Authors: X. Gao, C. Chien, G. Liu, A. Manullang
Abstract: This work is corresponding to the Gastro Competition for multi-label classification from capsule endoscopic videos (CEV). Deep learning network based on Transformers are fined-tune for this task. The based online mode is Google Vision Transformer (ViT) batch16 with 224 x 224 resolutions. In total, 17 labels are classified, which are mouth, esophagus, stomach, small intestine, colon, z-line, pylorus, ileocecal valve, active bleeding, angiectasia, blood, erosion, erythema, hematin, lymphangioectasis, polyp, and ulcer. For test dataset of three videos, the overall mAP @0.5 is 0.0205 whereas the overall mAP @0.95 is 0.0196.
Authors: Naichuan Zheng, Hailun Xia, Zepeng Sun, Weiyi Li, Yujia Wang
Abstract: Skeleton-based action recognition is crucial for multimedia applications but heavily relies on power-hungry Artificial Neural Networks (ANNs), limiting their deployment on resource-constrained edge devices. Spiking Neural Networks (SNNs) provide an energy-efficient alternative; however, existing spiking models for skeleton data often compromise the intrinsic sparsity of SNNs by resorting to dense matrix aggregations, heavy multimodal fusion modules, or non-sparse frequency domain transformations. Furthermore, they severely suffer from the short-term amnesia of spiking neurons. In this paper, we propose the Spiking State-Space Topology Transformer (S3T-Former), which, to the best of our knowledge, is the first purely spike-driven Transformer architecture specifically designed for energy-efficient skeleton action recognition. Rather than relying on heavy fusion overhead, we formulate a Multi-Stream Anatomical Spiking Embedding (M-ASE) that acts as a generalized kinematic differential operator, elegantly transforming multimodal skeleton features into heterogeneous, highly sparse event streams. To achieve true topological and temporal sparsity, we introduce Lateral Spiking Topology Routing (LSTR) for on-demand conditional spike propagation, and a Spiking State-Space (S3) Engine to systematically capture long-range temporal dynamics without non-sparse spectral workarounds. Extensive experiments on multiple large-scale datasets demonstrate that S3T-Former achieves highly competitive accuracy while theoretically reducing energy consumption compared to classic ANNs, establishing a new state-of-the-art for energy-efficient neuromorphic action recognition.
Authors: Wuqi Wang, Haochen Yang, Baolu Li, Jiaqi Sun, Xiangmo Zhao, Zhigang Xu, Qing Guo, Haigen Min, Tianyun Zhang, Hongkai Yu
Abstract: The low-light conditions are challenging to the vision-centric perception systems for autonomous driving in the dark environment. In this paper, we propose a new benchmark dataset (named DarkDriving) to investigate the low-light enhancement for autonomous driving. The existing real-world low-light enhancement benchmark datasets can be collected by controlling various exposures only in small-ranges and static scenes. The dark images of the current nighttime driving datasets do not have the precisely aligned daytime counterparts. The extreme difficulty to collect a real-world day and night aligned dataset in the dynamic driving scenes significantly limited the research in this area. With a proposed automatic day-night Trajectory Tracking based Pose Matching (TTPM) method in a large real-world closed driving test field (area: 69 acres), we collected the first real-world day and night aligned dataset for autonomous driving in the dark environment. The DarkDriving dataset has 9,538 day and night image pairs precisely aligned in location and spatial contents, whose alignment error is in just several centimeters. For each pair, we also manually label the object 2D bounding boxes. DarkDriving introduces four perception related tasks, including low-light enhancement, generalized low-light enhancement, and low-light enhancement for 2D detection and 3D detection of autonomous driving in the dark environment. The experimental results show that our DarkDriving dataset provides a comprehensive benchmark for evaluating low-light enhancement for autonomous driving and it can also be generalized to enhance dark images and promote detection in some other low-light driving environment, such as nuScenes.
Authors: Wei Tang, Xuejing Liu, Yanpeng Sun, Zechao Li
Abstract: The Segment Anything Model (SAM) excels at general image segmentation but has limited ability to understand natural language, which restricts its direct application in Referring Expression Segmentation (RES). Toward this end, we propose SSP-SAM, a framework that fully utilizes SAM's segmentation capabilities by integrating a Semantic-Spatial Prompt (SSP) encoder. Specifically, we incorporate both visual and linguistic attention adapters into the SSP encoder, which highlight salient objects within the visual features and discriminative phrases within the linguistic features. This design enhances the referent representation for the prompt generator, resulting in high-quality SSPs that enable SAM to generate precise masks guided by language. Although not specifically designed for Generalized RES (GRES), where the referent may correspond to zero, one, or multiple objects, SSP-SAM naturally supports this more flexible setting without additional modifications. Extensive experiments on widely used RES and GRES benchmarks confirm the superiority of our method. Notably, our approach generates segmentation masks of high quality, achieving strong precision even at strict thresholds such as Pr@0.9. Further evaluation on the PhraseCut dataset demonstrates improved performance in open-vocabulary scenarios compared to existing state-of-the-art RES methods. The code and checkpoints are available at: https://github.com/WayneTomas/SSP-SAM.
Authors: Thomas Duboudin, Xavier Fontaine, Etienne Andrier, Lionel Guillou, Alexandre Filiot, Thalyssa Baiocco-Rodrigues, Antoine Olivier, Alberto Romagnoni, John Klein, Jean-Baptiste Schiratti
Abstract: Computational pathology has made significant progress in recent years, fueling advances in both fundamental disease understanding and clinically ready tools. This evolution is driven by the availability of large amounts of digitized slides and specialized deep learning methods and models. Multiple self-supervised foundation feature extractors have been developed, enabling downstream predictive applications from cell segmentation to tumor sub-typing and survival analysis. In contrast, generative foundation models designed specifically for histopathology remain scarce. Such models could address tasks that are beyond the capabilities of feature extractors, such as virtual staining. In this paper, we introduce CytoSyn, a state-of-the-art foundation latent diffusion model that enables the guided generation of highly realistic and diverse histopathology H&E-stained images, as shown in an extensive benchmark. We explored methodological improvements, training set scaling, sampling strategies and slide-level overfitting, culminating in the improved CytoSyn-v2, and compared our work to PixCell, a state-of-the-art model, in an in-depth manner. This comparison highlighted the strong sensitivity of both diffusion models and performance metrics to preprocessing-specific details such as JPEG compression. Our model has been trained on a dataset obtained from more than 10,000 TCGA diagnostic whole-slide images of 32 different cancer types. Despite being trained only on oncology slides, it maintains state-of-the-art performance generating inflammatory bowel disease images. To support the research community, we publicly release CytoSyn's weights, its training and validation datasets, and a sample of synthetic images in this repository: https://huggingface.co/Owkin-Bioptimus/CytoSyn.
Authors: Chen Zhao, Zhuoran Wang, Haoyang Li, Shifeng Bao, Guanlin Li, Youhe Feng, Yang Li, Jie Tang, Jing Zhang
Abstract: Vision-Language-Action (VLA) models have recently demonstrated strong performance across embodied tasks. Modern VLAs commonly employ diffusion action experts to efficiently generate high-precision continuous action chunks, while auto-regressive generation can be slower and less accurate at low-level control. Yet auto-regressive paradigms still provide complementary priors that can improve robustness and generalization in out-of-distribution environments. To leverage both paradigms, we propose Action-Draft-and-Verify (ADV): diffusion action expert drafts multiple candidate action chunks, and the VLM selects one by scoring all candidates in a single forward pass with a perplexity-style metric. Under matched backbones, training data, and action-chunk length, ADV improves success rate by +4.3 points in simulation and +19.7 points in real-world over diffusion-based baseline, with a single-pass VLM reranking overhead.
Authors: Haoxiang Rao, Zhao Wang, Chenyang Si, Yan Lyu, Yuanyi Duan, Fang Zhao, Caifeng Shan
Abstract: Industrial anomaly detection (AD) is characterized by an abundance of normal images but a scarcity of anomalous ones. Although numerous few-shot anomaly synthesis methods have been proposed to augment anomalous data for downstream AD tasks, most existing approaches require time-consuming training and struggle to learn distributions that are faithful to real anomalies, thereby restricting the efficacy of AD models trained on such data. To address these limitations, we propose a training-free few-shot anomaly generation method, namely O2MAG, which leverages the self-attention in One reference anomalous image to synthesize More realistic anomalies, supporting effective downstream anomaly detection. Specifically, O2MAG manipulates three parallel diffusion processes via self-attention grafting and incorporates the anomaly mask to mitigate foreground-background query confusion, synthesizing text-guided anomalies that closely adhere to real anomalous distributions. To bridge the semantic gap between the encoded anomaly text prompts and the true anomaly semantics, Anomaly-Guided Optimization is further introduced to align the synthesis process with the target anomalous distribution, steering the generation toward realistic and text-consistent anomalies. Moreover, to mitigate faint anomaly synthesis inside anomaly masks, Dual-Attention Enhancement is adopted during generation to reinforce both self- and cross-attention on masked regions. Extensive experiments validate the effectiveness of O2MAG, demonstrating its superior performance over prior state-of-the-art methods on downstream AD tasks.
Authors: Sooyoung Ryu, Mathieu Salzmann, Saqib Javed
Abstract: Post-training quantization (PTQ) is a practical path to deploy large diffusion models, but quantization noise can accumulate over the denoising trajectory and degrade generation quality. We propose Q-Drift, a principled sampler-side correction that treats quantization error as an implicit stochastic perturbation on each denoising step and derives a marginal-distribution-preserving drift adjustment. Q-Drift estimates a timestep-wise variance statistic from calibration, in practice requiring as few as 5 paired full-precision/quantized calibration runs. The resulting sampler correction is plug-and-play with common samplers, diffusion models, and PTQ methods, while incurring negligible overhead at inference. Across six diverse text-to-image models (spanning DiT and U-Net), three samplers (Euler, flow-matching, DPM-Solver++), and two PTQ methods (SVDQuant, MixDQ), Q-Drift improves FID over the corresponding quantized baseline in most settings, with up to 4.59 FID reduction on PixArt-Sigma (SVDQuant W3A4), while preserving CLIP scores.
Authors: Mohammed Rahman Sherif Khan Mohammad, Ardhendu Behera, Sandip Pradhan, Swagat Kumar, Amr Ahmed
Abstract: Recent adapter-based CLIP tuning (e.g., Tip-Adapter) is a strong few-shot learner, achieving efficiency by caching support features for fast prototype matching. However, these methods rely on global uni-modal feature vectors, overlooking fine-grained patch relations and their structural alignment with class text. To bridge this gap without incurring inference costs, we introduce a novel asymmetric training-only framework. Instead of altering the lightweight adapter, we construct a high-capacity auxiliary Heterogeneous Graph Teacher that operates solely during training. This teacher (i) integrates multi-scale visual patches and text prompts into a unified graph, (ii) performs deep cross-modal reasoning via a Modality-aware Graph Transformer (MGT), and (iii) applies discriminative node filtering to extract high-fidelity class features. Crucially, we employ a cache-aware dual-objective strategy to supervise this relational knowledge directly into the Tip-Adapter's key-value cache, effectively upgrading the prototypes while the graph teacher is discarded at test time. Thus, inference remains identical to Tip-Adapter with zero extra latency or memory. Across standard 1-16-shot benchmarks, our method consistently establishes a new state-of-the-art. Ablations confirm that the auxiliary graph supervision, text-guided reasoning, and node filtering are the essential ingredients for robust few-shot adaptation. Code is available at https://github.com/MR-Sherif/TOGA.git.
Authors: Xiao-Chang Liu, Johan Wagemans
Abstract: Image aesthetic assessment (IAA) aims to predict the aesthetic quality of images as perceived by humans. While recent IAA models achieve strong predictive performance, they offer little insight into the factors driving their predictions. Yet for users, understanding why an image is considered pleasing or not is as valuable as the score itself, motivating growing interest in interpretability within IAA. When humans evaluate aesthetics, they naturally rely on high-level cues to justify their judgments. Motivated by this observation, we propose an interpretable IAA framework grounded in human-understandable aesthetic concepts. We learn these concepts in an accessible manner, constructing a subspace that forms the foundation of an inherently interpretable model. To capture nuanced influences on aesthetic perception beyond explicit concepts, we introduce a simple yet effective residual predictor. Experiments on photographic and artistic datasets demonstrate that our method achieves competitive predictive performance while offering transparent, human-understandable aesthetic judgments.
Authors: Yuhao Dong, Zuyan Liu, Shulin Tian, Yongming Rao, Ziwei Liu
Abstract: Large Language Models (LLMs) have achieved remarkable reliability and advanced capabilities through extended test-time reasoning. However, extending these capabilities to Multi-modal Large Language Models (MLLMs) remains a significant challenge due to a critical scarcity of high-quality, long-chain reasoning data and optimized training pipelines. To bridge this gap, we present a unified multi-agent visual reasoning framework that systematically evolves from our foundational image-centric model, Insight-V, into a generalized spatial-temporal architecture, Insight-V++. We first propose a scalable data generation pipeline equipped with multi-granularity assessment that autonomously synthesizes structured, complex reasoning trajectories across image and video domains without human intervention. Recognizing that directly supervising MLLMs with such intricate data yields sub-optimal results, we design a dual-agent architecture comprising a reasoning agent to execute extensive analytical chains, and a summary agent to critically evaluate and distill final outcomes. While our initial framework utilized Direct Preference Optimization (DPO), its off-policy nature fundamentally constrained reinforcement learning potential. To overcome these limitations, particularly for long-horizon video understanding, Insight-V++ introduces two novel algorithms, ST-GRPO and J-GRPO, which enhance spatial-temporal reasoning and improve evaluative robustness. Crucially, by leveraging reliable feedback from the summary agent, we guide an iterative reasoning path generation process, retraining the entire multi-agent system in a continuous, self-improving loop. Extensive experiments on base models like LLaVA-NeXT and Qwen2.5-VL demonstrate significant performance gains across challenging image and video reasoning benchmarks while preserving strong capabilities on traditional perception-focused tasks.
Authors: Mohammad Qazim Bhat, Yufan Huang, Niket Agarwal, Hao Wang, Michael Woods, John Kenyon, Tsung-Yi Lin, Xiaodong Yang, Ming-Yu Liu, Kevin Xie
Abstract: The rapid growth of ego-centric dashcam footage presents a major challenge for detecting safety-critical events such as collisions and near-collisions, scenarios that are brief, rare, and difficult for generic vision models to capture. While multimodal large language models (MLLMs) demonstrate strong general reasoning ability, they underperform in driving contexts due to domain and temporal misalignment. We introduce VLM-AutoDrive, a modular post-training framework for adapting pretrained Vision-Language Models (VLMs) to high-fidelity anomaly detection. The framework integrates metadata-derived captions, LLM-generated descriptions, visual question answering (VQA) pairs, and chain-of-thought (CoT) reasoning supervision to enable domain-aligned and interpretable learning. Off-the-shelf VLMs such as NVIDIA's Cosmos-Reason1 7B (CR1) exhibit near-zero Collision recall in zero-shot settings; fine-tuning with VLM-AutoDrive improves Collision F1 from 0.00 to 0.69 and overall accuracy from 35.35% to 77.27%. VLM-AutoDrive offers a scalable recipe for adapting general-purpose VLMs to safety-critical, temporally localized perception tasks. Evaluated on real-world Nexar dashcam videos, it achieves substantial gains in Collision and Near-Collision detection while producing interpretable reasoning traces, bridging the gap between perception, causality, and decision reasoning in autonomous driving.
Authors: Alexander Rasch, Rahul Rajendra Pai
Abstract: Micromobility is a growing mode of transportation, raising new challenges for traffic safety and planning due to increased interactions in areas where vulnerable road users (VRUs) share the infrastructure with micromobility, including parked micromobility vehicles (MMVs). Approaches to support traffic safety and planning increasingly rely on detecting road users in images -- a computer-vision task relying heavily on the quality of the images to train on. However, existing open image datasets for training such models lack focus and diversity in VRUs and MMVs, for instance, by categorizing both pedestrians and MMV riders as "person", or by not including new MMVs like e-scooters. Furthermore, datasets are often captured from a car perspective and lack data from areas where only VRUs travel (sidewalks, cycle paths). To help close this gap, we introduce the MicroVision dataset: an open image dataset and annotations for training and evaluating models for detecting the most common VRUs (pedestrians, cyclists, e-scooterists) and stationary MMVs (bicycles, e-scooters), from a VRU perspective. The dataset, recorded in Gothenburg (Sweden), consists of more than 8,000 anonymized, full-HD images with more than 30,000 carefully annotated VRUs and MMVs, captured over an entire year and part of almost 2,000 unique interaction scenes. Along with the dataset, we provide first benchmark object-detection models based on state-of-the-art architectures, which achieved a mean average precision of up to 0.723 on an unseen test set. The dataset and model can support traffic safety to distinguish between different VRUs and MMVs, or help monitoring systems identify the use of micromobility. The dataset and model weights can be accessed at https://doi.org/10.71870/eepz-jd52.
Authors: Guillem Casadesus Vila, Adam Dai, Grace Gao
Abstract: Navigation and mapping on the lunar surface require robust perception under challenging conditions, including poorly textured environments, high-contrast lighting, and limited computational resources. This paper presents a real-time mapping framework that integrates dense perception models with a 3D Gaussian Splatting (3DGS) representation. We first benchmark several models on synthetic datasets generated with the LuPNT simulator, selecting a stereo dense depth estimation model based on Gated Recurrent Units for its balance of speed and accuracy in depth estimation, and a convolutional neural network for its superior performance in detecting semantic segments. Using ground truth poses to decouple the local scene understanding from the global state estimation, our pipeline reconstructs a 120-meter traverse with a geometric height accuracy of approximately 3 cm, outperforming a traditional point cloud baseline without LiDAR. The resulting 3DGS map enables novel view synthesis and serves as a foundation for a full SLAM system, where its capacity for joint map and pose optimization would offer significant advantages. Our results demonstrate that combining semantic segmentation and dense depth estimation with learned map representations is an effective approach for creating detailed, large-scale maps to support future lunar surface missions.
Authors: Tamer Shanableh
Abstract: Neural Representations for Videos (NeRV) encode entire video sequences within neural network parameters, offering an alternative paradigm to conventional video codecs. However, the convolutional decoder of NeRV remains computationally expensive and memory intensive, limiting its deployment in resource-constrained environments. This paper proposes LRConv-NeRV, an efficient NeRV variant that replaces selected dense 3x3 convolutional layers with structured low-rank separable convolutions, trained end-to-end within the decoder architecture. By progressively applying low-rank factorization from the largest to earlier decoder stages, LRConv-NeRV enables controllable trade-offs between reconstruction quality and efficiency. Extensive experiments demonstrate that applying LRConv only to the final decoder stage reduces decoder complexity by 68%, from 201.9 to 64.9 GFLOPs, and model size by 9.3%, while incurring negligible quality loss and achieving approximately 9.2% bitrate reduction. Under INT8 post-training quantization, LRConv-NeRV preserves reconstruction quality close to the dense NeRV baseline, whereas more aggressive factorization of early decoder stages leads to disproportionate quality degradation. Compared to existing work under layer-aligned settings, LRConv-NeRV achieves a more favorable efficiency versus quality trade-off, offering substantial GFLOPs and parameter reductions while maintaining higher PSNR/MS-SSIM and improved temporal stability. Temporal flicker analysis using LPIPS further shows that the proposed solution preserves temporal coherence close to the NeRV baseline, results establish LRConv-NeRV as a potential architectural alternative for efficient neural video decoding under low-precision and resource-constrained settings.
Authors: Marios Krestenitis, Christos Tzelepis, Konstantinos Ioannidis, Steafanos Vrochidis, Ioannis Kompatsiaris, Georgios Tzimiropoulos, Shaogang Gong, Ioannis Patras
Abstract: Visual-Language Models (VLMs) have achieved remarkable progress in image captioning, visual question answering, and visual reasoning. Yet they remain prone to vision-language misalignment, often producing overly generic or hallucinated descriptions. Existing approaches address this via instruction tuning-requiring costly, large-scale annotated datasets or via complex test-time frameworks for caption refinement. In this work, we revisit image-text alignment through the lens of cycle consistency: given an image and a caption generated by an image-to-text model, the backward mapping through a text-to-image model should reconstruct an image that closely matches the original. In our setup, a VLM serves as the image-to-text component, while a pre-trained text-to-image model closes the loop by reconstructing the image from the generated caption. Building on this, we introduce CycleCap, a fine-tuning scheme to improve image captioning using Group Relative Policy Optimization (GRPO) with a reward based on the similarity between the original and reconstructed images, computed on-the-fly. Unlike previous work that uses cycle consistency loss for preference dataset construction, our method leverages cycle consistency directly as a self-supervised training signal. This enables the use of raw images alone, eliminating the need for curated image-text datasets, while steering the VLM to produce more accurate and grounded text descriptions. Applied to four VLMs ranging from 1B to 7B parameters, CycleCap yields consistent improvements across captioning and hallucination benchmarks, surpassing state-of-the-art methods that rely on supervised cycle consistency training.
Authors: Devjyoti Chakraborty, Zaki Sukma, Rakandhiya D. Rachmanto, Kriti Ghosh, In Kee Kim, Suchendra M. Bhandarkar, Lakshmish Ramaswamy, Nancy K. O'Hare, Deepak Mishra
Abstract: Neural Radiance Fields (NeRF) have emerged as a powerful approach for photorealistic 3D reconstruction from multi-view images. However, deploying NeRF for satellite imagery remains challenging. Each scene requires individual training, and optimizing architectures via Neural Architecture Search (NAS) demands hours to days of GPU time. While existing approaches focus on architectural improvements, our SHAP analysis reveals that multi-view consistency, rather than model architecture, determines reconstruction quality. Based on this insight, we develop PreSCAN, a predictive framework that estimates NeRF quality prior to training using lightweight geometric and photometric descriptors. PreSCAN selects suitable architectures in < 30 seconds with < 1 dB prediction error, achieving 1000$\times$ speedup over NAS. We further demonstrate PreSCAN's deployment utility on edge platforms (Jetson Orin), where combining its predictions with offline cost profiling reduces inference power by 26% and latency by 43% with minimal quality loss. Experiments on DFC2019 datasets confirm that PreSCAN generalizes across diverse satellite scenes without retraining.
Authors: Md Hasibul Husain Hisham, Shireen Elhabian, Ganesh Adluru, Jason Mendes, Andrew Arai, Eugene Kholmovski, Ravi Ranjan, Edward DiBella
Abstract: Accelerated 3D late gadolinium enhancement (LGE) MRI requires robust reconstruction methods to recover thin atrial structures from undersampled k-space data. While unrolled model-based networks effectively integrate physics-driven data consistency with learned priors, they operate at the acquired resolution and may fail to fully recover high-frequency detail. We propose a hybrid unrolled reconstruction framework in which an Enhanced Deep Super-Resolution (EDSR) network replaces the proximal operator within each iteration of the optimization loop, enabling joint super-resolution enhancement and data consistency enforcement. The model is trained end-to-end on retrospectively undersampled preclinical 3D LGE datasets and compared against compressed sensing, Model-Based Deep Learning (MoDL), and self-guided Deep Image Prior (DIP) baselines. Across acceleration factors, the proposed method consistently improves PSNR and SSIM over standard unrolled reconstruction and better preserves fine cardiac structures, leading to improved LA (left atrium) segmentation performance. These results demonstrate that integrating super-resolution priors directly within model-based reconstruction provides measurable gains in accelerated 3D LGE MRI.
Authors: Bo-Cheng Qiu, Yu-Fan Lin, Yu-Zhe Pien, Chia-Ming Lee, Fu-En Yang, Yu-Chiang Frank Wang, Chih-Chung Hsu
Abstract: Capsule endoscopy event detection is challenging because diagnostically relevant findings are sparse, visually heterogeneous, and embedded in long, noisy video streams, while evaluation is performed at the event level rather than by frame accuracy alone. We therefore formulate the RARE-VISION task as a metric-aligned event detection problem instead of a purely frame-wise classification task. Our framework combines two complementary backbones, EndoFM-LV for local temporal context and DINOv3 ViT-L/16 for strong frame-level visual semantics, followed by a Diverse Head Ensemble, Validation-Guided Hierarchical Fusion, and Anatomy-Aware Temporal Event Decoding. The fusion stage uses validation-derived class-wise model weighting, backbone weighting, and probability calibration, while the decoding stage applies temporal smoothing, anatomical constraints, threshold refinement, and per-label event generation to produce stable event predictions. Validation ablations indicate that complementary backbones, validation-guided fusion, and anatomy-aware temporal decoding all contribute to event-level performance. On the official hidden test set, the proposed method achieved an overall temporal mAP@0.5 of 0.3530 and temporal mAP@0.95 of 0.3235.
Authors: Rui Hong, Shuxue Quan
Abstract: When VLMs answer correctly, do they genuinely rely on visual information or exploit language shortcuts? We introduce the Tri-Layer Diagnostic Framework, which disentangles hallucination sources via three metrics: Latent Anomaly Detection (perceptual awareness), Visual Necessity Score (visual dependency, measured via KL divergence), and Competition Score (conflict between visual grounding and instruction following). Using counterfactual interventions (blind, noise, and conflict images) across 7 VLMs and 7,000 model-sample pairs, our taxonomy reveals that 69.6% of samples exhibit Visual Sycophancy--models detect visual anomalies but hallucinate to satisfy user expectations--while zero samples show Robust Refusal, indicating alignment training has systematically suppressed truthful uncertainty acknowledgment. A scaling analysis (Qwen2.5-VL 7B to 72B) shows larger models reduce Language Shortcuts but amplify Visual Sycophancy, demonstrating scale alone cannot resolve the grounding problem. Diagnostic scores further enable a post-hoc selective prediction strategy achieving up to +9.5pp accuracy at 50% coverage with no additional training cost.
Authors: Oleksii Nasypanyi, Francois Rameau
Abstract: Keypoint matching can be slow and unreliable in challenging conditions such as repetitive textures or wide-baseline views. In such cases, known geometric relations (e.g., the fundamental matrix) can be used to restrict potential correspondences to a narrow epipolar envelope, thereby reducing the search space and improving robustness. These epipolar-guided matching approaches have proved effective in tasks such as SfM; however, most rely on coarse spatial binning, which introduces approximation errors, requires costly post-processing, and may miss valid correspondences. We address these limitations with an exact formulation that performs candidate selection directly in angular space. In our approach, each keypoint is assigned a tolerance circle which, when viewed from the epipole, defines an angular interval. Matching then becomes a 1D angular interval query, solved efficiently in logarithmic time with a segment tree. This guarantees pixel-level tolerance, supports per-keypoint control, and removes unnecessary descriptor comparisons. Extensive evaluation on ETH3D demonstrates noticeable speedups over existing approaches while recovering exact correspondence sets.
Authors: Yonghan Lee, Dinesh Manocha
Abstract: We present Inst4DGS, an instance-decomposed 4D Gaussian Splatting (4DGS) approach with long-horizon per-Gaussian trajectories. While dynamic 4DGS has advanced rapidly, instance-decomposed 4DGS remains underexplored, largely due to the difficulty of associating inconsistent instance labels across independently segmented multi-view videos. We address this challenge by introducing per-video label-permutation latents that learn cross-video instance matches through a differentiable Sinkhorn layer, enabling direct multi-view supervision with consistent identity preservation. This explicit label alignment yields sharp decision boundaries and temporally stable identities without identity drift. To further improve efficiency, we propose instance-decomposed motion scaffolds that provide low-dimensional motion bases per object for long-horizon trajectory optimization. Experiments on Panoptic Studio and Neural3DV show that Inst4DGS jointly supports tracking and instance decomposition while achieving state-of-the-art rendering and segmentation quality. On the Panoptic Studio dataset, Inst4DGS improves PSNR from 26.10 to 28.36, and instance mIoU from 0.6310 to 0.9129, over the strongest baseline.
Authors: Yang Liu, Jiyao Yang, Hongjin Zhao, Xiaoyong Li, Yanzhe Ji, Xingjian Li, Runmin Jiang, Tianyang Wang, Saeed Anwar, Dongwoo Kim, Yue Yao, Zhenyue Qin, Min Xu
Abstract: Large vision-language models (LVLMs) demonstrate strong performance in dermatology; however, evaluating diagnostic reasoning for rare conditions remains largely unexplored. Existing benchmarks focus on common diseases and assess only final accuracy, overlooking the clinical reasoning process, which is critical for complex cases. We address this gap by constructing DermCase, a long-context benchmark derived from peer-reviewed case reports. Our dataset contains 26,030 multi-modal image-text pairs and 6,354 clinically challenging cases, each annotated with comprehensive clinical information and step-by-step reasoning chains. To enable reliable evaluation, we establish DermLIP-based similarity metrics that achieve stronger alignment with dermatologists for assessing differential diagnosis quality. Benchmarking 22 leading LVLMs exposes significant deficiencies across diagnosis accuracy, differential diagnosis, and clinical reasoning. Fine-tuning experiments demonstrate that instruction tuning substantially improves performance while Direct Preference Optimization (DPO) yields minimal gains. Systematic error analysis further reveals critical limitations in current models' reasoning capabilities.
Authors: Minjun Kim, Jongjin Kim, U Kang
Abstract: How can we accurately quantize a pre-trained model without any data? Quantization algorithms are widely used for deploying neural networks on resource-constrained edge devices. Zero-shot Quantization (ZSQ) addresses the crucial and practical scenario where training data are inaccessible for privacy or security reasons. However, three significant challenges hinder the performance of existing ZSQ methods: 1) noise in the synthetic dataset, 2) predictions based on off-target patterns, and the 3) misguidance by erroneous hard labels. In this paper, we propose SynQ (Synthesis-aware Fine-tuning for Zero-shot Quantization), a carefully designed ZSQ framework to overcome the limitations of existing methods. SynQ minimizes the noise from the generated samples by exploiting a low-pass filter. Then, SynQ trains the quantized model to improve accuracy by aligning its class activation map with the pre-trained model. Furthermore, SynQ mitigates misguidance from the pre-trained model's error by leveraging only soft labels for difficult samples. Extensive experiments show that SynQ provides the state-of-the-art accuracy, over existing ZSQ methods.
Authors: Huy Che, Dinh-Duy Phan, Duc-Khai Lam
Abstract: Collecting and annotating datasets for pixel-level semantic segmentation tasks are highly labor-intensive. Data augmentation provides a viable solution by enhancing model generalization without additional real-world data collection. Traditional augmentation techniques, such as translation, scaling, and color transformations, create geometric variations but fail to generate new structures. While generative models have been employed to extend semantic information of datasets, they often struggle to maintain consistency between the original and generated images, particularly for pixel-level tasks. In this work, we propose a novel synthetic data augmentation pipeline that integrates controllable diffusion models. Our approach balances diversity and reliability data, effectively bridging the gap between synthetic and real data. We utilize class-aware prompting and visual prior blending to improve image quality further, ensuring precise alignment with segmentation labels. By evaluating benchmark datasets such as PASCAL VOC and BDD100K, we demonstrate that our method significantly enhances semantic segmentation performance, especially in data-scarce scenarios, while improving model robustness in real-world applications. Our code is available at \href{https://github.com/chequanghuy/Enhanced-Generative-Data-Augmentation-for-Semantic-Segmentation-via-Stronger-Guidance}{https://github.com/chequanghuy/Enhanced-Generative-Data-Augmentation-for-Semantic-Segmentation-via-Stronger-Guidance}.
URLs: https://github.com/chequanghuy/Enhanced-Generative-Data-Augmentation-for-Semantic-Segmentation-via-Stronger-Guidance, https://github.com/chequanghuy/Enhanced-Generative-Data-Augmentation-for-Semantic-Segmentation-via-Stronger-Guidance
Authors: Yibo Shi, Jungang Li, Linghao Zhang, Zihao Dongfang, Biao Wu, Sicheng Tao, Yibo Yan, Chenxi Qin, Weiting Liu, Zhixin Lin, Hanqian Li, Yu Huang, Song Dai, Yonghua Hei, Yue Ding, Xiang Li, Shikang Wang, Chengdong Xu, Jingqi Liu, Xueying Ma, Zhiwen Zheng, Xiaofei Zhang, Bincheng Wang, Nichen Yang, Jie Wu, Lihua Tian, Chen Li, Xuming Hu
Abstract: Long-horizon GUI agents are a key step toward real-world deployment, yet effective interaction memory under prevailing paradigms remains under-explored. Replaying full interaction sequences is redundant and amplifies noise, while summaries often erase dependency-critical information and traceability. We present AndroTMem, a diagnostic framework for anchored memory in long-horizon Android GUI agents. Its core benchmark, AndroTMem-Bench, comprises 1,069 tasks with 34,473 interaction steps (avg. 32.1 per task, max. 65). We evaluate agents with TCR (Task Complete Rate), focusing on tasks whose completion requires carrying forward critical intermediate state; AndroTMem-Bench is designed to enforce strong step-to-step causal dependencies, making sparse yet essential intermediate states decisive for downstream actions and centering interaction memory in evaluation. Across open- and closed-source GUI agents, we observe a consistent pattern: as interaction sequences grow longer, performance drops are driven mainly by within-task memory failures, not isolated perception errors or local action mistakes. Guided by this diagnosis, we propose Anchored State Memory (ASM), which represents interaction sequences as a compact set of causally linked intermediate-state anchors to enable subgoal-targeted retrieval and attribution-aware decision making. Across multiple settings and 12 evaluated GUI agents, ASM consistently outperforms full-sequence replay and summary-based baselines, improving TCR by 5%-30.16% and AMS by 4.93%-24.66%, indicating that anchored, structured memory effectively mitigates the interaction-memory bottleneck in long-horizon GUI tasks. The code, benchmark, and related resources are publicly available at [https://github.com/CVC2233/AndroTMem](https://github.com/CVC2233/AndroTMem).
URLs: https://github.com/CVC2233/AndroTMem](https://github.com/CVC2233/AndroTMem).
Authors: Leyuan Fang, Zan Mao, Zijing Wang, Yinlong Yan
Abstract: Zero-shot object-goal navigation aims to find target objects in unseen environments using only egocentric observation. Recent methods leverage foundation models' comprehension and reasoning capabilities to enhance navigation performance. However, when faced with poor viewpoints or weak semantic cues, foundation models often fail to support reliable reasoning in both perception and planning, resulting in inefficient or failed navigation. We observe that inherent relationships among objects and regions encode structured scene priors, which help agents infer plausible target locations even under partial observations. Motivated by this insight, we propose Spatial Relation-aware Navigation (SR-Nav), a framework that models both observed and experience-based spatial relationships to enhance both perception and planning. Specifically, SR-Nav first constructs a Dynamic Spatial Relationship Graph (DSRG) that encodes the target-centered spatial relationships through the foundation models and updates dynamically with real-time observations. We then introduce a Relation-aware Matching Module. It utilizes relationship matching instead of naive detection, leveraging diverse relationships in the DSRG to verify and correct errors, enhancing visual perception robustness. Finally, we design a Dynamic Relationship Planning Module to reduce the planning search space by dynamically computing the optimal paths based on the DSRG from the current position, thereby guiding planning and reducing exploration redundancy. Experiments on HM3D show that our method achieves state-of-the-art performance in both success rate and navigation efficiency. The code will be publicly available at https://github.com/Mzyw-1314/SR-Nav
Authors: Arushi Rai, Adriana Kovashka
Abstract: Video-LLMs often attend to irrelevant frames, which is especially detrimental for sports coaching tasks requiring precise temporal grounding. Yet obtaining frame-level supervision is challenging: expensive to collect from humans and unreliable from other models. We improve temporal grounding without additional annotations by exploiting the observation that related tasks, such as generation and verification, must attend to the same frames. We enforce this via a self-consistency objective over select visual attention maps of tightly-related tasks. Using VidDiffBench, which provides ground-truth keyframe annotations, we first validate that attention misallocation is a significant bottleneck. We then show that training with our objective yields gains of +3.0%, +14.1% accuracy and +0.9 BERTScore over supervised finetuning across three sports coaching tasks: Exact, FitnessQA, and ExpertAF, even surpassing closed-source models.
Authors: Vahid Monfared, Mohammad Hadi Gharib, Ali Sabri, Maryam Shahali, Farid Rashidi, Amit Mehta, Reza Rawassizadeh
Abstract: Prostate cancer is a leading cause of mortality in men, yet interpretation of T2-weighted prostate MRI remains challenging due to subtle and heterogeneous lesions. We developed an interpretable framework for automatic cancer detection using a small dataset of 162 T2-weighted images (102 cancer, 60 normal), addressing data scarcity through transfer learning and augmentation. We performed a comprehensive comparison of Vision Transformers (ViT, Swin), CNNs (ResNet18), and classical methods (Logistic Regression, SVM, HOG+SVM). Transfer-learned ResNet18 achieved the best performance (90.9% accuracy, 95.2% sensitivity, AUC 0.905) with only 11M parameters, while Vision Transformers showed lower performance despite substantially higher complexity. Notably, HOG+SVM achieved comparable accuracy (AUC 0.917), highlighting the effectiveness of handcrafted features in small datasets. Unlike state-of-the-art approaches relying on biparametric MRI (T2+DWI) and large cohorts, our method achieves competitive performance using only T2-weighted images, reducing acquisition complexity and computational cost. In a reader study of 22 cases, five radiologists achieved a mean sensitivity of 67.5% (Fleiss Kappa = 0.524), compared to 95.2% for the AI model, suggesting potential for AI-assisted screening to reduce missed cancers and improve consistency. Code and data are publicly available.
