Integrating large language models (LLMs) into autonomous driving motion planning has recently emerged as a promising direction, offering enhanced interpretability, better controllability, and improved generalization in rare and long-tail scenarios. However, existing methods often rely on abstracted perception or map-based inputs, missing crucial visual context, such as fine-grained road cues, accident aftermath, or unexpected obstacles, which are essential for robust decision-making in complex driving environments. To bridge this gap, we propose VLMPlanner, a hybrid framework that combines a learning-based real-time planner with a vision-language model (VLM) capable of reasoning over raw images. The VLM processes multi-view images to capture rich, detailed visual information and leverages its common-sense reasoning capabilities to guide the real-time planner in generating robust and safe trajectories. Furthermore, we develop the Context-Adaptive Inference Gate (CAI-Gate) mechanism that enables the VLM to mimic human driving behavior by dynamically adjusting its inference frequency based on scene complexity, thereby achieving an optimal balance between planning performance and computational efficiency. We evaluate our approach on the large-scale, challenging nuPlan benchmark, with comprehensive experimental results demonstrating superior planning performance in scenarios with intricate road conditions and dynamic elements.
论文检索
输入标题、作者或关键词，从 1,526 篇学术成果中精准定位
SAGE: A Visual Language Model for Anomaly Detection via Fact Enhancement and Entropy-aware Alignment
While Vision-Language Models (VLMs) have shown promising progress in general multimodal tasks, they often struggle with industrial anomaly detection and reasoning, particularly in delivering interpretable explanations and generalizing to unseen categories. This limitation stems from the inherently domain-specific nature of anomaly detection, which hinders the applicability of existing VLMs in industrial scenarios that require precise, structured, and context-aware analysis. To address these challenges, we propose SAGE, a VLM-based framework that enhances anomaly reasoning through Self-Guided Fact Enhancement (SFE) and Entropy-aware Direct Preference Optimization (E-DPO). SFE integrates domain-specific knowledge into visual reasoning via fact extraction and fusion, while E-DPO aligns model outputs with expert preferences using entropy-aware optimization. Additionally, we introduce AD-PL, a preference-optimized dataset tailored for industrial anomaly reasoning, consisting of 28,415 question-answering instances with expert-ranked responses. To evaluate anomaly reasoning models, we develop Multiscale Logical Evaluation (MLE), a quantitative framework analyzing model logic and consistency. SAGE demonstrates superior performance on industrial anomaly datasets under zero-shot and one-shot settings. The code, model, and dataset are available at https://github.com/amoreZgx1n/SAGE.
Charts are a fundamental visualization format widely used in data analysis across research and industry. While enabling users to edit charts based on high-level intentions is of great practical value, existing methods primarily rely on natural language instructions, which are often too ambiguous to support fine-grained editing. In this work, we introduce a novel paradigm for multimodal chart editing, where user intent is expressed through a combination of natural language and visual indicators that explicitly highlight the elements to be modified. To support this paradigm, we present ChartM3, a new benchmark for Multimodal chart editing with Multi-level complexity and Multi-perspective evaluation. ChartM3 contains 1,000 samples spanning four levels of editing difficulty. Each sample includes triplets in the form of (chart, code, multimodal instructions). To comprehensively evaluate chart editing models, ChartM3 provides metrics that assess both visual appearance and code correctness. Our benchmark reveals significant limitations in current multimodal large language models (MLLMs), including GPT-4o, particularly in their ability to interpret and act on visual indicators. To address this, we construct ChartM3-Train, a large-scale training set with 24,000 multimodal chart editing samples. Fine-tuning MLLMs on this dataset leads to substantial improvements, demonstrating the importance of multimodal supervision in building practical chart editing systems. Our datasets, codes, and evaluation tools are available at https://github.com/MLrollIT/ChartM3.
