paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

Magnitude-Direction Decoupling for Fast Video Generation with Flow Matching Models

Haonan Xu, Feiyang Chen, Songkui Chen, Hongpeng Pan, Zhefeng Wang, Xinyu Duan, Baoxing Huai, Yang Yang

Flow matching models for video generation achieve impressive performance but suffer from high computational overhead due to iterative denoising. In fact, the original model is not necessary for all denoising steps, allowing some steps to use lightweight alternatives for faster sampling. However, directly using caching or lightweight models can deviate from the original denoising trajectory, resulting in suboptimal performance. Through empirical analysis, we find that lightweight models can robustly capture the magnitude components of the original model's output, while caching provides reliable directional guidance. Building on this insight, we propose the Magnitude-Direction Decoupling (MDD) method, which adaptively employs a direction-calibrated lightweight model as a substitute for the original model to accelerate inference and effectively correct deviations in the denoising trajectory. Moreover, MDD further reduces inference costs by reusing magnitude information under classifier-free guidance (CFG). As a result, MDD offers a more reliable and lightweight solution to accelerate sampling. Experiments show that MDD outperforms existing acceleration methods, delivering promising speedups (e.g., up to 2.95x on Wan2.1) while preserving high visual fidelity and content richness.

arXiv

Differentiable Voronoi Ray Tracing Beyond Rasterization Speeds

Bernardo Taveira, Carl Lindström, Joakim Johnander, Fredrik Kahl

Real-time novel view synthesis is dominated by rasterized explicit primitives. These projection-based pipelines provide high throughput but require specialized extensions for non-pinhole effects such as distortion, rolling shutter, and depth of field. Ray-based rendering expresses these effects naturally but is generally assumed too slow for competitive real-time rendering. We analyze the factors governing throughput in differentiable Voronoi ray tracing and identify traversal length, per-cell work, and memory locality as principal determinants. Guided by this, we introduce VoroTracing, which co-designs the scene representation, optimization, and GPU execution to reduce these costs. Compact octahedral appearance textures reduce memory traffic, while surface-concentrated opacity promotes early termination. The fixed-budget representation is optimized without pruning or densification and rendered with a GPU implementation designed for coherent traversal. On Mip-NeRF 360, VoroTracing renders at 623 FPS on an RTX 5090, providing $3.2\times$ the throughput of the fastest prior ray-based method and $2.8\times$ that of 3D Gaussian Splatting, while maintaining competitive reconstruction quality. Our renderer supports fisheye, rolling-shutter, motion-blur, and depth-of-field effects through ray generation and sampling, requiring no specialized rasterization. These results show that real-time throughput can be achieved with the flexibility of ray-based rendering. We release our source code, see https://research.zenseact.com/publications/vorotracing

arXiv

Is Haar Enough? Exploring Symlets and Coiflets for Wavelet Convolution Layers

Md Rifat Ur Rahman

Wavelet convolution layers have recently emerged as an efficient mechanism for enlarging receptive fields through multiresolution analysis, but prior work has fixed the wavelet basis to Haar or Daubechies at a chosen decomposition depth, leaving open whether a different basis can shift the underlying efficiency frontier. We identify and characterize a previously unexplored trade-off in this setting: bases with stronger approximation properties (longer filters) can reduce the decomposition depth required for competitive accuracy, yielding a net reduction in parameters and FLOPs despite higher perlevel transform cost. We formalize this as an F-vs.-L tradeoff (filter length vs. decomposition levels) and study it systematically across Haar, Daubechies, Symlets, and Coiflets under controlled architectures and budgets. On image classification (CIFAR-10, ImageNet-1K) and semantic segmentation (Cityscapes), Coiflet-based wavelet convolutions match Haar at deeper levels with approximately 32% fewer additional parameters and 33% fewer additional FLOPs, providing a concrete and actionable design choice for practitioners building wavelet-based architectures.