Authors: Kazuya Nishimura, Ryoma Bise, Shinnosuke Matsuo, Haruka Hirose, Yasuhiro Kojima
Abstract: Estimating slide- and patch-level gene expression profiles from pathology images enables rapid and low-cost molecular analysis with broad clinical impact. Despite strong results, existing approaches treat gene expression as a mere slide- or spot-level signal and do not incorporate the fact that the measured expression arises from the aggregation of underlying cell-level expression. To explicitly introduce this missing cell-resolved guidance, we propose a Cell-type Prototype-informed Neural Network (CPNN) that leverages publicly available single-cell RNA-sequencing datasets. Since single-cell measurements are noisy and not paired with histology images, we first estimate cell-type prototypes-mean expression profiles that reflect stable gene-gene co-variation patterns.CPNN then learns cell-type compositional weights directly from images and models the relationship between prototypes and observed bulk or spatial expression, providing a biologically grounded and structurally regularized prediction framework. We evaluate CPNN on three slide-level datasets and three patch-level spatial transcriptomics datasets. Across all settings, CPNN achieves the highest performance in terms of Spearman correlation. Moreover, by visualizing the inferred compositional weights, our framework provides interpretable insights into which cell types drive the predicted expression. Code is publicly available at https://github.com/naivete5656/CPNN.
Authors: Jiyao Liu, Junzhi Ning, Wanying Qu, Lihao Liu, Chenglong Ma, Junjun He, Ningsheng Xu
Abstract: Existing medical image restoration (Med-IR) methods are typically modality-specific or degradation-specific, failing to generalize across the heterogeneous degradations encountered in clinical practice. We argue this limitation stems from the isolation of Med-IR from medical image quality assessment (Med-IQA), as restoration models without explicit quality understanding struggle to adapt to diverse degradation types across modalities. To address these challenges, we propose MedQ-UNI, a unified vision-language model that follows an assess-then-restore paradigm, explicitly leveraging Med-IQA to guide Med-IR across arbitrary modalities and degradation types. MedQ-UNI adopts a multimodal autoregressive dual-expert architecture with shared attention: a quality assessment expert first identifies degradation issues through structured natural language descriptions, and a restoration expert then conditions on these descriptions to perform targeted image restoration. To support this paradigm, we construct a large-scale dataset of approximately 50K paired samples spanning three imaging modalities and five restoration tasks, each annotated with structured quality descriptions for joint Med-IQA and Med-IR training, along with a 2K-sample benchmark for evaluation. Extensive experiments demonstrate that a single MedQ-UNI model, without any task-specific adaptation, achieves state-of-the-art restoration performance across all tasks while generating superior descriptions, confirming that explicit quality understanding meaningfully improves restoration fidelity and interpretability.
Authors: Yuqi Yang, Dongliang Chang, Yijia Ling, Ruoyi Du, Zhanyu Ma
Abstract: Colour is one of the most perceptually salient yet least controllable attributes in image generation. Although recent diffusion models can modify object colours from user instructions, their results often deviate from the intended hue, especially for fine-grained and local edits. Early text-driven methods rely on discrete language descriptions that cannot accurately represent continuous chromatic variations. To overcome this limitation, we propose ColourCrafter, a unified diffusion framework that transforms colour editing from global tone transfer into a structured, region-aware generation process. Unlike traditional colour driven methods, ColourCrafter performs token-level fusion of RGB colour tokens and image tokens in latent space, selectively propagating colour information to semantically relevant regions while preserving structural fidelity. A perceptual Lab-space Loss further enhances pixel-level precision by decoupling luminance and chrominance and constraining edits within masked areas. Additionally, we build ColourfulSet, a largescale dataset of high-quality image pairs with continuous and diverse colour variations. Extensive experiments demonstrate that ColourCrafter achieves state-of-the-art colour accuracy, controllability and perceptual fidelity in fine-grained colour editing. Our project is available at https://yangyuqi317.github.io/ColourCrafter.github.io/.
URLs: https://yangyuqi317.github.io/ColourCrafter.github.io/.
Authors: Ziyi Wang, Qizan Guo, Rishitosh Singh, Xiyang Hu
Abstract: Inferring human engagement from gameplay video is important for game design and player-experience research, yet it remains unclear whether vision--language models (VLMs) can infer such latent psychological states from visual cues alone. Using the GameVibe Few-Shot dataset across nine first-person shooter games, we evaluate three VLMs under six prompting strategies, including zero-shot prediction, theory-guided prompts grounded in Flow, GameFlow, Self-Determination Theory, and MDA, and retrieval-augmented prompting. We consider both pointwise engagement prediction and pairwise prediction of engagement change between consecutive windows. Results show that zero-shot VLM predictions are generally weak and often fail to outperform simple per-game majority-class baselines. Memory- or retrieval-augmented prompting improves pointwise prediction in some settings, whereas pairwise prediction remains consistently difficult across strategies. Theory-guided prompting alone does not reliably help and can instead reinforce surface-level shortcuts. These findings suggest a perception--understanding gap in current VLMs: although they can recognize visible gameplay cues, they still struggle to robustly infer human engagement across games.
Authors: Aditi Naiknaware, Salimeh Sekeh
Abstract: Out-of-distribution (OOD) detection remains a critical challenge in open-world learning, where models must adapt to evolving data distributions. While recent vision-language models (VLMS) like CLIP enable multimodal OOD detection through Dual-Pattern Matching (DPM), existing methods typically suffer from two major shortcomings: (1) They rely on fixed fusion rules and assume static environments, failing under temporal drift; and (2) they lack robustness against covariate shifted inputs. In this paper, we propose a novel two-step framework to enhance OOD detection and covariate distribution shift robustness in dynamic settings. We extend the dual-pattern regime into Temporal Quadruple-Pattern Matching (T-QPM). First, by pairing OOD images with text descriptions, we introduce cross-modal consistency patterns between ID and OOD signals, refining the decision boundary through joint image-text reasoning. Second, we address temporal distribution shifts by learning lightweight fusion weights to optimally combine semantic matching and visual typicality. To ensure stability, we enforce explicit regularization based on Average Thresholded Confidence (ATC), preventing performance degradation as distributions evolve. Experiments on temporally partitioned benchmarks demonstrate that our approach significantly outperforms static baselines, offering a robust, temporally-consistent framework for multimodal OOD detection in non-stationary environments.
Authors: Bo Zhao, Yihang Liu, Chenfeng Zhang, Huan Yang, Kun Gai, Wei Ji
Abstract: Text-guided texture editing aims to modify object appearance while preserving the underlying geometric structure. However, our empirical analysis reveals that even SOTA editing models frequently struggle to maintain structural consistency during texture editing, despite the intended changes being purely appearance-related. Motivated by this observation, we jointly enhance structure preservation from both data and training perspectives, and build TexEditor, a dedicated texture editing model based on Qwen-Image-Edit-2509. Firstly, we construct TexBlender, a high-quality SFT dataset generated with Blender, which provides strong structural priors for a cold start. Sec- ondly, we introduce StructureNFT, a RL-based approach that integrates structure-preserving losses to transfer the structural priors learned during SFT to real-world scenes. Moreover, due to the limited realism and evaluation coverage of existing benchmarks, we introduce TexBench, a general-purpose real-world benchmark for text-guided texture editing. Extensive experiments on existing Blender-based texture benchmarks and our TexBench show that TexEditor consistently outperforms strong baselines such as Nano Banana Pro. In addition, we assess TexEditor on the general purpose benchmark ImgEdit to validate its generalization. Our code and data are available at https://github.com/KlingAIResearch/TexEditor.
Authors: Seonghyun Jin, Jong Chul Ye
Abstract: Streaming 3D reconstruction maintains a persistent latent state that is updated online from incoming frames, enabling constant-memory inference. A key failure mode is the state update rule: aggressive overwrites forget useful history, while conservative updates fail to track new evidence, and both behaviors become unstable beyond the training horizon. To address this challenge, we propose FILT3R, a training-free latent filtering layer that casts recurrent state updates as stochastic state estimation in token space. FILT3R maintains a per-token variance and computes a Kalman-style gain that adaptively balances memory retention against new observations. Process noise -- governing how much the latent state is expected to change between frames -- is estimated online from EMA-normalized temporal drift of candidate tokens. Using extensive experiments, we demonstrate that FILT3R yields an interpretable, plug-in update rule that generalizes common overwrite and gating policies as special cases. Specifically, we show that gains shrink in stable regimes as uncertainty contracts with accumulated evidence, and rise when genuine scene change increases process uncertainty, improving long-horizon stability for depth, pose, and 3D reconstruction, compared to the existing methods. Code will be released at https://github.com/jinotter3/FILT3R.
Authors: Daniel DeTone, Federica Bogo, Eric-Tuan Le, Duncan Frost, Julian Straub, Yawar Siddiqui, Yuting Ye, Jakob Engel, Richard Newcombe, Lingni Ma
Abstract: The Nymeria Dataset, released in 2024, is a large-scale collection of in-the-wild human activities captured with multiple egocentric wearable devices that are spatially localized and temporally synchronized. It provides body-motion ground truth recorded with a motion-capture suit, device trajectories, semi-dense 3D point clouds, and in-context narrations. In this paper, we upgrade Nymeria and introduce NymeriaPlus. NymeriaPlus features: (1) improved human motion in Momentum Human Rig (MHR) and SMPL formats; (2) dense 3D and 2D bounding box annotations for indoor objects and structural elements; (3) instance-level 3D object reconstructions; and (4) additional modalities e.g., basemap recordings, audio, and wristband videos. By consolidating these complementary modalities and annotations into a single, coherent benchmark, NymeriaPlus strengthens Nymeria into a more powerful in-the-wild egocentric dataset. We expect NymeriaPlus to bridge a key gap in existing egocentric resources and to support a broader range of research, including unique explorations of multimodal learning for embodied AI.
Authors: Mingde Zhou, Zheng Chen, Yulun Zhang
Abstract: Video compression aims to maximize reconstruction quality with minimal bitrates. Beyond standard distortion metrics, perceptual quality and temporal consistency are also critical. However, at ultra-low bitrates, traditional end-to-end compression models tend to produce blurry images of poor perceptual quality. Besides, existing generative compression methods often treat video frames independently and show limitations in time coherence and efficiency. To address these challenges, we propose the Efficient Video Diffusion with Sparse Information Transmission (Diff-SIT), which comprises the Sparse Temporal Encoding Module (STEM) and the One-Step Video Diffusion with Frame Type Embedder (ODFTE). The STEM sparsely encodes the original frame sequence into an information-rich intermediate sequence, achieving significant bitrate savings. Subsequently, the ODFTE processes this intermediate sequence as a whole, which exploits the temporal correlation. During this process, our proposed Frame Type Embedder (FTE) guides the diffusion model to perform adaptive reconstruction according to different frame types to optimize the overall quality. Extensive experiments on multiple datasets demonstrate that Diff-SIT establishes a new state-of-the-art in perceptual quality and temporal consistency, particularly in the challenging ultra-low-bitrate regime. Code is released at https://github.com/MingdeZhou/Diff-SIT.
Authors: Teerapong Panboonyuen
Abstract: Automated property risk detection is a high-impact yet underexplored frontier in computer vision with direct implications for real estate, underwriting, and insurance operations. We introduce HOMEY (Heuristic Object Masking with Enhanced YOLO), a novel detection framework that combines YOLO with a domain-specific masking mechanism and a custom-designed loss function. HOMEY is trained to detect 17 risk-related property classes, including structural damages (e.g., cracked foundations, roof issues), maintenance neglect (e.g., dead yards, overgrown bushes), and liability hazards (e.g., falling gutters, garbage, hazard signs). Our approach introduces heuristic object masking to amplify weak signals in cluttered backgrounds and risk-aware loss calibration to balance class skew and severity weighting. Experiments on real-world property imagery demonstrate that HOMEY achieves superior detection accuracy and reliability compared to baseline YOLO models, while retaining fast inference. Beyond detection, HOMEY enables interpretable and cost-efficient risk analysis, laying the foundation for scalable AI-driven property insurance workflows.
Authors: Jingzhi Chen, Lijian Xu
Abstract: The protein folding problem has been fundamentally transformed by artificial intelligence, evolving from static structure prediction toward the modeling of dynamic conformational ensembles and complex biomolecular interactions. This review systematically examines the paradigm shift in AI driven protein science across five interconnected dimensions: unified multimodal representations that integrate sequences, geometries, and textual knowledge; refinement of static prediction through MSA free architectures and all atom complex modeling; generative frameworks, including diffusion models and flow matching, that capture conformational distributions consistent with thermodynamic ensembles; prediction of heterogeneous interactions spanning protein ligand, protein nucleic acid, and protein protein complexes; and functional inference of fitness landscapes, mutational effects, and text guided property prediction. We critically analyze current bottlenecks, including data distribution biases, limited mechanistic interpretability, and the disconnect between geometric metrics and biophysical reality, while identifying future directions toward physically consistent generative models, multimodal foundation architectures, and experimental closed loop systems. This methodological transformation marks artificial intelligence's transition from a structural analysis tool into a universal simulator capable of understanding and ultimately rewriting the dynamic language of life.
Authors: Teerapong Panboonyuen
Abstract: This handbook presents a systematic treatment of the foundations and architectures of artificial intelligence for motor insurance, grounded in large-scale real-world deployment. It formalizes a vertically integrated AI paradigm that unifies perception, multimodal reasoning, and production infrastructure into a cohesive intelligence stack for automotive risk assessment and claims processing. At its core, the handbook develops domain-adapted transformer architectures for structured visual understanding, relational vehicle representation learning, and multimodal document intelligence, enabling end-to-end automation of vehicle damage analysis, claims evaluation, and underwriting workflows. These components are composed into a scalable pipeline operating under practical constraints observed in nationwide motor insurance systems in Thailand. Beyond model design, the handbook emphasizes the co-evolution of learning algorithms and MLOps practices, establishing a principled framework for translating modern artificial intelligence into reliable, production-grade systems in high-stakes industrial environments.
Authors: Hongjia Zhai, Qi Zhang, Xiaokun Pan, Xiyu Zhang, Yitong Dong, Huaqi Zhang, Dan Xu, Guofeng Zhang
Abstract: Open-vocabulary scene understanding with online panoptic mapping is essential for embodied applications to perceive and interact with environments. However, existing methods are predominantly offline or lack instance-level understanding, limiting their applicability to real-world robotic tasks. In this paper, we propose OnlinePG, a novel and effective system that integrates geometric reconstruction and open-vocabulary perception using 3D Gaussian Splatting in an online setting. Technically, to achieve online panoptic mapping, we employ an efficient local-to-global paradigm with a sliding window. To build local consistency map, we construct a 3D segment clustering graph that jointly leverages geometric and semantic cues, fusing inconsistent segments within sliding window into complete instances. Subsequently, to update the global map, we construct explicit grids with spatial attributes for the local 3D Gaussian map and fuse them into the global map via robust bidirectional bipartite 3D Gaussian instance matching. Finally, we utilize the fused VLM features inside the 3D spatial attribute grids to achieve open-vocabulary scene understanding. Extensive experiments on widely used datasets demonstrate that our method achieves better performance among online approaches, while maintaining real-time efficiency.
Authors: Elad Yoshai, Ariel D. Yoshai, Natan T. Shaked
Abstract: In digital pathology, whole-slide images routinely exceed gigapixel resolution, making computationally intensive generative super-resolution (SR) impractical for routine deployment. We introduce CAFlow, an adaptive-depth single-step flow-matching framework that routes each image tile to the shallowest network exit that preserves reconstruction quality. CAFlow performs flow matching in pixel-unshuffled rearranged space, reducing spatial computation by 16x while enabling direct inference. We show that dedicating half of training to exact t=0 samples is essential for single-step quality (-1.5 dB without it). The backbone, FlowResNet (1.90M parameters), mixes convolution and window self-attention blocks across four early exits spanning 3.1 to 13.3 GFLOPs. A lightweight exit classifier (~6K parameters) achieves 33% compute savings at only 0.12 dB cost. On multi-organ histopathology x4 SR, adaptive routing achieves 31.72 dB PSNR versus 31.84 dB at full depth, while the shallowest exit exceeds bicubic by +1.9 dB at 2.8x less compute than SwinIR-light. The method generalizes to held-out colon tissue with minimal quality loss (-0.02 dB), and at x8 upscaling it outperforms all comparable-compute baselines while remaining competitive with the much larger SwinIR-Medium model. Downstream nuclei segmentation confirms preservation of clinically relevant structure. The model trains in under 5 hours on a single GPU, and adaptive routing can reduce whole-slide inference from minutes to seconds.
Authors: Liwei Che, Zhiyu Xue, Yihao Quan, Benlin Liu, Zeru Shi, Michelle Hurst, Jacob Feldman, Ruixiang Tang, Ranjay Krishna, Vladimir Pavlovic
Abstract: Counting serves as a simple but powerful test of a Large Vision-Language Model's (LVLM's) reasoning; it forces the model to identify each individual object and then add them all up. In this study, we investigate how LVLMs implement counting using controlled synthetic and real-world benchmarks, combined with mechanistic analyses. Our results show that LVLMs display a human-like counting behavior, with precise performance on small numerosities and noisy estimation for larger quantities. We introduce two novel interpretability methods, Visual Activation Patching and HeadLens, and use them to uncover a structured "counting circuit" that is largely shared across a variety of visual reasoning tasks. Building on these insights, we propose a lightweight intervention strategy that exploits simple and abundantly available synthetic images to fine-tune arbitrary pretrained LVLMs exclusively on counting. Despite the narrow scope of this fine-tuning, the intervention not only enhances counting accuracy on in-distribution synthetic data, but also yields an average improvement of +8.36% on out-of-distribution counting benchmarks and an average gain of +1.54% on complex, general visual reasoning tasks for Qwen2.5-VL. These findings highlight the central, influential role of counting in visual reasoning and suggest a potential pathway for improving overall visual reasoning capabilities through targeted enhancement of counting mechanisms.
Authors: Hyun-kyu Ko, Jihyeon Park, Younghyun Kim, Dongheok Park, Eunbyung Park
Abstract: Creating dynamic, view-consistent videos of customized subjects is highly sought after for a wide range of emerging applications, including immersive VR/AR, virtual production, and next-generation e-commerce. However, despite rapid progress in subject-driven video generation, existing methods predominantly treat subjects as 2D entities, focusing on transferring identity through single-view visual features or textual prompts. Because real-world subjects are inherently 3D, applying these 2D-centric approaches to 3D object customization reveals a fundamental limitation: they lack the comprehensive spatial priors necessary to reconstruct the 3D geometry. Consequently, when synthesizing novel views, they must rely on generating plausible but arbitrary details for unseen regions, rather than preserving the true 3D identity. Achieving genuine 3D-aware customization remains challenging due to the scarcity of multi-view video datasets. While one might attempt to fine-tune models on limited video sequences, this often leads to temporal overfitting. To resolve these issues, we introduce a novel framework for 3D-aware video customization, comprising 3DreamBooth and 3Dapter. 3DreamBooth decouples spatial geometry from temporal motion through a 1-frame optimization paradigm. By restricting updates to spatial representations, it effectively bakes a robust 3D prior into the model without the need for exhaustive video-based training. To enhance fine-grained textures and accelerate convergence, we incorporate 3Dapter, a visual conditioning module. Following single-view pre-training, 3Dapter undergoes multi-view joint optimization with the main generation branch via an asymmetrical conditioning strategy. This design allows the module to act as a dynamic selective router, querying view-specific geometric hints from a minimal reference set. Project page: https://ko-lani.github.io/3DreamBooth/
Authors: Yongwei Jiang, Yixiong Zou, Yuhua Li, Ruixuan Li
Abstract: Cross-domain few-shot object detection (CD-FSOD) aims to adapt pretrained detectors from a source domain to target domains with limited annotations, suffering from severe domain shifts and data scarcity problems. In this work, we find a previously overlooked phenomenon: models exhibit dispersed and unfocused attention in target domains, leading to imprecise localization and redundant predictions, just like a human cannot focus on visual objects. Therefore, we call it the target-domain Astigmatism problem. Analysis on attention distances across transformer layers reveals that regular fine-tuning inherently shows a trend to remedy this problem, but results are still far from satisfactory, which we aim to enhance in this paper. Biologically inspired by the human fovea-style visual system, we enhance the fine-tuning's inherent trend through a center-periphery attention refinement framework, which contains (1) a Positive Pattern Refinement module to reshape attention toward semantic objects using class-specific prototypes, simulating the visual center region; (2) a Negative Context Modulation module to enhance boundary discrimination by modeling background context, simulating the visual periphery region; and (3) a Textual Semantic Alignment module to strengthen center-periphery distinction through cross-modal cues. Our bio-inspired approach transforms astigmatic attention into focused patterns, substantially improving adaptation to target domains. Experiments on six challenging CD-FSOD benchmarks consistently demonstrate improved detection accuracy and establish new state-of-the-art results.
Authors: Xiang Chen, Fangfang Yang, Chunlei Meng, Chengyin Hu, Ang Li, Yiwei Wei, Jiahuan Long, Jiujiang Guo
Abstract: Medical vision--language models (MVLMs) are increasingly used as perceptual backbones in radiology pipelines and as the visual front end of multimodal assistants, yet their reliability under real clinical workflows remains underexplored. Prior robustness evaluations often assume clean, curated inputs or study isolated corruptions, overlooking routine acquisition, reconstruction, display, and delivery operations that preserve clinical readability while shifting image statistics. To address this gap, we propose CoDA, a chain-of-distribution framework that constructs clinically plausible pipeline shifts by composing acquisition-like shading, reconstruction and display remapping, and delivery and export degradations. Under masked structural-similarity constraints, CoDA jointly optimizes stage compositions and parameters to induce failures while preserving visual plausibility. Across brain MRI, chest X-ray, and abdominal CT, CoDA substantially degrades the zero-shot performance of CLIP-style MVLMs, with chained compositions consistently more damaging than any single stage. We also evaluate multimodal large language models (MLLMs) as technical-authenticity auditors of imaging realism and quality rather than pathology. Proprietary multimodal models show degraded auditing reliability and persistent high-confidence errors on CoDA-shifted samples, while the medical-specific MLLMs we test exhibit clear deficiencies in medical image quality auditing. Finally, we introduce a post-hoc repair strategy based on teacher-guided token-space adaptation with patch-level alignment, which improves accuracy on archived CoDA outputs. Overall, our findings characterize a clinically grounded threat surface for MVLM deployment and show that lightweight alignment improves robustness in deployment.
Authors: Dan Ben-Ami, Gabriele Serussi, Kobi Cohen, Chaim Baskin
Abstract: Long-form video question answering requires reasoning over extended temporal contexts, making frame selection critical for large vision-language models (LVLMs) bound by finite context windows. Existing methods face a sharp trade-off: similarity-based selectors are fast but collapse compositional queries into a single dense vector, losing sub-event ordering and cross-modal bindings; agent-based methods recover this structure through iterative LVLM inference, but at prohibitive cost. We introduce HiMu, a training-free framework that bridges this gap. A single text-only LLM call decomposes the query into a hierarchical logic tree whose leaves are atomic predicates, each routed to a lightweight expert spanning vision (CLIP, open-vocabulary detection, OCR) and audio (ASR, CLAP). The resulting signals are normalized, temporally smoothed to align different modalities, and composed bottom-up through fuzzy-logic operators that enforce temporal sequencing and adjacency, producing a continuous satisfaction curve. Evaluations on Video-MME, LongVideoBench and HERBench-Lite show that HiMu advances the efficiency-accuracy Pareto front: at 16 frames with Qwen3-VL 8B it outperforms all competing selectors, and with GPT-4o it surpasses agentic systems operating at 32-512 frames while requiring roughly 10x fewer FLOPs.
Authors: Jiacheng Tang, Zhiyuan Zhou, Zhuolin He, Jia Zhang, Kai Zhang, Jian Pu
Abstract: Planning-oriented end-to-end driving models show great promise, yet they fundamentally learn statistical correlations instead of true causal relationships. This vulnerability leads to causal confusion, where models exploit dataset biases as shortcuts, critically harming their reliability and safety in complex scenarios. To address this, we introduce CausalVAD, a de-confounding training framework that leverages causal intervention. At its core, we design the sparse causal intervention scheme (SCIS), a lightweight, plug-and-play module to instantiate the backdoor adjustment theory in neural networks. SCIS constructs a dictionary of prototypes representing latent driving contexts. It then uses this dictionary to intervene on the model's sparse vectorized queries. This step actively eliminates spurious associations induced by confounders, thereby eliminating spurious factors from the representations for downstream tasks. Extensive experiments on benchmarks like nuScenes show CausalVAD achieves state-of-the-art planning accuracy and safety. Furthermore, our method demonstrates superior robustness against both data bias and noisy scenarios configured to induce causal confusion.
Authors: Swarnendu Banik, Manish Das, Shiv Ram Dubey, Satish Kumar Singh
Abstract: Vision Transformers have excelled in computer vision but their attention mechanisms operate independently across layers, limiting information flow and feature learning. We propose an effective cross-layer attention propagation method that preserves and integrates historical attention matrices across encoder layers, offering a principled refinement of inter-layer information flow in Vision Transformers. This approach enables progressive refinement of attention patterns throughout the transformer hierarchy, enhancing feature acquisition and optimization dynamics. The method requires minimal architectural changes, adding only attention matrix storage and blending operations. Comprehensive experiments on CIFAR-100 and TinyImageNet demonstrate consistent accuracy improvements, with ViT performance increasing from 75.74% to 77.07% on CIFAR-100 (+1.33%) and from 57.82% to 59.07% on TinyImageNet (+1.25%). Cross-architecture validation shows similar gains across transformer variants, with CaiT showing 1.01% enhancement. Systematic analysis identifies the blending hyperparameter of historical attention (alpha = 0.45) as optimal across all configurations, providing the ideal balance between current and historical attention information. Random initialization consistently outperforms zero initialization, indicating that diverse initial attention patterns accelerate convergence and improve final performance. Our code is publicly available at https://github.com/banik-s/HAViT.
Authors: Wei Wang, Yakun Li
Abstract: In this paper, we propose and develop a novel nonlocal variational technique based on saturation-value similarity for color image restoration. In traditional nonlocal methods, image patches are extracted from red, green and blue channels of a color image directly, and the color information can not be described finely because the patch similarity is mainly based on the grayscale value of independent channel. The main aim of this paper is to propose and develop a novel nonlocal regularization method by considering the similarity of image patches in saturation-value channel of a color image. In particular, we first establish saturation-value similarity based nonlocal total variation by incorporating saturation-value similarity of color image patches into the proposed nonlocal gradients, which can describe the saturation and value similarity of two adjacent color image patches. The proposed nonlocal variational models are then formulated based on saturation-value similarity based nonlocal total variation. Moreover, we design an effective and efficient algorithm to solve the proposed optimization problem numerically by employing bregmanized operator splitting method, and we also study the convergence of the proposed algorithms. Numerical examples are presented to demonstrate that the performance of the proposed models is better than that of other testing methods in terms of visual quality and some quantitative metrics including peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), quaternion structural similarity index (QSSIM) and S-CIELAB color error.
Authors: Jiahe Wang, Cong Liang, Xuandong Huang, Yuxin Wang, Xin Yun, Yi Wu, Yanan Chang, Shangfei Wang
Abstract: Facial behavior synthesis remains a critical yet underexplored challenge. While text-to-face models have made progress, they often rely on coarse emotion categories, which lack the nuance needed to capture the full spectrum of human nonverbal communication. Action Units (AUs) provide a more precise and anatomically grounded alternative. However, current AU-based approaches typically encode AUs as one-hot vectors, modeling compound expressions as simple linear combinations of individual AUs. This linearity becomes problematic when handling conflicting AUs--defined as those which activate the same facial muscle with opposing actions. Such cases lead to anatomically implausible artifacts and unnatural motion superpositions. To address this, we propose a novel method that represents facial behavior through natural language descriptions of AUs. This approach preserves the expressiveness of the AU framework while enabling explicit modeling of complex and conflicting AUs. It also unlocks the potential of modern text-to-image models for high-fidelity facial synthesis. Supporting this direction, we introduce BP4D-AUText, the first large-scale text-image paired dataset for complex facial behavior. It is synthesized by applying a rule-based Dynamic AU Text Processor to the BP4D and BP4D+ datasets. We further propose VQ-AUFace, a generative model that leverages facial structural priors to synthesize realistic and diverse facial behaviors from text. Extensive quantitative experiments and user studies demonstrate that our approach significantly outperforms existing methods. It excels in generating facial expressions that are anatomically plausible, behaviorally rich, and perceptually convincing, particularly under challenging conditions involving conflicting AUs.
Authors: Ye Kyaw Thu, Thazin Myint Oo, Thepchai Supnithi
Abstract: We present the first systematic benchmark on myMNIST (formerly BHDD), a publicly available Burmese handwritten digit dataset important for Myanmar NLP/AI research. We evaluate eleven architectures spanning classical deep learning models (Multi-Layer Perceptron, Convolutional Neural Network, Long Short-Term Memory, Gated Recurrent Unit, Transformer), recent alternatives (FastKAN, EfficientKAN), an energy-based model (JEM), and physics-inspired PETNN variants (Sigmoid, GELU, SiLU). Using Precision, Recall, F1-Score, and Accuracy as evaluation metrics, our results show that the CNN remains a strong baseline, achieving the best overall scores (F1 = 0.9959, Accuracy = 0.9970). The PETNN (GELU) model closely follows (F1 = 0.9955, Accuracy = 0.9966), outperforming LSTM, GRU, Transformer, and KAN variants. JEM, representing energy-based modeling, performs competitively (F1 = 0.9944, Accuracy = 0.9958). KAN-based models (FastKAN, EfficientKAN) trail the top performers but provide a meaningful alternative baseline (Accuracy ~0.992). These findings (i) establish reproducible baselines for myMNIST across diverse modeling paradigms, (ii) highlight PETNN's strong performance relative to classical and Transformer-based models, and (iii) quantify the gap between energy-inspired PETNNs and a true energy-based model (JEM). We release this benchmark to facilitate future research on Myanmar digit recognition and to encourage broader evaluation of emerging architectures on regional scripts.
Authors: Lu Yu, Haiyang Zhang, Changsheng Xu
Abstract: Due to the impressive zero-shot capabilities, pre-trained vision-language models (e.g., CLIP), have attracted widespread attention and adoption across various domains. Nonetheless, CLIP has been observed to be susceptible to adversarial examples. Through experimental analysis, we have observed a phenomenon wherein adversarial perturbations induce shifts in text-guided attention. Building upon this observation, we propose a simple yet effective strategy: Text-Guided Attention for Zero-Shot Robustness (TGA-ZSR). This framework incorporates two components: Local Attention Refinement Module and Global Attention Constraint Module. Our goal is to maintain the generalization of the CLIP model and enhance its adversarial robustness. Additionally, the Global Attention Constraint Module acquires text-guided attention from both the target and original models using clean examples. Its objective is to maintain model performance on clean samples while enhancing overall robustness. However, we observe that the method occasionally focuses on irrelevant or spurious features, which can lead to suboptimal performance and undermine its robustness in certain scenarios. To overcome this limitation, we further propose a novel approach called Complementary Text-Guided Attention (Comp-TGA). This method integrates two types of foreground attention: attention guided by the class prompt and reversed attention driven by the non-class prompt. These complementary attention mechanisms allow the model to capture a more comprehensive and accurate representation of the foreground. The experiments validate that TGA-ZSR and Comp-TGA yield 9.58% and 11.95% improvements respectively, in zero-shot robust accuracy over the current state-of-the-art techniques across 16 datasets.
Authors: Jialiang Kang, Han Shu, Wenshuo Li, Yingjie Zhai, Xinghao Chen
Abstract: Speculative Jacobi Decoding (SJD) offers a draft-model-free approach to accelerate autoregressive text-to-image synthesis. However, the high-entropy nature of visual generation yields low draft-token acceptance rates in complex regions, creating a bottleneck that severely limits overall throughput. To overcome this, we introduce SJD-PAC, an enhanced SJD framework. First, SJD-PAC employs a proactive drafting strategy to improve local acceptance rates in these challenging high-entropy regions. Second, we introduce an adaptive continuation mechanism that sustains sequence validation after an initial rejection, bypassing the need for full resampling. Working in tandem, these optimizations significantly increase the average acceptance length per step, boosting inference speed while strictly preserving the target distribution. Experiments on standard text-to-image benchmarks demonstrate that SJD-PAC achieves a $3.8\times$ speedup with lossless image quality.
Authors: Bingqi Ma, Linlong Lang, Ming Zhang, Dailan He, Xingtong Ge, Yi Zhang, Guanglu Song, Yu Liu
Abstract: The dual-stream transformer architecture-based joint audio-video generation method has become the dominant paradigm in current research. By incorporating pre-trained video diffusion models and audio diffusion models, along with a cross-modal interaction attention module, high-quality, temporally synchronized audio-video content can be generated with minimal training data. In this paper, we first revisit the dual-stream transformer paradigm and further analyze its limitations, including model manifold variations caused by the gating mechanism controlling cross-modal interactions, biases in multi-modal background regions introduced by cross-modal attention, and the inconsistencies in multi-modal classifier-free guidance (CFG) during training and inference, as well as conflicts between multiple conditions. To alleviate these issues, we propose Cross-Modal Context Learning (CCL), equipped with several carefully designed modules. Temporally Aligned RoPE and Partitioning (TARP) effectively enhances the temporal alignment between audio latent and video latent representations. The Learnable Context Tokens (LCT) and Dynamic Context Routing (DCR) in the Cross-Modal Context Attention (CCA) module provide stable unconditional anchors for cross-modal information, while dynamically routing based on different training tasks, further enhancing the model's convergence speed and generation quality. During inference, Unconditional Context Guidance (UCG) leverages the unconditional support provided by LCT to facilitate different forms of CFG, improving train-inference consistency and further alleviating conflicts. Through comprehensive evaluations, CCL achieves state-of-the-art performance compared with recent academic methods while requiring substantially fewer resources.
Authors: Lukas Bayer, Sheethal Bhat, Andreas Maier
Abstract: Accurate multi-organ segmentation in abdominal CT scans is essential for computer-aided diagnosis and treatment. While convolutional neural networks (CNNs) have long been the standard approach in medical image segmentation, transformer-based architectures have recently gained attention due to their ability to model long-range dependencies. In this study, we systematically benchmark the three hybrid transformer-based models UNETR, SwinUNETR, and UNETR++ against a strong CNN baseline, SegResNet, for volumetric multi-organ segmentation on the heterogeneous RATIC dataset. The dataset comprises 206 annotated CT scans from 23 institutions worldwide, covering five abdominal organs. All models were trained and evaluated under identical preprocessing and training conditions using the Dice Similarity Coefficient (DSC) as the primary metric. The results show that the CNN-based SegResNet achieves the highest overall performance, outperforming all hybrid transformer-based models across all organs. Among the transformer-based approaches, UNETR++ delivers the most competitive results, while UNETR demonstrates notably faster convergence with fewer training iterations. These findings suggest that, for small- to medium-sized heterogeneous datasets, well-optimized CNN architectures remain highly competitive and may outperform hybrid transformer-based designs.
Authors: Bin Cao, Sipeng Zheng, Hao Luo, Boyuan Li, Jing Liu, Zongqing Lu
Abstract: Text-to-motion (T2M) generation aims to create realistic human movements from text descriptions, with promising applications in animation and robotics. Despite recent progress, current T2M models perform poorly on unseen text descriptions due to the small scale and limited diversity of existing motion datasets. To address this problem, we introduce OpenT2M, a million-level, high-quality, and open-source motion dataset containing over 2800 hours of human motion. Each sequence undergoes rigorous quality control through physical feasibility validation and multi-granularity filtering, with detailed second-wise text annotations. We also develop an automated pipeline for creating long-horizon sequences, enabling complex motion generation. Building upon OpenT2M, we introduce MonoFrill, a pretrained motion model that achieves compelling T2M results without complicated designs or technique tricks as "frills". Its core component is 2D-PRQ, a novel motion tokenizer that captures spatiotemporal dependencies by dividing the human body into biology parts. Experiments show that OpenT2M significantly improves generalization of existing T2M models, while 2D-PRQ achieves superior reconstruction and strong zero-shot performance. We expect OpenT2M and MonoFrill will advance the T2M field by addressing longstanding data quality and benchmarking challenges.
Authors: Yueying Zou, Pei Pei Li, Zekun Li, Xinyu Guo, Xing Cui, Huaibo Huang, Ran He
Abstract: In recent years, AI-generated videos have become increasingly realistic and sophisticated. Meanwhile, Large Vision-Language Models (LVLMs) have shown strong potential for detecting such content. However, existing evaluation protocols largely treat the task as a binary classification problem and rely on coarse-grained metrics such as overall accuracy, providing limited insight into where LVLMs succeed or fail. To address this limitation, we introduce GenVideoLens, a fine-grained benchmark that enables dimension-wise evaluation of LVLM capabilities in AI-generated video detection. The benchmark contains 400 highly deceptive AI-generated videos and 100 real videos, annotated by experts across 15 authenticity dimensions covering perceptual, optical, physical, and temporal cues. We evaluate eleven representative LVLMs on this benchmark. Our analysis reveals a pronounced dimensional imbalance. While LVLMs perform relatively well on perceptual cues, they struggle with optical consistency, physical interactions, and temporal-causal reasoning. Model performance also varies substantially across dimensions, with smaller open-source models sometimes outperforming stronger proprietary models on specific authenticity cues. Temporal perturbation experiments further show that current LVLMs make limited use of temporal information. Overall, GenVideoLens provides diagnostic insights into LVLM behavior, revealing key capability gaps and offering guidance for improving future AI-generated video detection systems.