Long-form video understanding (LVU) addresses the challenge of answering complex questions over extended video length, where informative cues are sparse and easily overwhelmed by redundant content. To tackle this, it requires selecting a small set of question-relevant keyframes and reasoning over long-range, temporally dispersed visual evidence. However, current methods typically extract frame-level features with limited temporal context and store them in sequential memory structures. As a result, they struggle to capture the evolving relations among entities and fail to maintain identity consistency when entities temporarily leave and later reappear in the video. These limitations prevent accurate keyframe localization and coherent reasoning. In this paper, we propose GraphVideoAgent, a novel agent-based LVU framework that integrates a dynamic entity relation graph with a large language model (LLM)-based multi-round reasoning. Our framework emulates human cognitive strategies by iteratively retrieving keyframes and explicitly tracking both temporal and semantic interactions among entities. Our GraphVideoAgent iteratively reflects on question cues and visual observations, while the graph memory maintains a structured representation of evolving entity states and their causal relations. This design enables accurate keyframe selection, effective reasoning over sparse visual evidence, and interpretable prediction. Extensive experiments on two LVU benchmarks, EgoSchema and NExT-QA, demonstrate that GraphVideoAgent achieves state-of-the-art performance while using only 8.2 and 8.1 frames on average, significantly improving both accuracy and efficiency.
Novel view synthesis (NVS) in low-light scenes remains a significant challenge due to degraded inputs characterized by severe noise, low dynamic range (LDR) and unreliable initialization. While recent NeRF-based approaches have shown promising results, most suffer from high computational costs, and some rely on carefully captured or pre-processed data-such as RAW sensor inputs or multi-exposure sequences-which severely limits their practicality. In contrast, 3D Gaussian Splatting (3DGS) enables real-time rendering with competitive visual fidelity; however, existing 3DGS-based methods struggle with low-light sRGB inputs, resulting in unstable Gaussian initialization and ineffective noise suppression. To address these challenges, we propose LL-Gaussian, a novel framework for 3D reconstruction and enhancement from low-light sRGB images, enabling pseudo normal-light novel view synthesis. Our method introduces three key innovations: 1) an end-to-end Low-Light Gaussian Initialization Module (LLGIM) that leverages dense priors from learning-based MVS approach to generate high-quality initial point clouds; 2) a dual-branch Gaussian decomposition model that disentangles intrinsic scene properties (reflectance and illumination) from transient interference, enabling stable and interpretable optimization; 3) an unsupervised optimization strategy guided by both physical constrains and diffusion prior to jointly steer decomposition and enhancement. Additionally, we contribute a challenging dataset collected in extreme low-light environments and demonstrate the effectiveness of LL-Gaussian. Compared to state-of-the-art NeRF-based methods, LL-Gaussian achieves up to 2,000× faster inference and reduces training time to just 2%, while delivering superior reconstruction and rendering quality.
Understanding the content of multi-page documents with rich layout information is a challenging task. Recent multimodal large language models (MLLMs) have made remarkable progress in understanding single-page document images. However, the understanding of multi-page documents remains insufficiently explored. This work proposes a Document Retrieval-enhanced, Expert-guided, Attention-aware Multimodal Framework, dubbed DREAM. Specifically, we propose a confidence-based, high-level semantic, multimodal retrieval method. Then, we propose a machine learning algorithm to complement the result of confidence-based retrieval and multimodal embedding similarity retrieval to obtain the most query-relevant set of document images. Subsequently, we designed a decoupled cross-page attention-aware multimodal language model for multi-page documents to interpret these retrieved images and produce the final answer. Experimental results demonstrate the effectiveness of the retrieval module within the framework, as well as the robust performance of the multimodal model in multi-page document comprehension. These findings offer a compelling solution for multi-page document comprehension and cross-page document visual question answering.
In histopathology, tissue sections are typically stained using common H&E staining or special stains (MAS, PAS, PASM, etc. ) to clearly visualize specific tissue structures. The rapid advancement of deep learning offers an effective solution for generating virtually stained images, significantly reducing the time and labor costs associated with traditional histochemical staining. However, a new challenge arises in separating the fundamental visual characteristics of tissue sections from the visual differences induced by staining agents. Additionally, virtual staining often overlooks essential pathological knowledge and the physical properties of staining, resulting in only style-level transfer. To address these issues, we introduce, for the first time in virtual staining tasks, a pathological vision-language large model (VLM) as an auxiliary tool. We integrate contrastive learnable prompts, foundational concept anchors for tissue sections, and staining-specific concept anchors to leverage the extensive knowledge of the pathological VLM. This approach is designed to describe, frame, and enhance the direction of virtual staining. Furthermore, we have developed a data augmentation method based on the constraints of the VLM. This method utilizes the VLM's powerful image interpretation capabilities to further integrate image style and structural information, proving beneficial in high-precision pathological diagnostics. Extensive evaluations on publicly available multi-domain unpaired staining datasets demonstrate that our method can generate highly realistic images and enhance the accuracy of downstream tasks, such as glomerular detection and segmentation. Our code. https://github.com/CZZZZZZZZZZZZZZZZZ/VPGAN-HARBOR is available.
