Visual grounding is essential for precise perception and reasoning in multimodal large language models (MLLMs), especially in medical imaging domains. While existing medical visual grounding benchmarks primarily focus on single-image scenarios, real-world clinical applications often involve sequential images, where accurate lesion localization across different modalities and temporal tracking of disease progression (e.g., pre- vs. post-treatment comparison) require fine-grained cross-image semantic alignment and context-aware reasoning. To remedy the underrepresentation of image sequences in existing medical visual grounding benchmarks, we propose MedSG-Bench, the first benchmark tailored for Medical Image Sequences Grounding. It comprises eight VQA-style tasks, formulated into two paradigms of the grounding tasks, including 1) Image Difference Grounding, which focuses on detecting change regions across images, and 2) Image Consistency Grounding, which emphasizes detection of consistent or shared semantics across sequential images. MedSG-Bench covers 76 public datasets, 10 medical imaging modalities, and a wide spectrum of anatomical structures and diseases, totaling 9,630 question-answer pairs. We benchmark both general-purpose MLLMs (e.g., Qwen2.5-VL) and medical-domain specialized MLLMs (e.g., HuatuoGPT-vision), observing that even the advanced models exhibit substantial limitations in medical sequential grounding tasks. To advance this field, we construct MedSG-188K, a large-scale instruction-tuning dataset tailored for sequential visual grounding, and further develop MedSeq-Grounder, an MLLM designed to facilitate future research on fine-grained understanding across medical sequential images. The benchmark, dataset, and model are available at https://huggingface.co/MedSG-Bench
Current research has explored vision-language models for multi-modal embedding tasks, such as information retrieval, visual grounding, and classification. However, real-world scenarios often involve diverse modality combinations between queries and targets, such as text and image to text, text and image to text and image, and text to text and image. These diverse combinations pose significant challenges for existing models, as they struggle to align all modality combinations within a unified embedding space during training, which degrades performance at inference. To address this limitation, we propose UniMoCo, a novel vision-language model architecture designed for multi-modal embedding tasks. UniMoCo introduces a modality-completion module that generates visual features from textual inputs, ensuring modality completeness for both queries and targets. Additionally, we develop a specialized training strategy to align embeddings from both original and modality-completed inputs, ensuring consistency within the embedding space. This enables the model to robustly handle a wide range of modality combinations across embedding tasks. Experiments show that UniMoCo outperforms previous methods while demonstrating consistent robustness across diverse settings. More importantly, we identify and quantify the inherent bias in conventional approaches caused by imbalance of modality combinations in training data, which can be mitigated through our modality-completion paradigm. The code is available at https://github.com/HobbitQia/UniMoCo.
Graphical User Interface (GUI) agents have made substantial strides in understanding and executing user instructions across diverse platforms. Yet, grounding these instructions to precise interface elements remains challenging, especially in complex, high-resolution, professional environments. Traditional supervised finetuning (SFT) methods often require large volumes of diverse data and exhibit weak generalization. To overcome these limitations, we introduce a reinforcement learning (RL) based framework that incorporates three core strategies: (1) seed data curation to ensure high quality training samples, (2) a dense policy gradient that provides continuous feedback based on prediction accuracy, and (3) a self evolutionary reinforcement finetuning mechanism that iteratively refines the model using attention maps. With only 3k training samples, our 7B-parameter model achieves state-of-the-art results among similarly sized models on three grounding benchmarks. Notably, it attains 47.3\% accuracy on the ScreenSpot-Pro dataset, outperforming much larger models, such as UI-TARS-72B, by a margin of 24.2\%. These findings underscore the effectiveness of RL-based approaches in enhancing GUI agent performance, particularly in high-resolution, complex environments.