arXiv

Denoised Variance-Based Pruning with Optimal Brain Bias Compensation

Geon Tack Lee, Jaegul Choo, Kang Eun Jeon

Vision Transformers (ViTs) achieve state-of-the-art performance but carry massive computational overhead that restricts edge deployment. Although structural pruning has emerged as a key strategy to reduce these costs, existing methods often suffer from severe accuracy degradation or require expensive retraining. Recently, Variance-Based Pruning (VBP) introduced a promising paradigm by selecting neurons based on activation variance; however, it remains limited by statistical noise in finite-sample activation covariance and reliance on bias-only updates that cannot fully account for structural reconstruction error. To address these limitations, we introduce Denoised Variance-Based Pruning with Optimal Brain Bias Compensation (DVBP + OB$^2$C). We leverage random matrix theory to filter noise from the activation covariance spectrum for robust neuron selection and mathematically prove that integrating mean-shift compensation into the Optimal Brain Compression objective reduces the layer-wise Hessian exactly to the activation covariance matrix. This enables an optimal, closed-form update of the remaining weights using the same statistics gathered for selection. Extensive experiments on DeiT, Swin, and ConvNeXt architectures demonstrate that DVBP + OB$^2$C achieves state-of-the-art training-free performance; at 50% MLP pruning, it retains over 90% of the original Top-1 accuracy on Small and Base variants, outperforming VBP by up to 29.46% (ConvNeXt-T) and 7.33% (Swin-S). The code is available at: https://github.com/geontackee/DVBP_OB2C.

arXiv

MaLViL: Multi-axis Low-rank Vision-LSTM for Medical Image Segmentation

Afshin Bozorgpour, Sina Ghorbani Kolahi, Moein Heidari, Ilker Hacihaliloglu, Dorit Merhof

Vision-LSTM (ViL) enables efficient global modeling, but its cost still scales with the number of spatial tokens, so existing segmenters confine ViL to a coarse bottleneck and lose fine anatomical detail. Rasterizing 2D features into a 1D sequence further breaks adjacency across the orthogonal scan axis. We propose MaLViL, a Multi-axis Low-rank Vision-LSTM network that extends ViL across decoder resolutions. Bidirectional low-rank ViL (Bi-LRViL) reasons on a compact orthonormal subspace and preserves detail through an orthogonal residual; scale-aware SaLViL restores cross-axis neighbors before serialization; and a Cross-Directional Mixer (CDM) fuses orthogonal horizontal and vertical traversal paths. Statistics-Guided Skip Modulation (SGSM) further retains boundary cues in encoder skips. On skin-lesion, ultrasound, and multi-organ CT benchmarks, MaLViL achieves competitive or state-of-the-art segmentation accuracy, while reducing ViL operator memory by up to $83\times$ at fine decoder resolutions. Code is available at: https://github.com/xmindflow/malvil.

arXiv

RetiWave-Mamba: A Dual-Stream Network for Retinal Disease Detection based on Multi-scale Context and Frequency-Adaptive Mamba Projection

Cheng Cheng, Jin Hong

Retinal diseases are a leading cause of irreversible vision impairment, making early and accurate diagnosis essential for effective treatment. Optical Coherence Tomography (OCT) serves as a critical imaging modality for this purpose, yet its automated analysis is hindered by inherent speckle noise, varying lesion scales, and subtle inter-class similarities. To address these challenges, we propose a novel framework, RetiWave-Mamba, which integrates spatial-frequency domain learning with state-of-the-art state space models. The framework utilizes Discrete Wavelet Transform (DWT) to decompose OCT images into low- and high-frequency streams, enabling decoupled processing of structural context and fine-grained details. For the low-frequency branch, we design a Multi-scale Contextual Localization Module (MCLM), which synergizes multi-scale dilation with spatial attention to expand the global receptive field and precisely localize lesion regions. For the high-frequency branch, we introduce an Attention-Guided High-Resolution Network (AG-HRNet) equipped with an intelligent gating mechanism to suppress noise propagation during multi-scale interactions. Furthermore, a Frequency-Adaptive Mamba Projector (FAMP) is incorporated to capture long-range dependencies within disjoint high-frequency textural features. Extensive experiments on the OCT-C8 dataset demonstrate that our approach achieves a state-of-the-art (SOTA) classification accuracy of 98.25%, surpassing existing methods. These results highlight the efficacy of RetiWave-Mamba in robustly identifying retinal pathologies under noisy conditions, offering a promising tool for clinical diagnosis.

arXiv

PathoArgus: Advancing Evidence-Grounded Long-Context Visual Reasoning across Gigapixel Whole-Slide and Multi-Slide Case Contexts