Authors: Zelin Liu, Bocheng Li, Yuling Zhou, Xuanting Li, Yixuan Yang, Jing Wang, Weishu Zhao, Xiaofeng Gao
Abstract: The Mariana Trench and the Qinghai-Tibet Plateau exhibit significant similarities in geological origins and microbial metabolic functions. Given that deep-sea biological sampling faces prohibitive costs, recognizing structurally homologous terrestrial analogs of the Mariana Trench on the Qinghai-Tibet Plateau is of great significance. Yet, no existing model adequately addresses cross-domain topographic similarity retrieval, either neglecting geographical knowledge or sacrificing computational efficiency. To address these challenges, we present \underline{\textbf{G}}eography-knowledge \underline{\textbf{E}}nhanced \underline{\textbf{A}}nalog \underline{\textbf{R}}ecognition (\textbf{GEAR}) Framework, a three-stage pipeline designed to efficiently retrieve analogs from 2.5 million square kilometers of the Qinghai-Tibet Plateau: (1) Skeleton guided Screening and Clipping: Recognition of candidate valleys and initial screening based on size and linear morphological criteria. (2) Physics aware Filtering: The Topographic Waveform Comparator (TWC) and Morphological Texture Module (MTM) evaluate the waveform and texture and filter out inconsistent candidate valleys. (3) Graph based Fine Recognition: We design a \underline{\textbf{M}}orphology-integrated \underline{\textbf{S}}iamese \underline{\textbf{G}}raph \underline{\textbf{N}}etwork (\textbf{MSG-Net}) based on geomorphological metrics. Correspondingly, we release an expert-annotated topographic similarity dataset targeting tectonic collision zones. Experiments demonstrate the effectiveness of every stage. Besides, MSG-Net achieved an F1-Score 1.38 percentage points higher than the SOTA baseline. Using features extracted by MSG-Net, we discovered a significant correlation with biological data, providing evidence for future biological analysis.
Authors: Rong Fu, Jiekai Wu, Haiyun Wei, Xiaowen Ma, Shiyin Lin, Kangan Qian, Chuang Liu, Jianyuan Ni, Simon James Fong
Abstract: Rapid, large-scale 3D reconstruction from multi-date satellite imagery is vital for environmental monitoring, urban planning, and disaster response, yet remains difficult due to illumination changes, sensor heterogeneity, and the cost of per-scene optimization. We introduce SwiftGS, a meta-learned system that reconstructs 3D surfaces in a single forward pass by predicting geometry-radiation-decoupled Gaussian primitives together with a lightweight SDF, replacing expensive per-scene fitting with episodic training that captures transferable priors. The model couples a differentiable physics graph for projection, illumination, and sensor response with spatial gating that blends sparse Gaussian detail and global SDF structure, and incorporates semantic-geometric fusion, conditional lightweight task heads, and multi-view supervision from a frozen geometric teacher under an uncertainty-aware multi-task loss. At inference, SwiftGS operates zero-shot with optional compact calibration and achieves accurate DSM reconstruction and view-consistent rendering at significantly reduced computational cost, with ablations highlighting the benefits of the hybrid representation, physics-aware rendering, and episodic meta-training.
Authors: Jiayi Luo, Jiayu Chen, Jiankun Wang, Cong Wang, Hanxin Zhu, Qingyun Sun, Chen Gao, Zhibo Chen, Jianxin Li
Abstract: Diffusion Transformers (DiTs) achieve strong video generation quality but suffer from high inference cost due to dense 3D attention, leading to the development of sparse attention technologies to improve efficiency. However, existing training-free sparse attention methods in video generation still face two unresolved limitations: ignoring layer heterogeneity in attention pruning and ignoring query-key coupling in block partitioning, which hinder a better quality-speedup trade-off. In this work, we uncover a critical insight that the attention sparsity of each layer is its intrinsic property, with minor effects across different inputs. Motivated by this, we propose SVOO, a training-free Sparse attention framework for fast Video generation via Offline layer-wise sparsity profiling and Online bidirectional co-clustering. Specifically, SVOO adopts a two-stage paradigm: (i) offline layer-wise sensitivity profiling to derive intrinsic per-layer pruning levels, and (ii) online block-wise sparse attention via a novel bidirectional co-clustering algorithm. Extensive experiments on seven widely used video generation models demonstrate that SVOO achieves a superior quality-speedup trade-off over state-of-the-art methods, delivering up to $1.93\times$ speedup while maintaining a PSNR of up to 29 dB on Wan2.1.
Authors: Cong Wang, Hanxin Zhu, Xiao Tang, Jiayi Luo, Xin Jin, Long Chen, Fei-Yue Wang, Zhibo Chen
Abstract: Recent progress in video generation has led to substantial improvements in visual fidelity, yet ensuring physically consistent motion remains a fundamental challenge. Intuitively, this limitation can be attributed to the fact that real-world object motion unfolds in three-dimensional space, while video observations provide only partial, view-dependent projections of such dynamics. To address these issues, we propose PhysVideo, a two-stage framework that first generates physics-aware orthogonal foreground videos and then synthesizes full videos with background. In the first stage, Phys4View leverages physics-aware attention to capture the influence of physical attributes on motion dynamics, and enhances spatio-temporal consistency by incorporating geometry-enhanced cross-view attention and temporal attention. In the second stage, VideoSyn uses the generated foreground videos as guidance and learns the interactions between foreground dynamics and background context for controllable video synthesis. To support training, we construct PhysMV, a dataset containing 40K scenes, each consisting of four orthogonal viewpoints, resulting in a total of 160K video sequences. Extensive experiments demonstrate that PhysVideo significantly improves physical realism and spatial-temporal coherence over existing video generation methods. Home page: https://anonymous.4open.science/w/Phys4D/.
Authors: Teer Song, Yue Zhang, Yu Tian, Ziyang Wang, Xianlin Zhang, Guixuan Zhang, Xuan Liu, Xueming Li, Yasen Zhang
Abstract: To better preserve an individual's identity, face restoration has evolved from reference-free to reference-based approaches, which leverage high-quality reference images of the same identity to enhance identity fidelity in the restored outputs. However, most existing methods implicitly assume that the reference and degraded input are age-aligned, limiting their effectiveness in real-world scenarios where only cross-age references are available, such as historical photo restoration. This paper proposes MeInTime, a diffusion-based face restoration method that extends reference-based restoration from same-age to cross-age settings. Given one or few reference images along with an age prompt corresponding to the degraded input, MeInTime achieves faithful restoration with both identity fidelity and age consistency. Specifically, we decouple the modeling of identity and age conditions. During training, we focus solely on effectively injecting identity features through a newly introduced attention mechanism and introduce Gated Residual Fusion modules to facilitate the integration between degraded features and identity representations. At inference, we propose Age-Aware Gradient Guidance, a training-free sampling strategy, using an age-driven direction to iteratively nudge the identity-aware denoising latent toward the desired age semantic manifold. Extensive experiments demonstrate that MeInTime outperforms existing face restoration methods in both identity preservation and age consistency. Our code is available at: https://github.com/teer4/MeInTime
Authors: Ruizhi Yu, Keyang Zhong, Peng Liu, Qi Wu, Haoran Zhang, Yanhao Zhang, Chen Chen, Haonan Lu
Abstract: Live streaming commerce has become a prominent form of broadcasting in the modern era. To facilitate more efficient and convenient product promotions for streamers, we present Click-to-Ask, an AI-driven assistant for live streaming commerce with complementary offline and online components. The offline module processes diverse multimodal product information, transforming complex inputs into structured product data and generating compliant promotional copywriting. During live broadcasts, the online module enables real-time responses to viewer inquiries by allowing streamers to click on questions and leveraging both the structured product information generated by the offline module and an event-level historical memory maintained in a streaming architecture. This system significantly reduces the time needed for promotional preparation, enhances content engagement, and enables prompt interaction with audience inquiries, ultimately improving the effectiveness of live streaming commerce. On our collected dataset of TikTok live stream frames, the proposed method achieves a Question Recognition Accuracy of 0.913 and a Response Quality score of 0.876, demonstrating considerable potential for practical application. The video demonstration can be viewed here: https://www.youtube.com/shorts/mWIXK-SWhiE.
Authors: Pius Horn, Janis Keuper
Abstract: Reliably extracting tables from PDFs is essential for large-scale scientific data mining and knowledge base construction, yet existing evaluation approaches rely on rule-based metrics that fail to capture semantic equivalence of table content. We present a benchmarking framework based on synthetically generated PDFs with precise LaTeX ground truth, using tables sourced from arXiv to ensure realistic complexity and diversity. As our central methodological contribution, we apply LLM-as-a-judge for semantic table evaluation, integrated into a matching pipeline that accommodates inconsistencies in parser outputs. Through a human validation study comprising over 1,500 quality judgments on extracted table pairs, we show that LLM-based evaluation achieves substantially higher correlation with human judgment (Pearson r=0.93) compared to Tree Edit Distance-based Similarity (TEDS, r=0.68) and Grid Table Similarity (GriTS, r=0.70). Evaluating 21 contemporary PDF parsers across 100 synthetic documents containing 451 tables reveals significant performance disparities. Our results offer practical guidance for selecting parsers for tabular data extraction and establish a reproducible, scalable evaluation methodology for this critical task. Code and data: https://github.com/phorn1/pdf-parse-bench Metric study and human evaluation: https://github.com/phorn1/table-metric-study
URLs: https://github.com/phorn1/pdf-parse-bench, https://github.com/phorn1/table-metric-study
Authors: Jingguo Qu, Xinyang Han, Yao Pu, Man-Lik Chui, Simon Takadiyi Gunda, Ziman Chen, Jing Qin, Ann Dorothy King, Winnie Chiu-Wing Chu, Jing Cai, Michael Tin-Cheung Ying
Abstract: Medical ultrasound image segmentation faces significant challenges due to limited labeled data and characteristic imaging artifacts including speckle noise and low-contrast boundaries. While semi-supervised learning (SSL) approaches have emerged to address data scarcity, existing methods suffer from suboptimal unlabeled data utilization and lack robust feature representation mechanisms. In this paper, we propose Switch, a novel SSL framework with two key innovations: (1) Multiscale Switch (MSS) strategy that employs hierarchical patch mixing to achieve uniform spatial coverage; (2) Frequency Domain Switch (FDS) with contrastive learning that performs amplitude switching in Fourier space for robust feature representations. Our framework integrates these components within a teacher-student architecture to effectively leverage both labeled and unlabeled data. Comprehensive evaluation across six diverse ultrasound datasets (lymph nodes, breast lesions, thyroid nodules, and prostate) demonstrates consistent superiority over state-of-the-art methods. At 5\% labeling ratio, Switch achieves remarkable improvements: 80.04\% Dice on LN-INT, 85.52\% Dice on DDTI, and 83.48\% Dice on Prostate datasets, with our semi-supervised approach even exceeding fully supervised baselines. The method maintains parameter efficiency (1.8M parameters) while delivering superior performance, validating its effectiveness for resource-constrained medical imaging applications. The source code is publicly available at https://github.com/jinggqu/Switch
Authors: Peihang Wu, Zehong Chen, Lijian Xu
Abstract: Whole slide imaging (WSI) has transformed digital pathology by enabling computational analysis of gigapixel histopathology images. Recent foundation model advances have accelerated progress in computational pathology, facilitating joint reasoning across pathology images, clinical reports, and structured data. Despite this progress, challenges remain: the extreme resolution of WSIs creates computational hurdles for visual learning; limited expert annotations constrain supervised approaches; integrating multimodal information while preserving biological interpretability remains difficult; and the opacity of modeling ultra-long visual sequences hinders clinical transparency. This review comprehensively surveys recent advances in multimodal computational pathology. We systematically analyze four research directions: (1) self-supervised representation learning and structure-aware token compression for WSIs; (2) multimodal data generation and augmentation; (3) parameter-efficient adaptation and reasoning-enhanced few-shot learning; and (4) multi-agent collaborative reasoning for trustworthy diagnosis. We specifically examine how token compression enables cross-scale modeling and how multi-agent mechanisms simulate a pathologist's "Chain of Thought" across magnifications to achieve uncertainty-aware evidence fusion. Finally, we discuss open challenges and argue that future progress depends on unified multimodal frameworks integrating high-resolution visual data with clinical and biomedical knowledge to support interpretable and safe AI-assisted diagnosis.
Authors: Juan Miguel Valverde, Dim P. Papadopoulos, Rasmus Larsen, Anders Bjorholm Dahl
Abstract: Standard deep learning models for image segmentation cannot guarantee topology accuracy, failing to preserve the correct number of connected components or structures. This, in turn, affects the quality of the segmentations and compromises the reliability of the subsequent quantification analyses. Previous works have proposed to enhance topology accuracy with specialized frameworks, architectures, and loss functions. However, these methods are often cumbersome to integrate into existing training pipelines, they are computationally very expensive, or they are restricted to structures with tubular morphology. We present SCNP, an efficient method that improves topology accuracy by penalizing the logits with their poorest-classified neighbor, forcing the model to improve the prediction at the pixels' neighbors before allowing it to improve the pixels themselves. We show the effectiveness of SCNP across 13 datasets, covering different structure morphologies and image modalities, and integrate it into three frameworks for semantic and instance segmentation. Additionally, we show that SCNP can be integrated into several loss functions, making them improve topology accuracy. Our code can be found at https://jmlipman.github.io/SCNP-SameClassNeighborPenalization.
URLs: https://jmlipman.github.io/SCNP-SameClassNeighborPenalization.
Authors: Mohamed Youssef, Mayar Elfares, Anna-Maria Meer, Matteo Bortoletto, Andreas Bulling
Abstract: Bridging the simulation-to-reality (sim2real) gap remains challenging as labelled real-world data is scarce. Existing diffusion-based approaches rely on unstructured prompts or statistical alignment, which do not capture the structured factors that make images look real. We introduce Ontology- Guided Diffusion (OGD), a neuro-symbolic zero-shot sim2real image translation framework that represents realism as structured knowledge. OGD decomposes realism into an ontology of interpretable traits -- such as lighting and material properties -- and encodes their relationships in a knowledge graph. From a synthetic image, OGD infers trait activations and uses a graph neural network to produce a global embedding. In parallel, a symbolic planner uses the ontology traits to compute a consistent sequence of visual edits needed to narrow the realism gap. The graph embedding conditions a pretrained instruction-guided diffusion model via cross-attention, while the planned edits are converted into a structured instruction prompt. Across benchmarks, our graph-based embeddings better distinguish real from synthetic imagery than baselines, and OGD outperforms state-of-the-art diffusion methods in sim2real image translations. Overall, OGD shows that explicitly encoding realism structure enables interpretable, data-efficient, and generalisable zero-shot sim2real transfer.
Authors: Longfei Liu, Yongjie Hou, Yang Li, Qirui Wang, Youyang Sha, Yongjun Yu, Yinzhi Wang, Peizhe Ru, Xuanlong Yu, Xi Shen
Abstract: Deploying high-performance dense prediction models on resource-constrained edge devices remains challenging due to strict limits on computation and memory. In practice, lightweight systems for object detection, instance segmentation, and pose estimation are still dominated by CNN-based architectures such as YOLO, while compact Vision Transformers (ViTs) often struggle to achieve similarly strong accuracy efficiency tradeoff, even with large scale pretraining. We argue that this gap is largely due to insufficient task specific representation learning in small scale ViTs, rather than an inherent mismatch between ViTs and edge dense prediction. To address this issue, we introduce EdgeCrafter, a unified compact ViT framework for edge dense prediction centered on ECDet, a detection model built from a distilled compact backbone and an edge-friendly encoder decoder design. On the COCO dataset, ECDet-S achieves 51.7 AP with fewer than 10M parameters using only COCO annotations. For instance segmentation, ECInsSeg achieves performance comparable to RF-DETR while using substantially fewer parameters. For pose estimation, ECPose-X reaches 74.8 AP, significantly outperforming YOLO26Pose-X (71.6 AP) despite the latter's reliance on extensive Objects365 pretraining. These results show that compact ViTs, when paired with task-specialized distillation and edge-aware design, can be a practical and competitive option for edge dense prediction. Code is available at: https://intellindust-ai-lab.github.io/projects/EdgeCrafter/
URLs: https://intellindust-ai-lab.github.io/projects/EdgeCrafter/
Authors: Rundong Su, Jintao Zhang, Zhihang Yuan, Haojie Duanmu, Jianfei Chen, Jun Zhu
Abstract: Diffusion transformers have demonstrated remarkable capabilities in generating videos. However, their practical deployment is severely constrained by high memory usage and computational cost. Post-Training Quantization provides a practical way to reduce memory usage and boost computation speed. Existing quantization methods typically apply a static bit-width allocation, overlooking the quantization difficulty of activations across diffusion timesteps, leading to a suboptimal trade-off between efficiency and quality. In this paper, we propose a inference time NVFP4/INT8 Mixed-Precision Quantization framework. We find a strong linear correlation between a block's input-output difference and the quantization sensitivity of its internal linear layers. Based on this insight, we design a lightweight predictor that dynamically allocates NVFP4 to temporally stable layers to maximize memory compression, while selectively preserving INT8 for volatile layers to ensure robustness. This adaptive precision strategy enables aggressive quantization without compromising generation quality. Beside this, we observe that the residual between the input and output of a Transformer block exhibits high temporal consistency across timesteps. Leveraging this temporal redundancy, we introduce Temporal Delta Cache (TDC) to skip computations for these invariant blocks, further reducing the computational cost. Extensive experiments demonstrate that our method achieves 1.92$\times$ end-to-end acceleration and 3.32$\times$ memory reduction, setting a new baseline for efficient inference in Video DiTs.
Authors: Isabel Rio-Torto, Jaime S. Cardoso, Lu\'is F. Teixeira
Abstract: Natural language explanations provide an inherently human-understandable way to explain black-box models, closely reflecting how radiologists convey their diagnoses in textual reports. Most works explicitly supervise the explanation generation process using datasets annotated with explanations. Thus, though plausible, the generated explanations are not faithful to the model's reasoning. In this work, we propose WeNLEX, a weakly supervised model for the generation of natural language explanations for multilabel chest X-ray classification. Faithfulness is ensured by matching images generated from their corresponding natural language explanations with original images, in the black-box model's feature space. Plausibility is maintained via distribution alignment with a small database of clinician-annotated explanations. We empirically demonstrate, through extensive validation on multiple metrics to assess faithfulness, simulatability, diversity, and plausibility, that WeNLEX is able to produce faithful and plausible explanations, using as little as 5 ground-truth explanations per diagnosis. Furthermore, WeNLEX can operate in both post-hoc and in-model settings. In the latter, i.e., when the multilabel classifier is trained together with the rest of the network, WeNLEX improves the classification AUC of the standalone classifier by 2.21%, thus showing that adding interpretability to the training process can actually increase the downstream task performance. Additionally, simply by changing the database, WeNLEX explanations are adaptable to any target audience, and we showcase this flexibility by training a layman version of WeNLEX, where explanations are simplified for non-medical users.
Authors: Haochen Li, Rui Zhang, Hantao Yao, Xin Zhang, Yifan Hao, Shaohui Peng, Yongwei Zhao, Ling Li
Abstract: Domain Adaptive Object Detection (DAOD) aims to transfer detectors from a labeled source domain to an unlabeled target domain. Existing DAOD methods employ multi-granularity feature alignment to learn domain-invariant representations. However, the local connectivity of their CNN-based backbone and detection head restricts alignment to local regions, failing to extract global domain-invariant features. Although transformer-based DAOD methods capture global dependencies via attention mechanisms, their quadratic computational cost hinders practical deployment. To solve this, we propose DA-Mamba, a hybrid CNN-State Space Models (SSMs) architecture that combines the efficiency of CNNs with the linear-time long-range modeling capability of State Space Models (SSMs) to capture both global and local domain-invariant features. Specifically, we introduce two novel modules: Image-Aware SSM (IA-SSM) and Object-Aware SSM (OA-SSM). IA-SSM is integrated into the backbone to enhance global domain awareness, enabling image-level global and local alignment. OA-SSM is inserted into the detection head to model spatial and semantic dependencies among objects, enhancing instance-level alignment. Comprehensive experiments demonstrate that the proposed method can efficiently improve the cross-domain performance of the object detector.
Authors: Ying Zheng, Yiyi Zhang, Yi Wang, Lap-Pui Chau
Abstract: Source-Free Domain Adaptation (SFDA) adapts pre-trained models to unlabeled target domains without requiring access to source data. Although state-of-the-art methods leveraging local neighborhood structures show promise for SFDA, they tend to over-rely on prediction similarity among neighbors. This over-reliance accelerates the forgetting of source knowledge and increases susceptibility to local noise overfitting. To address these issues, we introduce ProCal, a probability calibration method that dynamically calibrates neighborhood-based predictions through a dual-model collaborative prediction mechanism. ProCal integrates the source model's initial predictions with the current model's online outputs to effectively calibrate neighbor probabilities. This strategy not only mitigates the interference of local noise but also preserves the discriminative information from the source model, thereby achieving a balance between knowledge retention and domain adaptation. Furthermore, we design a joint optimization objective that combines a soft supervision loss with a diversity loss to guide the target model. Our theoretical analysis shows that ProCal converges to an equilibrium where source knowledge and target information are effectively fused, reducing both knowledge forgetting and overfitting. We validate the effectiveness of our approach through extensive experiments on 31 cross-domain tasks across four public datasets. Our code is available at: https://github.com/zhengyinghit/ProCal.
Authors: Vsevolod Skorokhodov, Chenghao Xu, Shuo Sun, Olga Fink, Malcolm Mielle
Abstract: Foundational feed-forward visual geometry models enable accurate and efficient camera pose estimation and scene reconstruction by learning strong scene priors from massive RGB datasets. However, their effectiveness drops when applied to mixed sensing modalities, such as RGB-thermal (RGB-T) images. We observe that while a visual geometry grounded transformer pretrained on RGB data generalizes well to thermal-only reconstruction, it struggles to align RGB and thermal modalities when processed jointly. To address this, we propose SEAR, a simple yet efficient fine-tuning strategy that adapts a pretrained geometry transformer to multimodal RGB-T inputs. Despite being trained on a relatively small RGB-T dataset, our approach significantly outperforms state-of-the-art methods for 3D reconstruction and camera pose estimation, achieving significant improvements over all metrics (e.g., over 29\% in AUC@30) and delivering higher detail and consistency between modalities with negligible overhead in inference time compared to the original pretrained model. Notably, SEAR enables reliable multimodal pose estimation and reconstruction even under challenging conditions, such as low lighting and dense smoke. We validate our architecture through extensive ablation studies, demonstrating how the model aligns both modalities. Additionally, we introduce a new dataset featuring RGB and thermal sequences captured at different times, viewpoints, and illumination conditions, providing a robust benchmark for future work in multimodal 3D scene reconstruction. Code and models are publicly available at https://www.github.com/Schindler-EPFL-Lab/SEAR.
Authors: Jiatong Xia, Zicheng Duan, Anton van den Hengel, Lingqiao Liu
Abstract: Recent progress in 3D generation has been driven largely by models conditioned on images or text, while readily available 3D priors are still underused. In many real-world scenarios, the visible-region point cloud are easy to obtain from active sensors such as LiDAR or from feed-forward predictors like VGGT, offering explicit geometric constraints that current methods fail to exploit. In this work, we introduce Points-to-3D, a diffusion-based framework that leverages point cloud priors for geometry-controllable 3D asset and scene generation. Built on a latent 3D diffusion model TRELLIS, Points-to-3D first replaces pure-noise sparse structure latent initialization with a point cloud priors tailored input formulation.A structure inpainting network, trained within the TRELLIS framework on task-specific data designed to learn global structural inpainting, is then used for inference with a staged sampling strategy (structural inpainting followed by boundary refinement), completing the global geometry while preserving the visible regions of the input priors.In practice, Points-to-3D can take either accurate point-cloud priors or VGGT-estimated point clouds from single images as input. Experiments on both objects and scene scenarios consistently demonstrate superior performance over state-of-the-art baselines in terms of rendering quality and geometric fidelity, highlighting the effectiveness of explicitly embedding point-cloud priors for achieving more accurate and structurally controllable 3D generation.
Authors: Jakob L{\o}nborg Christensen, Vedrana Andersen Dahl, Morten Rieger Hannemose, Anders Bjorholm Dahl, Christian F. Baumgartner
Abstract: Uncertainty quantification (UQ) is crucial in safety-critical applications such as medical image segmentation. Total uncertainty is typically decomposed into data-related aleatoric uncertainty (AU) and model-related epistemic uncertainty (EU). Many methods exist for modeling AU (such as Probabilistic UNet, Diffusion) and EU (such as ensembles, MC Dropout), but it is unclear how they interact when combined. Additionally, recent work has revealed substantial entanglement between AU and EU, undermining the interpretability and practical usefulness of the decomposition. We present a comprehensive empirical study covering a broad range of AU-EU model combinations, propose a metric to quantify uncertainty entanglement, and evaluate both across downstream UQ tasks. For out-of-distribution detection, ensembles exhibit consistently lower entanglement and superior performance. For ambiguity modeling and calibration the best models are dataset-dependent, with softmax/SSN-based methods performing well and Probabilistic UNets being less entangled. A softmax ensemble fares remarkably well on all tasks. Finally, we analyze potential sources of uncertainty entanglement and outline directions for mitigating this effect.
Authors: Yuchen Li, Amanmeet Garg, Shalini Chaudhuri, Rui Zhao, Garin Kessler
Abstract: Large Vision Language Models (LVLMs) excel at semantic understanding but struggle with fine grained spatial grounding, as the model must implicitly infer complex geometry without ever producing a spatial interpretation. We present Perceptio, a perception enhanced LVLM with 2D and 3D spatial reasoning abilities, enabled via explicit semantic segmentation tokens and depth tokens generated directly within the autoregressive sequence. Concretely, we (i) distill a VQVAE depth codebook from a strong monocular teacher to tokenize dense depth into compact sequences, and (ii) integrate SAM2 based semantic segmentation tokens and VQ-VAE depth tokens inside the LLM so the model first emits spatial tokens and then answers. To stabilize depth token generation, we introduce novel composite depth-token objectives (marker, token, and count losses) and a soft-merging technique for differentiable reconstruction. We adopt a multi-task co-training strategy across diverse datasets, letting the model learn perception tokens to tackle multiple downstream tasks. Building on InternVL, Perceptio achieves state-of-the-art performance across benchmarks: improving referring expression segmentation by +0.8/+1.4/+1.1 cIoU on RefCOCO/+/g HardBLINK spatial understanding accuracy by 10.3%, and MMBench accuracy by 1.0%, demonstrating that explicit spatial chain-of-thought materially strengthens spatial grounding in LVLMs.
Authors: Chinmay Prabhakar, Bastian Wittmann, Tamaz Amiranashvili, Paul B\"uschl, Ezequiel de la Rosa, Julian McGinnis, Benedikt Wiestler, Bjoern Menze, Suprosanna Shit
Abstract: Spatial graphs provide a lightweight and elegant representation of curvilinear anatomical structures such as blood vessels, lung airways, and neuronal networks. Accurately modeling these graphs is crucial in clinical and (bio-)medical research. However, the high spatial resolution of large networks drastically increases their complexity, resulting in significant computational challenges. In this work, we aim to tackle these challenges by proposing VesselTok, a framework that approaches spatially dense graphs from a parametric shape perspective to learn latent representations (tokens). VesselTok leverages centerline points with a pseudo radius to effectively encode tubular geometry. Specifically, we learn a novel latent representation conditioned on centerline points to encode neural implicit representations of vessel-like, tubular structures. We demonstrate VesselTok's performance across diverse anatomies, including lung airways, lung vessels, and brain vessels, highlighting its ability to robustly encode complex topologies. To prove the effectiveness of VesselTok's learnt latent representations, we show that they (i) generalize to unseen anatomies, (ii) support generative modeling of plausible anatomical graphs, and (iii) transfer effectively to downstream inverse problems, such as link prediction.
Authors: Hesong Li, Ziqi Wu, Ruiwen Shao, Ying Fu
Abstract: High-Resolution Transmission Electron Microscopy (HRTEM) enables atomic-scale observation of nucleation dynamics, which boosts the studies of advanced solid materials. Nonetheless, due to the millisecond-scale rapid change of nucleation, it requires short-exposure rapid imaging, leading to severe noise that obscures atomic positions. In this work, we propose a statistical characteristic-guided denoising network, which utilizes statistical characteristics to guide the denoising process in both spatial and frequency domains. In the spatial domain, we present spatial deviation-guided weighting to select appropriate convolution operations for each spatial position based on deviation characteristic. In the frequency domain, we present frequency band-guided weighting to enhance signals and suppress noise based on band characteristics. We also develop an HRTEM-specific noise calibration method and generate a dataset with disordered structures and realistic HRTEM image noises. It can ensure the denoising performance of models on real images for nucleation observation. Experiments on synthetic and real data show our method outperforms the state-of-the-art methods in HRTEM image denoising, with effectiveness in the localization downstream task. Code will be available at https://github.com/HeasonLee/SCGN.
Authors: Samuel Ofosu Mensah, Maria Camila Roa Carvajal, Kerol Djoumessi, Philipp Berens
Abstract: Foundation models are used to extract transferable representations from large amounts of unlabeled data, typically via self-supervised learning (SSL). However, many of these models rely on architectures that offer limited interpretability, which is a critical issue in high-stakes domains such as medical imaging. We propose Dual-IFM, a foundation model that is interpretable-by-design in two ways: First, it provides local interpretability for individual images through class evidence maps that are faithful to the decision-making process. Second, it provides global interpretability for entire datasets through a 2D projection layer that allows for direct visualization of the model's representation space. We trained our model on over 800,000 color fundus photography from various sources to learn generalizable, interpretable representations for different downstream tasks. Our results show that our model reaches a performance range similar to that of state-of-the-art foundation models with up to $16\times$ the number of parameters, while providing interpretable predictions on out-of-distribution data. Our results suggest that large-scale SSL pretraining paired with inherent interpretability can lead to robust representations for retinal imaging.
Authors: Xiangyu Bai, Bishoy Galoaa, Sarah Ostadabbas
Abstract: Video question answering (VQA) with vision-language models (VLMs) depends critically on which frames are selected from the input video, yet most systems rely on uniform or heuristic sampling that cannot be optimized for downstream answering quality. We introduce \textbf{HORNet}, a lightweight frame selection policy trained with Group Relative Policy Optimization (GRPO) to learn which frames a frozen VLM needs to answer questions correctly. With fewer than 1M trainable parameters, HORNet reduces input frames by up to 99\% and VLM processing time by up to 93\%, while improving answer quality on short-form benchmarks (+1.7\% F1 on MSVD-QA) and achieving strong performance on temporal reasoning tasks (+7.3 points over uniform sampling on NExT-QA). We formalize this as Select Any Frames (SAF), a task that decouples visual input curation from VLM reasoning, and show that GRPO-trained selection generalizes better out-of-distribution than supervised and PPO alternatives. HORNet's policy further transfers across VLM answerers without retraining, yielding an additional 8.5\% relative gain when paired with a stronger model. Evaluated across six benchmarks spanning 341,877 QA pairs and 114.2 hours of video, our results demonstrate that optimizing \emph{what} a VLM sees is a practical and complementary alternative to optimizing what it generates while improving efficiency. Code is available at https://github.com/ostadabbas/HORNet.
Authors: Bishoy Galoaa, Shayda Moezzi, Xiangyu Bai, Sarah Ostadabbas
Abstract: Recent research has made substantial progress on video reasoning, with many models leveraging spatio-temporal evidence chains to strengthen their inference capabilities. At the same time, a growing set of datasets and benchmarks now provides structured annotations designed to support and evaluate such reasoning. However, little attention has been paid to reasoning about \emph{how} objects move between observations: no prior work has articulated the motion patterns by connecting successive observations, leaving trajectory understanding implicit and difficult to verify. We formalize this missing capability as Spatial-Temporal-Trajectory (STT) reasoning and introduce \textbf{Motion-o}, a motion-centric video understanding extension to visual language models that makes trajectories explicit and verifiable. To enable motion reasoning, we also introduce a trajectory-grounding dataset artifact that expands sparse keyframe supervision via augmentation to yield denser bounding box tracks and a stronger trajectory-level training signal. Finally, we introduce Motion Chain of Thought (MCoT), a structured reasoning pathway that makes object trajectories through discrete \texttt{
Authors: Tianci Luo, Jinpeng Wang, Shiyu Qin, Niu Lian, Yan Feng, Bin Chen, Chun Yuan, Shu-Tao Xia
Abstract: Visual In-Context Learning (VICL) aims to complete vision tasks by imitating pixel demonstrations. Recent work pioneered prompt fusion that combines the advantages of various demonstrations, which shows a promising way to extend VICL. Unfortunately, the patch-wise fusion framework and model-agnostic supervision hinder the exploitation of informative cues, thereby limiting performance gains. To overcome this deficiency, we introduce PromptHub, a framework that holistically strengthens multi-prompting through locality-aware fusion, concentration and alignment. PromptHub exploits spatial priors to capture richer contextual information, employs complementary concentration, alignment, and prediction objectives to mutually guide training, and incorporates data augmentation to further reinforce supervision. Extensive experiments on three fundamental vision tasks demonstrate the superiority of PromptHub. Moreover, we validate its universality, transferability, and robustness across out-of-distribution settings, and various retrieval scenarios. This work establishes a reliable locality-aware paradigm for prompt fusion, moving beyond prior patch-wise approaches. Code is available at https://github.com/luotc-why/ICLR26-PromptHub.
Authors: Youngwan Lee, Soojin Jang, Yoorhim Cho, Seunghwan Lee, Yong-Ju Lee, Sung Ju Hwang
Abstract: Spatial reasoning is foundational for Vision-Language Models (VLMs), particularly when deployed as Vision-Language-Action (VLA) agents in physical environments. However, existing benchmarks predominantly focus on elementary, single-hop relations, neglecting the multi-hop compositional reasoning and precise visual grounding essential for real-world scenarios. To address this, we introduce MultihopSpatial, offering three key contributions: (1) A comprehensive benchmark designed for multi-hop and compositional spatial reasoning, featuring 1- to 3-hop complex queries across diverse spatial perspectives. (2) Acc@50IoU, a complementary metric that simultaneously evaluates reasoning and visual grounding by requiring both answer selection and precise bounding box prediction - capabilities vital for robust VLA deployment. (3) MultihopSpatial-Train, a dedicated large-scale training corpus to foster spatial intelligence. Extensive evaluation of 37 state-of-the-art VLMs yields eight key insights, revealing that compositional spatial reasoning remains a formidable challenge. Finally, we demonstrate that reinforcement learning post-training on our corpus enhances both intrinsic VLM spatial reasoning and downstream embodied manipulation performance.
Authors: Yitong Li, Igor Yakushev, Dennis M. Hedderich, Christian Wachinger
Abstract: Positron emission tomography (PET) is a widely recognized technique for diagnosing neurodegenerative diseases, offering critical functional insights. However, its high costs and radiation exposure hinder its widespread use. In contrast, magnetic resonance imaging (MRI) does not involve such limitations. While MRI also detects neurodegenerative changes, it is less sensitive for diagnosis compared to PET. To overcome such limitations, one approach is to generate synthetic PET from MRI. Recent advances in generative models have paved the way for cross-modality medical image translation; however, existing methods largely emphasize structural preservation while neglecting the critical need for pathology awareness. To address this gap, we propose PASTA, a novel image translation framework built on conditional diffusion models with enhanced pathology awareness. PASTA surpasses state-of-the-art methods by preserving both structural and pathological details through its highly interactive dual-arm architecture and multi-modal condition integration. Additionally, we introduce a novel cycle exchange consistency and volumetric generation strategy that significantly enhances PASTA's ability to produce high-quality 3D PET images. Our qualitative and quantitative results demonstrate the high quality and pathology awareness of the synthesized PET scans. For Alzheimer's diagnosis, the performance of these synthesized scans improves over MRI by 4%, almost reaching the performance of actual PET. Our code is available at https://github.com/ai-med/PASTA.
Authors: Ahmed Tawfik Aboukhadra, Marcel Rogge, Nadia Robertini, Abdalla Arafa, Jameel Malik, Ahmed Elhayek, Didier Stricker
Abstract: Understanding realistic hand-object interactions from monocular RGB videos is essential for AR/VR, robotics, and embodied AI. Existing methods rely on category-specific templates or heavy computation, yet still produce physically inconsistent hand-object alignment in 3D. We introduce GHOST (Gaussian Hand-Object Splatting), a fast, category-agnostic framework for reconstructing dynamic hand-object interactions using 2D Gaussian Splatting. GHOST represents both hands and objects as dense, view-consistent Gaussian discs and introduces three key innovations: (1) a geometric-prior retrieval and consistency loss that completes occluded object regions, (2) a grasp-aware alignment that refines hand translations and object scale to ensure realistic contact, and (3) a hand-aware background loss that prevents penalizing hand-occluded object regions. GHOST achieves complete, physically consistent, and animatable reconstructions from a single RGB video while running an order of magnitude faster than prior category-agnostic methods. Extensive experiments on ARCTIC, HO3D, and in-the-wild datasets demonstrate state-of-the-art accuracy in 3D reconstruction and 2D rendering quality, establishing GHOST as an efficient and robust solution for realistic hand-object interaction modeling. Code is available at https://github.com/ATAboukhadra/GHOST.