Scene understanding enables intelligent agents to interpret and comprehend their environment. While existing large vision-language models (LVLMs) for scene understanding have primarily focused on indoor household tasks, they face two significant limitations when applied to outdoor large-scale scene understanding. First, outdoor scenarios typically encompass larger-scale environments observed through various sensors from multiple viewpoints (e.g., bird view and terrestrial view), while existing indoor LVLMs mainly analyze single visual modalities within building-scale contexts from humanoid viewpoints. Second, existing LVLMs suffer from missing multidomain perception outdoor data and struggle to effectively integrate 2D and 3D visual information. To address the aforementioned limitations, we build the first multidomain perception outdoor scene understanding dataset, named SVM-City, deriving from multi-Scale scenarios with multi-View and multi-Modal instruction tuning data. It contains 420k images and 4, 811M point clouds with 567k question-answering pairs from vehicles, low-altitude drones, high-altitude aerial planes, and satellite. To effectively fuse multimodal data in the absence of one modality, we introduce incomplete multimodal learning to model outdoor scene understanding and design the LVLM named City-VLM. Multimodal fusion is realized by constructed as a joint probabilistic distribution space rather than implementing directly explicit fusion operations (e.g., concatenation). Experimental results on three typical outdoor scene understanding tasks show City-VLM achieves 18.14 % performance surpassing existing LVLMs in question-answering tasks averagely. Our method demonstrates pragmatic and generalization performance across multiple outdoor scenes.
Despite recent progress in decoding static images from brain activity, reconstructing dynamic visual experiences from EEG signals remains challenging due to the complex temporal dynamics involved. Current approaches primarily rely on pre-trained video generation models while failing to fully leverage the rich temporal-spatial information embedded in EEG signals for video synthesis. This paper proposes MINDEV Multi-modal Integrated Neural DEcoding and Visualization), a framework that places EEG signal processing at the core of video reconstruction. We introduce three key technical contributions: (1) a dual-branch feature extractor that captures both temporal dynamics and spatial relationships in EEG signals, (2) an EEG-driven semantic bridge that uses neural patterns to guide language model interpretation, and (3) a multi-modal video synthesis pipeline where EEG features lead the generation process while semantic guidance provides refinement. Our framework prioritizes the millisecond-level temporal resolution of EEG signals, using them to drive both visual content generation and semantic understanding. Evaluated on the SEED-DV dataset, MINDEV demonstrates superior performance with a semantic classification accuracy of 93.2% and a structural similarity index (SSIM) of 0.4777, establishing a new state-of-the-art for EEG-based video reconstruction. Our code is publicly available at https://github.com/HHarr1son/MINDEV.
The reasoning segmentation task involves segmenting objects within an image by interpreting implicit user instructions. Despite significant advancements made by existing approaches, they remain constrained by low perceptual resolution, as visual encoders are typically pre-trained at lower resolutions. Furthermore, simply interpolating the positional embeddings of visual encoders to enhance perceptual resolution yields only marginal performance improvements while incurring substantial computational costs. To address this, we propose HRSeg, an efficient model with high-resolution fine-grained perception. It features two key innovations: High-Resolution Perception (HRP) and High-Resolution Enhancement (HRE). The HRP module processes high-resolution images through cropping, integrating local and global features for multi-granularity quality. The HRE module enhances mask features by integrating fine-grained information from high-resolution images, refining their alignment with text features for precise segmentation. Extensive ablation studies validate the effectiveness of our modules, while comprehensive experiments on multiple benchmark datasets demonstrate HRSeg's superior performance. Code will be available at https://github.com/WeihuangLin/HRSeg.