Bowen Liu, Qixiang ZHANG, Xiaomeng Li

Whole-slide pathology reasoning requires models to integrate gigapixel-scale visual evidence across complete case-linked slides, yet current question-answering benchmarks primarily measure final answer accuracy--a metric vulnerable to linguistic priors and benchmark regularities, and insufficient to establish that predictions are grounded in the supplied tissue. We introduce PathoArgus-Bench, a benchmark and evaluation protocol that explicitly tests the full evidence chain: availability, accessibility, use, and responsiveness. PathoArgus-Bench comprises 22,078 four-choice questions from 4,913 patients across 15 TCGA projects, covering six pathology capabilities across three levels of evidence demand, and operates under a fixed reader budget that retains only a small fraction of the gigapixel context. To further isolate evidence-grounded reasoning, we contribute ESG (Evidence State Quartets), a controlled set of 483 quartets where the question text is fixed while the target WSI set is moved, replaced, or removed, requiring consistent predictions across all states. Evaluating 20 general-purpose, medical, and pathology-specific systems reveals a stark gap: while GPT-5.6 achieves 57.09% overall accuracy and 57.04% on ESG, it correctly completes only 19 of 483 quartets (3.93% QExact), exposing that row-level accuracy does not translate into reliable evidence grounding. We also introduce PathoArgus, a fixed-budget reader that allocates context via question relevance and spatial coverage, attaining 50.39% overall accuracy yet only 1.86% QExact--demonstrating that improved context access alone does not ensure consistent evidence-based prediction. Our benchmark and diagnostics establish that acquiring useful whole-slide context is necessary but far from sufficient, and call for a shift from answer-centric to evidence-grounded evaluation in computational pathology.

arXiv

SpurCon: Weighted Supervised Contrastive Learning for Mitigating Spurious Cues in Medical Imaging

Shenhav Nadir, Meir Yossef Levi, Eyal Gofer, Guy Gilboa

Despite the rapid progress of deep neural networks in visual recognition, their adoption in high-risk medical applications remains limited due to reliability and robustness concerns. Models may exploit spurious correlations, particularly in medical imaging, where devices or treatment artifacts often co-occur with pathology. In small or imbalanced datasets, such cues further reduce worst-group performance and undermine clinical trust. To solve these issues, two major challenges should be addressed: identifying dataset-specific spurious cues, which typically require domain knowledge, and mitigating reliance on them. To tackle both, we propose SpurCon, a lightweight framework based on a novel supervised contrastive loss formulation that leverages available metadata and predicted spurious labels to enhance robustness. We introduce a fast few-shot procedure, without network training, to estimate spurious labels using a small number of expert-annotated samples. We then propose a weighted supervised contrastive objective, WtSupCon, that reshapes the representation geometry by assigning sample-specific weights that depend on the [pathology, spurious, metadata] combination. For example, the highest weight is assigned to samples that differ only in their spurious label. This yields highly similar representations for images with the same metadata and pathology, differing only in the predicted spurious label. Our method operates on pretrained image encoders (such as BiomedCLIP) and trains only a lightweight projection head. We evaluate SpurCon on a synthetic setting and on Waterbirds, CheXpert, a chest X-ray classification dataset, and ISIC 2020, a skin cancer classification dataset. Our approach delivers the best spurious-mitigation performance, balancing well worst-group and overall accuracy on multiple datasets.

arXiv

Where a New Concept Must Enter: Entry Point Gates Cross-Task Usability in Unified Multimodal Models