Authors: Feifan Luo, Hongyang Chen
Abstract: Estimating correspondences between pairs of non-rigid deformable 3D shapes remains a significant challenge in computer vision and graphics. While deep functional map methods have become the go-to solution for addressing this problem, they primarily focus on optimizing pointwise and functional maps either individually or jointly, rather than directly enhancing feature representations in the embedding space, which often results in inadequate feature quality and suboptimal matching performance. Furthermore, these approaches heavily rely on traditional functional map techniques, such as time-consuming functional map solvers, which incur substantial computational costs. In this work, we introduce, for the first time, a novel unsupervised contrastive learning-based approach for efficient and robust 3D shape matching. We begin by presenting an unsupervised contrastive learning framework that promotes feature learning by maximizing consistency within positive similarity pairs and minimizing it within negative similarity pairs, thereby improving both the consistency and discriminability of the learned features.We then design a significantly simplified functional map learning architecture that eliminates the need for computationally expensive functional map solvers and multiple auxiliary functional map losses, greatly enhancing computational efficiency. By integrating these two components into a unified two-branch pipeline, our method achieves state-of-the-art performance in both accuracy and efficiency. Extensive experiments demonstrate that our approach is not only computationally efficient but also outperforms current state-of-the-art methods across various challenging benchmarks, including near-isometric, non-isometric, and topologically inconsistent scenarios, even surpassing supervised techniques.
Authors: Jiayi Yuan, Haobo Jiang, De Wen Soh, Na Zhao
Abstract: This paper presents VGGT-360, a novel training-free framework for zero-shot, geometry-consistent panoramic depth estimation. Unlike prior view-independent training-free approaches, VGGT-360 reformulates the task as panoramic reprojection over multi-view reconstructed 3D models by leveraging the intrinsic 3D consistency of VGGT-like foundation models, thereby unifying fragmented per-view reasoning into a coherent panoramic understanding. To achieve robust and accurate estimation, VGGT-360 integrates three plug-and-play modules that form a unified panorama-to-3D-to-depth framework: (i) Uncertainty-guided adaptive projection slices panoramas into perspective views to bridge the domain gap between panoramic inputs and VGGT's perspective prior. It estimates gradient-based uncertainty to allocate denser views to geometry-poor regions, yielding geometry-informative inputs for VGGT. (ii) Structure-saliency enhanced attention strengthens VGGT's robustness during 3D reconstruction by injecting structure-aware confidence into its attention layers, guiding focus toward geometrically reliable regions and enhancing cross-view coherence. (iii) Correlation-weighted 3D model correction refines the reconstructed 3D model by reweighting overlapping points using attention-inferred correlation scores, providing a consistent geometric basis for accurate panoramic reprojection. Extensive experiments show that VGGT-360 outperforms both trained and training-free state-of-the-art methods across multiple resolutions and diverse indoor and outdoor datasets.
Authors: Zening Sun, Zhengpeng Xie, Lichen Bai, Shitong Shao, Shuo Yang, Zeke Xie
Abstract: Aligning Diffusion models has achieved remarkable breakthroughs in generating high-quality, human preference-aligned images. Existing techniques, such as supervised fine-tuning (SFT) and DPO-style preference optimization, have become principled tools for fine-tuning diffusion models. However, SFT relies on high-quality images that are costly to obtain, while DPO-style methods depend on large-scale preference datasets, which are often inconsistent in quality. Beyond data dependency, these methods are further constrained by computational inefficiency. To address these two challenges, we propose Composite Reward Assisted Fine-Tuning (CRAFT), a lightweight yet powerful fine-tuning paradigm that requires significantly reduced training data while maintaining computational efficiency. It first leverages a Composite Reward Filtering (CRF) technique to construct a high-quality and consistent training dataset and then perform an enhanced variant of SFT. We also theoretically prove that CRAFT actually optimizes the lower bound of group-based reinforcement learning, establishing a principled connection between SFT with selected data and reinforcement learning. Our extensive empirical results demonstrate that CRAFT with only 100 samples can easily outperform recent SOTA preference optimization methods with thousands of preference-paired samples. Moreover, CRAFT can even achieve 11-220$\times$ faster convergences than the baseline preference optimization methods, highlighting its extremely high efficiency.
Authors: Raffaele Cappelli
Abstract: Fingerprint recognition systems, which rely on the unique characteristics of human fingerprints, are essential in modern security and verification applications. Accurate minutiae extraction, a critical step in these systems, depends on the quality of fingerprint images. Despite recent improvements in fingerprint enhancement techniques, state-of-the-art methods often struggle with low-quality fingerprints and can be computationally demanding. This paper presents a minimalist approach to fingerprint enhancement, prioritizing simplicity and effectiveness. Two novel methods are introduced: a contextual filtering method and a learning-based method. These techniques consistently outperform complex state-of-the-art methods, producing clearer, more accurate, and less noisy images. The effectiveness of these methods is validated using a challenging latent fingerprint database. The open-source implementation of these techniques not only fosters reproducibility but also encourages further advancements in the field. The findings underscore the importance of simplicity in achieving high-quality fingerprint enhancement and suggest that future research should balance complexity and practical benefits.
Authors: Hui Yang, Wei Sun, Jian Liu, Jian Xiao Tao Xie, Hossein Rahmani, Ajmal Saeed mian, Nicu Sebe, Gim Hee Lee
Abstract: Generalized 3D hand-object pose estimation from a single RGB image remains challenging due to the large variations in object appearances and interaction patterns, especially under heavy occlusion. We propose GenHOI, a framework for generalized hand-object pose estimation with occlusion awareness. GenHOI integrates hierarchical semantic knowledge with hand priors to enhance model generalization under challenging occlusion conditions. Specifically, we introduce a hierarchical semantic prompt that encodes object states, hand configurations, and interaction patterns via textual descriptions. This enables the model to learn abstract high-level representations of hand-object interactions for generalization to unseen objects and novel interactions while compensating for missing or ambiguous visual cues. To enable robust occlusion reasoning, we adopt a multi-modal masked modeling strategy over RGB images, predicted point clouds, and textual descriptions. Moreover, we leverage hand priors as stable spatial references to extract implicit interaction constraints. This allows reliable pose inference even under significant variations in object shapes and interaction patterns. Extensive experiments on the challenging DexYCB and HO3Dv2 benchmarks demonstrate that our method achieves state-of-the-art performance in hand-object pose estimation.
Authors: Anqi Zhang, Xiaokang Ji, Guangyu Gao, Jianbo Jiao, Chi Harold Liu, Yunchao Wei
Abstract: Recent segmentation methods leveraging Multi-modal Large Language Models (MLLMs) have shown reliable object-level segmentation and enhanced spatial perception. However, almost all previous methods predominantly rely on specialist mask decoders to interpret masks from generated segmentation-related embeddings and visual features, or incorporate multiple additional tokens to assist. This paper aims to investigate whether and how we can unlock segmentation from MLLM itSELF with 1 segmentation Embedding (SELF1E) while achieving competitive results, which eliminates the need for external decoders. To this end, our approach targets the fundamental limitation of resolution reduction in pixel-shuffled image features from MLLMs. First, we retain image features at their original uncompressed resolution, and refill them with residual features extracted from MLLM-processed compressed features, thereby improving feature precision. Subsequently, we integrate pixel-unshuffle operations on image features with and without LLM processing, respectively, to unleash the details of compressed features and amplify the residual features under uncompressed resolution, which further enhances the resolution of refilled features. Moreover, we redesign the attention mask with dual perception pathways, i.e., image-to-image and image-to-segmentation, enabling rich feature interaction between pixels and the segmentation token. Comprehensive experiments across multiple segmentation tasks validate that SELF1E achieves performance competitive with specialist mask decoder-based methods, demonstrating the feasibility of decoder-free segmentation in MLLMs. Project page: https://github.com/ANDYZAQ/SELF1E.
Authors: Quentin Guimard, Federico Bartsch, Simone Caldarella, Rahaf Aljundi, Elisa Ricci, Massimiliano Mancini
Abstract: Models that bridge vision and language, such as CLIP, are key components of multimodal AI, yet their large-scale, uncurated training data introduce severe social and spurious biases. Existing post-hoc debiasing methods often operate directly in the dense CLIP embedding space, where bias and task-relevant information are highly entangled. This entanglement limits their ability to remove bias without degrading semantic fidelity. In this work, we propose Sparse Embedding Modulation (SEM), a post-hoc, zero-shot debiasing framework that operates in a Sparse Autoencoder (SAE) latent space. By decomposing CLIP text embeddings into disentangled features, SEM identifies and modulates bias-relevant neurons while preserving query-relevant ones. This enables more precise, non-linear interventions. Across four benchmark datasets and two CLIP backbones, SEM achieves substantial fairness gains in retrieval and zero-shot classification. Our results demonstrate that sparse latent representations provide an effective foundation for post-hoc debiasing of vision-language models.
Authors: Telang Xu, Chaoyang Zhang, Guangtao Zhai, Xiaohong Liu
Abstract: Single image reflection removal (SIRR) is challenging in real scenes, where reflection strength varies spatially and reflection patterns are tightly entangled with transmission structures. This paper presents a diffusion model with prior modulation framework (FUMO) that introduces explicit guidance signals to improve spatial controllability and structural faithfulness. Two priors are extracted directly from the mixed image, an intensity prior that estimates spatial reflection severity and a high-frequency prior that captures detail-sensitive responses via multi-scale residual aggregation. We propose a coarse-to-fine training paradigm. In the first stage, these cues are combined to gate the conditional residual injections, focusing the conditioning on regions that are both reflection-dominant and structure-sensitive. In the second stage, a fine-grained refinement network corrects local misalignment and sharpens fine details in the image space. Experiments conducted on both standard benchmarks and challenging images in the wild demonstrate competitive quantitative results and consistently improved perceptual quality. The code is released at https://github.com/Lucious-Desmon/FUMO.
Authors: Yan Shu, Bin Ren, Zhitong Xiong, Xiao Xiang Zhu, Beg\"um Demir, Nicu Sebe, Paolo Rota
Abstract: Vision-language models (VLMs) have shown promise in earth observation (EO), yet they struggle with tasks that require grounding complex spatial reasoning in precise pixel-level visual representations. To address this problem, we introduce TerraScope, a unified VLM that delivers pixel-grounded geospatial reasoning with two key capabilities: (1) modality-flexible reasoning: it handles single-modality inputs (optical or SAR) and adaptively fuses different modalities into the reasoning process when both are available; (2) multi-temporal reasoning: it integrates temporal sequences for change analysis across multiple time points. In addition, we curate Terra-CoT, a large-scale dataset containing 1 million samples with pixel-level masks embedded in reasoning chains across multiple sources. We also propose TerraScope-Bench, the first benchmark for pixel-grounded geospatial reasoning with six sub-tasks that evaluates both answer accuracy and mask quality to ensure authentic pixel-grounded reasoning. Experiments show that TerraScope significantly outperforms existing VLMs on pixel-grounded geospatial reasoning while providing interpretable visual evidence.
Authors: Weijia Dou, Wenzhao Zheng, Weiliang Chen, Yu Zheng, Jie Zhou, Jiwen Lu
Abstract: Recent generative models can produce high-fidelity videos, yet they often exhibit 3D spatial geometric inconsistencies. Existing evaluation methods fail to accurately characterize these inconsistencies: fidelity-centric metrics like FVD are insensitive to geometric distortions, while consistency-focused benchmarks often penalize valid foreground dynamics. To address this gap, we introduce SGC, a metric for evaluating 3D \textbf{S}patial \textbf{G}eometric \textbf{C}onsistency in dynamically generated videos. We quantify geometric consistency by measuring the divergence among multiple camera poses estimated from distinct local regions. Our approach first separates static from dynamic regions, then partitions the static background into spatially coherent sub-regions. We predict depth for each pixel, estimate a local camera pose for each subregion, and compute the divergence among these poses to quantify geometric consistency. Experiments on real and generative videos demonstrate that SGC robustly quantifies geometric inconsistencies, effectively identifying critical failures missed by existing metrics.
Authors: Phuc Pham, Uy Dieu Tran, Binh-Son Hua, Phong Nguyen
Abstract: Realistic and efficient 3D garment generation remains a longstanding challenge in computer vision and digital fashion. Existing methods typically rely on large vision- language models to produce serialized representations of 2D sewing patterns, which are then transformed into simulation-ready 3D meshes using garment modeling framework such as GarmentCode. Although these approaches yield high-quality results, they often suffer from slow inference times, ranging from 30 seconds to a minute. In this work, we introduce SwiftTailor, a novel two-stage framework that unifies sewing-pattern reasoning and geometry-based mesh synthesis through a compact geometry image representation. SwiftTailor comprises two lightweight modules: PatternMaker, an efficient vision-language model that predicts sewing patterns from diverse input modalities, and GarmentSewer, an efficient dense prediction transformer that converts these patterns into a novel Garment Geometry Image, encoding the 3D surface of all garment panels in a unified UV space. The final 3D mesh is reconstructed through an efficient inverse mapping process that incorporates remeshing and dynamic stitching algorithms to directly assemble the garment, thereby amortizing the cost of physical simulation. Extensive experiments on the Multimodal GarmentCodeData demonstrate that SwiftTailor achieves state-of-the-art accuracy and visual fidelity while significantly reducing inference time. This work offers a scalable, interpretable, and high-performance solution for next-generation 3D garment generation.
Authors: Yikai Zheng, Xin Ding, Yifan Yang, Shiqi Jiang, Hao Wu, Qianxi Zhang, Weijun Wang, Ting Cao, Yunxin Liu
Abstract: Recent advances in Streaming Video Understanding has enabled a new interaction paradigm where models respond proactively to user queries. Current proactive VideoLLMs rely on per-frame triggering decision making, which suffers from an efficiency-accuracy dilemma. We propose Em-Garde, a novel framework that decouples semantic understanding from streaming perception. At query time, the Instruction-Guided Proposal Parser transforms user queries into structured, perceptually grounded visual proposals; during streaming, a Lightweight Proposal Matching Module performs efficient embedding-based matching to trigger responses. Experiments on StreamingBench and OVO-Bench demonstrate consistent improvements over prior models in proactive response accuracy and efficiency, validating an effective solution for proactive video understanding under strict computational constraints.
Authors: Oliver Cory, Ozge Mercanoglu Sincan, Richard Bowden
Abstract: This paper introduces SignAgent, a novel agentic framework that utilises Large Language Models (LLMs) for scalable, linguistically-grounded Sign Language (SL) annotation and dataset curation. Traditional computational methods for SLs often operate at the gloss level, overlooking crucial linguistic nuances, while manual linguistic annotation remains a significant bottleneck, proving too slow and expensive for the creation of large-scale, phonologically-aware datasets. SignAgent addresses these challenges through SignAgent Orchestrator, a reasoning LLM that coordinates a suite of linguistic tools, and SignGraph, a knowledge-grounded LLM that provides lexical and linguistic grounding. We evaluate our framework on two downstream annotation tasks. First, on Pseudo-gloss Annotation, where the agent performs constrained assignment, using multi-modal evidence to extract and order suitable gloss labels for signed sequences. Second, on ID Glossing, where the agent detects and refines visual clusters by reasoning over both visual similarity and phonological overlap to correctly identify and group lexical sign variants. Our results demonstrate that our agentic approach achieves strong performance for large-scale, linguistically-aware data annotation and curation.
Authors: Moyang Li, Zihan Zhu, Marc Pollefeys, Daniel Barath
Abstract: We present a robust, real-time RGB SLAM system that handles dynamic environments by leveraging differentiable Uncertainty-aware Bundle Adjustment. Traditional SLAM methods typically assume static scenes, leading to tracking failures in the presence of motion. Recent dynamic SLAM approaches attempt to address this challenge using predefined dynamic priors or uncertainty-aware mapping, but they remain limited when confronted with unknown dynamic objects or highly cluttered scenes where geometric mapping becomes unreliable. In contrast, our method estimates per-pixel uncertainty by exploiting multi-view visual feature inconsistency, enabling robust tracking and reconstruction even in real-world environments. The proposed system achieves state-of-the-art camera poses and scene geometry in cluttered dynamic scenarios while running in real time at around 10 FPS. Code and datasets are available at https://github.com/MoyangLi00/DROID-W.git.
Authors: Ye Wang, Wei Lu, Zhihui You, Keyan Chen, Tongfei Liu, Kaiyu Li, Hongruixuan Chen, Qingling Shu, Sibao Chen
Abstract: Change detection in optical remote sensing imagery is susceptible to illumination fluctuations, seasonal changes, and variations in surface land-cover materials. Relying solely on RGB imagery often produces pseudo-changes and leads to semantic ambiguity in features. Incorporating near-infrared (NIR) information provides heterogeneous physical cues that are complementary to visible light, thereby enhancing the discriminability of building materials and tiny structures while improving detection accuracy. However, existing multi-modal datasets generally lack high-resolution and accurately registered bi-temporal imagery, and current methods often fail to fully exploit the inherent heterogeneity between these modalities. To address these issues, we introduce the Large-scale Small-change Multi-modal Dataset (LSMD), a bi-temporal RGB-NIR building change detection benchmark dataset targeting small changes in realistic scenarios, providing a rigorous testing platform for evaluating multi-modal change detection methods in complex environments. Based on LSMD, we further propose the Multi-modal Spectral Complementarity Network (MSCNet) to achieve effective cross-modal feature fusion. MSCNet comprises three key components: the Neighborhood Context Enhancement Module (NCEM) to strengthen local spatial details, the Cross-modal Alignment and Interaction Module (CAIM) to enable deep interaction between RGB and NIR features, and the Saliency-aware Multisource Refinement Module (SMRM) to progressively refine fused features. Extensive experiments demonstrate that MSCNet effectively leverages multi-modal information and consistently outperforms existing methods under multiple input configurations, validating its efficacy for fine-grained building change detection. The source code will be made publicly available at: https://github.com/AeroVILab-AHU/LSMD
Authors: Carlos Hinojosa, Clemens Grange, Bernard Ghanem
Abstract: Vision-language models (VLMs) are increasingly deployed in real-world and embodied settings where safety decisions depend on visual context. However, it remains unclear which visual evidence drives these judgments. We study whether multimodal safety behavior in VLMs can be steered by simple semantic cues. We introduce a semantic steering framework that applies controlled textual, visual, and cognitive interventions without changing the underlying scene content. To evaluate these effects, we propose SAVeS, a benchmark for situational safety under semantic cues, together with an evaluation protocol that separates behavioral refusal, grounded safety reasoning, and false refusals. Experiments across multiple VLMs and an additional state-of-the-art benchmark show that safety decisions are highly sensitive to semantic cues, indicating reliance on learned visual-linguistic associations rather than grounded visual understanding. We further demonstrate that automated steering pipelines can exploit these mechanisms, highlighting a potential vulnerability in multimodal safety systems.
Authors: Yuqiang Lin, Kehua Chen, Sam Lockyer, Arjun Yadav, Mingxuan Sui, Shucheng Zhang, Yan Shi, Bingzhang Wang, Yuang Zhang, Markus Zarbock, Florain Stanek, Adrian Evans, Wenbin Li, Yinhai Wang, Nic Zhang
Abstract: Traffic Anomaly Understanding (TAU) is important for traffic safety in Intelligent Transportation Systems. Recent vision-language models (VLMs) have shown strong capabilities in video understanding. However, progress on TAU remains limited due to the lack of benchmarks and task-specific methodologies. To address this limitation, we introduce Roundabout-TAU, a dataset constructed from real-world roundabout videos collected in collaboration with the City of Carmel, Indiana. The dataset contains 342 clips and is annotated with more than 2,000 question-answer pairs covering multiple aspects of traffic anomaly understanding. Building on this benchmark, we propose TAU-R1, a two-layer vision-language framework for TAU. The first layer is a lightweight anomaly classifier that performs coarse anomaly categorisation, while the second layer is a larger anomaly reasoner that generates detailed event summaries. To improve task-specific reasoning, we introduce a two-stage training strategy consisting of decomposed-QA-enhanced supervised fine-tuning followed by TAU-GRPO, a GRPO-based post-training method with TAU-specific reward functions. Experimental results show that TAU-R1 achieves strong performance on both anomaly classification and reasoning tasks while maintaining deployment efficiency. The dataset and code are available at: https://github.com/siri-rouser/TAU-R1
Authors: Weilin Chen, Jiahao Rao, Wenhao Wang, Xinyang Li, Xuan Cheng, Liujuan Cao
Abstract: The creation of high-fidelity, customizable 3D indoor scene textures remains a significant challenge. While text-driven methods offer flexibility, they lack the precision for fine-grained, instance-level control, and often produce textures with insufficient quality, artifacts, and baked-in shading. To overcome these limitations, we introduce CustomTex, a novel framework for instance-level, high-fidelity scene texturing driven by reference images. CustomTex takes an untextured 3D scene and a set of reference images specifying the desired appearance for each object instance, and generates a unified, high-resolution texture map. The core of our method is a dual-distillation approach that separates semantic control from pixel-level enhancement. We employ semantic-level distillation, equipped with an instance cross-attention, to ensure semantic plausibility and ``reference-instance'' alignment, and pixel-level distillation to enforce high visual fidelity. Both are unified within a Variational Score Distillation (VSD) optimization framework. Experiments demonstrate that CustomTex achieves precise instance-level consistency with reference images and produces textures with superior sharpness, reduced artifacts, and minimal baked-in shading compared to state-of-the-art methods. Our work establishes a more direct and user-friendly path to high-quality, customizable 3D scene appearance editing.
Authors: Ilia Sudakov, Artem Babenko, Dmitry Baranchuk
Abstract: Class-conditional generative models have emerged as accurate and robust classifiers, with diffusion models demonstrating clear advantages over other visual generative paradigms, including autoregressive (AR) models. In this work, we revisit visual AR-based generative classifiers and identify an important limitation of prior approaches: their reliance on a fixed token order, which imposes a restrictive inductive bias for image understanding. We observe that single-order predictions rely more on partial discriminative cues, while averaging over multiple token orders provides a more comprehensive signal. Based on this insight, we leverage recent any-order AR models to estimate order-marginalized predictions, unlocking the high classification potential of AR models. Our approach consistently outperforms diffusion-based classifiers across diverse image classification benchmarks, while being up to 25x more efficient. Compared to state-of-the-art self-supervised discriminative models, our method delivers competitive classification performance - a notable achievement for generative classifiers.
Authors: Yiren Lu, Yi Du, Disheng Liu, Yunlai Zhou, Chen Wang, Yu Yin
Abstract: Effective embodied exploration requires agents to accumulate and retain spatial knowledge over time. However, existing scene representations, such as discrete scene graphs or static view-based snapshots, lack \textit{post-hoc re-observability}. If an initial observation misses a target, the resulting memory omission is often irrecoverable. To bridge this gap, we propose \textbf{GSMem}, a zero-shot embodied exploration and reasoning framework built upon 3D Gaussian Splatting (3DGS). By explicitly parameterizing continuous geometry and dense appearance, 3DGS serves as a persistent spatial memory that endows the agent with \textit{Spatial Recollection}: the ability to render photorealistic novel views from optimal, previously unoccupied viewpoints. To operationalize this, GSMem employs a retrieval mechanism that simultaneously leverages parallel object-level scene graphs and semantic-level language fields. This complementary design robustly localizes target regions, enabling the agent to ``hallucinate'' optimal views for high-fidelity Vision-Language Model (VLM) reasoning. Furthermore, we introduce a hybrid exploration strategy that combines VLM-driven semantic scoring with a 3DGS-based coverage objective, balancing task-aware exploration with geometric coverage. Extensive experiments on embodied question answering and lifelong navigation demonstrate the robustness and effectiveness of our framework
Authors: Kwanyoung Lee, Hyunwoo Oh, SeungJu Cha, Sungho Koh, Dong-Jin Kim
Abstract: Generating rare compositional concepts in text-to-image synthesis remains a challenge for diffusion models, particularly for attributes that are uncommon in the training data. While recent approaches, such as R2F, address this challenge by utilizing LLM for prompt scheduling, they suffer from inherent variance due to the randomness of language models and suboptimal guidance from iterative text embedding switching. To address these problems, we propose the ADAPT framework, a training-free framework that deterministically plans and semantically aligns prompt schedules, providing consistent guidance to enhance the composition of rare concepts. By leveraging attention scores and orthogonal components, ADAPT significantly enhances compositional generation of rare concepts in the RareBench benchmark without additional training or fine-tuning. Through comprehensive experiments, we demonstrate that ADAPT achieves superior performance in RareBench and accurately reflects the semantic information of rare attributes, providing deterministic and precise control over the generation of rare compositions without compromising visual integrity.
Authors: Kwanyoung Lee, SeungJu Cha, Yebin Ahn, Hyunwoo Oh, Sungho Koh, Dong-Jin Kim
Abstract: Diffusion-based text-to-image (T2I) models have made remarkable progress in generating photorealistic and semantically rich images. However, when the target concepts lie in low-density regions of the training distribution, these models often produce semantically misaligned or structurally inconsistent results. This limitation arises from the long-tailed nature of text-image datasets, where rare concepts or editing instructions are underrepresented. To address this, we introduce Adaptive Auxiliary Prompt Blending (AAPB) - a unified framework that stabilizes the diffusion process in low-density regions. AAPB leverages auxiliary anchor prompts to provide semantic support in rare concept generation and structural support in image editing, ensuring faithful guidance toward the target prompt. Unlike prior heuristic prompt alternation methods, AAPB derives a closed-form adaptive coefficient that optimally balances the influence between the auxiliary anchor and the target prompt at each diffusion step. Grounded in Tweedie's identity, our formulation provides a principled and training-free framework for adaptive prompt blending, ensuring stable and target-faithful generation. We demonstrate the effectiveness of adaptive interpolation over fixed interpolation through controlled experiments and empirically show consistent improvements on the RareBench and FlowEdit datasets, achieving superior semantic accuracy and structural fidelity compared to prior training-free baselines.
Authors: Zhan Jin, Yu Luo, Yizhou Zhang, Ziyang Cui, Yuqing Wei, Xianchao Liu, Xueying Zeng, Qing Zhang
Abstract: Conventional pixel-wise loss functions fail to enforce topological constraints in coronary vessel segmentation, producing fragmented vascular trees despite high pixel-level accuracy. We present ARIADNE, a two-stage framework coupling preference-aligned perception with RL-based diagnostic reasoning for topologically coherent stenosis detection. The perception module employs DPO to fine-tune the Sa2VA vision-language foundation model using Betti number constraints as preference signals, aligning the policy toward geometrically complete vessel structures rather than pixel-wise overlap metrics. The reasoning module formulates stenosis localization as a Markov Decision Process with an explicit rejection mechanism that autonomously defers ambiguous anatomical candidates such as bifurcations and vessel crossings, shifting from coverage maximization to reliability optimization. On 1,400 clinical angiograms, ARIADNE achieves state-of-the-art centerline Dice of 0.838, reduces false positives by 41% compared to geometric baselines. External validation on multi-center benchmarks ARCADE and XCAD confirms generalization across acquisition protocols. This represents the first application of DPO for topological alignment in medical imaging, demonstrating that preference-based learning over structural constraints mitigates topological violations while maintaining diagnostic sensitivity in interventional cardiology workflows.
Authors: Yiren Lu, Xin Ye, Burhaneddin Yaman, Jingru Luo, Zhexiao Xiong, Liu Ren, Yu Yin
Abstract: Bird's-Eye-View (BEV) perception serves as a cornerstone for autonomous driving, offering a unified spatial representation that fuses surrounding-view images to enable reasoning for various downstream tasks, such as semantic segmentation, 3D object detection, and motion prediction. However, most existing BEV perception frameworks adopt an end-to-end training paradigm, where image features are directly transformed into the BEV space and optimized solely through downstream task supervision. This formulation treats the entire perception process as a black box, often lacking explicit 3D geometric understanding and interpretability, leading to suboptimal performance. In this paper, we claim that an explicit 3D representation matters for accurate BEV perception, and we propose Splat2BEV, a Gaussian Splatting-assisted framework for BEV tasks. Splat2BEV aims to learn BEV feature representations that are both semantically rich and geometrically precise. We first pre-train a Gaussian generator that explicitly reconstructs 3D scenes from multi-view inputs, enabling the generation of geometry-aligned feature representations. These representations are then projected into the BEV space to serve as inputs for downstream tasks. Extensive experiments on nuScenes and argoverse dataset demonstrate that Splat2BEV achieves state-of-the-art performance and validate the effectiveness of incorporating explicit 3D reconstruction into BEV perception.
Authors: Wan-Cyuan Fan, Jiayun Luo, Declan Kutscher, Leonid Sigal, Ritwik Gupta
Abstract: Vision-Language Models (VLMs) have been shown to be blind, often underutilizing their visual inputs even on tasks that require visual reasoning. In this work, we demonstrate that VLMs are selectively blind. They modulate the amount of attention applied to visual inputs based on linguistic framing even when alternative framings demand identical visual reasoning. Using visual attention as a probe, we quantify how framing alters both the amount and distribution of attention over the image. Constrained framings, such as multiple choice and yes/no, induce substantially lower attention to image context compared to open-ended, reduce focus on task-relevant regions, and shift attention towards uninformative tokens. We further demonstrate that this attention misallocation is the principal cause of degraded accuracy and cross-framing inconsistency. Building on this mechanistic insight, we introduce a lightweight prompt-tuning method using learnable tokens that encourages the robust, visually grounded attention patterns observed in open-ended settings, improving visual grounding and improving performance across framings.
Authors: Yue Gong, Hongyu Li, Shanyuan Liu, Bo Cheng, Yuhang Ma, Liebucha Wu, Xiaoyu Wu, Manyuan Zhang, Dawei Leng, Yuhui Yin, Lijun Zhang
Abstract: Diffusion models have become the dominant paradigm for image generation and editing, with latent diffusion models shifting denoising to a compact latent space for efficiency and scalability. Recent attempts to leverage pretrained visual representation models as tokenizer priors either align diffusion features to representation features or directly reuse representation encoders as frozen tokenizers. Although such approaches can improve generation metrics, they often suffer from limited reconstruction fidelity due to frozen encoders, which in turn degrades editing quality, as well as overly high-dimensional latents that make diffusion modeling difficult. To address these limitations, We propose Representation-Pivoted AutoEncoder, a representation-based tokenizer that improves both generation and editing. We introduce Representation-Pivot Regularization, a training strategy that enables a representation-initialized encoder to be fine-tuned for reconstruction while preserving the semantic structure of the pretrained representation space, followed by a variational bridge which compress latent space into a compact one for better diffusion modeling. We adopt an objective-decoupled stage-wise training strategy that sequentially optimizes generative tractability and reconstruction-fidelity objectives. Together, these components yield a tokenizer that preserves strong semantics, reconstructs faithfully, and produces latents with reduced diffusion modeling complexity. Experiments demonstrate that RPiAE outperforms other visual tokenizers on text-to-image generation and image editing, while delivering the best reconstruction fidelity among representation-based tokenizers.
Authors: Shang-Jui Ray Kuo, Paola Cascante-Bonilla
Abstract: Large vision--language models (VLMs) often use a frozen vision backbone, whose image features are mapped into a large language model through a lightweight connector. While transformer-based encoders are the standard visual backbone, we ask whether state space model (SSM) vision backbones can be a strong alternative. We systematically evaluate SSM vision backbones for VLMs in a controlled setting. Under matched ImageNet-1K initialization, the SSM backbone achieves the strongest overall performance across both VQA and grounding/localization. We further adapt both SSM and ViT-family backbones with detection or segmentation training and find that dense-task tuning generally improves performance across families; after this adaptation, the SSM backbone remains competitive while operating at a substantially smaller model scale. We further observe that (i) higher ImageNet accuracy or larger backbones do not reliably translate into better VLM performance, and (ii) some visual backbones are unstable in localization. Based on these findings, we propose stabilization strategies that improve robustness for both backbone families and highlight SSM backbones as a strong alternative to transformer-based vision encoders in VLMs.
Authors: Tianjiao Yu, Xinzhuo Li, Muntasir Wahed, Jerry Xiong, Yifan Shen, Ying Shen, Ismini Lourentzou
Abstract: Understanding and generating 3D objects as compositions of meaningful parts is fundamental to human perception and reasoning. However, most text-to-3D methods overlook the semantic and functional structure of parts. While recent part-aware approaches introduce decomposition, they remain largely geometry-focused, lacking semantic grounding and failing to model how parts align with textual descriptions or their inter-part relations. We propose DreamPartGen, a framework for semantically grounded, part-aware text-to-3D generation. DreamPartGen introduces Duplex Part Latents (DPLs) that jointly model each part's geometry and appearance, and Relational Semantic Latents (RSLs) that capture inter-part dependencies derived from language. A synchronized co-denoising process enforces mutual geometric and semantic consistency, enabling coherent, interpretable, and text-aligned 3D synthesis. Across multiple benchmarks, DreamPartGen delivers state-of-the-art performance in geometric fidelity and text-shape alignment.
Authors: Keda Tao, Yuhua Zheng, Jia Xu, Wenjie Du, Kele Shao, Hesong Wang, Xueyi Chen, Xin Jin, Junhan Zhu, Bohan Yu, Weiqiang Wang, Jian Liu, Can Qin, Yulun Zhang, Ming-Hsuan Yang, Huan Wang
Abstract: Recent advancements in omnimodal large language models (OmniLLMs) have significantly improved the comprehension of audio and video inputs. However, current evaluations primarily focus on short audio and video clips ranging from 10 seconds to 5 minutes, failing to reflect the demands of real-world applications, where videos typically run for tens of minutes. To address this critical gap, we introduce LVOmniBench, a new benchmark designed specifically for the cross-modal comprehension of long-form audio and video. This dataset comprises high-quality videos sourced from open platforms that feature rich audio-visual dynamics. Through rigorous manual selection and annotation, LVOmniBench comprises 275 videos, ranging in duration from 10 to 90 minutes, and 1,014 question-answer (QA) pairs. LVOmniBench aims to rigorously evaluate the capabilities of OmniLLMs across domains, including long-term memory, temporal localization, fine-grained understanding, and multimodal perception. Our extensive evaluation reveals that current OmniLLMs encounter significant challenges when processing extended audio-visual inputs. Open-source models generally achieve accuracies below 35%, whereas the Gemini 3 Pro reaches a peak accuracy of approximately 65%. We anticipate that this dataset, along with our empirical findings, will stimulate further research and the development of advanced models capable of resolving complex cross-modal understanding problems within long-form audio-visual contexts.
Authors: Chaoyang Wang, Yaobo Liang, Boci Peng, Fan Duan, Jingdong Wang, Yunhai Tong
Abstract: Taming diffusion models for generative segmentation has attracted increasing attention. While existing approaches primarily focus on architectural tweaks or training heuristics, there remains a limited understanding of the intrinsic mismatch between continuous flow matching objectives and discrete perception tasks. In this work, we revisit diffusion segmentation from the perspective of vector field learning. We identify two key limitations of the commonly used flow matching objective: gradient vanishing and trajectory traversing, which result in slow convergence and poor class separation. To tackle these issues, we propose a principled vector field reshaping strategy that augments the learned velocity field with a detached distance-aware correction term. This correction introduces both attractive and repulsive interactions, enhancing gradient magnitudes near centroids while preserving the original diffusion training framework. Furthermore, we design a computationally efficient, quasi-random category encoding scheme inspired by Kronecker sequences, which integrates seamlessly with an end-to-end pixel neural field framework for pixel-level semantic alignment. Extensive experiments consistently demonstrate significant improvements over vanilla flow matching approaches, substantially narrowing the performance gap between generative segmentation and strong discriminative specialists.
Authors: Dong Zhuo, Wenzhao Zheng, Sicheng Zuo, Siming Yan, Lu Hou, Jie Zhou, Jiwen Lu
Abstract: With the growing adoption of vision-language-action models and world models in autonomous driving systems, scalable image tokenization becomes crucial as the interface for the visual modality. However, most existing tokenizers are designed for monocular and 2D scenes, leading to inefficiency and inter-view inconsistency when applied to high-resolution multi-view driving scenes. To address this, we propose DriveTok, an efficient 3D driving scene tokenizer for unified multi-view reconstruction and understanding. DriveTok first obtains semantically rich visual features from vision foundation models and then transforms them into the scene tokens with 3D deformable cross-attention. For decoding, we employ a multi-view transformer to reconstruct multi-view features from the scene tokens and use multiple heads to obtain RGB, depth, and semantic reconstructions. We also add a 3D head directly on the scene tokens for 3D semantic occupancy prediction for better spatial awareness. With the multiple training objectives, DriveTok learns unified scene tokens that integrate semantic, geometric, and textural information for efficient multi-view tokenization. Extensive experiments on the widely used nuScenes dataset demonstrate that the scene tokens from DriveTok perform well on image reconstruction, semantic segmentation, depth prediction, and 3D occupancy prediction tasks.
