Remarkable progress in 2D Vision-Language Models (VLMs) has spurred interest in extending them to 3D settings for tasks like 3D Question Answering, Dense Captioning, and Visual Grounding. Unlike 2D VLMs that typically process images through an image encoder, 3D scenes, with their intricate spatial structures, allow for diverse model architectures. Based on their encoder design, this paper categorizes recent 3D VLMs into 3D object-centric, 2D image-based, and 3D scene-centric approaches. Despite the architectural similarity of 3D scene-centric VLMs to their 2D counterparts, they have exhibited comparatively lower performance compared with the latest 3D object-centric and 2D image-based approaches. To understand this gap, we conduct an in-depth analysis, revealing that 3D scene-centric VLMs show limited reliance on the 3D scene encoder, and the pre-train stage appears less effective than in 2D VLMs. Furthermore, we observe that data scaling benefits are less pronounced on larger datasets. Our investigation suggests that while these models possess cross-modal alignment capabilities, they tend to over-rely on linguistic cues and overfit to frequent answer distributions, thereby diminishing the effective utilization of the 3D encoder. To address these limitations and encourage genuine 3D scene understanding, we introduce a novel 3D Relevance Discrimination QA dataset designed to disrupt shortcut learning and improve 3D understanding. Our findings highlight the need for advanced evaluation and improved strategies for better 3D understanding in 3D VLMs.
3D visual grounding has made notable progress in localizing objects within complex 3D scenes. However, grounding referring expressions beyond objects in 3D scenes remains unexplored. In this paper, we introduce Anywhere3D-Bench, a holistic 3D visual grounding benchmark consisting of 2,632 referring expression-3D bounding box pairs spanning four different grounding levels: human-activity areas, unoccupied space beyond objects, objects in the scene, and fine-grained object parts. We assess a range of state-of-the-art 3D visual grounding methods alongside large language models (LLMs) and multimodal LLMs (MLLMs) on Anywhere3D-Bench. Experimental results reveal that space-level and part-level visual grounding pose the greatest challenges: space-level tasks require a more comprehensive spatial reasoning ability, for example, modeling distances and spatial relations within 3D space, while part-level tasks demand fine-grained perception of object composition. Even the best performance model, OpenAI o4-mini, achieves only 23.57% accuracy on space-level tasks and 33.94% on part-level tasks, significantly lower than its performance on area-level and object-level tasks. These findings underscore a critical gap in current models' capacity to understand and reason about 3D scene beyond object-level semantics.
Recent advances in slow-thinking language models (e.g., OpenAI-o1 and DeepSeek-R1) have demonstrated remarkable abilities in complex reasoning tasks by emulating human-like reflective cognition. However, extending such capabilities to multi-modal large language models (MLLMs) remains challenging due to the high cost of retraining vision-language alignments when upgrading the underlying reasoner LLMs. A straightforward solution is to decouple perception from reasoning, i.e., converting visual inputs into language representations (e.g., captions) that are then passed to a powerful text-only reasoner. However, this decoupling introduces a critical challenge: the visual extractor must generate descriptions that are both faithful to the image and informative enough to support accurate downstream reasoning. To address this, we propose Reasoning-Aligned Perceptual Decoupling via Caption Reward Optimization (RACRO) - a reasoning-guided reinforcement learning strategy that aligns the extractor's captioning behavior with the reasoning objective. By closing the perception-reasoning loop via reward-based optimization, RACRO significantly enhances visual grounding and extracts reasoning-optimized representations. Experiments on multi-modal math and science benchmarks show that the proposed RACRO method achieves state-of-the-art average performance while enabling superior scalability and plug-and-play adaptation to more advanced reasoning LLMs without the necessity for costly multi-modal re-alignment.
Multi-modal Large Language Models (MLLMs) have demonstrated remarkable reasoning capability while lack explicit mechanisms for visual grounding and segmentation, creating a gap between cognitive reasoning and visual perception. To bridge this gap, we introduce Reasoning Segmentation via Visual Prompting (RSVP), a novel framework that unifies multi-step multimodal reasoning with grounded visual understanding. RSVP is a two-stage structuralized framework that integrates reasoning-driven localization with segmentation refinement. In the reasoning stage, RSVP employs multimodal chain-of-thought visual prompts to help MLLMs understand queries and infer targets, generating interpretable region proposals that enhance visual grounding. In segmentation stage, RSVP refines these proposals with a Vision-Language Segmentation Module (VLSM), seamlessly integrates textual and visual cues to produce precise segmentation masks. By explicitly modelling the interaction between multimodal reasoning and segmentation, RSVP introduces a new paradigm for interpretable reasoning segmentation. It exploits MLLMs' inherent localization capabilities, enabling the models to not only reason about objects but also generate structured visual representations. Our extensive experiments demonstrate that RSVP achieves state-of-the-art performance, surpasses state-of-the-art methods by up to +6.5 gIoU and +9.2 cIoU on ReasonSeg, and achieves 49.7 mAP on SegInW under zero-shot settings. These results validate RSVP as an effective and scalable framework for integrating cognitive reasoning with structured visual understanding.