Zongyang Qiu, Yihan Wu, Kaixuan Fan, Bo Li, Hui Xiong

Unified multimodal models (UMMs) are motivated by the hope that understanding and generation reinforce each other but controlled ablations repeatedly find that adding a generation objective leaves understanding flat. Joint-training studies cannot settle the disagreement: with overlapping supervision, a gain cannot be attributed to the architecture rather than the data. To further investigate the relationship between the two directions in UMMs, we separate them by construction. A novel visual entity, a rendered 3D asset paired with a pseudo-word screened for absence from the frozen model's behavior, is bound through exactly one task direction, and the untrained direction is then measured. We find that the channel is real in both directions, but the directions differ in kind: generation training installs a name the model can only match among candidates; understanding training installs one it can also produce. What governs cross-task usability is where the binding enters the shared computation. An alignment probe predicts export across 36 configurations (Spearman $ρ= +0.68$). That objective's alignment term, maximized in closed form over activations with every weight frozen, makes a concept drawable when injected at layer 7 of 28 and is indistinguishable from the base model from layer 14 on, while the weight-based version of the same edit peaks at layers 10-14. In an observational series of four models, this window appears only where the understanding pathway is a semantic vision encoder, suggesting that unified weights are not enough: the two directions must share a semantic format at the entry point. Exploiting the rule, a mid-stack alignment objective acquires the concept for a $0.1\%$ relative loss of the model's general text-to-image ability, against $41\%$ for the standard generative route. Our code is at https://github.com/Zane-ZYQiu/entry-point-umm.

arXiv

Leveraging existing sparse point annotations for benthic imagery dense segmentation

Cesar Borja, Breck A. McCollum, Jarret E. Byrnes, Kenneth Sebens, Ana C. Murillo

The health of marine ecosystems is a critical indicator of global environmental change, yet the physical constraints of underwater observation and the intrinsic challenges of processing marine imagery severely limit the scalability of systematic monitoring. While recent visual foundation models such as the Segment Anything Model (SAM) series show great promise, they still struggle with the fine-grained recognition required in these complex scenarios and still require expert supervision. Our work addresses this gap by bridging state-of-the-art foundation models with existing sparse supervision. Because historical benthic surveys are typically annotated with only a few sparse expert points per image, we utilize these legacy point-labels as visual prompts for SAM2. Our primary contribution is a novel mechanism to automatically identify which of these points are suitable, and which are actively harmful, when used for propagation. By filtering out unreliable points, we extract high-quality pseudo-ground-truth masks capable of training more accurate, fine-grained semantic segmentation models. We demonstrate the effectiveness of our approach on public benthic data and introduce a new, challenging benchmark featuring real-world sparse expert annotations, paving the way for scalable ecological analysis.

arXiv

MSEditor: Toward Consistent Multi-Shot Video Editing

Kunyu Feng, Yue Ma, Bingyuan Wang, Yuefeng Wang, Zhiyuan Qin, Hao Cheng, Hao Li, Qifeng Chen, Zeyu Wang

In this paper, we tackle the problem of performing consistent, unified modifications to a multi-shot video sequence. This task is particularly challenging because multi-shot videos consist of discontinuous temporal segments that vary significantly in viewpoint, camera scale, and subject pose, leading to severe identity drift and cumulative error propagation. Achieving coherent edits requires establishing reliable cross-shot semantic awareness to maintain stable subject appearance and visual continuity across these disjointed boundaries. To address this, we propose MSEditor, the first framework designed specifically for consistent multi-shot video editing. To overcome the scarcity of high-quality multi-shot training data, we repurpose existing multi-view video datasets to provide robust cross-shot supervision. Architecturally, we introduce a Supervisory Adapter that injects this cross-shot information into the diffusion backbone, enabling the model to learn identity-consistent representations. Furthermore, to effectively mitigate cumulative errors and ensure long-range temporal coherence, we design a Cross-Shot Packing strategy that dynamically aggregates information from semantically related shots within the self-attention window. Extensive experiments demonstrate that MSEditor significantly outperforms existing methods on our curated multi-shot video editing benchmark in terms of identity preservation, temporal stability, and overall visual quality.

arXiv

GroupForward: Building Referable 3D Scenes via Instance-Grouped Feed-Forward Gaussian Splatting