Authors: Carlos Esteves, Ameesh Makadia
Abstract: Denoising diffusion models are widely used for high-quality image and video generation. Their performance depends on noise schedules, which define the distribution of noise levels applied during training and the sequence of noise levels traversed during sampling. Noise schedules are typically handcrafted and require manual tuning across different resolutions. In this work, we propose a principled way to design per-instance noise schedules for pixel diffusion, based on the image's spectral properties. By deriving theoretical bounds on the efficacy of minimum and maximum noise levels, we design ``tight'' noise schedules that eliminate redundant steps. During inference, we propose to conditionally sample such noise schedules. Experiments show that our noise schedules improve generative quality of single-stage pixel diffusion models, particularly in the low-step regime.
Authors: Yang Fu, Yike Zheng, Ziyun Dai, Henghui Ding
Abstract: Video object removal aims to eliminate dynamic target objects and their visual effects, such as deformation, shadows, and reflections, while restoring seamless backgrounds. Recent diffusion-based video inpainting and object removal methods can remove the objects but often struggle to erase these effects and to synthesize coherent backgrounds. Beyond method limitations, progress is further hampered by the lack of a comprehensive dataset that systematically captures common object effects across varied environments for training and evaluation. To address this, we introduce VOR (Video Object Removal), a large-scale dataset that provides diverse paired videos, each consisting of one video where the target object is present with its effects and a counterpart where the object and effects are absent, with corresponding object masks. VOR contains 60K high-quality video pairs from captured and synthetic sources, covers five effects types, and spans a wide range of object categories as well as complex, dynamic multi-object scenes. Building on VOR, we propose EffectErase, an effect-aware video object removal method that treats video object insertion as the inverse auxiliary task within a reciprocal learning scheme. The model includes task-aware region guidance that focuses learning on affected areas and enables flexible task switching. Then, an insertion-removal consistency objective that encourages complementary behaviors and shared localization of effect regions and structural cues. Trained on VOR, EffectErase achieves superior performance in extensive experiments, delivering high-quality video object effect erasing across diverse scenarios.
Authors: Nobuo Yoshii, Xinran Nicole Han, Ryo Kawahara, Todd Zickler, Ko Nishino
Abstract: We introduce Multi-Object Generative Perception (MultiGP), a generative inverse rendering method for stochastic sampling of all radiometric constituents -- reflectance, texture, and illumination -- underlying object appearance from a single image. Our key idea to solve this inherently ambiguous radiometric disentanglement is to leverage the fact that while their texture and reflectance may differ, objects in the same scene are all lit by the same illumination. MultiGP exploits this consensus to produce samples of reflectance, texture, and illumination from a single image of known shapes based on four key technical contributions: a cascaded end-to-end architecture that combines image-space and angular-space disentanglement; Coordinated Guidance for diffusion convergence to a single consistent illumination estimate; Axial Attention applied to facilitate ``cross-talk'' between objects of different reflectance; and a Texture Extraction ControlNet to preserve high-frequency texture details while ensuring decoupling from estimated lighting. Experimental results demonstrate that MultiGP effectively leverages the complementary spatial and frequency characteristics of multiple object appearances to recover individual texture and reflectance as well as the common illumination.
Authors: Chenyang Gu, Mingyuan Zhang, Haozhe Xie, Zhongang Cai, Lei Yang, Ziwei Liu
Abstract: Prior motion generation largely follows two paradigms: continuous diffusion models that excel at kinematic control, and discrete token-based generators that are effective for semantic conditioning. To combine their strengths, we propose a three-stage framework comprising condition feature extraction (Perception), discrete token generation (Planning), and diffusion-based motion synthesis (Control). Central to this framework is MoTok, a diffusion-based discrete motion tokenizer that decouples semantic abstraction from fine-grained reconstruction by delegating motion recovery to a diffusion decoder, enabling compact single-layer tokens while preserving motion fidelity. For kinematic conditions, coarse constraints guide token generation during planning, while fine-grained constraints are enforced during control through diffusion-based optimization. This design prevents kinematic details from disrupting semantic token planning. On HumanML3D, our method significantly improves controllability and fidelity over MaskControl while using only one-sixth of the tokens, reducing trajectory error from 0.72 cm to 0.08 cm and FID from 0.083 to 0.029. Unlike prior methods that degrade under stronger kinematic constraints, ours improves fidelity, reducing FID from 0.033 to 0.014.
Authors: Xinyao Zhang, Wenkai Dong, Yuxin Song, Bo Fang, Qi Zhang, Jing Wang, Fan Chen, Hui Zhang, Haocheng Feng, Yu Lu, Hang Zhou, Chun Yuan, Jingdong Wang
Abstract: Current instruction-guided video editing models struggle to simultaneously balance precise semantic modifications with faithful motion preservation. While existing approaches rely on injecting explicit external priors (e.g., VLM features or structural conditions) to mitigate these issues, this reliance severely bottlenecks model robustness and generalization. To overcome this limitation, we present SAMA (factorized Semantic Anchoring and Motion Alignment), a framework that factorizes video editing into semantic anchoring and motion modeling. First, we introduce Semantic Anchoring, which establishes a reliable visual anchor by jointly predicting semantic tokens and video latents at sparse anchor frames, enabling purely instruction-aware structural planning. Second, Motion Alignment pre-trains the same backbone on motion-centric video restoration pretext tasks (cube inpainting, speed perturbation, and tube shuffle), enabling the model to internalize temporal dynamics directly from raw videos. SAMA is optimized with a two-stage pipeline: a factorized pre-training stage that learns inherent semantic-motion representations without paired video-instruction editing data, followed by supervised fine-tuning on paired editing data. Remarkably, the factorized pre-training alone already yields strong zero-shot video editing ability, validating the proposed factorization. SAMA achieves state-of-the-art performance among open-source models and is competitive with leading commercial systems (e.g., Kling-Omni). Code, models, and datasets will be released.
Authors: Haitian Li, Haozhe Xie, Junxiang Xu, Beichen Wen, Fangzhou Hong, Ziwei Liu
Abstract: Reconstructing articulated 3D objects from a single image requires jointly inferring object geometry, part structure, and motion parameters from limited visual evidence. A key difficulty lies in the entanglement between motion cues and object structure, which makes direct articulation regression unstable. Existing methods address this challenge through multi-view supervision, retrieval-based assembly, or auxiliary video generation, often sacrificing scalability or efficiency. We present MonoArt, a unified framework grounded in progressive structural reasoning. Rather than predicting articulation directly from image features, MonoArt progressively transforms visual observations into canonical geometry, structured part representations, and motion-aware embeddings within a single architecture. This structured reasoning process enables stable and interpretable articulation inference without external motion templates or multi-stage pipelines. Extensive experiments on PartNet-Mobility demonstrate that OM achieves state-of-the-art performance in both reconstruction accuracy and inference speed. The framework further generalizes to robotic manipulation and articulated scene reconstruction.
Authors: Yuqing Wang, Chuofan Ma, Zhijie Lin, Yao Teng, Lijun Yu, Shuai Wang, Jiaming Han, Jiashi Feng, Yi Jiang, Xihui Liu
Abstract: Visual generation with discrete tokens has gained significant attention as it enables a unified token prediction paradigm shared with language models, promising seamless multimodal architectures. However, current discrete generation methods remain limited to low-dimensional latent tokens (typically 8-32 dims), sacrificing the semantic richness essential for understanding. While high-dimensional pretrained representations (768-1024 dims) could bridge this gap, their discrete generation poses fundamental challenges. In this paper, we present Cubic Discrete Diffusion (CubiD), the first discrete generation model for high-dimensional representations. CubiD performs fine-grained masking throughout the high-dimensional discrete representation -- any dimension at any position can be masked and predicted from partial observations. This enables the model to learn rich correlations both within and across spatial positions, with the number of generation steps fixed at $T$ regardless of feature dimensionality, where $T \ll hwd$. On ImageNet-256, CubiD achieves state-of-the-art discrete generation with strong scaling behavior from 900M to 3.7B parameters. Crucially, we validate that these discretized tokens preserve original representation capabilities, demonstrating that the same discrete tokens can effectively serve both understanding and generation tasks. We hope this work will inspire future research toward unified multimodal architectures. Code is available at: https://github.com/YuqingWang1029/CubiD.
Authors: Zhilin Guo, Boqiao Zhang, Hakan Aktas, Kyle Fogarty, Jeffrey Hu, Nursena Koprucu Aslan, Wenzhao Li, Canberk Baykal, Albert Miao, Josef Bengtson, Chenliang Zhou, Weihao Xia, Cristina Nader Vasconcelos. Cengiz Oztireli
Abstract: The ability to render scenes at adjustable fidelity from a single model, known as level of detail (LoD), is crucial for practical deployment of 3D Gaussian Splatting (3DGS). Existing discrete LoD methods expose only a limited set of operating points, while concurrent continuous LoD approaches enable smoother scaling but often suffer noticeable quality degradation at full capacity, making LoD a costly design decision. We introduce Matryoshka Gaussian Splatting (MGS), a training framework that enables continuous LoD for standard 3DGS pipelines without sacrificing full-capacity rendering quality. MGS learns a single ordered set of Gaussians such that rendering any prefix, the first k splats, produces a coherent reconstruction whose fidelity improves smoothly with increasing budget. Our key idea is stochastic budget training: each iteration samples a random splat budget and optimises both the corresponding prefix and the full set. This strategy requires only two forward passes and introduces no architectural modifications. Experiments across four benchmarks and six baselines show that MGS matches the full-capacity performance of its backbone while enabling a continuous speed-quality trade-off from a single model. Extensive ablations on ordering strategies, training objectives, and model capacity further validate the designs.
Authors: Xianjin Wu, Dingkang Liang, Tianrui Feng, Kui Xia, Yumeng Zhang, Xiaofan Li, Xiao Tan, Xiang Bai
Abstract: While Multimodal Large Language Models demonstrate impressive semantic capabilities, they often suffer from spatial blindness, struggling with fine-grained geometric reasoning and physical dynamics. Existing solutions typically rely on explicit 3D modalities or complex geometric scaffolding, which are limited by data scarcity and generalization challenges. In this work, we propose a paradigm shift by leveraging the implicit spatial prior within large-scale video generation models. We posit that to synthesize temporally coherent videos, these models inherently learn robust 3D structural priors and physical laws. We introduce VEGA-3D (Video Extracted Generative Awareness), a plug-and-play framework that repurposes a pre-trained video diffusion model as a Latent World Simulator. By extracting spatiotemporal features from intermediate noise levels and integrating them with semantic representations via a token-level adaptive gated fusion mechanism, we enrich MLLMs with dense geometric cues without explicit 3D supervision. Extensive experiments across 3D scene understanding, spatial reasoning, and embodied manipulation benchmarks demonstrate that our method outperforms state-of-the-art baselines, validating that generative priors provide a scalable foundation for physical-world understanding. Code is publicly available at https://github.com/H-EmbodVis/VEGA-3D.
Authors: Xinyuan Qian, Xinjia Zhu, Alessio Brutti, Dong Liang
Abstract: TTM (Talking to Me) task is a pivotal component in understanding human social interactions, aiming to determine who is engaged in conversation with the camera-wearer. Traditional models often face challenges in real-world scenarios due to missing visual data, neglecting the role of head orientation, and background noise. This study addresses these limitations by introducing EgoAdapt, an adaptive framework designed for robust egocentric "Talking to Me" speaker detection under missing modalities. Specifically, EgoAdapt incorporates three key modules: (1) a Visual Speaker Target Recognition (VSTR) module that captures head orientation as a non-verbal cue and lip movement as a verbal cue, allowing a comprehensive interpretation of both verbal and non-verbal signals to address TTM, setting it apart from tasks focused solely on detecting speaking status; (2) a Parallel Shared-weight Audio (PSA) encoder for enhanced audio feature extraction in noisy environments; and (3) a Visual Modality Missing Awareness (VMMA) module that estimates the presence or absence of each modality at each frame to adjust the system response dynamically.Comprehensive evaluations on the TTM benchmark of the Ego4D dataset demonstrate that EgoAdapt achieves a mean Average Precision (mAP) of 67.39% and an Accuracy (Acc) of 62.01%, significantly outperforming the state-of-the-art method by 4.96% in Accuracy and 1.56% in mAP.
Authors: Saket Sanjeev Chaturvedi, Joshua Bergerson, Tanwi Mallick
Abstract: As large language models (LLMs) evolve into autonomous "AI scientists," they promise transformative advances but introduce novel vulnerabilities, from potential "biosafety risks" to "dangerous explosions." Ensuring trustworthy deployment in science requires a new paradigm centered on reliability (ensuring factual accuracy and reproducibility), safety (preventing unintentional physical or biological harm), and security (preventing malicious misuse). Existing general-purpose safety benchmarks are poorly suited for this purpose, suffering from a fundamental domain mismatch, limited threat coverage of science-specific vectors, and benchmark overfitting, which create a critical gap in vulnerability evaluation for scientific applications. This paper examines the unique security and safety landscape of LLM agents in science. We begin by synthesizing a detailed taxonomy of LLM threats contextualized for scientific research, to better understand the unique risks associated with LLMs in science. Next, we conceptualize a mechanism to address the evaluation gap by utilizing dedicated multi-agent systems for the automated generation of domain-specific adversarial security benchmarks. Based on our analysis, we outline how existing safety methods can be brought together and integrated into a conceptual multilayered defense framework designed to combine a red-teaming exercise and external boundary controls with a proactive internal Safety LLM Agent. Together, these conceptual elements provide a necessary structure for defining, evaluating, and creating comprehensive defense strategies for trustworthy LLM agent deployment in scientific disciplines.
Authors: Nikhil Gosala, B. Ravi Kiran, Senthil Yogamani, Abhinav Valada
Abstract: Monocular 3D object tracking aims to estimate temporally consistent 3D object poses across video frames, enabling autonomous agents to reason about scene dynamics. However, existing state-of-the-art approaches are fully supervised and rely on dense 3D annotations over long video sequences, which are expensive to obtain and difficult to scale. In this work, we address this fundamental limitation by proposing the first sparsely supervised framework for monocular 3D object tracking. Our approach decomposes the task into two sequential sub-problems: 2D query matching and 3D geometry estimation. Both components leverage the spatio-temporal consistency of image sequences to augment a sparse set of labeled samples and learn rich 2D and 3D representations of the scene. Leveraging these learned cues, our model automatically generates high-quality 3D pseudolabels across entire videos, effectively transforming sparse supervision into dense 3D track annotations. This enables existing fully-supervised trackers to effectively operate under extreme label sparsity. Extensive experiments on the KITTI and nuScenes datasets demonstrate that our method significantly improves tracking performance, achieving an improvement of up to 15.50 p.p. while using at most four ground truth annotations per track.
Authors: Zilin Huang, Zihao Sheng, Zhengyang Wan, Yansong Qu, Junwei You, Sicong Jiang, Sikai Chen
Abstract: Ensuring safe decision-making in autonomous vehicles remains a fundamental challenge despite rapid advances in end-to-end learning approaches. Traditional reinforcement learning (RL) methods rely on manually engineered rewards or sparse collision signals, which fail to capture the rich contextual understanding required for safe driving and make unsafe exploration unavoidable in real-world settings. Recent vision-language models (VLMs) offer promising semantic understanding capabilities; however, their high inference latency and susceptibility to hallucination hinder direct application to real-time vehicle control. To address these limitations, this paper proposes DriveVLM-RL, a neuroscience-inspired framework that integrates VLMs into RL through a dual-pathway architecture for safe and deployable autonomous driving. The framework decomposes semantic reward learning into a Static Pathway for continuous spatial safety assessment using CLIP-based contrasting language goals, and a Dynamic Pathway for attention-gated multi-frame semantic risk reasoning using a lightweight detector and a large VLM. A hierarchical reward synthesis mechanism fuses semantic signals with vehicle states, while an asynchronous training pipeline decouples expensive VLM inference from environment interaction. All VLM components are used only during offline training and are removed at deployment, ensuring real-time feasibility. Experiments in the CARLA simulator show significant improvements in collision avoidance, task success, and generalization across diverse traffic scenarios, including strong robustness under settings without explicit collision penalties. These results demonstrate that DriveVLM-RL provides a practical paradigm for integrating foundation models into autonomous driving without compromising real-time feasibility. Demo video and code are available at: https://zilin-huang.github.io/DriveVLM-RL-website/
Authors: Muhammad Mubashar, Fabio Cuzzolin
Abstract: Generative models, particularly Generative Adversarial Networks (GANs), often suffer from a lack of output diversity, frequently generating similar samples rather than a wide range of variations. This paper introduces a novel generalization of the GAN loss function based on Dempster-Shafer theory of evidence, applied to both the generator and discriminator. Additionally, we propose an architectural enhancement to the generator that enables it to predict a mass function for each image pixel. This modification allows the model to quantify uncertainty in its outputs and leverage this uncertainty to produce more diverse and representative generations. Experimental evidence shows that our approach not only improves generation variability but also provides a principled framework for modeling and interpreting uncertainty in generative processes.
Authors: Chuxuan Hu, Philip Li, Maxwell Yang, Daniel Kang
Abstract: During research, domain experts often ask analytical questions whose answers require integrating data from a wide range of web sources. Thus, they must spend substantial effort searching, extracting, and organizing raw data before analysis can begin. We formalize this process as the SODIUM task, where we conceptualize open domains such as the web as latent databases that must be systematically instantiated to support downstream querying. Solving SODIUM requires (1) conducting in-depth and specialized exploration of the open web, which is further strengthened by (2) exploiting structural correlations for systematic information extraction and (3) integrating collected information into coherent, queryable database instances. To quantify the challenges in automating SODIUM, we construct SODIUM-Bench, a benchmark of 105 tasks derived from published academic papers across 6 domains, where systems are tasked with exploring the open web to collect and aggregate data from diverse sources into structured tables. Existing systems struggle with SODIUM tasks: we evaluate 6 advanced AI agents on SODIUM-Bench, with the strongest baseline achieving only 46.5% accuracy. To bridge this gap, we develop SODIUM-Agent, a multi-agent system composed of a web explorer and a cache manager. Powered by our proposed ATP-BFS algorithm and optimized through principled management of cached sources and navigation paths, SODIUM-Agent conducts deep and comprehensive web exploration and performs structurally coherent information extraction. SODIUM-Agent achieves 91.1% accuracy on SODIUM-Bench, outperforming the strongest baseline by approximately 2 times and the weakest by up to 73 times.
Authors: Yinghui Li, Jiayi Kuang, Peng Xing, Daixian Liu, Junnan Dong, Shu-Yu Guo, Yangning Li, Qingyu Zhou, Wenhao Jiang, Hai-Tao Zheng, Ying Shen, Liang Lin, Philip S. Yu
Abstract: While Multimodal Large Language Models (MLLMs) have achieved remarkable success in interpreting natural scenes, their ability to process discrete symbols -- the fundamental building blocks of human cognition -- remains a critical open question. Unlike continuous visual data, symbols such as mathematical formulas, chemical structures, and linguistic characters require precise, deeper interpretation. This paper introduces a comprehensive benchmark to evaluate how top-tier MLLMs navigate these "discrete semantic spaces" across five domains: language, culture, mathematics, physics, and chemistry. Our investigation uncovers a counterintuitive phenomenon: models often fail at basic symbol recognition yet succeed in complex reasoning tasks, suggesting they rely on linguistic probability rather than true visual perception. By exposing this "cognitive mismatch", we highlight a significant gap in current AI capabilities: the struggle to truly perceive and understand the symbolic languages that underpin scientific discovery and abstract thought. This work offers a roadmap for developing more rigorous, human-aligned intelligent systems.
Authors: Haonan Ping, Jian Jiang, Cheng Yuan, Qizhen Sun, Lv Wu, Yutong Ban
Abstract: Accurate segmentation of tissues and instruments in surgical scenes is annotation-intensive due to irregular shapes, thin structures, specularities, and frequent occlusions. While SAM models support point, box, and mask prompts, points are often too sparse and boxes too coarse to localize such challenging targets. We present SCISSR, a scribble-promptable framework for interactive surgical scene segmentation. It introduces a lightweight Scribble Encoder that converts freehand scribbles into dense prompt embeddings compatible with the mask decoder, enabling iterative refinement for a target object by drawing corrective strokes on error regions. Because all added modules (the Scribble Encoder, Spatial Gated Fusion, and LoRA adapters) interact with the backbone only through its standard embedding interfaces, the framework is not tied to a single model: we build on SAM 2 in this work, yet the same components transfer to other prompt-driven segmentation architectures such as SAM 3 without structural modification. To preserve pre-trained capabilities, we train only these lightweight additions while keeping the remaining backbone frozen. Experiments on EndoVis 2018 demonstrate strong in-domain performance, while evaluation on the out-of-distribution CholecSeg8k further confirms robustness across surgical domains. SCISSR achieves 95.41% Dice on EndoVis 2018 with five interaction rounds and 96.30% Dice on CholecSeg8k with three interaction rounds, outperforming iterative point prompting on both benchmarks.
Authors: Xue Yang, Rigui Zhou, Shizheng Jia, Dax Enshan Koh, Siong Thye Goh, Yaochong Li, Hongyu Chen, Fuhui Xiong
Abstract: Quantum Generative Adversarial Networks (QGANs) offer a promising path for learning data distributions on near-term quantum devices. However, existing QGANs for image synthesis avoid direct full-image generation, relying on classical post-processing or patch-based methods. These approaches dilute the quantum generator's role and struggle to capture global image semantics. To address this, we propose ReQGAN, an end-to-end framework that synthesizes an entire N=2^D-pixel image using a single D-qubit quantum circuit. ReQGAN overcomes two fundamental bottlenecks hindering direct pixel generation: (1) the rigid classical-to-quantum noise interface and (2) the output mismatch between normalized quantum statistics and the desired pixel-intensity space. We introduce a learnable Neural Noise Encoder for adaptive state preparation and a differentiable Intensity Calibration module to map measurements to a stable, visually meaningful pixel domain. Experiments on MNIST and Fashion-MNIST demonstrate that ReQGAN achieves stable training and effective image synthesis under stringent qubit budgets, with ablation studies verifying the contribution of each component.
Authors: Xiang Zhou, Hong Shang, Zijian Zhan, Tianyu He, Jintao Meng, Dong Liang
Abstract: Deep unrolled models (DUMs) have become the state of the art for accelerated MRI reconstruction, yet their robustness under domain shift remains a critical barrier to clinical adoption. In this work, we identify coil sensitivity map (CSM) estimation as the primary bottleneck limiting generalization. To address this, we propose UEPS, a novel DUM architecture featuring three key innovations: (i) an Unrolled Expanded (UE) design that eliminates CSM dependency by reconstructing each coil independently; (ii) progressive resolution, which leverages k-space-to-image mapping for efficient coarse-to-fine refinement; and (iii) sparse attention tailored to MRI's 1D undersampling nature. These physics-grounded designs enable simultaneous gains in robustness and computational efficiency. We construct a large-scale zero-shot transfer benchmark comprising 10 out-of-distribution test sets spanning diverse clinical shifts -- anatomy, view, contrast, vendor, field strength, and coil configurations. Extensive experiments demonstrate that UEPS consistently and substantially outperforms existing DUM, end-to-end, diffusion, and untrained methods across all OOD tests, achieving state-of-the-art robustness with low-latency inference suitable for real-time deployment.
Authors: Xuan Liu, Xiaobin Chang
Abstract: Weight regularization methods in continual learning (CL) alleviate catastrophic forgetting by assessing and penalizing changes to important model weights. Elastic Weight Consolidation (EWC) is a foundational and widely used approach within this framework that estimates weight importance based on gradients. However, it has consistently shown suboptimal performance. In this paper, we conduct a systematic analysis of importance estimation in EWC from a gradient-based perspective. For the first time, we find that EWC's reliance on the Fisher Information Matrix (FIM) results in gradient vanishing and inaccurate importance estimation in certain scenarios. Our analysis also reveals that Memory Aware Synapses (MAS), a variant of EWC, imposes unnecessary constraints on parameters irrelevant to prior tasks, termed the redundant protection. Consequently, both EWC and its variants exhibit fundamental misalignments in estimating weight importance, leading to inferior performance. To tackle these issues, we propose the Logits Reversal (LR) operation, a simple yet effective modification that rectifies EWC's importance estimation. Specifically, reversing the logit values during the calculation of FIM can effectively prevent both gradient vanishing and redundant protection. Extensive experiments across various CL tasks and datasets show that the proposed method significantly outperforms existing EWC and its variants. Therefore, we refer to it as EWC Done Right (EWC-DR).
Authors: Thi Huyen Nguyen, Koustav Rudra, Wolfgang Nejdl
Abstract: Advances in social media data dissemination enable the provision of real-time information during a crisis. The information comes from different classes, such as infrastructure damages, persons missing or stranded in the affected zone, etc. Existing methods attempted to classify text and images into various humanitarian categories, but their decision-making process remains largely opaque, which affects their deployment in real-life applications. Recent work has sought to improve transparency by extracting textual rationales from tweets to explain predicted classes. However, such explainable classification methods have mostly focused on text, rather than crisis-related images. In this paper, we propose an interpretable-by-design multimodal classification framework. Our method first learns the joint representation of text and image using a visual language transformer model and extracts text rationales. Next, it extracts the image rationales via the mapping with text rationales. Our approach demonstrates how to learn rationales in one modality from another through cross-modal rationale transfer, which saves annotation effort. Finally, tweets are classified based on extracted rationales. Experiments are conducted over CrisisMMD benchmark dataset, and results show that our proposed method boosts the classification Macro-F1 by 2-35% while extracting accurate text tokens and image patches as rationales. Human evaluation also supports the claim that our proposed method is able to retrieve better image rationale patches (12%) that help to identify humanitarian classes. Our method adapts well to new, unseen datasets in zero-shot mode, achieving an accuracy of 80%.
Authors: Shuqi Xiao, Maani Ghaffari, Chengzhong Xu, Hui Kong
Abstract: Zero-shot object-goal navigation (ZSON) requires navigating unknown environments to find a target object without task-specific training. Prior hierarchical training-free solutions invest in scene understanding (\textit{belief}) and high-level decision-making (\textit{policy}), yet overlook the design of \textit{option}, i.e., a subgoal candidate proposed from evolving belief and presented to policy for selection. In practice, options are reduced to isolated waypoints scored independently: single destinations hide the value gathered along the journey; an unstructured collection obscures the relationships among candidates. Our insight is that the option space should be a \textit{tree of paths}. Full paths expose en-route information gain that destination-only scoring systematically neglects; a tree of shared segments enables coarse-to-fine LLM reasoning that dismisses or pursues entire branches before examining individual leaves, compressing the combinatorial path space into an efficient hierarchy. We instantiate this insight in \textbf{REST} (Receding Horizon Explorative Steiner Tree), a training-free framework that (1) builds an explicit open-vocabulary 3D map from online RGB-D streams; (2) grows an agent-centric tree of safe and informative paths as the option space via sampling-based planning; and (3) textualizes each branch into a spatial narrative and selects the next-best path through chain-of-thought LLM reasoning. Across the Gibson, HM3D, and HSSD benchmarks, REST consistently ranks among the top methods in success rate while achieving the best or second-best path efficiency, demonstrating a favorable efficiency-success balance.
Authors: Joerg H. Mueller, Martin Winter, Markus Steinberger
Abstract: Recent advancements in Gaussian Splatting (3DGS) have introduced various modifications to the original kernel, resulting in significant performance improvements. However, many of these kernel changes are incompatible with existing datasets optimized for the original Gaussian kernel, presenting a challenge for widespread adoption. In this work, we address this challenge by proposing an alternative kernel that maintains compatibility with existing datasets while improving computational efficiency. Specifically, we replace the original exponential kernel with a polynomial approximation combined with a ReLU function. This modification allows for more aggressive culling of Gaussians, leading to enhanced performance across different 3DGS implementations. Our results show a notable performance improvement of 4 to 15% with negligible impact on image quality. We also provide a detailed mathematical analysis of the new kernel and discuss its potential benefits for 3DGS implementations on NPU hardware.
Authors: Hung-Yue Suen, Kuo-En Hung, Fan-Hsun Tseng
Abstract: This paper outlines a machine learning-enabled speaker-centric Emotion AI approach capable of predicting audience-affective engagement and vocal attractiveness in asynchronous video-based learning, relying solely on speaker-side affective expressions. Inspired by the demand for scalable, privacy-preserving affective computing applications, this speaker-centric Emotion AI approach incorporates two distinct regression models that leverage a massive corpus developed within Massive Open Online Courses (MOOCs) to enable affectively engaging experiences. The regression model predicting affective engagement is developed by assimilating emotional expressions emanating from facial dynamics, oculomotor features, prosody, and cognitive semantics, while incorporating a second regression model to predict vocal attractiveness based exclusively on speaker-side acoustic features. Notably, on speaker-independent test sets, both regression models yielded impressive predictive performance (R2 = 0.85 for affective engagement and R2 = 0.88 for vocal attractiveness), confirming that speaker-side affect can functionally represent aggregated audience feedback. This paper provides a speaker-centric Emotion AI approach substantiated by an empirical study discovering that speaker-side multimodal features, including acoustics, can prospectively forecast audience feedback without necessarily employing audience-side input information.
Authors: Swagat Padhan, Lakshya Jain, Bhavya Minesh Shah, Omkar Patil, Thao Nguyen, Nakul Gopalan
Abstract: Robots collaborating with humans must convert natural language goals into actionable, physically grounded decisions. For example, executing a command such as "go two meters to the right of the fridge" requires grounding semantic references, spatial relations, and metric constraints within a 3D scene. While recent vision language models (VLMs) demonstrate strong semantic grounding capabilities, they are not explicitly designed to reason about metric constraints in physically defined spaces. In this work, we empirically demonstrate that state-of-the-art VLM-based grounding approaches struggle with complex metric-semantic language queries. To address this limitation, we propose MAPG (Multi-Agent Probabilistic Grounding), an agentic framework that decomposes language queries into structured subcomponents and queries a VLM to ground each component. MAPG then probabilistically composes these grounded outputs to produce metrically consistent, actionable decisions in 3D space. We evaluate MAPG on the HM-EQA benchmark and show consistent performance improvements over strong baselines. Furthermore, we introduce a new benchmark, MAPG-Bench, specifically designed to evaluate metric-semantic goal grounding, addressing a gap in existing language grounding evaluations. We also present a real-world robot demonstration showing that MAPG transfers beyond simulation when a structured scene representation is available.
Authors: Amandine Brunetto
Abstract: Generating audio that is acoustically consistent with a scene is essential for immersive virtual environments. Recent neural acoustic field methods enable spatially continuous sound rendering but remain scene-specific, requiring dense audio measurements and costly training for each environment. Few-shot approaches improve scalability across rooms but still rely on multiple recordings and, being deterministic, fail to capture the inherent uncertainty of scene acoustics under sparse context. We introduce flow-matching acoustic generation (FLAC), a probabilistic method for few-shot acoustic synthesis that models the distribution of plausible room impulse responses (RIRs) given minimal scene context. FLAC leverages a diffusion transformer trained with a flow-matching objective to generate RIRs at arbitrary positions in novel scenes, conditioned on spatial, geometric, and acoustic cues. FLAC outperforms state-of-the-art eight-shot baselines with one-shot on both the AcousticRooms and Hearing Anything Anywhere datasets. To complement standard perceptual metrics, we further introduce AGREE, a joint acoustic-geometry embedding, enabling geometry-consistent evaluation of generated RIRs through retrieval and distributional metrics. This work is the first to apply generative flow matching to explicit RIR synthesis, establishing a new direction for robust and data-efficient acoustic synthesis.
Authors: Yuxiang Lu, Zhe Liu, Xianzhe Fan, Zhenya Yang, Jinghua Hou, Junyi Li, Kaixin Ding, Hengshuang Zhao
Abstract: Real-time execution is crucial for deploying Vision-Language-Action (VLA) models in the physical world. Existing asynchronous inference methods primarily optimize trajectory smoothness, but neglect the critical latency in reacting to environmental changes. By rethinking the notion of reaction in action chunking policies, this paper presents a systematic analysis of the factors governing reaction time. We show that reaction time follows a uniform distribution determined jointly by the Time to First Action (TTFA) and the execution horizon. Moreover, we reveal that the standard practice of applying a constant schedule in flow-based VLAs can be inefficient and forces the system to complete all sampling steps before any movement can start, forming the bottleneck in reaction latency. To overcome this issue, we propose Fast Action Sampling for ImmediaTE Reaction (FASTER). By introducing a Horizon-Aware Schedule, FASTER adaptively prioritizes near-term actions during flow sampling, compressing the denoising of the immediate reaction by tenfold (e.g., in $\pi_{0.5}$ and X-VLA) into a single step, while preserving the quality of long-horizon trajectory. Coupled with a streaming client-server pipeline, FASTER substantially reduces the effective reaction latency on real robots, especially when deployed on consumer-grade GPUs. Real-world experiments, including a highly dynamic table tennis task, prove that FASTER unlocks unprecedented real-time responsiveness for generalist policies, enabling rapid generation of accurate and smooth trajectories.
Authors: Huaide Jiang, Yash Chaudhary, Yuping Wang, Zehao Wang, Raghav Sharma, Manan Mehta, Yang Zhou, Lichao Sun, Zhiwen Fan, Zhengzhong Tu, Jiachen Li
Abstract: There are two major categories of embodied navigation: Vision-Language Navigation (VLN), where agents navigate by following natural language instructions; and Object-Goal Navigation (OGN), where agents navigate to a specified target object. However, existing work primarily evaluates model performance under nominal conditions, overlooking the potential corruptions that arise in real-world settings. To address this gap, we present NavTrust, a unified benchmark that systematically corrupts input modalities, including RGB, depth, and instructions, in realistic scenarios and evaluates their impact on navigation performance. To our best knowledge, NavTrust is the first benchmark that exposes embodied navigation agents to diverse RGB-Depth corruptions and instruction variations in a unified framework. Our extensive evaluation of seven state-of-the-art approaches reveals substantial performance degradation under realistic corruptions, which highlights critical robustness gaps and provides a roadmap toward more trustworthy embodied navigation systems. Furthermore, we systematically evaluate four distinct mitigation strategies to enhance robustness against RGB-Depth and instructions corruptions. Our base models include Uni-NaVid and ETPNav. We deployed them on a real mobile robot and observed improved robustness to corruptions. The project website is: https://navtrust.github.io.
Authors: Laila Khalid, Wei Gong
Abstract: Fashion-focused artificial intelligence has rapidly advanced in recent years, driven by deep learning and its deployment in recommender systems, detection, retrieval, and analytics. Yet several consumer-facing domains remain comparatively under-surveyed despite their practical impact. This work provides a comprehensive review of methods, datasets, and evaluation metrics across four such domains: aesthetics, personalization, virtual try-on, and forecasting. We synthesize technical approaches spanning representation learning, preference modeling, image transformation, and time-series analysis; relate them to downstream recommender systems and user experience; and highlight cross-domain dependencies (e.g., aesthetics-informed personalization, trend-informed recommendations). We also catalog commonly used datasets and metrics, including those from object detection and image segmentation pipelines, where relevant to try-on and visual understanding. Finally, we identify open challenges and promising directions for integrated AI-driven fashion systems.
Authors: Jianjian Qin, Chao Zhang, Chunzhi Gu, Zi Wang, Jun Yu, Yijin Wei, Hui Xiao, Xin Yu
Abstract: We present PD-REAL, a novel large-scale dataset for unsupervised anomaly detection (AD) in the 3D domain. It is motivated by the fact that 2D-only representations in the AD task may fail to capture the geometric structures of anomalies due to uncertainty in lighting conditions or shooting angles. PD-REAL consists entirely of Play-Doh models for 15 object categories and focuses on the analysis of potential benefits from 3D information in a controlled environment. Specifically, objects are first created with six types of anomalies, such as \textit{dent}, \textit{crack}, or \textit{perforation}, and then photographed under different lighting conditions to mimic real-world inspection scenarios. To demonstrate the usefulness of 3D information, we use a commercially available RealSense camera to capture RGB and depth images. Compared to the existing 3D dataset for AD tasks, the data acquisition of PD-REAL is significantly cheaper, easily scalable, and easier to control variables. Furthermore, we introduce a multi-scale teacher--student framework with hierarchical distillation for multimodal anomaly detection. This architecture overcomes the inherent limitation of single-scale distillation approaches, which often struggle to reconcile global context with local features. Leveraging multi-level guidance from the teacher network, the student network can effectively capture richer features for anomaly detection. Extensive evaluations with our method and state-of-the-art AD algorithms on our dataset qualitatively and quantitatively demonstrate the higher detection accuracy of our method. Our dataset can be downloaded from https://github.com/Andy-cs008/PD-REAL
Authors: Vaibhav Vavilala, Florian Kluger, Seemandhar Jain, Bodo Rosenhahn, Anand Bhattad, David Forsyth
Abstract: Describing a scene in terms of primitives -- geometrically simple shapes that offer a parsimonious but accurate abstraction of structure -- is an established and difficult fitting problem. Different scenes require different numbers of primitives, and these primitives interact strongly. Existing methods are evaluated by comparing predicted depth, normals, and segmentation against ground truth. The state of the art method involves a learned regression procedure to predict a start point consisting of a fixed number of primitives, followed by a descent method to refine the geometry and remove redundant primitives. CSG (Constructive Solid Geometry) representations are significantly enhanced by a set-differencing operation. Our representation incorporates negative primitives, which are differenced from the positive primitives. These notably enrich the geometry that the model can encode, while complicating the fitting problem. This paper presents a method that can (a) incorporate these negative primitives and (b) choose the overall number of positive and negative primitives by ensembling. Extensive experiments on the standard NYUv2 dataset confirm that (a) this approach results in substantial improvements in depth representation and segmentation over SOTA and (b) negative primitives improve fitting accuracy. Our method is robustly applicable across datasets: in a first, we evaluate primitive prediction for LAION images.