Recently, Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on instruction-following tasks by integrating pretrained visual encoders with large language models (LLMs). However, existing approaches often struggle to ground fine-grained visual concepts in complex scenes. In this paper, we propose MoDA (Modulation Adapter), a lightweight yet effective module designed to refine pre-aligned visual features through instruction-guided modulation. Our approach follows the standard LLaVA training protocol, consisting of a two-stage process: (1) aligning image features to the LLMs input space via a frozen vision encoder and adapter layers, and (2) refining those features using the MoDA adapter during the instructional tuning stage. MoDA employs a Transformer-based cross-attention mechanism to generate a modulation mask over the aligned visual tokens, thereby emphasizing semantically relevant embedding dimensions based on the language instruction. The modulated features are then passed to the LLM for autoregressive language generation. Our experimental evaluation shows that MoDA improves visual grounding and generates more contextually appropriate responses, demonstrating its effectiveness as a general-purpose enhancement for image-based MLLMs.
Visual Grounding is a task that aims to localize a target region in an image based on a free-form natural language description. With the rise of Transformer architectures, there is an increasing need for larger datasets to boost performance. However, the high cost of manual annotation poses a challenge, hindering the scale of data and the ability of large models to enhance their effectiveness. Previous pseudo label generation methods heavily rely on human-labeled captions of the original dataset, limiting scalability and diversity. To address this, we propose D2AF, a robust annotation framework for visual grounding using only input images. This approach overcomes dataset size limitations and enriches both the quantity and diversity of referring expressions. Our approach leverages multimodal large models and object detection models. By implementing dual-driven annotation strategies, we effectively generate detailed region-text pairs using both closed-set and open-set approaches. We further conduct an in-depth analysis of data quantity and data distribution. Our findings demonstrate that increasing data volume enhances model performance. However, the degree of improvement depends on how well the pseudo labels broaden the original data distribution. Based on these insights, we propose a consistency and distribution aware filtering method to further improve data quality by effectively removing erroneous and redundant data. This approach effectively eliminates noisy data, leading to improved performance. Experiments on three visual grounding tasks demonstrate that our method significantly improves the performance of existing models and achieves state-of-the-art results.
Large Vision-Language Models (LVLMs) have made remarkable strides in multimodal tasks such as visual question answering, visual grounding, and complex reasoning. However, they remain limited by static training data, susceptibility to hallucinations, and inability to verify claims against up-to-date, external evidence, compromising their performance in dynamic real-world applications. Retrieval-Augmented Generation (RAG) offers a practical solution to mitigate these challenges by allowing the LVLMs to access large-scale knowledge databases via retrieval mechanisms, thereby grounding model outputs in factual, contextually relevant information. Here in this paper, we conduct the first systematic dissection of the multimodal RAG pipeline for LVLMs, explicitly investigating (1) the retrieval phase: on the modality configurations and retrieval strategies, (2) the re-ranking stage: on strategies to mitigate positional biases and improve the relevance of retrieved evidence, and (3) the generation phase: we further investigate how to best integrate retrieved candidates into the final generation process. Finally, we extend to explore a unified agentic framework that integrates re-ranking and generation through self-reflection, enabling LVLMs to select relevant evidence and suppress irrelevant context dynamically. Our full-stack exploration of RAG for LVLMs yields substantial insights, resulting in an average performance boost of 5% without any fine-tuning.
Given the central role of charts in scientific, business, and communication contexts, enhancing the chart understanding capabilities of vision-language models (VLMs) has become increasingly critical. A key limitation of existing VLMs lies in their inaccurate visual grounding of infographic elements, including charts and human-recognizable objects (HROs) such as icons and images. However, chart understanding often requires identifying relevant elements and reasoning over them. To address this limitation, we introduce OrionBench, a benchmark designed to support the development of accurate object detection models for charts and HROs in infographics. It contains 26,250 real and 78,750 synthetic infographics, with over 6.9 million bounding box annotations. These annotations are created by combining the model-in-the-loop and programmatic methods. We demonstrate the usefulness of OrionBench through three applications: 1) constructing a Thinking-with-Boxes scheme to boost the chart understanding performance of VLMs, 2) comparing existing object detection models, and 3) applying the developed detection model to document layout and UI element detection.