Large multimodal models (LMMs) now excel on many vision language benchmarks, however, they still struggle with human centered criteria such as fairness, ethics, empathy, and inclusivity, key to aligning with human values. We introduce HumaniBench, a holistic benchmark of 32K real-world image question pairs, annotated via a scalable GPT4o assisted pipeline and exhaustively verified by domain experts. HumaniBench evaluates seven Human Centered AI (HCAI) principles: fairness, ethics, understanding, reasoning, language inclusivity, empathy, and robustness, across seven diverse tasks, including open and closed ended visual question answering (VQA), multilingual QA, visual grounding, empathetic captioning, and robustness tests. Benchmarking 15 state of the art LMMs (open and closed source) reveals that proprietary models generally lead, though robustness and visual grounding remain weak points. Some open-source models also struggle to balance accuracy with adherence to human-aligned principles. HumaniBench is the first benchmark purpose built around HCAI principles. It provides a rigorous testbed for diagnosing alignment gaps and guiding LMMs toward behavior that is both accurate and socially responsible. Dataset, annotation prompts, and evaluation code are available at: https://vectorinstitute.github.io/HumaniBench
Existing methods for vision-language task planning excel in short-horizon tasks but often fall short in complex, long-horizon planning within dynamic environments. These challenges primarily arise from the difficulty of effectively training models to produce high-quality reasoning processes for long-horizon tasks. To address this, we propose Structured Preference Optimization (SPO), which aims to enhance reasoning and action selection in long-horizon task planning through structured preference evaluation and optimized training strategies. Specifically, SPO introduces: 1) Preference-Based Scoring and Optimization, which systematically evaluates reasoning chains based on task relevance, visual grounding, and historical consistency; and 2) Curriculum-Guided Training, where the model progressively adapts from simple to complex tasks, improving its generalization ability in long-horizon scenarios and enhancing reasoning robustness. To advance research in vision-language long-horizon task planning, we introduce ExtendaBench, a comprehensive benchmark covering 1,509 tasks across VirtualHome and Habitat 2.0, categorized into ultra-short, short, medium, and long tasks. Experimental results demonstrate that SPO significantly improves reasoning quality and final decision accuracy, outperforming prior methods on long-horizon tasks and underscoring the effectiveness of preference-driven optimization in vision-language task planning. Specifically, SPO achieves a +5.98% GCR and +4.68% SR improvement in VirtualHome and a +3.30% GCR and +2.11% SR improvement in Habitat over the best-performing baselines.
The Large Visual-Language Models (LVLMs) have significantly advanced image understanding. Their comprehension and reasoning capabilities enable promising applications in autonomous driving scenarios. However, existing research typically focuses on front-view perspectives and partial objects within scenes, struggling to achieve comprehensive scene understanding. Meanwhile, existing LVLMs suffer from the lack of mapping relationship between 2D and 3D and insufficient integration of 3D object localization and instruction understanding. To tackle these limitations, we first introduce NuInteract, a large-scale dataset with over 1.5M multi-view image language pairs spanning dense scene captions and diverse interactive tasks. Furthermore, we propose DriveMonkey, a simple yet effective framework that seamlessly integrates LVLMs with a spatial processor using a series of learnable queries. The spatial processor, designed as a plug-and-play component, can be initialized with pre-trained 3D detectors to improve 3D perception. Our experiments show that DriveMonkey outperforms general LVLMs, especially achieving a 9.86% notable improvement on the 3D visual grounding task. The dataset and code will be released at https://github.com/zc-zhao/DriveMonkey.