Authors: Wei Peng, Tian Xia, Fabio De Sousa Ribeiro, Tomas Bosschieter, Ehsan Adeli, Qingyu Zhao, Ben Glocker, Kilian M. Pohl
Abstract: The number of samples in structural brain MRI studies is often too small to properly train deep learning models. Generative models show promise in addressing this issue by effectively learning the data distribution and generating high-fidelity MRI. However, they struggle to produce diverse, high-quality data outside the distribution defined by the training data. One way to address this issue is to use causal models developed for 3D volume counterfactuals. However, accurately modeling causality in high-dimensional spaces is challenging, so these models generally generate 3D brain MRIs of lower quality. To address these challenges, we propose a two-stage method that constructs a Structural Causal Model (SCM) within the latent space. In the first stage, we employ a VQ-VAE to learn a compact embedding of the MRI volume. Subsequently, we integrate our causal model into this latent space and execute a three-step counterfactual procedure using a closed-form Generalized Linear Model (GLM). Our experiments conducted on real-world high-resolution MRI data (1 mm) provided by the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA) demonstrate that our method can generate high-quality 3D MRI counterfactuals.
Authors: Yifan Zhang, Junhui Hou
Abstract: Cross-modal contrastive distillation has recently been explored for learning effective 3D representations. However, existing methods focus primarily on modality-shared features, neglecting the modality-specific features during the pre-training process, which leads to suboptimal representations. In this paper, we theoretically analyze the limitations of current contrastive methods for 3D representation learning and propose a new framework, namely CMCR (Cross-Modal Comprehensive Representation Learning), to address these shortcomings. Our approach improves upon traditional methods by better integrating both modality-shared and modality-specific features. Specifically, we introduce masked image modeling and occupancy estimation tasks to guide the network in learning more comprehensive modality-specific features. Furthermore, we propose a novel multi-modal unified codebook that learns an embedding space shared across different modalities. Besides, we introduce geometry-enhanced masked image modeling to further boost 3D representation learning. Extensive experiments demonstrate that our method mitigates the challenges faced by traditional approaches and consistently outperforms existing image-to-LiDAR contrastive distillation methods in downstream tasks. Code will be available at https://github.com/Eaphan/CMCR.
Authors: Yuanzhi Zhu, Ruiqing Wang, Shilin Lu, Junnan Li, Hanshu Yan, Kai Zhang
Abstract: Recent advances in diffusion and flow-based generative models have demonstrated remarkable success in image restoration tasks, achieving superior perceptual quality compared to traditional deep learning approaches. However, these methods either require numerous sampling steps to generate high-quality images, resulting in significant computational overhead, or rely on common model distillation, which usually imposes a fixed fidelity-realism trade-off and thus lacks flexibility. In this paper, we introduce OFTSR, a novel flow-based framework for one-step image super-resolution that can produce outputs with tunable levels of fidelity and realism. Our approach first trains a conditional flow-based super-resolution model to serve as a teacher model. We then distill this teacher model by applying a specialized constraint. Specifically, we force the predictions from our one-step student model for same input to lie on the same sampling ODE trajectory of the teacher model. This alignment ensures that the student model's single-step predictions from initial states match the teacher's predictions from a closer intermediate state. Through extensive experiments on datasets including FFHQ (256$\times$256), DIV2K, and ImageNet (256$\times$256), we demonstrate that OFTSR achieves state-of-the-art performance for one-step image super-resolution, while having the ability to flexibly tune the fidelity-realism trade-off. Codes: \href{https://github.com/yuanzhi-zhu/OFTSR}{https://github.com/yuanzhi-zhu/OFTSR}.
URLs: https://github.com/yuanzhi-zhu/OFTSR, https://github.com/yuanzhi-zhu/OFTSR
Authors: Zehao Chen, Rong Pan
Abstract: Scalable Vector Graphics (SVG) are essential XML-based formats for versatile graphics, offering resolution independence and scalability. Unlike raster images, SVGs use geometric shapes and support interactivity, animation, and manipulation via CSS and JavaScript. Current SVG generation methods face challenges related to high computational costs and complexity. In contrast, human designers use component-based tools for efficient SVG creation. Inspired by this, SVGBuilder introduces a component-based, autoregressive model for generating high-quality colored SVGs from textual input. It significantly reduces computational overhead and improves efficiency compared to traditional methods. Our model generates SVGs up to 604 times faster than optimization-based approaches. To address the limitations of existing SVG datasets and support our research, we introduce ColorSVG-100K, the first large-scale dataset of colored SVGs, comprising 100,000 graphics. This dataset fills the gap in color information for SVG generation models and enhances diversity in model training. Evaluation against state-of-the-art models demonstrates SVGBuilder's superior performance in practical applications, highlighting its efficiency and quality in generating complex SVG graphics.
Authors: Harrish Thasarathan, Julian Forsyth, Thomas Fel, Matthew Kowal, Konstantinos G. Derpanis
Abstract: We present Universal Sparse Autoencoders (USAEs), a framework for uncovering and aligning interpretable concepts spanning multiple pretrained deep neural networks. Unlike existing concept-based interpretability methods, which focus on a single model, USAEs jointly learn a universal concept space that can reconstruct and interpret the internal activations of multiple models at once. Our core insight is to train a single, overcomplete sparse autoencoder (SAE) that ingests activations from any model and decodes them to approximate the activations of any other model under consideration. By optimizing a shared objective, the learned dictionary captures common factors of variation-concepts-across different tasks, architectures, and datasets. We show that USAEs discover semantically coherent and important universal concepts across vision models; ranging from low-level features (e.g., colors and textures) to higher-level structures (e.g., parts and objects). Overall, USAEs provide a powerful new method for interpretable cross-model analysis and offers novel applications, such as coordinated activation maximization, that open avenues for deeper insights in multi-model AI systems
Authors: Keyan Chen, Chenyang Liu, Bowen Chen, Wenyuan Li, Zhengxia Zou, Shijian Lu, Zhenwei Shi
Abstract: The advancement of RS technology has enabled high-resolution Earth observation; however, interpreting these images using modern VFMs remains a significant challenge. Unlike object-centric natural images, RS imagery is fundamentally characterized by extreme target sparsity and massive spatial redundancy. Key objects of interest (e.g., ships, vehicles) often occupy less than 1% of the spatial extent, surrounded by vast, target-free backgrounds. Existing VFMs predominantly rely on uniform dense processing (e.g., ViTs) and pixel-reconstruction pre-training paradigms (e.g., MAE). These approaches inherently waste substantial computational capacity on modeling redundant backgrounds and inadvertently dilute the feature representations of small, sparse targets. To bridge this structural misalignment, we propose DynamicVis, a visual foundation model explicitly tailored to the sparse nature of RS imagery. Architecturally, DynamicVis introduces a Dynamic Region-Aware SSM that bypasses uniform computation. It adaptively routes and incrementally models only task-relevant, high-salience tokens while employing a parameter-free integration for background context, drastically reducing the complexity of processing ultra-long 2D token sequences ($\sim$100,000). Crucially, to equip the network with robust spatial-selection capabilities, we propose a novel Region-Level Meta-Embedding Multi-Instance Learning (MIL) pre-training paradigm. Trained on a million-scale dataset, this paradigm explicitly disentangles sparse foreground instances from dense backgrounds in the latent semantic space, overcoming the semantic ambiguity of conventional pixel-reconstruction methods. Extensive evaluations across nine diverse downstream tasks reveal that DynamicVis exhibits exceptional efficacy, particularly dominating in sparse-target and instance-level perception tasks (e.g., small object detection, and change detection).
Authors: Abdelrahman Shaker, Muhammad Maaz, Chenhui Gou, Hamid Rezatofighi, Salman Khan, Fahad Shahbaz Khan
Abstract: Video understanding models often struggle with high computational requirements, extensive parameter counts, and slow inference speed, making them inefficient for practical use. To tackle these challenges, we propose Mobile-VideoGPT, an efficient multimodal framework designed to operate with fewer than a billion parameters. Unlike traditional video large multimodal models (LMMs), Mobile-VideoGPT consists of lightweight dual visual encoders, efficient projectors, and a small language model (SLM), enabling real-time throughput. To further improve efficiency, we present an Attention-Based Frame Scoring mechanism to select the key-frames, along with an efficient token projector that prunes redundant visual tokens and preserves essential contextual cues. We evaluate our model across well-established six video understanding benchmarks (e.g., MVBench, EgoSchema, NextQA, and PercepTest). Our results show that Mobile-VideoGPT-0.5B can generate up to 46 tokens per second while outperforming existing state-of-the-art 0.5B-parameter models by 6 points on average with 40% fewer parameters and more than 2x higher throughput. Our code and models are publicly available at: https://github.com/Amshaker/Mobile-VideoGPT.
Authors: Elisabetta Fedele, Boyang Sun, Leonidas Guibas, Marc Pollefeys, Francis Engelmann
Abstract: We present SuperDec, an approach for creating compact 3D scene representations via decomposition into superquadric primitives. While most recent works leverage geometric primitives to obtain photorealistic 3D scene representations, we propose to leverage them to obtain a compact yet expressive representation. We propose to solve the problem locally on individual objects and leverage the capabilities of instance segmentation methods to scale our solution to full 3D scenes. In doing that, we design a new architecture which efficiently decompose point clouds of arbitrary objects in a compact set of superquadrics. We train our architecture on ShapeNet and we prove its generalization capabilities on object instances extracted from the ScanNet++ dataset as well as on full Replica scenes. Finally, we show how a compact representation based on superquadrics can be useful for a diverse range of downstream applications, including robotic tasks and controllable visual content generation and editing.
Authors: Guillaume Balezo, Roger Trullo, Albert Pla Planas, Etienne Decenciere, Thomas Walter
Abstract: Histopathological analysis is a cornerstone of cancer diagnosis, with Hematoxylin and Eosin (H&E) staining routinely acquired for every patient to visualize cell morphology and tissue architecture. On the other hand, multiplex immunofluorescence (mIF) enables more precise cell type identification via proteomic markers, but has yet to achieve widespread clinical adoption due to cost and logistical constraints. To bridge this gap, we introduce MIPHEI (Multiplex Immunofluorescence Prediction from H&E Images), a U-Net-inspired architecture that leverages a ViT pathology foundation model as encoder to predict mIF signals from H&E images using rich pretrained representations. MIPHEI targets a comprehensive panel of markers spanning nuclear content, immune lineages (T cells, B cells, myeloid), epithelium, stroma, vasculature, and proliferation. We train our model using the publicly available OrionCRC dataset of restained H&E and mIF images from colorectal cancer tissue, and validate it on five independent datasets: HEMIT, PathoCell, IMMUcan, Lizard and PanNuke. On OrionCRC test set, MIPHEI achieves accurate cell-type classification from H&E alone, with F1 scores of 0.93 for Pan-CK, 0.83 for alpha-SMA, 0.68 for CD3e, 0.36 for CD20, and 0.28 for CD68, substantially outperforming both a state-of-the-art baseline and a random classifier for most markers. Our results indicate that, for some molecular markers, our model captures the complex relationships between nuclear morphologies in their tissue context, as visible in H&E images and molecular markers defining specific cell types. MIPHEI offers a promising step toward enabling cell-type-aware analysis of large-scale H&E datasets, in view of uncovering relationships between spatial cellular organization and patient outcomes.
Authors: Jun Chen, Xinke Li, Mingyue Xu, Chongshou Li, Truiani Li
Abstract: Gradient-based adversarial attacks are widely used to evaluate the robustness of 3D point cloud classifiers, yet they often rely on uniform update rules that neglect point-wise heterogeneity, leading to perceptible perturbations. We propose two complementary strategies to improve both the effectiveness and imperceptibility of the attack. \textbf{WAAttack} employs weighted gradients to dynamically adjust per-point perturbation magnitudes and uses an adaptive step size strategy to regulate the global perturbation scale. \textbf{SubAttack} partitions the point cloud into subsets and, at each iteration, perturbs only those combinations with high adversarial efficacy and low perceptual saliency. Together, these methods offer a principled refinement of gradient-based attacks for 3D point clouds. Extensive experiments show that our approach consistently outperforms state-of-the-art methods in generating highly imperceptible adversarial examples. The code is available at https://github.com/chenjun0326/WA_SubAttack.
Authors: Juntong Li, Lingwei Dang, Qingxin Xiao, Shishuo Shang, Jiajia Cheng, Haomin Wu, Yun Hao, Qingyao Wu
Abstract: Semi-supervised video anomaly detection methods face two critical challenges: (1) Strong generalization blurs the boundary between normal and abnormal patterns. Although existing approaches attempt to alleviate this issue using memory modules, their rigid prototype-matching process limits adaptability to diverse scenarios; (2) Relying solely on low-level appearance and motion cues makes it difficult to perceive high-level semantic anomalies in complex scenes. To address these limitations, we propose SIB-VAD, a novel framework based on adaptive information bottleneck filtering and semantic-aware enhancement. We propose the Sparse Feature Filtering Module (SFFM) to replace traditional memory modules. It compresses normal features directly into a low-dimensional manifold based on the information bottleneck principle and uses an adaptive routing mechanism to dynamically select the most suitable normal bottleneck subspace. Trained only on normal data, SFFMs only learn normal low-dimensional manifolds, while abnormal features deviate and are effectively filtered. Unlike memory modules, SFFM directly removes abnormal information and adaptively handles scene variations. To improve semantic awareness, we further design a multimodal prediction framework that jointly models appearance, motion, and semantics. Through multimodal consistency constraints and joint error computation, it achieves more robust VAD performance. Experimental results validate the effectiveness of our feature filtering paradigm based on semantics-aware information bottleneck. Project page at https://qzfm.github.io/sib_vad_project_page/
Authors: Yechi Ma, Wei Hua, Shu Kong
Abstract: Data annotation is crucial for developing machine learning solutions. The current paradigm is to hire ordinary human annotators to annotate data instructed by expert-crafted guidelines. As this paradigm is laborious, tedious, and costly, we are motivated to explore auto-annotation with expert-crafted guidelines. To this end, we first develop a supporting benchmark AutoExpert by repurposing the established nuScenes dataset, which has been widely used in autonomous driving research and provides authentic expert-crafted guidelines. The guidelines define 18 object classes using both nuanced language descriptions and a few visual examples, and require annotating objects in LiDAR data with 3D cuboids. Notably, the guidelines do not provide LiDAR visuals to demonstrate how to annotate. Therefore, AutoExpert requires methods to learn on few-shot labeled images and texts to perform 3D detection in LiDAR data. Clearly, the challenges of AutoExpert lie in the data-modality and annotation-task discrepancies. Meanwhile, publicly-available foundation models (FMs) serve as promising tools to tackle these challenges. Hence, we address AutoExpert by leveraging appropriate FMs within a conceptually simple pipeline, which (1) utilizes FMs for 2D object detection and segmentation in RGB images, (2) lifts 2D detections into 3D using known sensor poses, and (3) generates 3D cuboids for the 2D detections. In this pipeline, we progressively refine key components and eventually boost 3D detection mAP to 25.4, significantly higher than 12.1 achieved by prior arts.
Authors: Beilei Cui, Yiming Huang, Long Bai, Hongliang Ren
Abstract: This work presents a generalizable framework to transfer relative depth to metric depth. Current monocular depth estimation methods are mainly divided into metric depth estimation (MMDE) and relative depth estimation (MRDE). MMDEs estimate depth in metric scale but are often limited to a specific domain. MRDEs generalize well across different domains, but with uncertain scales which hinders downstream applications. To this end, we aim to build up a framework to solve scale uncertainty and transfer relative depth to metric depth. Previous methods used language as input and estimated two factors for conducting rescaling. Our approach, TR2M, utilizes both text description and image as inputs and estimates two rescale maps to transfer relative depth to metric depth at pixel level. Features from two modalities are fused with a cross-modality attention module to better capture scale information. A strategy is designed to construct and filter confident pseudo metric depth for more comprehensive supervision. We also develop scale-oriented contrastive learning to utilize depth distribution as guidance to enforce the model learning about intrinsic knowledge aligning with the scale distribution. TR2M only exploits a small number of trainable parameters to train on datasets in various domains and experiments not only demonstrate TR2M's great performance in seen datasets but also reveal superior zero-shot capabilities on five unseen datasets. We show the huge potential in pixel-wise transferring relative depth to metric depth with language assistance. (Code is available at: https://github.com/BeileiCui/TR2M)
Authors: Zhening Huang, Xiaoyang Wu, Fangcheng Zhong, Hengshuang Zhao, Matthias Nie{\ss}ner, Joan Lasenby
Abstract: We propose LiteReality, a novel pipeline that converts RGB-D scans of indoor environments into compact, realistic, and interactive 3D virtual replicas. LiteReality not only reconstructs scenes that visually resemble reality but also supports key features essential for graphics pipelines -- such as object individuality, articulation, high-quality physically based rendering materials, and physically based interaction. At its core, LiteReality first performs scene understanding and parses the results into a coherent 3D layout and objects with the help of a structured scene graph. It then reconstructs the scene by retrieving the most visually similar 3D artist-crafted models from a curated asset database. Next, the Material Painting module enhances realism by recovering high-quality, spatially varying materials. Finally, the reconstructed scene is integrated into a simulation engine with basic physical properties to enable interactive behavior. The resulting scenes are compact, editable, and fully compatible with standard graphics pipelines, making them suitable for applications in AR/VR, gaming, robotics, and digital twins. In addition, LiteReality introduces a training-free object retrieval module that achieves state-of-the-art similarity performance on the Scan2CAD benchmark, along with a robust material painting module capable of transferring appearances from images of any style to 3D assets -- even under severe misalignment, occlusion, and poor lighting. We demonstrate the effectiveness of LiteReality on both real-life scans and public datasets. Project page: https://litereality.github.io; Video: https://www.youtube.com/watch?v=ecK9m3LXg2c
URLs: https://litereality.github.io;, https://www.youtube.com/watch?v=ecK9m3LXg2c
Authors: Yegyu Han, Taegyoon Yoon, Dayeon Woo, Sojeong Kim, Hyung-Sin Kim
Abstract: Recent advances on 6D object pose estimation have achieved high performance on representative benchmarks such as LM-O, YCB-V, and T-Less. However, these datasets were captured under fixed illumination and camera settings, leaving the impact of real-world variations in illumination, exposure, gain or depth-sensor mode largely unexplored. To bridge this gap, we introduce SenseShift6D, the first RGB-D dataset that physically sweeps 13 RGB exposures, 9 RGB gains, auto-exposure, 4 depth-capture modes, and 5 illumination levels. For six common household objects, we acquire 198.8k RGB and 20.0k depth images (i.e., 795.4k RGB-D scenes), providing 1,380 unique sensor-lighting permutations per object pose. Experiments with state-of-the-art pretrained, generalizable pose estimators reveal substantial performance variation across lighting and sensor settings, despite their large-scale pretraining. Strikingly, even instance-level estimators-trained and tested on identical objects and backgrounds-exhibit pronounced sensitivity to environmental and sensor shifts. These findings establish sensor- and environment-aware robustness as an underexplored yet essential dimension for real-world deployment, and motivate SenseShift6D as a necessary benchmark for the community. Finally, to illustrate the opportunity enabled by this benchmark, we evaluate test-time multimodal sensor selection without retraining. An idealized (oracle) controller yields remarkable gains of up to +16.7 pp for generalizable models, whereas a practical consistency-based proxy improves performance only marginally, highlighting substantial headroom and the need for future research on reliable sensor-aware adaptation.
Authors: Xiang Li, Zhangchi Hu, Xiao Xu, Bin Kong
Abstract: Integrating LiDAR and camera inputs into a unified Bird's-Eye-View (BEV) representation is crucial for enhancing 3D perception capabilities of autonomous vehicles. However, existing methods suffer from spatial misalignment between LiDAR and camera features, which causes inaccurate depth supervision in camera branch and erroneous fusion during cross-modal feature aggregation. The root cause of this misalignment lies in projection errors, stemming from calibration inaccuracies and rolling shutter effect. The key insight of this work is that locations of these projection errors are not random but highly predictable, as they are concentrated at object-background boundaries which 2D detectors can reliably identify. Based on this, our main motivation is to utilize 2D object priors to pre-align cross-modal features before fusion. To address local misalignment, we propose Prior Guided Depth Calibration (PGDC), which leverages 2D priors to alleviate misalignment and preserve correct cross-modal feature pairs. To resolve global misalignment, we introduce Discontinuity Aware Geometric Fusion (DAGF) to suppress residual noise from PGDC and explicitly enhance sharp depth transitions at object-background boundaries, yielding a structurally aware representation. To effectively utilize these aligned representations, we incorporate Structural Guidance Depth Modulator (SGDM), using a gated attention mechanism to efficiently fuse aligned depth and image features. Our method achieves SOTA performance on nuScenes validation dataset, with its mAP and NDS reaching 71.5% and 73.6% respectively. Additionally, on the Argoverse 2 validation set, we achieve a competitive mAP of 41.7%.
Authors: Simona Kocour, Assia Benbihi, Torsten Sattler
Abstract: An object can disappear from a 3D scene, yet still be detectable. Even after visual removal, modern vision models may infer what was originally present. In this work, we introduce a novel benchmark and evaluation framework to quantify semantic residuals, the unintended cues left behind after object removal in 3D Gaussian Splatting. We conduct experiments across a diverse set of indoor and outdoor scenes, showing that current methods often preserve semantic information despite the absence of visual geometry. Notably, even when removal is followed by inpainting, residual cues frequently remain detectable by foundation models. We also present Remove360, a real-world dataset of pre- and post-removal RGB captures with object-level masks. Unlike prior datasets focused on isolated object instances, Remove360 contains complex, cluttered scenes that enable evaluation of object removal in full-scene settings. By leveraging the ground-truth post-removal images, we directly assess whether semantic presence is eliminated and whether downstream models can still infer what was removed. Our results reveal a consistent gap between geometric removal and semantic erasure, exposing critical limitations in existing 3D editing pipelines and highlighting the need for privacy-aware removal methods that eliminate recoverable cues, not only visible geometry. Dataset and evaluation code are publicly available.
Authors: Cong Wang, Ruiqi Song, Wei Tian, Chenming Zhang, Lingxi Li, Long Chen
Abstract: Reconstructing large-scale dynamic driving scenes remains challenging due to the coexistence of static environments with extreme depth variation and diverse dynamic actors exhibiting complex motions. Existing Gaussian Splatting based methods have primarily focused on limited-scale or object-centric settings, and their applicability to large-scale dynamic driving scenes remains underexplored, particularly in the presence of extreme scale variation and non-rigid motions. In this work, we propose DriveSplat, a unified neural Gaussian framework for reconstructing dynamic driving scenes within a unified Gaussian-based representation. For static backgrounds, we introduce a scene-aware learnable level-of-detail (LOD) modeling strategy that explicitly accounts for near, intermediate, and far depth ranges in driving environments, enabling adaptive multi-scale Gaussian allocation. For dynamic actors, we use an object-centric formulation with neural Gaussian primitives, modeling motion through a global rigid transformation and handling non-rigid dynamics via a two-stage deformation that first adjusts anchors and subsequently updates the Gaussians. To further regularize the optimization, we incorporate dense depth and surface normal priors from pre-trained models as auxiliary supervision. Extensive experiments on the Waymo and KITTI benchmarks demonstrate that DriveSplat achieves state-of-the-art performance in novel-view synthesis while producing temporally stable and geometrically consistent reconstructions of dynamic driving scenes. Project page: https://physwm.github.io/drivesplat.
Authors: Qinqian Lei, Bo Wang, Robby T. Tan
Abstract: HOI detection has long been dominated by task-specific models, sometimes with early vision-language backbones such as CLIP. With the rise of large generative VLMs, a key question is whether standalone VLMs can perform HOI detection competitively against specialized HOI methods. Existing benchmarks such as HICO-DET require exact label matching under incomplete annotations, so any unmatched prediction is marked wrong. This unfairly penalizes valid outputs, especially from less constrained VLMs, and makes cross-paradigm comparison unreliable. To address this limitation, we introduce CrossHOI-Bench, a multiple-choice HOI benchmark with explicit positives and curated negatives, enabling unified and reliable evaluation of both VLMs and HOI-specific models. We further focus on challenging scenarios, such as multi-person scenes and fine-grained interaction distinctions, which are crucial for revealing real differences between the two paradigms. Experiments show that large VLMs achieve competitive, sometimes superior, zero-shot performance, yet they struggle with multiple concurrent actions and with correctly assigning interactions to the target person. Conversely, HOI-specific methods remain weaker in general HOI reasoning but demonstrate stronger multi-action recognition and more reliable identification of which person performs which action. These findings expose complementary strengths and weaknesses of VLMs and HOI-specific methods, which existing benchmarks fail to reveal due to incorrect penalization.
Authors: Weixin Ye, Hongguang Zhu, Wei Wang, Yahui Liu, Mengyu Wang, Xuecheng Nie
Abstract: Text-to-image (T2I) diffusion models have made significant strides in generating high-quality images. However, progressively manipulating certain attributes of generated images to meet the desired user expectations remains challenging, particularly for content with rich details, such as human faces. Some studies have attempted to address this by training slider modules. However, they follow a **One-for-One** manner, where an independent slider is trained for each attribute, requiring additional training whenever a new attribute is introduced. This not only results in parameter redundancy accumulated by sliders but also restricts the flexibility of practical applications and the scalability of attribute manipulation. To address this issue, we introduce the **All-in-On** Slider, a lightweight module that decomposes the text embedding space into sparse, semantically meaningful attribute directions. Once trained, it functions as a general-purpose slider, enabling interpretable and fine-grained continuous control over various attributes. Moreover, by recombining the learned directions, the All-in-One Slider supports the composition of multiple attributes and zero-shot manipulation of unseen attributes (e.g., races and celebrities). Extensive experiments demonstrate that our method enables accurate and scalable attribute manipulation, achieving notable improvements compared to previous methods. Furthermore, our method can be extended to integrate with the inversion framework to perform attribute manipulation on real images, broadening its applicability to various real-world scenarios. The code is available on [our project](https://github.com/ywxsuperstar/ksaedit) page.
Authors: Scarlett Raine, Emilio Olivastri, Benjamin Moshirian, Tobias Fischer
Abstract: Coral reefs are on the brink of collapse, with climate change, ocean acidification, and pollution leading to a projected 70-90% loss of coral species within the next decade. Reef restoration is crucial, but its success hinges on introducing automation to upscale efforts. In this work, we present a highly configurable AI pipeline for the real-time deployment of coral reseeding devices. The pipeline consists of three core components: (i) the image labeling scheme, designed to address data availability and reduce the cost of expert labeling; (ii) the classifier which performs automated analysis of underwater imagery, at the image or patch-level, while also enabling quantitative coral coverage estimation; and (iii) the decision-making module that determines whether deployment should occur based on the classifier's analysis. By reducing reliance on manual experts, our proposed pipeline increases operational range and efficiency of reef restoration. We validate the proposed pipeline at five sites across the Great Barrier Reef, benchmarking its performance against annotations from expert marine scientists. The pipeline achieves 77.8% deployment accuracy, 89.1% accuracy for sub-image patch classification, and real-time model inference at 5.5 frames per second on a Jetson Orin. To address the limited availability of labeled data in this domain and encourage further research, we publicly release a comprehensive, annotated dataset of substrate imagery from the surveyed sites.
Authors: Shuzhou Yang, Xiaoyu Li, Xiaodong Cun, Guangzhi Wang, Lingen Li, Ying Shan, Jian Zhang
Abstract: Video compositing combines live-action footage to create video production, serving as a crucial technique in video creation and film production. Traditional pipelines require intensive labor efforts and expert collaboration, resulting in lengthy production cycles and high manpower costs. To address this issue, we automate this process with generative models, called generative video compositing. This new task strives to adaptively inject identity and motion information of foreground video to the target video in an interactive manner, allowing users to customize the size, motion trajectory, and other attributes of the dynamic elements added in final video. Specifically, we designed a novel Diffusion Transformer (DiT) pipeline based on its intrinsic properties. To maintain consistency of the target video before and after editing, we revised a light-weight DiT-based background preservation branch with masked token injection. As to inherit dynamic elements from other sources, a DiT fusion block is proposed using full self-attention, along with a simple yet effective foreground augmentation for training. Besides, for fusing background and foreground videos with different layouts based on user control, we developed a novel position embedding, named Extended Rotary Position Embedding (ERoPE). Finally, we curated a dataset comprising 61K sets of videos for our new task, called VideoComp. This data includes complete dynamic elements and high-quality target videos. Experiments demonstrate that our method effectively realizes generative video compositing, outperforming existing possible solutions in fidelity and consistency. Project is available at https://gencompositor.github.io/
Authors: Huy Che, Le-Chuong Nguyen, Gia-Nghia Tran, Dinh-Duy Phan, Vinh-Tiep Nguyen
Abstract: In person re-identification, re-ranking is a crucial step to enhance the overall accuracy by refining the initial ranking of retrieved results. Previous studies have mainly focused on features from single-view images, which can cause view bias and issues like pose variation, viewpoint changes, and occlusions. Using multi-view features to present a person can help reduce view bias. In this work, we present an efficient re-ranking method that generates multi-view features by aggregating neighbors' features using K-nearest Weighted Fusion (KWF) method. Specifically, we hypothesize that features extracted from re-identification models are highly similar when representing the same identity. Thus, we select K neighboring features in an unsupervised manner to generate multi-view features. Additionally, this study explores the weight selection strategies during feature aggregation, allowing us to identify an effective strategy. Our re-ranking approach does not require model fine-tuning or extra annotations, making it applicable to large-scale datasets. We evaluate our method on the person re-identification datasets Market1501, MSMT17, and Occluded-DukeMTMC. The results show that our method significantly improves Rank@1 and mAP when re-ranking the top M candidates from the initial ranking results. Specifically, compared to the initial results, our re-ranking method achieves improvements of 9.8%/22.0% in Rank@1 on the challenging datasets: MSMT17 and Occluded-DukeMTMC, respectively. Furthermore, our approach demonstrates substantial enhancements in computational efficiency compared to other re-ranking methods. Code is available at https://github.com/chequanghuy/Enhancing-Person-Re-Identification-via-UFFM-and-AMC.
URLs: https://github.com/chequanghuy/Enhancing-Person-Re-Identification-via-UFFM-and-AMC.
Authors: Song Fei, Tian Ye, Lujia Wang, Lei Zhu
Abstract: Image restoration (IR) aims to recover images degraded by unknown mixtures while preserving semanticsconditions under which discriminative restorers and UNet-based diffusion priors often oversmooth, hallucinate, or drift. We present LucidFlux, a caption-free IR framework that adapts a large diffusion transformer (Flux.1) without image captions. Our LucidFlux introduces a lightweight dual-branch conditioner that injects signals from the degraded input and a lightly restored proxy to respectively anchor geometry and suppress artifacts. Then, a timestep- and layer-adaptive modulation schedule is designed to route these cues across the backbones hierarchy, in order to yield coarse-to-fine and context-aware updates that protect the global structure while recovering texture. After that, to avoid the latency and instability of text prompts or Vision-Language Model (VLM) captions, we enforce caption-free semantic alignment via SigLIP features extracted from the proxy. A scalable curation pipeline further filters large-scale data for structure-rich supervision. Across synthetic and in-the-wild benchmarks, our LucidFlux consistently outperforms strong open-source and commercial baselines, and ablation studies verify the necessity of each component. LucidFlux shows that, for large DiTs, when, where, and what to condition onrather than adding parameters or relying on text promptsis the governing lever for robust and caption-free image restoration in the wild.
Authors: Yuanzhi Zhu, Xi Wang, St\'ephane Lathuili\`ere, Vicky Kalogeiton
Abstract: One-step generators distilled from Masked Diffusion Models (MDMs) compress multiple sampling steps into a single forward pass, enabling efficient text and image synthesis. However, they suffer two key limitations: they inherit modeling bias from the teacher, and their discrete token outputs block gradient flow, preventing post-distillation refinements such as adversarial training, reward-based fine-tuning, and Test-Time Embedding Optimization (TTEO). In this work, we introduce soft embeddings, a simple relaxation that replaces discrete tokens with the expected embeddings under the generator's output distribution. Soft embeddings preserve representation fidelity for one-step discrete generator while providing a fully differentiable continuous surrogate that is compatible with teacher backbones and tokenizer decoders. Integrating soft embeddings into the Di[M]O distillation framework (denoted Soft-Di[M]O) makes one-step generators end-to-end trainable and enables straightforward application of GAN-based refinement, differentiable reward fine-tuning, and TTEO. Empirically, across multiple MDM teachers (e.g., MaskBit, MaskGen), Soft-Di[M]O achieves state-of-the-art one-step results: improved class-to-image performance, a one-step FID of 1.56 on ImageNet-256 with GAN-based refinement, along with higher GenEval and HPS scores on text-to-image with reward fine-tuning, and further gains from TTEO.
Authors: Na Min An, Inha Kang, Minhyun Lee, Hyunjung Shim
Abstract: Vision-Language Encoders (VLEs) are widely adopted as the backbone of zero-shot referring image segmentation (RIS), enabling text-guided localization without task-specific training. However, prior works underexplored the underlying biases within mid-layer representations that preserve positional and language-specific information. Through layer-wise investigation, we reveal that the conventionally used final-layer multimodal embeddings prioritize global semantic alignment, leading to two coupled consequences. First, vision embeddings exhibit weak sensitivity to positional cues. Second, multilingual text embeddings form language-dependent geometric shifts within the shared space. Motivated by these findings, we identify an underexplored pathway within VLE mid-layers to construct a spatial map, applicable for improving zero-shot RIS by 1-7 mIoU on nine RefCOCO benchmarks. Furthermore, leveraging mixed-language mid-layer embeddings yields enhanced spatial grounding accuracy (+7-8 mIoU and IoU@50), albeit with increased inference cost, and also improves performance on the zero-shot text-to-image retrieval task. Our work opens up the discussion about the effects of effective representational bias probing of VLEs for enhanced spatial grounding.
Authors: Yibin Zhao, Yihan Pan, Jun Nan, Liwei Chen, Jianjun Yi
Abstract: Gaussian Splatting has become a leading reconstruction technique, known for its high-quality novel view synthesis and detailed reconstruction. However, most existing methods require dense, calibrated views. Reconstructing from free sparse images often leads to poor surface due to limited overlap and overfitting. We introduce FSFSplatter, a new approach for fast surface reconstruction from free sparse images. Our method integrates end-to-end dense Gaussian initialization, camera parameter estimation, and geometry-enhanced scene optimization. Specifically, FSFSplatter employs a large Transformer to encode multi-view images and generates a dense and geometrically consistent Gaussian scene initialization via a self-splitting Gaussian head. It eliminates local floaters through contribution-based pruning and mitigates overfitting to limited views by leveraging depth and multi-view feature supervision with differentiable camera parameters during rapid optimization. FSFSplatter outperforms current state-of-the-art methods on widely used DTU, Replica, and BlendedMVS datasets.
Authors: KunHo Heo, GiHyun Kim, SuYeon Kim, MyeongAh Cho
Abstract: 3D Semantic Scene Graph Prediction aims to detect objects and their semantic relationships in 3D scenes, and has emerged as a crucial technology for robotics and AR/VR applications. While previous research has addressed dataset limitations and explored various approaches including Open-Vocabulary settings, they frequently fail to optimize the representational capacity of object and relationship features, showing excessive reliance on Graph Neural Networks despite insufficient discriminative capability. In this work, we demonstrate through extensive analysis that the quality of object features plays a critical role in determining overall scene graph accuracy. To address this challenge, we design a highly discriminative object feature encoder and employ a contrastive pretraining strategy that decouples object representation learning from the scene graph prediction. This design not only enhances object classification accuracy but also yields direct improvements in relationship prediction. Notably, when plugging in our pretrained encoder into existing frameworks, we observe substantial performance improvements across all evaluation metrics. Additionally, whereas existing approaches have not fully exploited the integration of relationship information, we effectively combine both geometric and semantic features to achieve superior relationship prediction. Comprehensive experiments on the 3DSSG dataset demonstrate that our approach significantly outperforms previous state-of-the-art methods. Our code is publicly available at https://github.com/VisualScienceLab-KHU/OCRL-3DSSG-Codes.
URLs: https://github.com/VisualScienceLab-KHU/OCRL-3DSSG-Codes.