3D Visual Grounding (3DVG) seeks to locate target objects in 3D scenes using natural language descriptions, enabling downstream applications such as augmented reality and robotics. Existing approaches typically rely on labeled 3D data and predefined categories, limiting scalability to open-world settings. We present SeeGround, a zero-shot 3DVG framework that leverages 2D Vision-Language Models (VLMs) to bypass the need for 3D-specific training. To bridge the modality gap, we introduce a hybrid input format that pairs query-aligned rendered views with spatially enriched textual descriptions. Our framework incorporates two core components: a Perspective Adaptation Module that dynamically selects optimal viewpoints based on the query, and a Fusion Alignment Module that integrates visual and spatial signals to enhance localization precision. Extensive evaluations on ScanRefer and Nr3D confirm that SeeGround achieves substantial improvements over existing zero-shot baselines -- outperforming them by 7.7% and 7.1%, respectively -- and even rivals fully supervised alternatives, demonstrating strong generalization under challenging conditions.
Large vision-language models (LVLMs) achieve impressive performance on multimodal tasks but often suffer from hallucination, and confidently describe objects or attributes not present in the image. Current inference-time interventions, while training-free, struggle to maintain accuracy in open-ended and long-form generation scenarios. We introduce the Confidence-Aware Attention Calibration (CAAC) framework to address this challenge by targeting two key biases: spatial perception bias, which distributes attention disproportionately across image tokens, and modality bias, which shifts focus from visual to textual inputs over time. CAAC employs a two-step approach: Visual-Token Calibration (VTC) to balance attention across visual tokens, and Adaptive Attention Re-Scaling (AAR) to reinforce visual grounding based on the model's confidence. This confidence-driven adjustment ensures consistent visual alignment during generation. Experiments on CHAIR, AMBER, and POPE benchmarks demonstrate that CAAC outperforms baselines, particularly in long-form generations, effectively reducing hallucination.
While large language models (LLMs) demonstrate strong reasoning capabilities utilizing reinforcement learning (RL) with verifiable reward, whether large vision-language models (VLMs) can directly inherit such capabilities through similar post-training strategies remains underexplored. In this work, we conduct a systematic compositional probing study to evaluate whether current VLMs trained with RL or other post-training strategies can compose capabilities across modalities or tasks under out-of-distribution conditions. We design a suite of diagnostic tasks that train models on unimodal tasks or isolated reasoning skills, and evaluate them on multimodal, compositional variants requiring skill integration. Through comparisons between supervised fine-tuning (SFT) and RL-trained models, we identify three key findings: (1) RL-trained models consistently outperform SFT on compositional generalization, demonstrating better integration of learned skills; (2) although VLMs achieve strong performance on individual tasks, they struggle to generalize compositionally under cross-modal and cross-task scenario, revealing a significant gap in current training strategies; (3) enforcing models to explicitly describe visual content before reasoning (e.g., caption-before-thinking), along with rewarding progressive vision-to-text grounding, yields notable gains. It highlights two essential ingredients for improving compositionality in VLMs: visual-to-text alignment and accurate visual grounding. Our findings shed light on the current limitations of RL-based reasoning VLM training and provide actionable insights toward building models that reason compositionally across modalities and tasks.
Evaluating the video understanding capabilities of Video-Language Models (VLMs) remains a significant challenge. We propose a long-context video understanding benchmark, Causal2Needles, that assesses two crucial abilities insufficiently evaluated by existing benchmarks: (1) the ability to extract information from two separate locations in a long video and understand them jointly, and (2) the ability to model the world in terms of cause and effect in human behaviors. Specifically, Causal2Needles introduces 2-needle questions, which require extracting information from both the cause and effect human-behavior events in a long video and the associated narration text. To prevent textual bias, these questions comprise two complementary formats: one asking to identify the video clip containing the answer, and one asking for the textual description of an unrelated visual detail from that video clip. Our experiments reveal that models excelling in pre-existing benchmarks struggle with 2-needle visual grounding, and the model performance is negatively correlated with the distance between the two needles. These findings highlight critical limitations in current VLMs.