The burgeoning growth of open-source vision-language models (VLMs) has catalyzed a plethora of applications across diverse domains. Ensuring the transparency and interpretability of these models is critical for fostering trustworthy and responsible AI systems. In this study, our objective is to delve into the internals of VLMs to interpret the functions of individual neurons. We observe the activations of neurons with respects to the input visual tokens and text tokens, and reveal some interesting findings. Particularly, we found that there are neurons responsible for only visual or text information, or both, respectively, which we refer to them as visual neurons, text neurons, and multi-modal neurons, respectively. We build a framework that automates the explanation of neurons with the assistant of GPT-4o. Meanwhile, for visual neurons, we propose an activation simulator to assess the reliability of the explanations for visual neurons. System statistical analyses on top of one representative VLM of LLaVA, uncover the behaviors/characteristics of different categories of neurons.
Vision-grounded medical report generation aims to produce clinically accurate descriptions of medical images, anchored in explicit visual evidence to improve interpretability and facilitate integration into clinical workflows. However, existing methods often rely on separately trained detection modules that require extensive expert annotations, introducing high labeling costs and limiting generalizability due to pathology distribution bias across datasets. To address these challenges, we propose Self-Supervised Anatomical Consistency Learning (SS-ACL)-a novel and annotation-free framework that aligns generated reports with corresponding anatomical regions using simple textual prompts. SS-ACL constructs a hierarchical anatomical graph inspired by the invariant top-down inclusion structure of human anatomy, organizing entities by spatial location. It recursively reconstructs fine-grained anatomical regions to enforce intra-sample spatial alignment, inherently guiding attention maps toward visually relevant areas prompted by text. To further enhance inter-sample semantic alignment for abnormality recognition, SS-ACL introduces a region-level contrastive learning based on anatomical consistency. These aligned embeddings serve as priors for report generation, enabling attention maps to provide interpretable visual evidence. Extensive experiments demonstrate that SS-ACL, without relying on expert annotations, (i) generates accurate and visually grounded reports-outperforming state-of-the-art methods by 10% in lexical accuracy and 25% in clinical efficacy, and (ii) achieves competitive performance on various downstream visual tasks, surpassing current leading visual foundation models by 8% in zero-shot visual grounding. Our code is available at https://github.com/kaelsunkiller/ssacl.
Human-Object Interaction (HOI) detection aims to identify humans and objects within images and interpret their interactions. Existing HOI methods rely heavily on large datasets with manual annotations to learn interactions from visual cues. These annotations are labor-intensive to create, prone to inconsistency, and limit scalability to new domains and rare interactions. We argue that recent advances in Vision-Language Models (VLMs) offer untapped potential, particularly in enhancing interaction representation. While prior work has injected such potential and even proposed training-free methods, there remain key gaps. Consequently, we propose a novel training-free HOI detection framework for Dynamic Scoring with enhanced semantics (dysco) that effectively utilizes textual and visual interaction representations within a multimodal registry, enabling robust and nuanced interaction understanding. This registry incorporates a small set of visual cues and uses innovative interaction signatures to improve the semantic alignment of verbs, facilitating effective generalization to rare interactions. Additionally, we propose a unique multi-head attention mechanism that adaptively weights the contributions of the visual and textual features. Experimental results demonstrate that our dysco surpasses training-free state-of-the-art models and is competitive with training-based approaches, particularly excelling in rare interactions. Code is available at https://github.com/francescotonini/dysco.
Multimodal Sentiment Analysis (MSA) faces two critical challenges: the lack of interpretability in the decision logic of multimodal fusion and modality imbalance caused by disparities in inter-modal information density. To address these issues, we propose KAN-MCP, a novel framework that integrates the interpretability of Kolmogorov-Arnold Networks (KAN) with the robustness of the Multimodal Clean Pareto (MCPareto) framework. First, KAN leverages its univariate function decomposition to achieve transparent analysis of cross-modal interactions. This structural design allows direct inspection of feature transformations without relying on external interpretation tools, thereby ensuring both high expressiveness and interpretability. Second, the proposed MCPareto enhances robustness by addressing modality imbalance and noise interference. Specifically, we introduce the Dimensionality Reduction and Denoising Modal Information Bottleneck (DRD-MIB) method, which jointly denoises and reduces feature dimensionality. This approach provides KAN with discriminative low-dimensional inputs to reduce the modeling complexity of KAN while preserving critical sentiment-related information. Furthermore, MCPareto dynamically balances gradient contributions across modalities using the purified features output by DRD-MIB, ensuring lossless transmission of auxiliary signals and effectively alleviating modality imbalance. This synergy of interpretability and robustness not only achieves superior performance on benchmark datasets such as CMU-MOSI, CMU-MOSEI, and CH-SIMS v2 but also offers an intuitive visualization interface through KAN's interpretable architecture. Our code is released on https://github.com/LuoMSen/KAN-MCP.