Modern automotive infotainment systems require intelligent and adaptive solutions to handle frequent User Interface (UI) updates and diverse design variations. We introduce a vision-language framework for understanding and interacting with automotive infotainment systems, enabling seamless adaptation across different UI designs. To further support research in this field, we release AutomotiveUI-Bench-4K, an open-source dataset of 998 images with 4,208 annotations. Additionally, we present a synthetic data pipeline to generate training data. We fine-tune a Molmo-7B-based model using Low-Rank Adaptation (LoRa) and incorporating reasoning generated by our pipeline, along with visual grounding and evaluation capabilities. The fine-tuned Evaluative Large Action Model (ELAM) achieves strong performance on AutomotiveUI-Bench-4K (model and dataset are available on Hugging Face) and demonstrating strong cross-domain generalization, including a +5.2% improvement on ScreenSpot over the baseline model. Notably, our approach achieves 80.4% average accuracy on ScreenSpot, closely matching or even surpassing specialized models for desktop, mobile, and web, such as ShowUI, despite being trained for the infotainment domain. This research investigates how data collection and subsequent fine-tuning can lead to AI-driven progress within automotive UI understanding and interaction. The applied method is cost-efficient and fine-tuned models can be deployed on consumer-grade GPUs.
Despite the existing evolution of Multimodal Large Language Models (MLLMs), a non-neglectable limitation remains in their struggle with visual text grounding, especially in text-rich images of documents. Document images, such as scanned forms and infographics, highlight critical challenges due to their complex layouts and textual content. However, current benchmarks do not fully address these challenges, as they mostly focus on visual grounding on natural images, rather than text-rich document images. Thus, to bridge this gap, we introduce TRIG, a novel task with a newly designed instruction dataset for benchmarking and improving the Text-Rich Image Grounding capabilities of MLLMs in document question-answering. Specifically, we propose an OCR-LLM-human interaction pipeline to create 800 manually annotated question-answer pairs as a benchmark and a large-scale training set of 90$ synthetic data based on four diverse datasets. A comprehensive evaluation of various MLLMs on our proposed benchmark exposes substantial limitations in their grounding capability on text-rich images. In addition, we propose two simple and effective TRIG methods based on general instruction tuning and plug-and-play efficient embedding, respectively. By finetuning MLLMs on our synthetic dataset, they promisingly improve spatial reasoning and grounding capabilities.
Enabling intelligent agents to comprehend and interact with 3D environments through natural language is crucial for advancing robotics and human-computer interaction. A fundamental task in this field is ego-centric 3D visual grounding, where agents locate target objects in real-world 3D spaces based on verbal descriptions. However, this task faces two significant challenges: (1) loss of fine-grained visual semantics due to sparse fusion of point clouds with ego-centric multi-view images, (2) limited textual semantic context due to arbitrary language descriptions. We propose DenseGrounding, a novel approach designed to address these issues by enhancing both visual and textual semantics. For visual features, we introduce the Hierarchical Scene Semantic Enhancer, which retains dense semantics by capturing fine-grained global scene features and facilitating cross-modal alignment. For text descriptions, we propose a Language Semantic Enhancer that leverages large language models to provide rich context and diverse language descriptions with additional context during model training. Extensive experiments show that DenseGrounding significantly outperforms existing methods in overall accuracy, with improvements of 5.81% and 7.56% when trained on the comprehensive full dataset and smaller mini subset, respectively, further advancing the SOTA in egocentric 3D visual grounding. Our method also achieves 1st place and receives the Innovation Award in the CVPR 2024 Autonomous Grand Challenge Multi-view 3D Visual Grounding Track, validating its effectiveness and robustness.
3D visual grounding aims to localize the unique target described by natural languages in 3D scenes. The significant gap between 3D and language modalities makes it a notable challenge to distinguish multiple similar objects through the described spatial relationships. Current methods attempt to achieve cross-modal understanding in complex scenes via a target-centered learning mechanism, ignoring the perception of referred objects. We propose a novel 2D-assisted 3D visual grounding framework that constructs semantic-spatial scene graphs with referred object discrimination for relationship perception. The framework incorporates a dual-branch visual encoder that utilizes 2D pre-trained attributes to guide the multi-modal object encoding. Furthermore, our cross-modal interaction module uses graph attention to facilitate relationship-oriented information fusion. The enhanced object representation and iterative relational learning enable the model to establish effective alignment between 3D vision and referential descriptions. Experimental results on the popular benchmarks demonstrate our superior performance compared to state-of-the-art methods, especially in addressing the challenges of multiple similar distractors.