We present v1, a lightweight extension to Multimodal Large Language Models (MLLMs) that enables selective visual revisitation during inference. While current MLLMs typically consume visual input only once and reason purely over internal memory, v1 introduces a simple point-and-copy mechanism that allows the model to dynamically retrieve relevant image regions throughout the reasoning process. This mechanism augments existing architectures with minimal modifications, enabling contextual access to visual tokens based on the model's evolving hypotheses. To train this capability, we construct v1g, a dataset of 300K multimodal reasoning traces with interleaved visual grounding annotations. Experiments on three multimodal mathematical reasoning benchmarks -- MathVista, MathVision, and MathVerse -- demonstrate that v1 consistently improves performance over comparable baselines, particularly on tasks requiring fine-grained visual reference and multi-step reasoning. Our results suggest that dynamic visual access is a promising direction for enhancing grounded multimodal reasoning. Code, models, and data will be released to support future research.
Evaluating image captions requires cohesive assessment of both visual semantics and language pragmatics, which is often not entirely captured by most metrics. We introduce Redemption Score, a novel hybrid framework that ranks image captions by triangulating three complementary signals: (1) Mutual Information Divergence (MID) for global image-text distributional alignment, (2) DINO-based perceptual similarity of cycle-generated images for visual grounding, and (3) BERTScore for contextual text similarity against human references. A calibrated fusion of these signals allows Redemption Score to offer a more holistic assessment. On the Flickr8k benchmark, Redemption Score achieves a Kendall-$\tau$ of 56.43, outperforming twelve prior methods and demonstrating superior correlation with human judgments without requiring task-specific training. Our framework provides a more robust and nuanced evaluation by effectively redeeming image semantics and linguistic interpretability indicated by strong transfer of knowledge in the Conceptual Captions and MS COCO datasets.
Recent advances in Reasoning LLMs (e.g., DeepSeek-R1 and OpenAI-o1) have showcased impressive reasoning capabilities via reinforcement learning. However, extending these capabilities to Multimodal LLMs (MLLMs) is hampered by the prohibitive costs of retraining and the scarcity of high-quality, verifiable multimodal reasoning datasets. This paper introduces FRANK Model, a training-FRee ANd r1-liKe MLLM that imbues off-the-shelf MLLMs with reasoning and reflection abilities, without any gradient updates or extra supervision. Our key insight is to decouple perception and reasoning across MLLM decoder layers. Specifically, we observe that compared to the deeper decoder layers, the shallow decoder layers allocate more attention to visual tokens, while the deeper decoder layers concentrate on textual semantics. This observation motivates a hierarchical weight merging approach that combines a visual-pretrained MLLM with a reasoning-specialized LLM. To this end, we propose a layer-wise, Taylor-derived closed-form fusion mechanism that integrates reasoning capacity into deep decoder layers while preserving visual grounding in shallow decoder layers. Extensive experiments on challenging multimodal reasoning benchmarks demonstrate the effectiveness of our approach. On the MMMU benchmark, our model FRANK-38B achieves an accuracy of 69.2, outperforming the strongest baseline InternVL2.5-38B by +5.3, and even surpasses the proprietary GPT-4o model. Our project homepage is at: http://iip.whu.edu.cn/frank/index.html
Language-Guided object recognition in remote sensing imagery is crucial for large-scale mapping and automated data annotation. However, existing open-vocabulary and visual grounding methods rely on explicit category cues, limiting their ability to handle complex or implicit queries that require advanced reasoning. To address this issue, we introduce a new suite of tasks, including Instruction-Oriented Object Counting, Detection, and Segmentation (InstructCDS), covering open-vocabulary, open-ended, and open-subclass scenarios. We further present EarthInstruct, the first InstructCDS benchmark for earth observation. It is constructed from two diverse remote sensing datasets with varying spatial resolutions and annotation rules across 20 categories, necessitating models to interpret dataset-specific instructions. Given the scarcity of semantically rich labeled data in remote sensing, we propose InstructSAM, a training-free framework for instruction-driven object recognition. InstructSAM leverages large vision-language models to interpret user instructions and estimate object counts, employs SAM2 for mask proposal, and formulates mask-label assignment as a binary integer programming problem. By integrating semantic similarity with counting constraints, InstructSAM efficiently assigns categories to predicted masks without relying on confidence thresholds. Experiments demonstrate that InstructSAM matches or surpasses specialized baselines across multiple tasks while maintaining near-constant inference time regardless of object count, reducing output tokens by 89% and overall runtime by over 32% compared to direct generation approaches. We believe the contributions of the proposed tasks, benchmark, and effective approach will advance future research in developing versatile object recognition systems.