Qijian Tian, Zimeng Wu, Xuhong Wang, Lizhuang Ma, Xin Tan

Simultaneously reconstructing and understanding 3D environments is essential for embodied agents. Toward this goal, feed-forward semantic 3D Gaussian Splatting (3DGS) efficiently constructs semantic scene representations from sparse multi-view observations. However, existing methods lack explicit instance discrimination and mainly support category- or phrase-based semantic queries. To this end, we propose GroupForward, an instance-grouped feed-forward Gaussian splatting model that reconstructs geometry, appearance, instance structure, and semantics from sparse, unposed, and uncalibrated multi-view images. Unlike existing methods that attach high-dimensional semantic features to each Gaussian, GroupForward learns compact instance embeddings that group Gaussians into cross-view consistent 3D instances, reformulating feed-forward semantic 3DGS from per-Gaussian semantic feature rendering to instance-level semantic aggregation and propagation. Building on these instance groups, we further propose a Referential Scene Reasoning Framework (RSRF) for complex 3D referring segmentation. RSRF constructs an instance-grouped 3D scene graph and retrieves candidate instances for a given referring expression. A vision-language model then reasons over structured instance evidence and multi-view observations to identify the referred instance among the candidates. RSRF thereby extends language interaction from simple semantic querying to complex referential scene reasoning. Experiments on semantic reconstruction and referential reasoning demonstrate the effectiveness of our instance-grouped reconstruction and reasoning framework.

arXiv

Explainable AI-Powered Framework for Video-Based Skill Assessment in Cataract Surgery

Mohammad Javad Ahmadi, Hamid D. Taghirad

Persistent shortages in the surgical workforce and inherent limitations of traditional training methods highlight the necessity of automated, data-driven approaches in surgical education. This study addresses these challenges by introducing a novel, explainable AI-powered framework for automated skill assessment, specifically focusing on cataract surgery. We present the world's largest dataset of cataract surgery videos, comprising 2,000 recordings. Additionally, we propose an AI-powered analytical framework that employs advanced computer vision and signal-processing techniques to automatically evaluate surgical videos to derive objective, quantitative performance indicators that complement or potentially replace subjective scoring methods. A significant advantage of our framework over previous methods lies precisely in its explainability of outputs, elevating it beyond merely an opaque skill classification tool. Through experimental analysis of 83 cataract surgery videos, we demonstrate that the automatically computed metrics exhibit strong correlations with expert-based subjective evaluations, achieving up to 87% accuracy in surgical skill assessment. Each metric was individually examined, and expert surgeons provided subjective ratings using the newly introduced Capsulorhexis Skill Assessment System (CSAS). These subjective assessments were compared with ten objective motion-based metrics extracted through our framework. The results indicated a robust correlation between subjective ratings and automated indicators, underscoring the framework's capacity to accurately model surgical expertise.

arXiv

BrainNorm: A Foundation Model that knows Normal via Semantic Atlas Pretraining

Madhumitha Venkatesh, Shanawaj S Madarkar, Konda Reddy Mopuri

We introduce BrainNorm, a normative foundation model, trained and tested on ~66,000 T1-weighted structural MRI (T1w sMRI) scans. By leveraging language-image style contrastive pretraining on healthy cohorts across ages, BrainNorm learns a Semantic Atlas Latent space (SAL), where each scan is represented as a set of atlas-parcel embeddings. This yields parcel-specific healthy aging template trajectories that support age-consistent template matching and localized deviation scoring relative to a subject's chronological age. Across 6 downstream cohorts, BrainNorm demonstrates generalization evaluated across 25 task-setting combinations spanning age estimation, brain-age gap estimation, parcel identification, and single- & multi-disease classification tasks under direct inference, zero-shot, few-shot & full-data linear-probe settings. The resulting deviation patterns in SAL space enable zero-shot tasks for disease prediction using parcel-wise abnormalities. Fine-tuning on healthy-only cohorts of downstream datasets further improves the performance of various tasks. Across all classification tasks, linear probing on BrainNorm's frozen embeddings outperforms 9 baselines finetuned under end-to-end supervision. Furthermore, the localized deviations identified by BrainNorm across various neurodegenerative disorders closely align with established neurodegeneration pathology in clinical literature.

arXiv

Looking Beyond the Scale: Do Surgical Skill Models Learn Transferable Representations Across Assessment Rubrics?