The 3D weakly-supervised visual grounding task aims to localize oriented 3D boxes in point clouds based on natural language descriptions without requiring annotations to guide model learning. This setting presents two primary challenges: category-level ambiguity and instance-level complexity. Category-level ambiguity arises from representing objects of fine-grained categories in a highly sparse point cloud format, making category distinction challenging. Instance-level complexity stems from multiple instances of the same category coexisting in a scene, leading to distractions during grounding. To address these challenges, we propose a novel weakly-supervised grounding approach that explicitly differentiates between categories and instances. In the category-level branch, we utilize extensive category knowledge from a pre-trained external detector to align object proposal features with sentence-level category features, thereby enhancing category awareness. In the instance-level branch, we utilize spatial relationship descriptions from language queries to refine object proposal features, ensuring clear differentiation among objects. These designs enable our model to accurately identify target-category objects while distinguishing instances within the same category. Compared to previous methods, our approach achieves state-of-the-art performance on three widely used benchmarks: Nr3D, Sr3D, and ScanRef.
Visual storytelling is an interdisciplinary field combining computer vision and natural language processing to generate cohesive narratives from sequences of images. This paper presents a novel approach that leverages recent advancements in multimodal models, specifically adapting transformer-based architectures and large multimodal models, for the visual storytelling task. Leveraging the large-scale Visual Storytelling (VIST) dataset, our VIST-GPT model produces visually grounded, contextually appropriate narratives. We address the limitations of traditional evaluation metrics, such as BLEU, METEOR, ROUGE, and CIDEr, which are not suitable for this task. Instead, we utilize RoViST and GROOVIST, novel reference-free metrics designed to assess visual storytelling, focusing on visual grounding, coherence, and non-redundancy. These metrics provide a more nuanced evaluation of narrative quality, aligning closely with human judgment.
With the surge of large language models (LLMs), Large Vision-Language Models (VLMs)--which integrate vision encoders with LLMs for accurate visual grounding--have shown great potential in tasks like generalist agents and robotic control. However, VLMs are typically trained on massive web-scraped images, raising concerns over copyright infringement and privacy violations, and making data auditing increasingly urgent. Membership inference (MI), which determines whether a sample was used in training, has emerged as a key auditing technique, with promising results on open-source VLMs like LLaVA (AUC > 80%). In this work, we revisit these advances and uncover a critical issue: current MI benchmarks suffer from distribution shifts between member and non-member images, introducing shortcut cues that inflate MI performance. We further analyze the nature of these shifts and propose a principled metric based on optimal transport to quantify the distribution discrepancy. To evaluate MI in realistic settings, we construct new benchmarks with i.i.d. member and non-member images. Existing MI methods fail under these unbiased conditions, performing only marginally better than chance. Further, we explore the theoretical upper bound of MI by probing the Bayes Optimality within the VLM's embedding space and find the irreducible error rate remains high. Despite this pessimistic outlook, we analyze why MI for VLMs is particularly challenging and identify three practical scenarios--fine-tuning, access to ground-truth texts, and set-based inference--where auditing becomes feasible. Our study presents a systematic view of the limits and opportunities of MI for VLMs, providing guidance for future efforts in trustworthy data auditing.
Visual grounding associates textual descriptions with objects in an image. Conventional methods target third-person image inputs and named object queries. In applications such as AI assistants, the perspective shifts -- inputs are egocentric, and objects may be referred to implicitly through needs and intentions. To bridge this gap, we introduce EgoIntention, the first dataset for egocentric visual intention grounding. EgoIntention challenges multimodal LLMs to 1) understand and ignore unintended contextual objects and 2) reason about uncommon object functionalities. Benchmark results show that current models misidentify context objects and lack affordance understanding in egocentric views. We also propose Reason-to-Ground (RoG) instruction tuning; it enables hybrid training with normal descriptions and egocentric intentions with a chained intention reasoning and object grounding mechanism. RoG significantly outperforms naive finetuning and hybrid training on EgoIntention, while maintaining or slightly improving naive description grounding. This advancement enables unified visual grounding for egocentric and exocentric visual inputs while handling explicit object queries and implicit human intentions.