Authors: Yu Huang, Zelin Peng, Changsong Wen, Xiaokang Yang, Wei Shen
Abstract: Affordance segmentation aims to decompose 3D objects into parts that serve distinct functional roles, enabling models to reason about object interactions rather than mere recognition. Existing methods, mostly following the paradigm of 3D semantic segmentation or prompt-based frameworks, struggle when geometric cues are weak or ambiguous, as sparse point clouds provide limited functional information. To overcome this limitation, we leverage the rich semantic knowledge embedded in large-scale 2D Vision Foundation Models (VFMs) to guide 3D representation learning through a cross-modal alignment mechanism. Specifically, we propose Cross-Modal Affinity Transfer (CMAT), a pretraining strategy that compels the 3D encoder to align with the semantic structures induced by lifted 2D features. CMAT is driven by a core affinity alignment objective, supported by two auxiliary losses, geometric reconstruction and feature diversity, which together encourage structured and discriminative feature learning. Built upon the CMAT-pretrained backbone, we employ a lightweight affordance segmentor that injects text or visual prompts into the learned 3D space through an efficient cross-attention interface, enabling dense and prompt-aware affordance prediction while preserving the semantic organization established during pretraining. Extensive experiments demonstrate consistent improvements over previous state-of-the-art methods in both accuracy and efficiency.
Authors: Bo Peng, Zichuan Wang, Sheng Yu, Xiaochuan Jin, Wei Wang, Jing Dong
Abstract: Deep learning based face-swap videos, widely known as deepfakes, have drawn wide attention due to their threat to information credibility. Recent works mainly focus on the problem of deepfake detection that aims to reliably tell deepfakes apart from real ones, in an objective way. On the other hand, the subjective perception of deepfakes, especially its computational modeling and imitation, is also a significant problem but lacks adequate study. In this paper, we focus on the photorealism assessment of deepfakes, which is defined as the automatic assessment of deepfake photorealism that approximates human perception of deepfakes. It is important for evaluating the quality and deceptiveness of deepfakes which can be used for predicting the influence of deepfakes on Internet, and it also has potentials in improving the deepfake generation process by serving as a critic. This paper promotes this new direction by presenting a comprehensive benchmark called DREAM, which stands for Deepfake photoREalism AssessMent. It is comprised of a deepfake video dataset of diverse quality, a large scale annotation that includes 140,000 photorealism scores and textual descriptions obtained from 3,500 human annotators, and a comprehensive evaluation and analysis of 18 representative photorealism assessment methods, including recent large vision language model based methods and a newly proposed description-aligned CLIP method. The benchmark and insights included in this study can lay the foundation for future research in this direction and other related areas. We make the dataset available to the research community at https://github.com/bomb2peng/DREAM-A-Benchmark-Study-for-Deepfake-photoREalism-AssessMent.
URLs: https://github.com/bomb2peng/DREAM-A-Benchmark-Study-for-Deepfake-photoREalism-AssessMent.
Authors: Zhenyu Lu, Liupeng Li, Jinpeng Wang, Yan Feng, Bin Chen, Ke Chen, Yaowei Wang
Abstract: Existing works on reasoning segmentation either connect hidden features from a language model directly to a mask decoder or represent positions in text, which limits interpretability and semantic detail. To solve this, we present CoPRS, a Multi-modal Chain-of-Thought (MCoT)-based positional perception model that bridges language reasoning to segmentation through a differentiable and interpretable positional prior instantiated as a heatmap. By making the reasoning process clear via MCoT and expressing it as a dense, differentiable heatmap, this interface enhances interpretability and diagnostic analysis and yields more concentrated evidence on the target. A learnable concentration token aggregates features of the image and reasoning text to generate this positional prior, which is decoded to precise masks through a lightweight decoder, providing a direct connection between reasoning and segmentation. Across the RefCOCO series and ReasonSeg, CoPRS matches or surpasses the best reported metrics on each standard split under comparable protocols, with performance at or above the prior state of the art across both validation and test partitions. Extensive experiments demonstrate a strong positive correlation among the CoT trajectory, the generated heatmap, and the decoded mask, supporting an interpretable alignment between the reasoning output and downstream mask generation. Collectively, these findings support the utility of this paradigm in bridging reasoning and segmentation and show advantages in concentration driven by reasoning and in more precise mask prediction. Code has been released at https://github.com/ZhenyuLU-Heliodore/CoPRS.
Authors: Gaoxiang Huang, Songning Lai, Yutao Yue
Abstract: Concept Bottleneck Models (CBMs) enhance interpretability by predicting human-understandable concepts as intermediate representations. However, existing CBMs often suffer from input-to-concept mapping bias and limited controllability, which restricts their practical utility and undermines the reliability of concept-based strategies. To address these challenges, we propose a Lightweight Disentangled Concept Bottleneck Model (LDCBM) that automatically groups visual features into semantically meaningful components without the need for region annotations. By introducing a filter grouping loss and joint concept supervision, our method improves the alignment between visual patterns and concepts, enabling more transparent and robust decision-making. Notably, experiments on three diverse datasets demonstrate that LDCBM achieves higher concept and class accuracy, outperforming previous CBMs in both interpretability and classification performance. Complexity analysis reveals that the parameter count and FLOPs of LDCBM are less than 5% higher than those of Vanilla CBM. Furthermore, background mask intervention experiments validate the model's strong capability to suppress irrelevant image regions, further corroborating the high precision of the visual-concept mapping under LDCBM's lightweight design paradigm. By grounding concepts in visual evidence, our method overcomes a fundamental limitation of prior models and enhances the reliability of interpretable AI.
Authors: Xiaohan Sun, Carol O'Sullivan
Abstract: In this paper, we investigate how users perceive the visual quality of crowd character representations at different levels of detail (LoD) and viewing distances. Each representation, including geometric meshes, image-based impostors, Neural Radiance Fields (NeRFs), and 3D Gaussians, exhibits distinct trade-offs between visual fidelity and computational performance. Our qualitative and quantitative results provide insights to guide the design of perceptually optimized LoD strategies for crowd rendering.
Authors: Jiahao Meng, Xiangtai Li, Haochen Wang, Yue Tan, Tao Zhang, Lingdong Kong, Yunhai Tong, Anran Wang, Zhiyang Teng, Yujing Wang, Zhuochen Wang
Abstract: Most video reasoning models only generate textual reasoning traces without indicating when and where key evidence appears. Recent models such as OpenAI-o3 have sparked wide interest in evidence-centered reasoning for images, yet extending this ability to videos is more challenging due to the need for joint temporal tracking and spatial localization across dynamic scenes. We introduce Open-o3-Video, a non-agent framework that integrates explicit spatio-temporal evidence into video reasoning by highlighting key timestamps, objects, and bounding boxes, making the reasoning process traceable and verifiable. To enable this capability, we first construct high-quality datasets STGR that provide unified spatio-temporal supervision, which is absent in existing resources. We further adopt a cold-start reinforcement learning strategy with specially designed rewards that jointly encourage answer accuracy, temporal alignment, and spatial precision. On the V-STAR benchmark, Open-o3-Video achieves state-of-the-art performance, improving mAM by 14.4% and mLGM by 24.2% over the Qwen2.5-VL baseline, and shows consistent gains across a range of video understanding benchmarks. Beyond accuracy, the grounded reasoning traces produced by Open-o3-Video support confidence-aware test-time scaling, improving answer reliability.
Authors: Farheen Ramzan (Cherise), Yusuf Kiberu (Cherise), Nikesh Jathanna (Cherise), Meryem Jabrane (Cherise), Vicente Grau (Cherise), Shahnaz Jamil-Copley (Cherise), Richard H. Clayton (Cherise), Chen (Cherise), Chen (Cherise)
Abstract: Accurate segmentation of myocardial scar from late gadolinium enhanced (LGE) cardiac MRI is essential for evaluating tissue viability, yet remains challenging due to variable contrast and imaging artifacts. Electrocardiogram (ECG) signals provide complementary physiological information, as conduction abnormalities can help localize or suggest scarred myocardial regions. In this work, we propose a novel multimodal framework that integrates ECG-derived electrophysiological information with anatomical priors from the AHA-17 atlas for physiologically consistent LGE-based scar segmentation. As ECGs and LGE-MRIs are not acquired simultaneously, we introduce a Temporal Aware Feature Fusion (TAFF) mechanism that dynamically weights and fuses features based on their acquisition time difference. Our method was evaluated on a clinical dataset and achieved substantial gains over the state-of-the-art image-only baseline (nnU-Net), increasing the average Dice score for scars from 0.6149 to 0.8463 and achieving high performance in both precision (0.9115) and sensitivity (0.9043). These results show that integrating physiological and anatomical knowledge allows the model to "see beyond the image", setting a new direction for robust and physiologically grounded cardiac scar segmentation.
Authors: Hidir Yesiltepe, Tuna Han Salih Meral, Adil Kaan Akan, Kaan Oktay, Pinar Yanardag
Abstract: Current autoregressive video diffusion models are constrained by three core bottlenecks: (i) the finite temporal horizon imposed by the base model's 3D Rotary Positional Embedding (3D-RoPE), (ii) slow prompt responsiveness in maintaining fine-grained action control during long-form rollouts, and (iii) the inability to realize discontinuous cinematic transitions within a single generation stream. We introduce $\infty$-RoPE, a unified inference-time framework that addresses all three limitations through three interconnected components: Block-Relativistic RoPE, KV Flush, and RoPE Cut. Block-Relativistic RoPE reformulates temporal encoding as a moving local reference frame, where each newly generated latent block is rotated relative to the base model's maximum frame horizon while earlier blocks are rotated backward to preserve relative temporal geometry. This relativistic formulation eliminates fixed temporal positions, enabling continuous video generation far beyond the base positional limits. To obtain fine-grained action control without re-encoding, KV Flush renews the KV cache by retaining only two latent frames, the global sink and the last generated latent frame, thereby ensuring immediate prompt responsiveness. Finally, RoPE Cut introduces controlled discontinuities in temporal RoPE coordinates, enabling multi-cut scene transitions within a single continuous rollout. Together, these components establish $\infty$-RoPE as a training-free foundation for infinite-horizon, controllable, and cinematic video diffusion. Comprehensive experiments show that $\infty$-RoPE consistently surpasses previous autoregressive models in overall VBench scores.
Authors: Daniel Sungho Jung, Kyoung Mu Lee
Abstract: Foot contact plays a critical role in human interaction with the world, and thus exploring foot contact can advance our understanding of human movement and physical interaction. Despite its importance, existing methods often approximate foot contact using a zero-velocity constraint and focus on joint-level contact, failing to capture the detailed interaction between the foot and the world. Dense estimation of foot contact is crucial for accurately modeling this interaction, yet predicting dense foot contact from a single RGB image remains largely underexplored. There are two main challenges for learning dense foot contact estimation. First, shoes exhibit highly diverse appearances, making it difficult for models to generalize across different styles. Second, ground often has a monotonous appearance, making it difficult to extract informative features. To tackle these issues, we present a FEet COntact estimation (FECO) framework that learns dense foot contact with shoe style-invariant and ground-aware learning. To overcome the challenge of shoe appearance diversity, our approach incorporates shoe style adversarial training that enforces shoe style-invariant features for contact estimation. To effectively utilize ground information, we introduce a ground feature extractor that captures ground properties based on spatial context. As a result, our proposed method achieves robust foot contact estimation regardless of shoe appearance and effectively leverages ground information. The codes are available at https://github.com/dqj5182/FECO_RELEASE.
Authors: Boran Wen, Ye Lu, Sirui Wang, Keyan Wan, Jiahong Zhou, Junxuan Liang, Xinpeng Liu, Bang Xiao, Ruiyang Liu, Yong-Lu Li
Abstract: Generalized robots must learn from diverse, large-scale human-object interactions (HOI) to operate robustly in the real world. Monocular internet videos offer a nearly limitless and readily available source of data, capturing an unparalleled diversity of human activities, objects, and environments. However, accurately and scalably extracting 4D interaction data from these in-the-wild videos remains a significant and unsolved challenge. To overcome the annotation bottleneck, we introduce an efficient sparse contact annotation paradigm. To scale this process, we develop InterPoint, a multi-modal predictor that drives a human-in-the-loop data engine. Building upon these efficiently acquired annotations, we introduce 4DHOISolver, a novel optimization framework that constrains the ill-posed 4D HOI reconstruction problem, maintaining high spatio-temporal coherence and physical plausibility. Leveraging this framework, we introduce Open4DHOI, a new large-scale 4D HOI dataset featuring a diverse catalog of 135 object types and 133 actions. Furthermore, we demonstrate the effectiveness of our reconstructions by enabling an RL-based agent to imitate the recovered motions. Data and code will be publicly available at https://github.com/wenboran2002/open4dhoi_code.
Authors: Fan Yang, Xingping Dong, Xin Yu, Wenhan Luo, Wei Liu, Kaihao Zhang
Abstract: Understanding high-resolution (HR) images remains a critical challenge for multimodal large language models (MLLMs). Recent approaches leverage vision-based retrieval-augmented generation (RAG) to retrieve query-relevant crops from HR images, improving understanding capacity of MLLMs. However, this paradigm often leads to object fragmentation, resulting in semantic bias and incomplete retrieval, while also introducing false positives from irrelevant background patches. To address these issues, we propose Multi-resolution Retrieval-Detection (MRD), a training-free framework that enhances HR image understanding from both local and global perspectives. Locally, MRD enforces cross-scale semantic consistency via multi-resolution semantic fusion to mitigate single-resolution bias and alleviate object fragmentation. Globally, it integrates open-vocabulary object detection (OVD) as localization priors within a unified framework. Extensive experiments across multiple MLLMs on HR image benchmarks demonstrate that MRD achieves state-of-the-art (SOTA) performance on both single-object and multi-object understanding tasks. Code will be available at: https://github.com/yf0412/MRD.
Authors: Shilin Hu, Jingyi Xu, Akshat Dave, Dimitris Samaras, Hieu Le
Abstract: Generating realistic shadows for inserted objects requires reasoning about scene geometry and illumination. However, most existing methods operate purely in image space, leaving the physical relationship between objects, lighting, and shadows to be learned implicitly, often resulting in misaligned or implausible shadows. We instead ground shadow generation in the physics of shadow formation. Given a composite image and an object mask, we recover approximate scene geometry and estimate a dominant light direction to derive a physics-grounded shadow estimate via geometric reasoning. While coarse, this estimate provides a spatial anchor for shadow placement. Because illumination cannot always be uniquely inferred from a single image, we predict confidence scores for both lighting and shadow cues and use them to regulate their influence during generation. These cues, shadow mask, light direction, and their confidences, condition a diffusion-based generator that refines the estimate into a realistic shadow. Experiments on DESOBAV2 show that our method improves both shadow realism and localization, achieving 23% lower shadow-region RMSE and 30% lower shadow-region BER over prior state-of-the-art.
Authors: Shilin Hu, Jingyi Xu, Sagnik Das, Dimitris Samaras, Hieu Le
Abstract: Shadows encode rich information about scene geometry and illumination, yet existing methods either predict a unified shadow mask or overlook attached shadows entirely. We address this gap by proposing a framework for jointly detecting cast and attached shadows through explicit physical modeling of light direction and surface geometry. Our approach is grounded in a simple observation: surfaces facing away from the light source tend to fall into shadow. We exploit the reciprocal relationship between shadow formation and light estimation to construct a closed feedback loop, a dual-module architecture in which a shadow detection module and a light estimation module iteratively refine each other. At each pass, updated light estimates with surface normals produce partial attached shadow maps that guide detection, while improved shadow predictions sharpen light estimation. To support training and evaluation, we introduce a dataset of 1,458 images with manually annotated cast and attached shadow masks sourced from three existing benchmarks. Experiments demonstrate that our physically grounded, iterative formulation outperforms prior methods, with at least a 33% reduction in attached BER, while maintaining strong full and cast performance.
Authors: Kelian Baert, Mae Younes, Francois Bourel, Marc Christie, Adnane Boukhayma
Abstract: Recent advancements in Gaussian Splatting have enabled increasingly accurate reconstruction of photorealistic head avatars, opening the door to numerous applications in visual effects, videoconferencing, and virtual reality. This, however, comes with the lack of intuitive editability offered by traditional triangle mesh-based methods. In contrast, we propose a method that combines the accuracy and fidelity of 2D Gaussian Splatting with the intuitiveness of UV texture mapping. By embedding each canonical Gaussian primitive's local frame into a patch in the UV space of a template mesh in a computationally efficient manner, we reconstruct continuous editable material head textures from a single monocular video on a conventional UV domain. Furthermore, we leverage an efficient physically based reflectance model to enable relighting and editing of these intrinsic material maps. Through extensive comparisons with state-of-the-art methods, we demonstrate the accuracy of our reconstructions, the quality of our relighting results, and the ability to provide intuitive controls for modifying an avatar's appearance and geometry via texture mapping without additional optimization.
Authors: Rao Muhammad Umer, Daniel Sens, Jonathan Noll, Sohom Dey, Christian Matek, Lukas Wolfseher, Rainer Spang, Ralf Huss, Johannes Raffler, Sarah Reinke, Ario Sadafi, Wolfram Klapper, Katja Steiger, Kristina Schwamborn, Carsten Marr
Abstract: Timely and accurate lymphoma diagnosis is essential for guiding cancer treatment. Standard diagnostic practice combines hematoxylin and eosin (HE)-stained whole slide images with immunohistochemistry, flow cytometry, and molecular genetic tests to determine lymphoma subtypes, a process requiring costly equipment, and skilled personnel, causing treatment delays. Deep learning methods could assist pathologists by extracting diagnostic information from routinely available HE-stained slides directly, yet comprehensive benchmarks for lymphoma subtyping on multicenter data are lacking. In this work, we present the first multicenter lymphoma benchmark, covering four common lymphoma subtypes and healthy control tissue. We systematically evaluate five publicly available pathology foundation models (H-optimus-1, H0-mini, Virchow2, UNI2, Titan) combined with attention-based (AB-MIL) and transformer-based (TransMIL) multiple instance learning aggregators across three magnifications (10x, 20x, 40x). On in-distribution test sets, models achieve multiclass balanced accuracies exceeding 80% across all magnifications, with foundation models performing similarly, and aggregation methods showing comparable results. The magnification study reveals that 40x resolution is sufficient, with no performance gains from higher resolutions or cross-magnification aggregation. However, on out-of-distribution test sets, performance drops substantially to around 60%, highlighting significant generalization challenges. To advance the field, larger multicenter studies covering additional rare lymphoma subtypes are needed. We provide an automated benchmarking pipeline to facilitate such future research. Our paper codes is publicly available at https://github.com/RaoUmer/LymphomaMIL.
Authors: Snehal Singh Tomar, Alexandros Graikos, Arjun Krishna, Dimitris Samaras, Klaus Mueller
Abstract: Modern deep learning methods typically treat image sequences as large tensors of sequentially stacked frames. However, is this straightforward representation ideal given the current state-of-the-art (SoTA)? In this work, we address this question in the context of generative models and aim to devise a more effective way of modeling image sequence data. Observing the inefficiencies and bottlenecks of current SoTA image sequence generation methods, we showcase that rather than working with large tensors, we can improve the generation process by factorizing it into first generating the coarse sequence at low resolution and then refining the individual frames at high resolution. We train a generative model solely on grid images comprising subsampled frames. Yet, we learn to generate image sequences, using the strong self-attention mechanism of the Diffusion Transformer (DiT) to capture correlations between frames. In effect, our formulation extends a 2D image generator to operate as a low-resolution 3D image-sequence generator without introducing any architectural modifications. Subsequently, we super-resolve each frame individually to add the sequence-independent high-resolution details. This approach offers several advantages and can overcome key limitations of the SoTA in this domain. Compared to existing image sequence generation models, our method achieves superior synthesis quality and improved coherence across sequences. It also delivers high-fidelity generation of arbitrary-length sequences and increased efficiency in inference time and training data usage. Furthermore, our straightforward formulation enables our method to generalize effectively across diverse data domains, which typically require additional priors and supervision to model in a generative context. Our method consistently outperforms SoTA in quality and inference speed (at least twice-as-fast) across datasets.
Authors: Liam Frija-Altarac, Matthew Toews
Abstract: This paper proposes elementary information mechanics as a new model for understanding the mechanical properties of convolutional filtering with rectification, inspired by physical theories of special relativity and quantum mechanics. We consider kernels decomposed into orthogonal even and odd components. Even components cause image content to diffuse isotropically while preserving the center of mass, analogously to rest or potential energy with zero net momentum. Odd kernels cause directional displacement of the center of mass, analogously to kinetic energy with non-zero momentum. The speed of information displacement is linearly related to the ratio of odd vs total kernel energy. Even-Odd properties are analyzed in the spectral domain via the discrete cosine transform (DCT), where the structure of small convolutional filters (e.g. $3 \times 3$ pixels) is dominated by low-frequency bases, specifically the DC $\Sigma$ and gradient components $\nabla$, which define the fundamental modes of information propagation. To our knowledge, this is the first work demonstrating the link between information processing in generic CNNs and the energy-momentum relation, a cornerstone of modern relativistic physics.
Authors: Wenzhi Chen, Bo Hu, Leida Li, Lihuo He, Wen Lu, Xinbo Gao
Abstract: With the rapid development of text-to-image generation technology, accurately assessing the alignment between generated images and text prompts has become a critical challenge. Existing methods rely on Euclidean space metrics, neglecting the structured nature of semantic alignment, while lacking adaptive capabilities for different samples. To address these limitations, we propose HyperAlign, an adaptive text-to-image alignment assessment framework based on hyperbolic entailment geometry. First, we extract Euclidean features using CLIP and map them to hyperbolic space. Second, we design a dynamic-supervision entailment modeling mechanism that transforms discrete entailment logic into continuous geometric structure supervision. Finally, we propose an adaptive modulation regressor that utilizes hyperbolic geometric features to generate sample-level modulation parameters, adaptively calibrating Euclidean cosine similarity to predict the final score. HyperAlign achieves highly competitive performance on both single database evaluation and cross-database generalization tasks, fully validating the effectiveness of hyperbolic geometric modeling for image-text alignment assessment.
Authors: Zhankai Ye, Bofan Li, Yukai Jin, Shuoqiu Li, Wei Wang, Yanfu Zhang, Shangqian Gao, Xin Liu
Abstract: Discrete motion tokenization has recently enabled Large Language Models (LLMs) to serve as versatile backbones for motion understanding and motion-language reasoning. However, existing pipelines typically decouple motion quantization from semantic embedding learning, linking them solely via token IDs. This approach fails to effectively align the intrinsic geometry of the motion space with the embedding space, thereby hindering the LLM's capacity for nuanced motion reasoning. We argue that alignment is most effective when both modalities share a unified geometric basis. Therefore, instead of forcing the LLM to reconstruct the complex geometry among motion tokens from scratch, we present a novel framework that explicitly enforces orthogonality on both the motion codebook and the LLM embedding space, ensuring that their relational structures naturally mirror each other. Specifically, we employ a decoder-only quantizer with Gumbel-Softmax for differentiable training and balanced codebook usage. To bridge the modalities, we use a sparse projection that maps motion codes into the LLM embedding space while preserving orthogonality. Finally, a two-stage orthonormal regularization schedule enforces soft constraints during tokenizer training and LLM fine-tuning to maintain geometric alignment without hindering semantic adaptation. Extensive experiments show that our framework improves the aggregated Average by 22.4% over the strongest baseline on HumanML3D and by 14.4% on KIT-ML, while ablations confirm the effectiveness of the tokenizer, projection, and regularization designs.
Authors: Selim Emir Can, Jan Ackermann, Kiyohiro Nakayama, Ruofan Liu, Tong Wu, Yang Zheng, Hugo Bertiche, Menglei Chai, Thabo Beeler, Gordon Wetzstein
Abstract: Estimating physically accurate, simulation-ready garments from a single image is challenging due to the absence of image-to-physics datasets and the ill-posed nature of this problem. Prior methods either require multi-view capture and expensive differentiable simulation or predict only garment geometry without the material properties required for realistic simulation. We propose a feed-forward framework that sidesteps these limitations by first fine-tuning a vision-language model to infer material composition and fabric attributes from real images, and then training a lightweight predictor that maps these attributes to the corresponding physical fabric parameters using a small dataset of material-physics measurements. Our approach introduces two new datasets (FTAG and T2P) and delivers simulation-ready garments from a single image without iterative optimization. Experiments show that our estimator achieves superior accuracy in material composition estimation and fabric attribute prediction, and by passing them through our physics parameter estimator, we further achieve higher-fidelity simulations compared to state-of-the-art image-to-garment methods.
Authors: Daniel Kyselica, Jon\'a\v{s} Herec, Oliver Kutis, Rado Pito\v{n}\'ak
Abstract: Natural disaster monitoring through continuous satellite observation requires processing multi-temporal data under strict operational constraints. This paper addresses flood detection, a critical application for hazard management, by developing an onboard change detection system that operates within the memory and computational limits of small satellites. We propose History Injection mechanism for Transformer models (HiT), that maintains historical context from previous observations while reducing data storage by over 99\% of original image size. Moreover, testing on the STTORM-CD flood dataset confirms that the HiT mechanism within the Prithvi-tiny foundation model maintains detection accuracy compared to the bi-temporal baseline. The proposed HiT-Prithvi model achieved 43 FPS on Jetson Orin Nano, a representative onboard hardware used in nanosats. This work establishes a practical framework for satellite-based continuous monitoring of natural disasters, supporting real-time hazard assessment without dependency on ground-based processing infrastructure. Architecture as well as model checkpoints is available at https://github.com/zaitra/HiT-change-detection .
Authors: James Brock, Ce Zhang, Nantheera Anantrasirichai
Abstract: The increasing availability of high-resolution satellite imagery, together with advances in deep learning, creates new opportunities for forest monitoring workflows. Two central challenges in this domain are pixel-level change detection and semantic change interpretation, particularly for complex forest dynamics. While large language models (LLMs) are increasingly adopted for data exploration, their integration with vision-language models (VLMs) for remote sensing image change interpretation (RSICI) remains underexplored, especially beyond urban environments. This paper introduces Forest-Chat, an LLM-driven agent for forest change analysis, enabling natural language querying across multiple RSICI tasks, including change detection and captioning, object counting, deforestation characterisation, and change reasoning. Forest-Chat builds upon a multi-level change interpretation (MCI) vision-language backbone with LLM-based orchestration, incorporating zero-shot change detection via AnyChange and multimodal LLM-based zero-shot change captioning and refinement. To support adaptation and evaluation in forest environments, we introduce the Forest-Change dataset, comprising bi-temporal satellite imagery, pixel-level change masks, and semantic change captions via human annotation and rule-based methods. Forest-Chat achieves mIoU and BLEU-4 scores of 67.10% and 40.17% on Forest-Change, and 88.13% and 34.41% on LEVIR-MCI-Trees, a tree-focused subset of LEVIR-MCI. In a zero-shot capacity, it achieves 60.15% and 34.00% on Forest-Change, and 47.32% and 18.23% on LEVIR-MCI-Trees. Further experiments demonstrate the value of caption refinement for injecting geographic domain knowledge into supervised captions, and the system's limited label domain transfer onto JL1-CD-Trees. These findings demonstrate that interactive, LLM-driven systems can support accessible and interpretable forest change analysis.
Authors: Zichen Yu, Quanli Liu, Wei Wang, Liyong Zhang, Xiaoguang Zhao
Abstract: 3D occupancy prediction plays a pivotal role in the realm of autonomous driving, as it provides a comprehensive understanding of the driving environment. Most existing methods construct dense scene representations for occupancy prediction, overlooking the inherent sparsity of real-world driving scenes. Recently, 3D superquadric representation has emerged as a promising sparse alternative to dense scene representations due to the strong geometric expressiveness of superquadrics. However, existing superquadric frameworks still suffer from insufficient temporal modeling, a challenging trade-off between query sparsity and geometric expressiveness, and inefficient superquadric-to-voxel splatting. To address these issues, we propose SuperOcc, a novel framework for superquadric-based 3D occupancy prediction. SuperOcc incorporates three key designs: (1) a cohesive temporal modeling mechanism to simultaneously exploit view-centric and object-centric temporal cues; (2) a multi-superquadric decoding strategy to enhance geometric expressiveness without sacrificing query sparsity; and (3) an efficient superquadric-to-voxel splatting scheme to improve computational efficiency. Extensive experiments on the SurroundOcc and Occ3D benchmarks demonstrate that SuperOcc achieves state-of-the-art performance while maintaining superior efficiency. The code is available at https://github.com/Yzichen/SuperOcc.
Authors: Shirin Reyhanian, Laurenz Wiskott
Abstract: Vector-quantized variational autoencoders (VQ-VAEs) are central to models that rely on high reconstruction fidelity, from neural compression to generative pipelines. Hierarchical extensions, such as VQ-VAE2, are often credited with superior reconstruction performance because they split global and local features across multiple levels. However, since higher levels derive all their information from lower levels, they should not carry additional reconstructive content beyond what the lower-level already encodes. Combined with recent advances in training objectives and quantization mechanisms, this leads us to ask whether a single-level VQ-VAE, with matched representational budget and no codebook collapse, can equal the reconstruction fidelity of its hierarchical counterpart. Although the multi-scale structure of hierarchical models may improve perceptual quality in downstream tasks, the effect of hierarchy on reconstruction accuracy, isolated from codebook utilization and overall representational capacity, remains empirically underexamined. We revisit this question by comparing a two-level VQ-VAE and a capacity-matched single-level model on high-resolution ImageNet images. Consistent with prior observations, we confirm that inadequate codebook utilization limits single-level VQ-VAEs and that overly high-dimensional embeddings destabilize quantization and increase codebook collapse. We show that lightweight interventions such as initialization from data, periodic reset of inactive codebook vectors, and systematic tuning of codebook hyperparameters significantly reduce collapse. Our results demonstrate that when representational budgets are matched, and codebook collapse is mitigated, single-level VQ-VAEs can match the reconstruction fidelity of hierarchical variants, challenging the assumption that hierarchical quantization is inherently superior for high-quality reconstructions.
Authors: Yunwei Bai, Ying Kiat Tan, Yao Shu, Tsuhan Chen
Abstract: Few-shot learning (FSL) challenges model generalization to novel classes based on just a few shots of labeled examples, a testbed where traditional test-time augmentations fail to be effective. We introduce 1S-DAug, a one-shot generative augmentation operator that synthesizes diverse yet faithful variants from just one example image at test time. 1S-DAug couples traditional geometric perturbations with controlled noise injection and a denoising diffusion process conditioned on the original image. The generated images are then encoded and aggregated, alongside the original image, into a combined representation for more robust FSL predictions. Integrated as a training-free model-agnostic plugin, 1S-DAug consistently improves FSL across standard benchmarks of 4 different datasets without any model parameter update, including achieving up to 20\% proportional accuracy improvement on the miniImagenet 5-way-1-shot benchmark. Code will be released.
Authors: Xingsong Ye, Yongkun Du, JiaXin Zhang, Chen Li, Jing Lyu, Zhineng Chen
Abstract: Large-scale and categorical-balanced text data is essential for training effective Scene Text Recognition (STR) models, which is hard to achieve when collecting real data. Synthetic data offers a cost-effective and perfectly labeled alternative. However, its performance often lags behind, revealing a significant domain gap between real and current synthetic data. In this work, we systematically analyze mainstream rendering-based synthetic datasets and identify their key limitations: insufficient diversity in corpus, font, and layout, which restricts their realism in complex scenarios. To address these issues, we introduce UnionST, a strong data engine synthesizes text covering a union of challenging samples and better aligns with the complexity observed in the wild. We then construct UnionST-S, a large-scale synthetic dataset with improved simulations in challenging scenarios. Furthermore, we develop a self-evolution learning (SEL) framework for effective real data annotation. Experiments show that models trained on UnionST-S achieve significant improvements over existing synthetic datasets. They even surpass real-data performance in certain scenarios. Moreover, when using SEL, the trained models achieve competitive performance by only seeing 9% of real data labels. Code is available at https://github.com/YesianRohn/UnionST.
Authors: Xinyong Cai, Changbin Sun, Yong Wang, Hongyu Yang, Yuankai Wu
Abstract: Spatiotemporal predictive learning (STPL) aims to forecast future frames from past observations and is essential across a wide range of applications. Compared with recurrent or hybrid architectures, pure convolutional models offer superior efficiency and full parallelism, yet their fixed receptive fields limit their ability to adaptively capture spatially varying motion patterns. Inspired by biological center-surround organization and frequency-selective signal processing, we propose PFGNet, a fully convolutional framework that dynamically modulates receptive fields through pixel-wise frequency-guided gating. The core Peripheral Frequency Gating (PFG) block extracts localized spectral cues and adaptively fuses multi-scale large-kernel peripheral responses with learnable center suppression, effectively forming spatially adaptive band-pass filters. To maintain efficiency, all large kernels are decomposed into separable 1D convolutions ($1 \times k$ followed by $k \times 1$), reducing per-channel computational cost from $O(k^2)$ to $O(2k)$. PFGNet enables structure-aware spatiotemporal modeling without recurrence or attention. Experiments on Moving MNIST, TaxiBJ, Human3.6M, and KTH show that PFGNet delivers SOTA or near-SOTA forecasting performance with substantially fewer parameters and FLOPs. Our code is available at https://github.com/fhjdqaq/PFGNet.
Authors: Francesco Laiti, Davide Talon, Jacopo Staiano, Elisa Ricci
Abstract: Image memorability, i.e., how likely an image is to be remembered, has traditionally been studied in computer vision either as a passive prediction task, with models regressing a scalar score, or with generative methods altering the visual input to boost the image likelihood of being remembered. Yet, none of these paradigms supports users at capture time, when the crucial question is how to improve a photo memorability. We introduce the task of Memorability Feedback (MemFeed), where an automated model should provide actionable, human-interpretable guidance to users with the goal to enhance an image future recall. We also present MemCoach, the first approach designed to provide concrete suggestions in natural language for memorability improvement (e.g., "emphasize facial expression," "bring the subject forward"). Our method, based on Multimodal Large Language Models (MLLMs), is training-free and employs a teacher-student steering strategy, aligning the model internal activations toward more memorable patterns learned from a teacher model progressing along least-to-most memorable samples. To enable systematic evaluation on this novel task, we further introduce MemBench, a new benchmark featuring sequence-aligned photoshoots with annotated memorability scores. Our experiments, considering multiple MLLMs, demonstrate the effectiveness of MemCoach, showing consistently improved performance over several zero-shot models. The results indicate that memorability can not only be predicted but also taught and instructed, shifting the focus from mere prediction to actionable feedback for human creators.
Authors: Song Fei, Tian Ye, Sixiang Chen, Zhaohu Xing, Jianyu Lai, Lei Zhu
Abstract: Generative real-world image super-resolution (Real-ISR) can synthesize visually convincing details from severely degraded low-resolution (LR) inputs, yet its stochastic sampling makes a critical failure mode hard to avoid: outputs may look sharp but be unfaithful to the LR evidence (semantic and structural hallucination), while such LR-anchored faithfulness is difficult to assess without HR ground truth. Preference-based reinforcement learning (RL) is a natural fit because each LR input yields a rollout group of candidates to compare. However, effective alignment in Real-ISR is hindered by (i) the lack of a degradation-robust LR-referenced faithfulness signal, and (ii) a rollout-group optimization bottleneck where naive multi-reward scalarization followed by normalization compresses objective-wise contrasts, causing advantage collapse and weakening the reward-weighted updates in DiffusionNFT-style forward fine-tuning. Moreover, (iii) limited coverage of real degradations restricts rollout diversity and preference signal quality. We propose LucidNFT, a multi-reward RL framework for flow-matching Real-ISR. LucidNFT introduces LucidConsistency, a degradation-robust semantic evaluator that makes LR-anchored faithfulness measurable and optimizable; a decoupled advantage normalization strategy that preserves objective-wise contrasts within each LR-conditioned rollout group before fusion, preventing advantage collapse; and LucidLR, a large-scale collection of real-world degraded images to support robust RL fine-tuning. Experiments show that LucidNFT consistently improves strong flow-based Real-ISR baselines, achieving better perceptual-faithfulness trade-offs with stable optimization dynamics across diverse real-world scenarios.
Authors: Shuai Lu, Meng Wang, Jia Guo, Jiawei Du, Bo Liu, Shengzhu Yang, Weihang Zhang, Huazhu Fu, Huiqi Li
Abstract: Large Vision Language Models (LVLMs) show immense potential for automated ophthalmic diagnosis. However, their clinical deployment is severely hindered by lacking domain-specific knowledge. In this work, we identify two structural deficiencies hindering reliable medical reasoning: 1) the Perception Gap, where general-purpose visual encoders fail to resolve fine-grained pathological cues (e.g., microaneurysms); and 2) the Reasoning Gap, where sparse visual evidence is progressively overridden by massive language priors in deeper transformer layers, leading to ungrounded hallucinations. To bridge these gaps, we propose EyExIn, a data-efficient framework designed to anchor retinal VLMs with expert knowledge via a Deep Expert Injection mechanism. Our architecture employs an Expert-Aware Dual-Stream encoding strategy that decouples visual representation into a general stream for anatomical context and a specialized expert stream for pathological semantics. To ensure high-fidelity integration, we design a Semantic-Adaptive Gated Fusion module, which dynamically amplifies subtle lesion signals while filtering irrelevant background noise. Furthermore, we introduce Adaptive Deep Expert Injection to embed persistent "Vision Anchors" by integrating fused visual features as residual biases directly into intermediate LLM layers. This mechanism creates a visual shortcut that forces the reasoning stack to remain strictly grounded in visual evidence. Extensive experiments across four benchmarks demonstrate that our model consistently outperforms massive proprietary systems. EyExIn significantly enhances domain-specific knowledge embedding and achieves state-of-the-art precision in ophthalmic visual question answering, advancing the development of trustworthy ophthalmic AI.