Hanna Hoffmann, Felix von Bechtolsheim, Stefanie Speidel, Rebecca Hisey

Vision-based surgical skill assessment has shown strong in-domain results, yet a fundamental question remains unasked: do these models learn transferable representations of surgical proficiency, or do they merely encode dataset-specific visual patterns? This paper systematically analyzes what limits cross-domain skill transfer between the GOALS and OSATS assessment scales using the LASANA and JIGSAWS datasets. Each evaluated method serves a targeted diagnostic purpose: end-to-end training to test whether supervised skill learning transfers directly, Adaptive Sharpness-Aware Minimization (ASAM) to probe whether flatter loss landscapes improve generalization, and augmentation-based self-supervised and contrastive learning to assess whether domain-invariant pretraining decouples skill from visual context. Transfer is evaluated in both directions using a disjoint-participant held-out test set for JIGSAWS. Results reveal an asymmetry: backbones pretrained on JIGSAWS achieve CCC values of 0.77 to 0.80 on LASANA, closely matching the end-to-end baseline, showing cross-rubric transfer is feasible when the target domain provides consistent supervision. Transfer to JIGSAWS fails across all methods, likely due to annotation inconsistencies. Control experiments with a Kinetics-pretrained backbone suggest task-specific heads carry the majority of the skill prediction burden, while the backbone need only provide adequate spatiotemporal features. These findings offer a new perspective on vision-based skill assessment: the central question of whether skill representations transfer across scoring systems has not been previously investigated. Results indicate the visual component is dominant but not solely responsible for skill prediction; further work is needed to conclusively disentangle transferable skill features from those bound to a specific visual domain.

arXiv

When More Foundation Models Means Less: Diagnosing and Addressing Multi-View Fusion Failure

Yibo Liu, Bowen Jiang

Foundation-model hubs turn multi-view fusion into a selection problem: from a large heterogeneous encoder pool, which views should be fused, and how many? We show that downstream performance is non-monotonic in the number of fused encoders; later views can be redundant or task-misaligned, causing accuracy to saturate or decline. We formalise this setting as view-set composition and propose KAGES (Kernel-Alignment Greedy Encoder Selector), a label-aware method that orders frozen encoders by their marginal gain in centred kernel-target alignment. KAGES requires no downstream classifier training during selection, evaluates each candidate in $\mathcal{O}(n^2)$ time independent of encoder dimension, and admits a conditional $(1-e^{-γ})$ prefix-wise guarantee under monotonicity and a positive submodularity ratio. Across five recognition regimes and low-shot, larger-pool, and full-data protocols, KAGES improves average AULC over full fusion by 3.9, 5.8, and 3.3 points, respectively, and exceeds DPP and facility-location selection in average AULC. Image retrieval exhibits later, task-dependent saturation along the KAGES ordering, while peak-then-decline reproduces in frozen-LLM fusion. These results show that effective large-pool fusion depends on selecting a compact, task-aligned set of views rather than indiscriminately fusing more encoders.

arXiv

NeuroPath: Brain-Inspired Dual-Pathway Graph Convolutional Networks for Skeleton-Based Action Recognition

Kanglei Zhou, Ruizhi Cai, Hubert P. H. Shum, Frederick W. B. Li, Xiaohui Liang

Skeleton-based action recognition aims to recognize human actions from sequences of human joint coordinates. Most existing Spatial-Temporal Graph Convolutional Networks (STGCNs) have achieved promising results by modeling skeletal structures with implicit spatial-temporal representations. However, our empirical study reveals a clear performance imbalance across different skeletal modalities, indicating that implicitly coupling spatial and temporal information limits the full exploitation of complementary structural and motion cues. Inspired by the ventral and dorsal pathways in human perception, we propose Dual-Pathway Graph Convolutional Networks (NeuroPath), which adopt a dual-pathway architecture for separate yet collaborative modeling of spatial and temporal information. Specifically, transformation units first convert the input into pathway-specific skeletal representations, allowing each pathway to focus on complementary aspects of human motion. To further capture coordinated joint behaviors and their interrelationships, we introduce a group graph convolution block that dynamically identifies key body parts and models their spatial-temporal dependencies. In addition, inter-pathway dynamic fusion modules integrate complementary inter-modal information across pathways, facilitating higher-level semantic interpretation of actions. Extensive experiments on Kinetics Skeleton 400, NTU RGB+D 60, and NTU RGB+D 120 demonstrate consistent performance improvements, validating the effectiveness of dual-pathway spatial-temporal modeling for skeleton-based action recognition.

arXiv

S$^3$AM: A Single-Stream SAM with Reliability-Calibrated Frequency Adapter for Multi-modal Salient Object Detection