Salient object detection in optical remote sensing images (ORSI-SOD) faces unique challenges due to complex backgrounds, diverse scales, and multi-directional objects. Existing methods primarily rely on visual features, often struggling to distinguish salient objects from visually similar backgrounds. To address this limitation, we leverage large language models (LLMs) to expend existing ORSI-SOD datasets with detailed textual annotations, creating a more comprehensive benchmark for image-text ORSI-SOD. Building upon this foundation, we propose the Frequency Meets Semantics Network (FMS-Net), a novel framework that integrates text-visual fusion with directional spectral enhancement for ORSI-SOD. FMS-Net consists of two key innovations: the Hierarchical Multi-Modal Dual-Channel Fusion (HMDF) module and the Adaptive Directional Spectral Enhancement (ADSE) module. The HMDF module enables bidirectional interactions between visual and textual features via parallel global-local attention mechanisms, progressively enriching visual representations with semantic context. Meanwhile, the ADSE module enhances feature representations in the frequency domain, capturing directional patterns and boundary details critical for accurate saliency detection. Extensive experiments on two public datasets, ORSSD and EORSSD, demonstrate that FMS-Net outperforms state-of-the-art methods, particularly in complex scenes with ambiguous boundaries. Our work paves the way for integrating multi-modal and frequency-based approaches in the interpretation of optical remote sensing images (ORSI).
Low-light image enhancement aims to improve brightness, suppress noise, and recover accurate color and structure, requiring precise illumination modeling and reliable reflectance recovery. However, most Retinex-based methods adopt explicit, multi-stage pipelines prone to decomposition bias, error accumulation, and chromatic entanglement between illumination and reflectance. To tackle these issues, we propose IDAR (Implicit Decomposition, illumination Adjustment, and reflectance Restoration), a unified Retinex-inspired framework with two key innovations. First, we design an implicit decomposition strategy based on dual-branch feature learning: a low-frequency-constrained illumination branch models lighting with chromaticity awareness, while a contrast-guided reflection branch preserves details by decoupling reflectance from illumination. This implicit design avoids intermediate supervision and reduces decomposition bias. Second, we introduce the Illumination Chromaticity Expansion Module (ICEM), which employs text-guided chromaticity learning to enhance chromaticity perception. By learning a reflectance-independent spectral representation, ICEM reduces color shifts and improves fidelity under complex lighting. Experiments on multiple benchmarks validate the superior visual quality, quantitative performance, and physical interpretability of IDAR.
Model Diagram-to-Code Generation aims to translate model diagrams from research papers into implementation code that reconstructs the model's architecture. This task plays a crucial role in accelerating scientific workflows and enhancing the efficiency of industrial model deployment. While recent studies have explored various Image-to-Code Generation tasks using Multimodal Large Language Models (MLLMs), these efforts have primarily focused on reconstructing the visual appearance depicted in input images, leaving this task largely underexplored. The complex structural elements and implicit relationships in model diagrams present greater challenges for MLLMs, particularly in terms of visual reasoning and semantic interpretation. To support this task, we introduce MDCDataset, a dataset designed to evaluate the ability of MLLMs to generate code from model diagrams. It comprises 1,008 instances spanning 16 research domains, each with a model diagram, structured textual content, and the ground-truth code implementation. Furthermore, to address the inherent challenges of this task, we propose MDCAgent, a collaborative multi-agent framework composed of Parsing, Generation, and Check Agents. These agents work in coordination to analyze, extract, and verify complex elements and implicit relationships within model diagrams, thereby enhancing the visual architecture-aware reasoning capabilities of MLLMs. Our extensive experiments confirm the effectiveness of the framework.