Current object detectors often suffer significant perfor-mance degradation in real-world applications when encountering distributional shifts. Consequently, the out-of-distribution (OOD) generalization capability of object detectors has garnered increasing attention from researchers. Despite this growing interest, there remains a lack of a large-scale, comprehensive dataset and evaluation benchmark with fine-grained annotations tailored to assess the OOD generalization on more intricate tasks like object detection and grounding. To address this gap, we introduce COUNTS, a large-scale OOD dataset with object-level annotations. COUNTS encompasses 14 natural distributional shifts, over 222K samples, and more than 1,196K labeled bounding boxes. Leveraging COUNTS, we introduce two novel benchmarks: O(OD)2 and OODG. O(OD)2 is designed to comprehensively evaluate the OOD generalization capabilities of object detectors by utilizing controlled distribution shifts between training and testing data. OODG, on the other hand, aims to assess the OOD generalization of grounding abilities in multimodal large language models (MLLMs). Our findings reveal that, while large models and extensive pre-training data substantially en hance performance in in-distribution (IID) scenarios, significant limitations and opportunities for improvement persist in OOD contexts for both object detectors and MLLMs. In visual grounding tasks, even the advanced GPT-4o and Gemini-1.5 only achieve 56.7% and 28.0% accuracy, respectively. We hope COUNTS facilitates advancements in the development and assessment of robust object detectors and MLLMs capable of maintaining high performance under distributional shifts.
3-Dimensional Embodied Reference Understanding (3D-ERU) combines a language description and an accompanying pointing gesture to identify the most relevant target object in a 3D scene. Although prior work has explored pure language-based 3D grounding, there has been limited exploration of 3D-ERU, which also incorporates human pointing gestures. To address this gap, we introduce a data augmentation framework-Imputer, and use it to curate a new benchmark dataset-ImputeRefer for 3D-ERU, by incorporating human pointing gestures into existing 3D scene datasets that only contain language instructions. We also propose Ges3ViG, a novel model for 3D-ERU that achieves ~30% improvement in accuracy as compared to other 3D-ERU models and ~9% compared to other purely language-based 3D grounding models. Our code and dataset are available at https://github.com/AtharvMane/Ges3ViG.
In recent years, with the growing research and application of multimodal large language models (VLMs) in robotics, there has been an increasing trend of utilizing VLMs for robotic scene understanding tasks. Existing approaches that use VLMs for 3D Visual Grounding tasks often focus on obtaining scene information through geometric and visual information, overlooking the extraction of diverse semantic information from the scene and the understanding of rich implicit semantic attributes, such as appearance, physics, and affordance. The 3D scene graph, which combines geometry and language, is an ideal representation method for environmental perception and is an effective carrier for language models in 3D Visual Grounding tasks. To address these issues, we propose a diverse semantic map construction method specifically designed for robotic agents performing 3D Visual Grounding tasks. This method leverages VLMs to capture the latent semantic attributes and relations of objects within the scene and creates a Diverse Semantic Map (DSM) through a geometry sliding-window map construction strategy. We enhance the understanding of grounding information based on DSM and introduce a novel approach named DSM-Grounding. Experimental results show that our method outperforms current approaches in tasks like semantic segmentation and 3D Visual Grounding, particularly excelling in overall metrics compared to the state-of-the-art. In addition, we have deployed this method on robots to validate its effectiveness in navigation and grasping tasks.