Visual grounding (VG) is the capability to identify the specific regions in an image associated with a particular text description. In medical imaging, VG enhances interpretability by highlighting relevant pathological features corresponding to textual descriptions, improving model transparency and trustworthiness for wider adoption of deep learning models in clinical practice. Current models struggle to associate textual descriptions with disease regions due to inefficient attention mechanisms and a lack of fine-grained token representations. In this paper, we empirically demonstrate two key observations. First, current VLMs assign high norms to background tokens, diverting the model's attention from regions of disease. Second, the global tokens used for cross-modal learning are not representative of local disease tokens. This hampers identifying correlations between the text and disease tokens. To address this, we introduce simple, yet effective Disease-Aware Prompting (DAP) process, which uses the explainability map of a VLM to identify the appropriate image features. This simple strategy amplifies disease-relevant regions while suppressing background interference. Without any additional pixel-level annotations, DAP improves visual grounding accuracy by 20.74% compared to state-of-the-art methods across three major chest X-ray datasets.
Recent Graphical User Interface (GUI) agents replicate the R1-Zero paradigm, coupling online Reinforcement Learning (RL) with explicit chain-of-thought reasoning prior to object grounding and thereby achieving substantial performance gains. In this paper, we first conduct extensive analysis experiments of three key components of that training pipeline: input design, output evaluation, and policy update-each revealing distinct challenges arising from blindly applying general-purpose RL without adapting to GUI grounding tasks. Input design: Current templates encourage the model to generate chain-of-thought reasoning, but longer chains unexpectedly lead to worse grounding performance. Output evaluation: Reward functions based on hit signals or box area allow models to exploit box size, leading to reward hacking and poor localization quality. Policy update: Online RL tends to overfit easy examples due to biases in length and sample difficulty, leading to under-optimization on harder cases. To address these issues, we propose three targeted solutions. First, we adopt a Fast Thinking Template that encourages direct answer generation, reducing excessive reasoning during training. Second, we incorporate a box size constraint into the reward function to mitigate reward hacking. Third, we revise the RL objective by adjusting length normalization and adding a difficulty-aware scaling factor, enabling better optimization on hard samples. Our GUI-G1-3B, trained on 17K public samples with Qwen2.5-VL-3B-Instruct, achieves 90.3% accuracy on ScreenSpot and 37.1% on ScreenSpot-Pro. This surpasses all prior models of similar size and even outperforms the larger UI-TARS-7B, establishing a new state-of-the-art in GUI agent grounding. The project repository is available at https://github.com/Yuqi-Zhou/GUI-G1.
Traditional visual grounding methods primarily focus on single-image scenarios with simple textual references. However, extending these methods to real-world scenarios that involve implicit and complex instructions, particularly in conjunction with multiple images, poses significant challenges, which is mainly due to the lack of advanced reasoning ability across diverse multi-modal contexts. In this work, we aim to address the more practical universal grounding task, and propose UniVG-R1, a reasoning guided multimodal large language model (MLLM) for universal visual grounding, which enhances reasoning capabilities through reinforcement learning (RL) combined with cold-start data. Specifically, we first construct a high-quality Chain-of-Thought (CoT) grounding dataset, annotated with detailed reasoning chains, to guide the model towards correct reasoning paths via supervised fine-tuning. Subsequently, we perform rule-based reinforcement learning to encourage the model to identify correct reasoning chains, thereby incentivizing its reasoning capabilities. In addition, we identify a difficulty bias arising from the prevalence of easy samples as RL training progresses, and we propose a difficulty-aware weight adjustment strategy to further strengthen the performance. Experimental results demonstrate the effectiveness of UniVG-R1, which achieves state-of-the-art performance on MIG-Bench with a 9.1% improvement over the previous method. Furthermore, our model exhibits strong generalizability, achieving an average improvement of 23.4% in zero-shot performance across four image and video reasoning grounding benchmarks. The project page can be accessed at https://amap-ml.github.io/UniVG-R1-page/.
Remote-sensing applications often run on edge hardware that cannot host today's 7B-parameter multimodal language models. This paper introduces TinyRS, the first 2B-parameter multimodal small language model (MSLM) optimized for remote sensing tasks, and TinyRS-R1, its reasoning-augmented variant. Built upon Qwen2-VL-2B, TinyRS is trained through a four-stage pipeline: pre-training on million satellite images, instruction tuning on visual instruction examples, fine-tuning with Chain-of-Thought (CoT) annotations from the proposed reasoning dataset, and alignment via Group Relative Policy Optimization (GRPO). TinyRS-R1 achieves or surpasses the performance of recent 7B-parameter remote sensing models across classification, VQA, visual grounding, and open-ended question answering-while requiring just one-third of the memory and latency. Our analysis shows that CoT reasoning substantially benefits spatial grounding and scene understanding, while the non-reasoning TinyRS excels in concise, latency-sensitive VQA tasks. TinyRS-R1 represents the first domain-specialized MSLM with GRPO-aligned CoT reasoning for general-purpose remote sensing.