Open-vocabulary object detection seeks to recognize objects from arbitrary language inputs, extending detection beyond fixed training categories. While recent methods have made progress in detecting unseen categories, they typically require a set of predefined categories during the inference stage, hindering practical deployment in open-world scenarios. To overcome this crucial limitation, we propose UniPerception , a novel universal perception framework based on open-vocabulary object detection. It not only excels at open-vocabulary object detection but is also capable of generating labels for target objects in the absence of predefined vocabularies, and can be adapted to a broad range of vision-language tasks simply by modifying the language instructions. UniPerception seamlessly integrates three key innovations: 1) a robust visual detector trained on diverse data sources to capture rich and generalizable visual representations; 2) a language model with interleaved cross-modality fusion layers to interpret instructions and generate fine-grained responses conditioned on visual features; and 3) a tailored multi-stage training strategy that effectively bridges detection-specific learning with general vision-language understanding. We conduct extensive experiments on multiple benchmarks for open-vocabulary object detection (COCO, LVIS, ODinW), referring expression comprehension (RefCOCO/+/g, D3), and vision-language understanding (Flickr30k, VQAv2, GQA). The results show that UniPerception achieves strong open-world generalization and multi-modal understanding, outperforming the existing state-of-the-art methods and establishing itself as a unified, instruction-driven perception system.
Technical Element Score (TES) and Program Component Score (PCS) evaluations in figure skating demand precise assessment of athletic actions and artistic interpretation, respectively. Existing methods face three major challenges. Firstly, video and audio cues are regarded as common features for both TES and PCS predictions in previous works without considering the prior evaluation criterion of figure skating. Secondly, action elements in competitions are separated in time, TES should be derived from each element's score, but existing methods try to give an overall TES prediction without evaluating each action element. Thirdly, lengthy competition videos make it difficult and inefficient to handle long-range contexts. To address these challenges, we propose a two-stream Mamba pyramid network that aligns with actual judging criteria to predict TES and PCS by separating visual-feature based TES evaluation stream from audio-visual-feature based PCS evaluation stream. In the PCS evaluation stream, we introduce a multi-level fusion mechanism to guarantee that video-based features remain unaffected when assessing TES, and enhance PCS estimation by fusing visual and auditory cues across each contextual level of the pyramid. In the TES evaluation stream, the multi-scale Mamba pyramid and TES head we proposed effectively address the challenges of localizing and evaluating action elements with various temporal scales and give score predictions. With Mamba's superior ability to capture long-range dependencies and its linear computational complexity, our method is ideal for handling lengthy figure skating videos. Comprehensive experimentation demonstrates that our framework attains state-of-the-art performance on the FineFS benchmark. Furthermore, it yields competitive outcomes on two additional datasets without further training. Our source code is available at https://github.com/ycwfs/Figure-Skating-Action-Quality-Assessment.
Given that action evolution follows temporal progression, recent studies for Online Action Detection (OAD) and Online Action Anticipation (OAA) generally adopt forward temporal modeling to capture dependencies in observable video sequences. However, the strictly sequential nature of forward temporal modeling prevents subsequent frames from being used to enhance the earlier modeling process. In particular, the current frame, the last observable frame in the online video stream, serves as the direct visual cue for ongoing action recognition and the informative context for future action anticipation. As modeling errors accumulate over time, the resulting representations may progressively deviate from the actual semantics. Findings in cognitive neuroscience show that the hippocampus performs backward replay after observation to reinforce and correct the interpretation of previous observations. Inspired by this, we propose to incorporate backward temporal modeling following forward temporal modeling, enabling the model to leverage backward temporal modeling to enhance forward temporal modeling. Based on this idea, we propose a unified model for OAD and OAA, named Bidirectional Online Mamba (BiOMamba). Specifically, to address the excessive length and relevance imbalance in observable sequences, BiOMamba compresses distant long-term memory and preserves recent short-term memory. Then, BiOMamba sequentially model both forward and backward temporal dependencies in the whole memory. Finally, according to the temporal modeling result, BiOMamba generates representations for current and future actions. BiOMamba achieves state-of-the-art performance on THUMOS'14 (OAD: 73.3% mAP, OAA: 59.7% mAP) and TVSeries (OAD: 89.9% mcAP, OAA: 83.7% mcAP).