Ruichao Hou, Boyue Xu, Tongwei Ren, Dongming Zhou, Gangshan Wu, Jinde Cao

Vision foundation models have recently advanced multi-modal salient object detection (MSOD) through parameter-efficient tuning and prompt learning. However, existing Segment Anything Model (SAM)-adapted MSOD methods often rely on dual-stream encoders or auxiliary prompt generators, leading to redundant computation. Although a single-stream alternative can reduce this cost, early fusion may also propagate noisy or misaligned auxiliary high-frequency cues through the backbone. In this paper, we propose a novel single-stream framework that integrates reliability-calibrated frequency adaptation into the adopted SAM backbone for MSOD. It avoids duplicated foundation backbones while explicitly controlling auxiliary frequency injection. Specifically, we design a mixture of frequency experts module, which uses the stationary wavelet transform to decompose each modality and aggregate cross-modal frequency information. We further introduce a reliability-calibrated frequency adapter with a dual-gate calibration mechanism, which selectively propagates the calibrated residual across transformer stages while jointly controlling its injection strength and cross-modal reliability. A hypernetwork-guided semantic-structural decoder then combines semantic mask features from the adopted backbone with Mamba-based structural detail recovery. Comprehensive experiments on RGB-D, RGB-T, and RGB-NIR salient object detection benchmarks validate that the proposed framework achieves competitive performance with only 12.20M trainable parameters, accounting for 5.4\% of the total parameters. The code will be available at https://github.com/xuboyue1999/SSSAM.

arXiv

Counterfactual Anatomy-guided Spatial-Temporal Decoding for Annotation-Free Hallucination Mitigation in Medical VLMs

Yifan Lu, Adinath Dukre, Abhijit Das, Ziyun Zou, Haolin Yang, Yutong Xie, Imran Razzak

Medical vision-language models (Med-VLMs) have demonstrated strong performance on medical visual question answering, yet they remain prone to hallucination, generating clinically unsupported statements that are insufficiently grounded in image evidence. Mitigation methods applied during decoding offer a practical solution, but they typically lack anatomical awareness or rely heavily on ground truth annotations, which limits their applicability. We propose Counterfactual Anatomy-guided Spatial-Temporal decoding (CAST), a framework that operates entirely during inference and requires no manual annotations for anatomically grounded hallucination mitigation. CAST automatically discovers anatomical regions relevant to the given query through broad medical segmentation. It then selects a compact, causally informative area using counterfactual intervention based on the drop in answer likelihood under occlusion. Guided by this chosen region, CAST performs a unified contrastive decoding process, combining classifier-free guidance to correct spatial attention with stepwise temporal contrast to regulate generation dynamics. Experiments on the SLAKE and MIMIC-CXR datasets across three Med-VLMs demonstrate that CAST consistently outperforms strong baselines and surpasses decoding strategies reliant on ground truth. Our results indicate that compact, automatically selected regions provide highly effective contrastive guidance without expert annotations, offering a practical and generalizable solution for improving spatial grounding and reducing hallucinations. Code is available at https://github.com/csyifan/CAST.

arXiv

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Keyu Tu, Zhuowei Chen, Mengqi Huang, Yuxin Wang, Jiahao Zhu, Zhendong Mao, Yongdong Zhang

We introduce Semantic Task Completion Video Generation, an outcome-oriented video generation task. Under this formulation, success requires both achievement of the intended outcome and semantic grounding. Semantic grounding characterizes the correspondence between the reference image and the generated outcome in terms of high-level semantics relevant to the task. Evaluation focuses on the generated outcome and requires neither the presentation of a complete sequence of intermediate task steps nor conventional appearance consistency with the reference image. To support systematic evaluation, we construct SemComp-Data, an evaluation dataset covering six domains. Each instance comprises a reference image, a detailed instruction, a brief instruction, and an outcome-centric video clip. A scalable four-stage curation pipeline converts raw videos into standardized SemComp-Data instances. We further introduce SemComp-Bench, an evaluation protocol that uses a vision-language model (VLM) to answer structured binary questions. SemComp-Bench reports the OA Score and the GR Score for Outcome Achievement and Generation Reliability, respectively. Experiments on representative video generation models show that achieving intended outcomes while maintaining task-relevant semantic grounding in reference images remains challenging.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.