While MLLMs have demonstrated adequate image understanding capabilities, they still struggle with pixel-level comprehension, limiting their practical applications. Current evaluation tasks like VQA and visual grounding remain too coarse to assess fine-grained pixel comprehension accurately. Though segmentation is foundational for pixel-level understanding, existing methods often require MLLMs to generate implicit tokens, decoded through external pixel decoders. This approach disrupts the MLLM's text output space, potentially compromising language capabilities and reducing flexibility and extensibility, while failing to reflect the model's intrinsic pixel-level understanding. Thus, we introduce the Human-Like Mask Annotation Task (HLMAT), a new paradigm where MLLMs mimic human annotators using interactive segmentation tools. Modeling segmentation as a multi-step Markov Decision Process, HLMAT enables MLLMs to iteratively generate text-based click points, achieving high-quality masks without architectural changes or implicit tokens. Through this setup, we develop SegAgent, a model fine-tuned on human-like annotation trajectories, which achieves performance comparable to state-of-the-art (SOTA) methods and supports additional tasks like mask refinement and annotation filtering. HLMAT provides a protocol for assessing fine-grained pixel understanding in MLLMs and introduces a vision-centric, multi-step decision-making task that facilitates exploration of MLLMs' visual reasoning abilities. Our adaptations of policy improvement method StaR and PRM-guided tree search further enhance model robustness in complex segmentation tasks, laying a foundation for future advancements in fine-grained visual perception and multi-step decision-making for MLLMs.
Visual grounding (VG) aims to localize target objects in an image based on natural language descriptions. In this paper, we propose AerialVG, a new task focusing on visual grounding from aerial views. Compared to traditional VG, AerialVG poses new challenges, \emph{e.g.}, appearance-based grounding is insufficient to distinguish among multiple visually similar objects, and positional relations should be emphasized. Besides, existing VG models struggle when applied to aerial imagery, where high-resolution images cause significant difficulties. To address these challenges, we introduce the first AerialVG dataset, consisting of 5K real-world aerial images, 50K manually annotated descriptions, and 103K objects. Particularly, each annotation in AerialVG dataset contains multiple target objects annotated with relative spatial relations, requiring models to perform comprehensive spatial reasoning. Furthermore, we propose an innovative model especially for the AerialVG task, where a Hierarchical Cross-Attention is devised to focus on target regions, and a Relation-Aware Grounding module is designed to infer positional relations. Experimental results validate the effectiveness of our dataset and method, highlighting the importance of spatial reasoning in aerial visual grounding. The code and dataset will be released.
Recently DeepSeek R1 has shown that reinforcement learning (RL) can substantially improve the reasoning capabilities of Large Language Models (LLMs) through a simple yet effective design. The core of R1 lies in its rule-based reward formulation, which leverages tasks with deterministic ground-truth answers to enable precise and stable reward computation. In the visual domain, we similarly observe that a wide range of visual understanding tasks are inherently equipped with well-defined ground-truth annotations. This property makes them naturally compatible with rule-based reward mechanisms. Motivated by this observation, we investigate the extension of R1-style reinforcement learning to Vision-Language Models (VLMs), aiming to enhance their visual reasoning capabilities. To this end, we develop VLM-R1, a dedicated framework designed to harness RL for improving VLMs' performance on general vision-language tasks. Using this framework, we further explore the feasibility of applying RL to visual domain. Experimental results indicate that the RL-based model not only delivers competitive performance on visual understanding tasks but also surpasses Supervised Fine-Tuning (SFT) in generalization ability. Furthermore, we conduct comprehensive ablation studies that uncover a series of noteworthy insights, including the presence of reward hacking in object detection, the emergence of the "OD aha moment", the impact of training data quality, and the scaling behavior of RL across different model sizes. Through these analyses, we aim to deepen the understanding of how reinforcement learning enhances the capabilities of vision-language models, and we hope our findings and open-source contributions will support continued progress in the vision-language RL community. Our code and model are available at https://github.com/om-ai-lab/VLM-R1