of unlabeled image data. Starting from a single base VLM, VisPlay assigns the model into two interacting roles: an Image-Conditioned Questioner that formulates challenging yet answerable visual questions, and a Multimodal Reasoner that generates silver responses. These roles are jointly trained with Group Relative Policy Optimization (GRPO), which incorporates diversity and difficulty rewards to balance the complexity of generated questions with the quality of the silver answers. VisPlay scales efficiently across two model families. When trained on Qwen2.5-VL and MiMo-VL, VisPlay achieves consistent improvements in visual reasoning, compositional generalization, and hallucination reduction across eight benchmarks, including MM-Vet and MMMU, demonstrating a scalable path toward self-evolving multimodal intelligence. The project page is available at https://bruno686.github.io/VisPlay/
Read the full abstract
Computer Vision
GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI
Geospatial Foundation Models (GeoFMs) are transforming Earth Observation (EO), but evaluation lacks standardized protocols. GEO-Bench-2 addresses this with a comprehensive framework spanning classification, segmentation, regression, object detection, and instance segmentation across 19 permissively-licensed datasets. We introduce ”capability” groups to rank models on datasets that share common characteristics (e.g., resolution, bands, temporality). This enables users to identify which models excel in each capability and determine which areas need improvement in future work. To support both fair comparison and methodological innovation, we define a prescriptive yet flexible evaluation protocol. This not only ensures consistency in benchmarking but also facilitates research into model adaptation strategies, a key and open challenge in advancing GeoFMs for downstream tasks. Our experiments show that no single model dominates across all tasks, confirming the specificity of the choices made during architecture design and pretraining. While models pretrained on natural images (ConvNext ImageNet, DINO V3) excel on high-resolution tasks, EO-specific models (TerraMind, Prithvi, and Clay) outperform them on multispectral applications such as agriculture and disaster response. These findings demonstrate that optimal model choice depends on task requirements, data modalities, and constraints. This shows that the goal of a single GeoFM model that performs well across all tasks remains open for future research. GEO-Bench-2 enables informed, reproducible GeoFM evaluation tailored to specific use cases. Code, data, and leaderboard for GEO-Bench-2 are publicly released under a permissive license.
Read the full abstract
Computer Vision
INQUIRE-Search: Interactive Discovery in Large-Scale Biodiversity Databases
Many ecological questions center on complex phenomena, such as species interactions, behaviors, phenology, and responses to disturbance, that are inherently difficult to observe and sparsely documented. Community science platforms such as iNaturalist contain hundreds of millions of biodiversity images, which often contain evidence of these complex phenomena. However, current workflows that seek to discover and analyze this evidence often rely on manual inspection, leaving this information largely inaccessible at scale. We introduce INQUIRE-Search, an open-source system that uses natural language to enable scientists to rapidly search within an ecological image database like iNaturalist for specific phenomena, verify and export relevant observations, and use these outputs for downstream scientific analysis. Across five illustrative case studies, INQUIRE-Search concentrates relevant observations 3-25x more efficiently than comparable manual inspection budgets. These examples demonstrate how the system can be used for ecological inference, from analyzing seasonal variation in behavior across species to forest regrowth after wildfires. These examples illustrate a new paradigm for interactive, efficient, and scalable scientific discovery that can begin to unlock previously inaccessible scientific value in large-scale biodiversity datasets. Finally, we highlight how AI-enabled discovery tools for science require reframing aspects of the scientific process, including experiment design, data collection, survey effort, and uncertainty analysis.
Read the full abstract
Computer Vision
FDIO: Frequency Decomposed Inertial Odometry
Pedestrian inertial odometry (PIO) estimates autonomous pedestrian motion using only acceleration and angular velocity measurements collected by an inertial measurement unit (IMU), making it highly valuable for consumer level localization applications. However, under a dual device acquisition setting, IMU signals collected by a freely carried mobile device are inherently composite signals in which the global motion of the human torso is coupled with perturbations induced by local limb motion. This coupling makes accurate human motion modeling more challenging. To address this issue, this paper proposes frequency decomposed inertial odometry (FDIO). The proposed method first decomposes input IMU signals into low frequency and high frequency components using a Laplacian pyramid. It then adopts a Mamba module to model long range motion information from the low frequency component and uses a multi scale convolution module to extract fine grained local dynamic features from the high frequency component. Experiments on five public PIO datasets show that FDIO achieves an average absolute trajectory error of 3.221~m and an average relative trajectory error of 2.550~m, reducing the errors by 33.3% and 16.7% compared with the RoNIN ResNet baseline, respectively. These results validate the effectiveness of the proposed frequency decomposition strategy. To the best of our knowledge, this work is among the first efforts to introduce Mamba and a frequency decomposition architecture into inertial odometry.