Authors: Haihua Luo, Xuming Ran, Jiangrong Shen, Timo H\"am\"al\"ainen, Zhonghua Chen, Qi Xu, Fengyu Cong
Abstract: Incremental Learning (IL) aims to learn new tasks while preserving previously acquired knowledge. Integrating the zero-shot learning capabilities of pre-trained vision-language models into IL methods has marked a significant advancement. However, these methods face three primary challenges: (1) the need for improved training efficiency; (2) reliance on a memory bank to store previous data; and (3) the necessity of a strong backbone to augment the model's capabilities. In this paper, we propose SimE, a Simple and Efficient framework that employs a vision-language model with adapters designed specifically for the IL task. We report a remarkable phenomenon: there is a nonlinear correlation between the number of adaptive adapter connections and the model's IL capabilities. While increasing adapter connections between transformer blocks improves model performance, adding more adaptive connections within transformer blocks during smaller incremental steps does not enhance, and may even degrade the model's IL ability. Extensive experimental results show that SimE surpasses traditional methods by 9.6% on TinyImageNet and outperforms other CLIP-based methods by 5.3% on CIFAR-100. Furthermore, we conduct a systematic study to enhance the utilization of the zero-shot capabilities of CLIP. We suggest replacing SimE's encoder with a CLIP model trained on larger datasets (e.g., LAION2B) and stronger architectures (e.g., ViT-L/14).
Authors: Guillem Gonz\'alez, Guillem Aleny\`a, Sergi Foix
Abstract: Cotton harvesting is a critical phase where cotton capsules are physically manipulated and can lead to fibre degradation. To maintain the highest quality, harvesting methods must emulate delicate manual grasping, to preserve cotton's intrinsic properties. Automating this process requires systems capable of recognising cotton capsules across various phenological stages. To address this challenge, we propose COTONET, an enhanced custom YOLO11 model tailored with attention mechanisms to improve the detection of difficult instances. The architecture incorporates gradients in non-learnable operations to enhance shape and feature extraction. Key architectural modifications include: the replacement of convolutional blocks with Squeeze-and-Exitation blocks, a redesigned backbone integrating attention mechanisms, and the substitution of standard upsampling operations for Content Aware Reassembly of Features (CARAFE). Additionally, we integrate Simple Attention Modules (SimAM) for primary feature aggregation and Parallel Hybrid Attention Mechanisms (PHAM) for channel-wise, spatial-wise and coordinate-wise attention in the downward neck path. This configuration offers increased flexibility and robustness for interpreting the complexity of cotton crop growth. COTONET aligns with small-to-medium YOLO models utilizing 7.6M parameters and 27.8 GFLOPS, making it suitable for low-resource edge computing and mobile robotics. COTONET outperforms the standard YOLO baselines, achieving a mAP50 of 81.1% and a mAP50-95 of 60.6%.
Authors: Dingcheng Zhen, Xu Zheng, Ruixin Zhang, Zhiqi Jiang, Yichao Yan, Ming Tao, Shunshun Yin
Abstract: Autoregressive (AR) diffusion models offer a promising framework for sequential generation tasks such as video synthesis by combining diffusion modeling with causal inference. Although they support streaming generation, existing AR diffusion methods struggle to scale efficiently. In this paper, we identify two key challenges in hour-scale real-time human animation. First, most forcing strategies propagate sample-level representations with mismatched diffusion states, causing inconsistent learning signals and unstable convergence. Second, historical representations grow unbounded and lack structure, preventing effective reuse of cached states and severely limiting inference efficiency. To address these challenges, we propose Neighbor Forcing, a diffusion-step-consistent AR formulation that propagates temporally adjacent frames as latent neighbors under the same noise condition. This design provides a distribution-aligned and stable learning signal while preserving drifting throughout the AR chain. Building upon this, we introduce a structured ConvKV memory mechanism that compresses the keys and values in causal attention into a fixed-length representation, enabling constant-memory inference and truly infinite video generation without relying on short-term motion-frame memory. Extensive experiments demonstrate that our approach significantly improves training convergence, hour-scale generation quality, and inference efficiency compared to existing AR diffusion methods. Numerically, LiveAct enables hour-scale real-time human animation and supports 20 FPS real-time streaming inference on as few as two NVIDIA H100 or H200 GPUs. Quantitative results demonstrate that our method attains state-of-the-art performance in lip-sync accuracy, human animation quality, and emotional expressiveness, with the lowest inference cost.
Authors: Handong Zheng, Yumeng Li, Kaile Zhang, Liang Xin, Guangwei Zhao, Hao Liu, Jiayu Chen, Jie Lou, Qi Fu, Rui Yang, Shuo Jiang, Weijian Luo, Weijie Su, Weijun Zhang, Xingyu Zhu, Yabin Li, Yiwei ma, Yu Chen, Yuqiu Ji, Zhaohui Yu, Guang Yang, Colin Zhang, Lei Zhang, Yuliang Liu, Xiang Bai
Abstract: We present Multimodal OCR (MOCR), a document parsing paradigm that jointly parses text and graphics into unified textual representations. Unlike conventional OCR systems that focus on text recognition and leave graphical regions as cropped pixels, our method, termed dots.mocr, treats visual elements such as charts, diagrams, tables, and icons as first-class parsing targets, enabling systems to parse documents while preserving semantic relationships across elements. It offers several advantages: (1) it reconstructs both text and graphics as structured outputs, enabling more faithful document reconstruction; (2) it supports end-to-end training over heterogeneous document elements, allowing models to exploit semantic relations between textual and visual components; and (3) it converts previously discarded graphics into reusable code-level supervision, unlocking multimodal supervision embedded in existing documents. To make this paradigm practical at scale, we build a comprehensive data engine from PDFs, rendered webpages, and native SVG assets, and train a compact 3B-parameter model through staged pretraining and supervised fine-tuning. We evaluate dots.mocr from two perspectives: document parsing and structured graphics parsing. On document parsing benchmarks, it ranks second only to Gemini 3 Pro on our OCR Arena Elo leaderboard, surpasses existing open-source document parsing systems, and sets a new state of the art of 83.9 on olmOCR Bench. On structured graphics parsing, our model achieves higher reconstruction quality than Gemini 3 Pro across image-to-SVG benchmarks, demonstrating strong performance on charts, UI layouts, scientific figures, and chemical diagrams. These results show a scalable path toward building large-scale image-to-code corpora for multimodal pretraining. Code and models are publicly available at https://github.com/rednote-hilab/dots.mocr.
Authors: Yichang Xu, Gaowen Liu, Ramana Rao Kompella, Tiansheng Huang, Sihao Hu, Fatih Ilhan, Selim Furkan Tekin, Zachary Yahn, Ling Liu
Abstract: This paper presents a multi-agent perception-action exploration alliance, dubbed A4VL, for efficient long-video reasoning. A4VL operates in a multi-round perception-action exploration loop with a selection of VLM agents. In each round, the team of agents performs video question-answer (VideoQA) via perception exploration followed by action exploration. During perception exploration, each agent learns to extract query-specific perception clue(s) from a few sampled frames and performs clue-based alignment to find the video block(s) that are most relevant to the query-specific event. During action exploration, A4VL performs video reasoning in three steps: (1) each agent produces its initial answer with rational, (2) all agents collaboratively scores one another through cross-reviews and relevance ranking, and (3) based on whether a satisfactory consensus is reached, the decision is made either to start a new round of perception-action deliberation by pruning (e.g., filtering out the lowest performing agent) and re-staging (e.g., new-clue and matching block based perception-action exploration), or to conclude by producing its final answer. The integration of the multi-agent alliance through multi-round perception-action exploration, coupled with event-driven partitioning and cue-guided block alignment, enables A4VL to effectively scale to real world long videos while preserving high quality video reasoning. Evaluation Results on five popular VideoQA benchmarks show that A4VL outperforms 18 existing representative VLMs and 11 recent methods optimized for long-video reasoning, while achieving significantly lower inference latency. Our code is released at https://github.com/git-disl/A4VL.
Authors: Zhuoxuan Peng, Boan Zhu, Xingjian Zhang, Wenying Li, S. -H. Gary Chan
Abstract: Current millimeter-wave (mmWave) datasets for human pose estimation (HPE) are scarce and lack diversity in both point cloud (PC) attributes and human poses, hindering the generalization ability of their trained models. On the other hand, unlabeled mmWave HPE data and diverse LiDAR HPE datasets are readily available. We propose EMDUL, a novel approach to expand the volume and diversity of an existing mmWave dataset using unlabeled mmWave data and LiDAR datasets. EMDUL consists of two independent modules, namely a pseudo-label estimator to annotate unlabeled mmWave data, and a closed-form converter that translates an annotated LiDAR PC to its mmWave counterpart. Expanding the original dataset with both LiDAR-converted and pseudo-labeled mmWave PCs significantly boosts the performance and generalization ability of all the examined HPE models, reducing 15.1% and 18.9% error for in-domain and out-of-domain settings, respectively. Code is available at https://github.com/Shimmer93/EMDUL.
Authors: Elad Hirsch, Shubham Yadav, Mohit Garg, Purvanshi Mehta
Abstract: We introduce LICA (Layered Image Composition Annotations), a large scale dataset of 1,550,244 multi-layer graphic design compositions designed to advance structured understanding and generation of graphic layouts. In addition to rendered PNG images, LICA represents each design as a hierarchical composition of typed components including text, image, vector, and group elements, each paired with rich per-element metadata such as spatial geometry, typographic attributes, opacity, and visibility. The dataset spans 20 design categories and 971,850 unique templates, providing broad coverage of real-world design structures. We further introduce graphic design video as a new and largely unexplored challenge for current vision-language models through 27,261 animated layouts annotated with per-component keyframes and motion parameters. Beyond scale, LICA establishes a new paradigm of research tasks for graphic design, enabling structured investigations into problems such as layer-aware inpainting, structured layout generation, controlled design editing, and temporally-aware generative modeling. By representing design as a system of compositional layers and relationships, the dataset supports research on models that operate directly on design structure rather than pixels alone.
Authors: Zhiwei Wang, Yayu Zheng, Defeng He, Li Zhao, Xiaoqin Zhang, Yuxing Li, Edmund Y. Lam
Abstract: Overexposure frequently occurs in practical scenarios, causing the loss of critical visual information. However, existing infrared and visible fusion methods still exhibit unsatisfactory performance in highly bright regions. To address this, we propose EPOFusion, an exposure-aware fusion model. Specifically, a guidance module is introduced to facilitate the encoder in extracting fine-grained infrared features from overexposed regions. Meanwhile, an iterative decoder incorporating a multiscale context fusion module is designed to progressively enhance the fused image, ensuring consistent details and superior visual quality. Finally, an adaptive loss function dynamically constrains the fusion process, enabling an effective balance between the modalities under varying exposure conditions. To achieve better exposure awareness, we construct the first infrared and visible overexposure dataset (IVOE) with high quality infrared guided annotations for overexposed regions. Extensive experiments show that EPOFusion outperforms existing methods. It maintains infrared cues in overexposed regions while achieving visually faithful fusion in non-overexposed areas, thereby enhancing both visual fidelity and downstream task performance. Code, fusion results and IVOE dataset will be made available at https://github.com/warren-wzw/EPOFusion.git.
Authors: Duc T. Nguyen, Hoang-Long Nguyen, Huy-Hieu Pham
Abstract: Automated white blood cell (WBC) classification is essential for leukemia screening yet remains challenging under extreme class imbalance and domain shift. These limitations often cause deep models to overfit dominant classes while failing to generalize to rare pathological subtypes. To address this issue, we propose a three-stage hybrid framework. First, a self-supervised Pix2Pix restoration module mitigates synthetic noise and restores high frequency cytoplasmic details. Second, we integrate a Swin Transformer ensemble with MedSigLIP contrastive embeddings to enhance rare-class semantic representation. Finally, we introduce a biologically inspired refinement strategy combining geometric spikiness analysis and Mahalanobis-based morphological constraints to explicitly rescue suppressed minority predictions. Our hybrid framework achieves a Macro-F1 score of 0.77139 on the private leaderboard, demonstrating strong robustness under extreme long-tail distributions. The code is available at https://github.com/trongduc-nguyen/WBCBench2026.
Authors: Xinhao Cai, Gensheng Pei, Zeren Sun, Yazhou Yao, Fumin Shen, Wenguan Wang
Abstract: In this paper, we propose \textbf{Iris}, a deterministic framework for Monocular Depth Estimation (MDE) that integrates real-world priors into the diffusion model. Conventional feed-forward methods rely on massive training data, yet still miss details. Previous diffusion-based methods leverage rich generative priors yet struggle with synthetic-to-real domain transfer. Iris, in contrast, preserves fine details, generalizes strongly from synthetic to real scenes, and remains efficient with limited training data. To this end, we introduce a two-stage Priors-to-Geometry Deterministic (PGD) schedule: the prior stage uses Spectral-Gated Distillation (SGD) to transfer low-frequency real priors while leaving high-frequency details unconstrained, and the geometry stage applies Spectral-Gated Consistency (SGC) to enforce high-frequency fidelity while refining with synthetic ground truth. The two stages share weights and are executed with a high-to-low timestep schedule. Extensive experimental results confirm that Iris achieves significant improvements in MDE performance with strong in-the-wild generalization.
Authors: Jilles S. van Hulst, W. P. M. H. Heemels, Duarte J. Antunes
Abstract: Electron microscopy has enabled many scientific breakthroughs across multiple fields. A key challenge is the tuning of microscope parameters based on images to overcome optical aberrations that deteriorate image quality. This calibration problem is challenging due to the high-dimensional and noisy nature of the diagnostic images, and the fact that optimal parameters cannot be identified from a single image. We tackle the calibration problem for Scanning Transmission Electron Microscopes (STEM) by employing variational autoencoders (VAEs), trained on simulated data, to learn low-dimensional representations of images, whereas most existing methods extract only scalar values. We then simultaneously estimate the model that maps calibration parameters to encoded representations and the optimal calibration parameters using an expectation maximization (EM) approach. This joint estimation explicitly addresses the simulation-to-reality gap inherent in data-driven methods that train on simulated data from a digital twin. We leverage the known symmetry property of the optical system to establish global identifiability of the joint estimation problem, ensuring that a unique optimum exists. We demonstrate that our approach is substantially faster and more consistent than existing methods on a real STEM, achieving a 2x reduction in estimation error while requiring fewer observations. This represents a notable advance in automated STEM calibration and demonstrates the potential of VAEs for information compression in images. Beyond microscopy, the VAE-EM framework applies to inverse problems where simulated training data introduces a reality gap and where non-injective mappings would otherwise prevent unique solutions.
Authors: Redwan Sony, Anil K Jain, Ross Arun
Abstract: Multimodal Large Language Models (MLLMs) have recently been proposed as a means to generate natural-language explanations for face recognition decisions. While such explanations facilitate human interpretability, their reliability on unconstrained face images remains underexplored. In this work, we systematically analyze MLLM-generated explanations for the unconstrained face verification task on the challenging IJB-S dataset, with a particular focus on extreme pose variation and surveillance imagery. Our results show that even when MLLMs produce correct verification decisions, the accompanying explanations frequently rely on non-verifiable or hallucinated facial attributes that are not supported by visual evidence. We further study the effect of incorporating information from traditional face recognition systems, viz., scores and decisions, alongside the input images. Although such information improves categorical verification performance, it does not consistently lead to faithful explanations. To evaluate the explanations beyond decision accuracy, we introduce a likelihood-ratio-based framework that measures the evidential strength of textual explanations. Our findings highlight fundamental limitations of current MLLMs for explainable face recognition and underscore the need for a principled evaluation of reliable and trustworthy explanations in biometric applications. Code is available at https://github.com/redwankarimsony/LR-MLLMFR-Explainability.
URLs: https://github.com/redwankarimsony/LR-MLLMFR-Explainability.
Authors: Shihao Zhu, Ziheng Ouyang, Yijia Kang, Qilong Wang, Mi Zhou, Bo Li, Ming-Ming Cheng, Qibin Hou
Abstract: Diffusion-based stylization has advanced significantly, yet existing methods are limited to color-driven transformations, neglecting complex semantics and material details. We introduce StyleExpert, a semantic-aware framework based on the Mixture of Experts (MoE). Our framework employs a unified style encoder, trained on our large-scale dataset of content-style-stylized triplets, to embed diverse styles into a consistent latent space. This embedding is then used to condition a similarity-aware gating mechanism, which dynamically routes styles to specialized experts within the MoE architecture. Leveraging this MoE architecture, our method adeptly handles diverse styles spanning multiple semantic levels, from shallow textures to deep semantics. Extensive experiments show that StyleExpert outperforms existing approaches in preserving semantics and material details, while generalizing to unseen styles. Our code and collected images are available at the project page: https://hh-lg.github.io/StyleExpert-Page/.
Authors: Shenzhi Wang, Shixuan Liu, Jing Zhou, Chang Gao, Xiong-Hui Chen, Binghai Wang, An Yang, Shiji Song, Bowen Yu, Gao Huang, Junyang Lin
Abstract: Vision-language models (VLMs) show strong multimodal capabilities but still struggle with fine-grained vision-language reasoning. We find that long chain-of-thought (CoT) reasoning exposes diverse failure modes, including perception, reasoning, knowledge, and hallucination errors, which can compound across intermediate steps. However, most existing vision-language data used for reinforcement learning with verifiable rewards (RLVR) does not involve complex reasoning chains that rely on visual evidence throughout, leaving these weaknesses largely unexposed. We therefore propose HopChain, a scalable framework for synthesizing multi-hop vision-language reasoning data for RLVR training of VLMs. Each synthesized multi-hop query forms a logically dependent chain of instance-grounded hops, where earlier hops establish the instances, sets, or conditions needed for later hops, while the final answer remains a specific, unambiguous number suitable for verifiable rewards. We train Qwen3.5-35B-A3B and Qwen3.5-397B-A17B under two RLVR settings: the original data alone, and the original data plus HopChain's multi-hop data, and compare them across 24 benchmarks spanning STEM and Puzzle, General VQA, Text Recognition and Document Understanding, and Video Understanding. Although this multi-hop data is not synthesized for any specific benchmark, it improves 20 of 24 benchmarks on both models, indicating broad and generalizable gains. Consistently, replacing full chained queries with half-multi-hop or single-hop variants reduces the average score across five representative benchmarks from 70.4 to 66.7 and 64.3, respectively. Notably, multi-hop gains peak in long-CoT vision-language reasoning, exceeding 50 points in the ultra-long-CoT regime. These experiments establish HopChain as an effective, scalable framework for synthesizing multi-hop data that improves generalizable vision-language reasoning.
Authors: Hongbing Li, Jiamin Liu, Shuo Zhang, Bo Xiao
Abstract: Grounded Multimodal Named Entity Recognition (GMNER) identifies named entities, including their spans and types, in natural language text and grounds them to the corresponding regions in associated images. Most existing approaches split this task into two steps: they first detect objects using a pre-trained general-purpose detector and then match named entities to the detected objects. However, these methods face a major limitation. Because pre-trained general-purpose object detectors operate independently of textual entities, they tend to detect common objects and frequently overlook specific fine-grained regions required by named entities. This misalignment between object detectors and entities introduces imprecision and can impair overall system performance. In this paper, we propose a proposal-free Query-Guided Network (QGN) that unifies multimodal reasoning and decoding through text guidance and cross- modal interaction. QGN enables accurate grounding and robust performance in open-domain scenarios. Extensive experiments demonstrate that QGN achieves top performance among compared GMNER models on widely used benchmarks.
Authors: Fei Zhang, Zijian Zhou, Bohao Tang, Sen He, Hang Li, Zhe Wang, Soubhik Sanyal, Pengfei Liu, Viktar Atliha, Tao Xiang, Frost Xu, Semih Gunel
Abstract: We introduce the first method, to the best of our knowledge, for adapting image-to-video models to layer-aware text (glyph) animation, a capability critical for practical dynamic visual design. Existing approaches predominantly handle the transparency-encoding (alpha channel) as an extra latent dimension appended to the RGB space, necessitating the reconstruction of the underlying RGB-centric variational autoencoder (VAE). However, given the scarcity of high-quality transparent glyph data, retraining the VAE is computationally expensive and may erode the robust semantic priors learned from massive RGB corpora, potentially leading to latent pattern mixing. To mitigate these limitations, we propose TransText, a framework based on a novel Alpha-as-RGB paradigm to jointly model appearance and transparency without modifying the pre-trained generative manifold. TransText embeds the alpha channel as an RGB-compatible visual signal through latent spatial concatenation, explicitly ensuring strict cross-modal (RGB-and-Alpha) consistency while preventing feature entanglement. Our experiments demonstrate that TransText significantly outperforms baselines, generating coherent, high-fidelity transparent animations with diverse, fine-grained effects.
Authors: Francesco Pasti, Riccardo De Monte, Davide Dalle Pezze, Gian Antonio Susto, Nicola Bellotto
Abstract: Detecting objects with visual sensors is crucial for numerous mobile robotics applications, from autonomous navigation to inspection. However, robots often need to operate under significant domains shifts from those they were trained in, requiring them to adjust to these changes. Tiny mobile robots, subject to size, power, and computational constraints, face even greater challenges when running and adapting detection models on low-resolution and noisy images. Such adaptability, though, is crucial for real-world deployment, where robots must operate effectively in dynamic and unpredictable settings. In this work, we introduce a new vision benchmark to evaluate lightweight continual learning strategies tailored to the unique characteristics of tiny robotic platforms. Our contributions include: (i) Tiny Robotics Object Detection~(TiROD), a challenging video dataset collected using the onboard camera of a small mobile robot, designed to test object detectors across various domains and classes; (ii) a comprehensive benchmark of several continual learning strategies on different scenarios using NanoDet, a lightweight, real-time object detector for resource-constrained devices.. Our results highlight some key challenges in developing robust and efficient continual learning strategies for object detectors in tiny robotics.es; (ii) a benchmark of different continual learning strategies on this dataset using NanoDet, a lightweight object detector. Our results highlight key challenges in developing robust and efficient continual learning strategies for object detectors in tiny robotics.
Authors: Ji-Hun Oh, Kianoush Falahkheirkhah, John Cheville, Rohit Bhargava
Abstract: Histopathologic analysis of stained tissue remains central to biomedical research and clinical care. Virtual staining (VS) offers a promising alternative, with potential to reduce costs and streamline workflows, yet hallucinations pose serious risks to clinical reliability. Here, we formalize the problem of hallucination detection in VS and propose a scalable post-hoc method: Neural Hallucination Precursor (NHP), which leverages the generator's latent space to preemptively flag hallucinations. Extensive experiments across diverse VS tasks show NHP is both effective and robust. Critically, we also find that models with fewer hallucinations do not necessarily offer better detectability, exposing a gap in current VS evaluation and underscoring the need for hallucination detection benchmarks.
Authors: Alec S. Xu, Can Yaras, Peng Wang, Qing Qu
Abstract: Deep neural networks have attained remarkable success across diverse classification tasks. Recent empirical studies have shown that deep networks learn features that are linearly separable across classes. However, these findings often lack rigorous justifications, even under relatively simple settings. In this work, we address this gap by examining the linear separation capabilities of shallow nonlinear networks. Specifically, inspired by the low intrinsic dimensionality of image data, we model inputs as a union of low-dimensional subspaces (UoS) and demonstrate that a single nonlinear layer can transform such data into linearly separable sets. Theoretically, we show that this transformation occurs with high probability when using random weights and quadratic activations. Notably, we prove this can be achieved when the network width scales polynomially with the intrinsic dimension of the data rather than the ambient dimension. Experimental results corroborate these theoretical findings and demonstrate that similar linear separation properties hold in practical scenarios beyond our analytical scope. This work bridges the gap between empirical observations and theoretical understanding of the separation capacity of nonlinear networks, offering deeper insights into model interpretability and generalization.
Authors: Sahara Sheikholeslami, Ladislau B\"ol\"oni
Abstract: Robotic manipulation requires explicit or implicit knowledge of the robot's joint positions. Precise proprioception is standard in high-quality industrial robots but is often unavailable in inexpensive robots operating in unstructured environments. In this paper, we ask: to what extent can a fast, single-pass regression architecture perform visual proprioception from a single external camera image, available even in the simplest manipulation settings? We explore several latent representations, including CNNs, VAEs, ViTs, and bags of uncalibrated fiducial markers, using fine-tuning techniques adapted to the limited data available. We evaluate the achievable accuracy through experiments on an inexpensive 6-DoF robot.
Authors: Mayar Elfares, Pascal Reisert, Ralf K\"usters, Andreas Bulling
Abstract: Gaze-based applications are increasingly advancing with the availability of large datasets but ensuring data quality presents a substantial challenge when collecting data at scale. It further requires different parties to collaborate, therefore, privacy concerns arise. We propose QualitEye--the first method for verifying image-based gaze data quality. QualitEye employs a new semantic representation of eye images that contains the information required for verification while excluding irrelevant information for better domain adaptation. QualitEye covers a public setting where parties can freely exchange data and a privacy-preserving setting where parties cannot reveal their raw data nor derive gaze features/labels of others with adapted private set intersection protocols. We evaluate QualitEye on the MPIIFaceGaze and GazeCapture datasets and achieve a high verification performance (with a small overhead in runtime for privacy-preserving versions). Hence, QualitEye paves the way for new gaze analysis methods at the intersection of machine learning, human-computer interaction, and cryptography.
Authors: Kateryna Lutsai, Pavel Stra\v{n}\'ak
Abstract: Digitization projects in humanities often generate vast quantities of page images from historical documents, presenting significant challenges for manual sorting and analysis. These archives contain diverse content, including various text types (handwritten, typed, printed), graphical elements (drawings, maps, photos), and layouts (plain text, tables, forms). Efficiently processing this heterogeneous data requires automated methods to categorize pages based on their content, enabling tailored downstream analysis pipelines. This project addresses this need by developing and evaluating an image classification system specifically designed for historical document pages, leveraging advancements in artificial intelligence and machine learning. The set of categories was chosen to facilitate content-specific processing workflows, separating pages requiring different analysis techniques (e.g., OCR for text, image analysis for graphics)
Authors: Jiacheng Liu, Pengxiang Ding, Qihang Zhou, Yuxuan Wu, Da Huang, Zimian Peng, Wei Xiao, Weinan Zhang, Lixin Yang, Cewu Lu, Donglin Wang
Abstract: Recent Vision-Language-Action models show potential to generalize across embodiments but struggle to quickly align with a new robot's action space when high-quality demonstrations are scarce, especially for bipedal humanoids. We present TrajBooster, a cross-embodiment framework that leverages abundant wheeled-humanoid data to boost bipedal VLA. Our key idea is to use end-effector trajectories as a morphology-agnostic interface. TrajBooster (i) extracts 6D dual-arm end-effector trajectories from real-world wheeled humanoids, (ii) retargets them in simulation to Unitree G1 with a whole-body controller trained via a heuristic-enhanced harmonized online DAgger to lift low-dimensional trajectory references into feasible high-dimensional whole-body actions, and (iii) forms heterogeneous triplets that couple source vision/language with target humanoid-compatible actions to post-pre-train a VLA, followed by only 10 minutes of teleoperation data collection on the target humanoid domain. Deployed on Unitree G1, our policy achieves beyond-tabletop household tasks, enabling squatting, cross-height manipulation, and coordinated whole-body motion with markedly improved robustness and generalization. Results show that TrajBooster allows existing wheeled-humanoid data to efficiently strengthen bipedal humanoid VLA performance, reducing reliance on costly same-embodiment data while enhancing action space understanding and zero-shot skill transfer capabilities. For more details, For more details, please refer to our \href{https://jiachengliu3.github.io/TrajBooster/}.
Authors: Seunghyeon Kim, Taesun Yeom, Jinho Kim, Wonpyo Park, Kyuyeun Kim, Jaeho Lee
Abstract: Large pretrained vision encoders are central to multimodal intelligence, powering applications from on-device vision processing to vision-language models. Since these applications often demand real-time processing of massive visual data, reducing the inference cost of vision encoders is critical. Quantization offers a practical path, but it remains challenging even at 8-bit precision due to so-called outliers. In this work, we propose $\textit{RegCache}$, a training-free algorithm that mitigates outliers in large-scale pretrained vision encoders and serves as a plug-in module that can be applied on top of other quantization methods. RegCache introduces outlier-prone yet semantically meaningless prefix tokens to the vision encoder, which prevent other tokens from having outliers. Notably, we observe that outliers in vision encoders behave differently from those in language models, motivating two technical innovations: middle-layer prefixing and token deletion. Experimental results show that our method consistently improves quantized model performance across various vision encoders, particularly in extremely low-bit regimes (e.g., 4-bit).
Authors: Adam Diamant
Abstract: This study develops an AI-based pose estimation pipeline for quantifying movement kinematics in resistance training. Using videos from Wolf et al. (2025), comprising 303 recordings of 26 participants performing eight upper-body exercises under full (fROM) and lengthened partial (pROM) conditions, we extract joint-angle trajectories using five distinct deep-learning pose estimation models and a unified signal-processing framework. From these trajectories, we derive repetition-level metrics including range of motion (ROM) and repetition duration. We use these outputs as dependent variables in a crossed random-effects model that accounts for participant-, exercise-, and model-level variability to assess systematic differences between ROM conditions. Results indicate that pROM reduces range of motion without significantly affecting repetition duration. Variance decomposition shows that pROM increases both between-participant and between-exercise variability, suggesting reduced consistency in execution. To enable cross-exercise comparison, we model ROM on a logarithmic scale and define %ROM as the proportion of fROM achieved under pROM. While the estimated mean is approximately 56\%, significant heterogeneity across exercises indicates that lengthened partials are not characterized by a fixed proportion of full ROM. The results demonstrate that AI-based motion analysis can provide reliable kinematic insights to inform evidence-based training recommendations.
Authors: Junsik Kim, Gun Bang, Soowoong Kim
Abstract: Hierarchical LiDAR geometry compression encodes voxel occupancies from low to high bit-depths, yet prior methods treat each depth independently and re-estimate local context from coordinates at every level, limiting compression efficiency. We present ELiC, a real-time framework that combines cross-bit-depth feature propagation, a Bag-of-Encoders (BoE) selection scheme, and a Morton-order-preserving hierarchy. Cross-bit-depth propagation reuses features extracted at denser, lower depths to support prediction at sparser, higher depths. BoE selects, per depth, the most suitable coding network from a small pool, adapting capacity to observed occupancy statistics without training a separate model for each level. The Morton hierarchy maintains global Z-order across depth transitions, eliminating per-level sorting and reducing latency. Together these components improve entropy modeling and computation efficiency, yielding state-of-the-art compression at real-time throughput on Ford and SemanticKITTI. Code and pretrained models are available at https://github.com/moolgom/ELiCv1.
Authors: Wei Yang, Yiran Zhu, Zilin Li, Xunjia Zhang, Jun Xia, Hongtao Wang
Abstract: Coarse-to-fine path decision-making requires predicting a valid taxonomy path in which earlier decisions constrain later ones. However, existing benchmarks score each level independently, obscuring cross-level validity and consistency. To better align evaluation with this setting, we introduce a Joint Path Decision (JPD) protocol that requires predicting the full path in one call, together with Depth-Weighted Prefix Accuracy (DWPA), a metric family that measures path reliability with tunable emphasis on deeper levels. Under JPD, strong vision-language models (VLMs) frequently produce invalid parent-child pairs and brittle full-path predictions, suggesting that their failures stem not only from incomplete taxonomic knowledge but also from unstable cross-level decision coordination. To address this problem, we propose DuoTeach, a dual-role self-teaching distillation framework that requires no ground-truth labels and reuses the same pretrained VLM in two roles. Its Decision-Conditioned Rollout (DCR) generates more coherent teacher traces by conditioning each level on prior decisions, and distills this coordinated behavior into the student without additional test-time rollouts. Across multiple taxonomy-structured benchmarks and VLM base models, DuoTeach improves in-domain DWPA (alpha = 0.95) by up to 30.24 points and boosts zero-shot performance on unseen taxonomies from 17.17% to 43.66%. Further analyses attribute these gains to improved within-call multi-level decision coordination.
Authors: Chieh-Hsin Lai, Bac Nguyen, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Yuki Mitsufuji, Stefano Ermon, Molei Tao
Abstract: Drifting models train one-step generators by optimizing a mean-shift discrepancy induced by a kernel between the data and model distributions, with Laplace kernels used by default in practice. At each point, this discrepancy compares the kernel-weighted displacement toward nearby data samples with the corresponding displacement toward nearby model samples, yielding a transport direction for generated samples. In this paper, we make its relationship to the score-matching principle behind diffusion models precise by showing that drifting admits a score-based formulation on kernel-smoothed distributions. For Gaussian kernels, the population mean-shift field coincides with the score difference between the Gaussian-smoothed data and model distributions. This identity follows from Tweedie's formula, which links the score of a Gaussian-smoothed density to the corresponding conditional mean, and implies that Gaussian-kernel drifting is exactly a score-matching-style objective on smoothed distributions. It also clarifies the connection to Distribution Matching Distillation (DMD): both methods use score-mismatch transport directions, but drifting realizes the score signal nonparametrically from kernel neighborhoods, whereas DMD uses a pretrained diffusion teacher. Beyond Gaussians, we derive an exact decomposition for general radial kernels, and for the Laplace kernel we prove rigorous error bounds showing that drifting remains an accurate proxy for score matching in low-temperature and high-dimensional regimes.
Authors: Zihui Yu, Pingcong Li, Bichi Zhang, S\"oren Schwertfeger
Abstract: Vision-and-Language Navigation (VLN) is shifting from rigid, step-by-step instruction following toward open-vocabulary, goal-oriented autonomy. Achieving this transition without exhaustive routing prompts requires agents to leverage structural priors. While prior work often assumes computationally heavy 2D/3D metric maps, we instead exploit a lightweight, text-based osmAG (OpenStreetMap Area Graph), a floorplan-level topological representation that is easy to obtain and maintain. However, global planning over a prior map alone is brittle in real-world deployments, where local connectivity can change (e.g., closed doors or crowded passages), leading to execution-time failures. To address this gap, we propose a hierarchical navigation framework HaltNav that couples the robust global planning of osmAG with the local exploration and instruction-grounding capability of VLN. Our approach features an MLLM-based brain module, which is capable of high-level task grounding and obstruction awareness. Conditioned on osmAG, the brain converts the global route into a sequence of localized execution snippets, providing the VLN executor with prior-grounded, goal-centric sub-instructions. Meanwhile, it detects local anomalies via a mechanism we term Reactive Visual Halting (RVH), which interrupts the local control loop, updates osmAG by invalidating the corresponding topology, and triggers replanning to orchestrate a viable detour. To train this halting capability efficiently, we introduce a data synthesis pipeline that leverages generative models to inject realistic obstacles into otherwise navigable scenes, substantially enriching hard negative samples. Extensive experiments demonstrate that our hierarchical framework outperforms several baseline methods without tedious language instructions, and significantly improves robustness for long-horizon vision-language navigation under environmental changes.
Authors: Yiqin Zhang, Meiling Chen
Abstract: CT images are widely used in clinical diagnosis and treatment, and their data have formed a de facto standard - DICOM. It is clear and easy to use, and can be efficiently utilized by data-driven analysis methods such as deep learning. In the past decade, many program frameworks for medical image analysis have emerged in the open-source community. ITKIT analyzed the characteristics of these frameworks and hopes to provide a better choice in terms of ease of use and configurability. ITKIT offers a complete pipeline from DICOM to 3D segmentation inference. Its basic practice only includes some essential steps, enabling users with relatively weak computing capabilities to quickly get started using the CLI according to the documentation. For advanced users, the OneDL-MMEngine framework provides a flexible model configuration and deployment entry. This paper conducted 12 typical experiments to verify that ITKIT can meet the needs of most basic scenarios.
Authors: Andrea Tupini, Lars Liden, Reuben Tan, Yu Wang, Jianfeng Gao
Abstract: With AsgardBench we aim to evaluate visually grounded, high-level action sequence generation and interactive planning, focusing specifically on plan adaptation during execution based on visual observations rather than navigation or low-level manipulation. In the landscape of embodied AI benchmarks, AsgardBench targets the capability category of interactive planning, which is more sophisticated than offline high-level planning as it requires agents to revise plans in response to environmental feedback, yet remains distinct from low-level execution. Unlike prior embodied AI benchmarks that conflate reasoning with navigation or provide rich corrective feedback that substitutes for perception, AsgardBench restricts agent input to images, action history, and lightweight success/failure signals, isolating interactive planning in a controlled simulator without low-level control noise. The benchmark contains 108 task instances spanning 12 task types, each systematically varied through object state, placement, and scene configuration. These controlled variations create conditional branches in which a single instruction can require different action sequences depending on what the agent observes, emphasizing conditional branching and plan repair during execution. Our evaluations of leading vision language models show that performance drops sharply without visual input, revealing weaknesses in visual grounding and state tracking that ultimately undermine interactive planning. Our benchmark zeroes in on a narrower question: can a model actually use what it sees to adapt a plan when things do not go as expected?