This paper introduces Test-time Correction (TTC), an online 3D detection system designed to rectify test-time errors using various auxiliary feedback, aiming to enhance the safety of deployed autonomous driving systems. Unlike conventional offline 3D detectors that remain fixed during inference, TTC enables immediate online error correction without retraining, allowing autonomous vehicles to adapt to new scenarios and reduce deployment risks. To achieve this, we equip existing 3D detectors with an Online Adapter (OA) module -- a prompt-driven query generator for real-time correction. At the core of OA module are visual prompts: image-based descriptions of objects of interest derived from auxiliary feedback such as mismatches with 2D detections, road descriptions, or user clicks. These visual prompts, collected from risky objects during inference, are maintained in a visual prompt buffer to enable continuous correction in future frames. By leveraging this mechanism, TTC consistently detects risky objects, achieving reliable, adaptive, and versatile driving autonomy. Extensive experiments show that TTC significantly improves instant error rectification over frozen 3D detectors, even under limited labels, zero-shot settings, and adverse conditions. We hope this work inspires future research on post-deployment online rectification systems for autonomous driving.
While promptable segmentation (\textit{e.g.}, SAM) has shown promise for various segmentation tasks, it still requires manual visual prompts for each object to be segmented. In contrast, task-generic promptable segmentation aims to reduce the need for such detailed prompts by employing only a task-generic prompt to guide segmentation across all test samples. However, when applied to Camouflaged Object Segmentation (COS), current methods still face two critical issues: 1) \textit{\textbf{semantic ambiguity in getting instance-specific text prompts}}, which arises from insufficient discriminative cues in holistic captions, leading to foreground-background confusion; 2) \textit{\textbf{semantic discrepancy combined with spatial separation in getting instance-specific visual prompts}}, which results from global background sampling far from object boundaries with low feature correlation, causing SAM to segment irrelevant regions. To address the issues above, we propose \textbf{RDVP-MSD}, a novel training-free test-time adaptation framework that synergizes \textbf{R}egion-constrained \textbf{D}ual-stream \textbf{V}isual \textbf{P}rompting (RDVP) via \textbf{M}ultimodal \textbf{S}tepwise \textbf{D}ecomposition Chain of Thought (MSD-CoT). MSD-CoT progressively disentangles image captions to eliminate semantic ambiguity, while RDVP injects spatial constraints into visual prompting and independently samples visual prompts for foreground and background points, effectively mitigating semantic discrepancy and spatial separation. Without requiring any training or supervision, RDVP-MSD achieves a state-of-the-art segmentation result on multiple COS benchmarks and delivers a faster inference speed than previous methods, demonstrating significantly improved accuracy and efficiency. The codes will be available at \href{https://github.com/ycyinchao/RDVP-MSD}{https://github.com/ycyinchao/RDVP-MSD}
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.
In this paper, we propose a Grid-based Local and Global Area Transcription (Grid-LoGAT) system for Video Question Answering (VideoQA). The system operates in two phases. First, extracting text transcripts from video frames using a Vision-Language Model (VLM). Next, processing questions using these transcripts to generate answers through a Large Language Model (LLM). This design ensures image privacy by deploying the VLM on edge devices and the LLM in the cloud. To improve transcript quality, we propose grid-based visual prompting, which extracts intricate local details from each grid cell and integrates them with global information. Evaluation results show that Grid-LoGAT, using the open-source VLM (LLaVA-1.6-7B) and LLM (Llama-3.1-8B), outperforms state-of-the-art methods with similar baseline models on NExT-QA and STAR-QA datasets with an accuracy of 65.9% and 50.11% respectively. Additionally, our method surpasses the non-grid version by 24 points on localization-based questions we created using NExT-QA. (This paper is accepted by IEEE ICIP 2025.)
The recent explosive interest in the reasoning capabilities of large language models, such as DeepSeek-R1, has demonstrated remarkable success through reinforcement learning-based fine-tuning frameworks, exemplified by methods like Group Relative Policy Optimization (GRPO). However, such reasoning abilities remain underexplored and notably absent in vision foundation models, including representation models like the DINO series. In this work, we propose \textbf{DINO-R1}, the first such attempt to incentivize visual in-context reasoning capabilities of vision foundation models using reinforcement learning. Specifically, DINO-R1 introduces \textbf{Group Relative Query Optimization (GRQO)}, a novel reinforcement-style training strategy explicitly designed for query-based representation models, which computes query-level rewards based on group-normalized alignment quality. We also apply KL-regularization to stabilize the objectness distribution to reduce the training instability. This joint optimization enables dense and expressive supervision across queries while mitigating overfitting and distributional drift. Building upon Grounding-DINO, we train a series of DINO-R1 family models that integrate a visual prompt encoder and a visual-guided query selection mechanism. Extensive experiments on COCO, LVIS, and ODinW demonstrate that DINO-R1 significantly outperforms supervised fine-tuning baselines, achieving strong generalization in both open-vocabulary and closed-set visual prompting scenarios.
Endoscopic procedures are essential for diagnosing and treating internal diseases, and multi-modal large language models (MLLMs) are increasingly applied to assist in endoscopy analysis. However, current benchmarks are limited, as they typically cover specific endoscopic scenarios and a small set of clinical tasks, failing to capture the real-world diversity of endoscopic scenarios and the full range of skills needed in clinical workflows. To address these issues, we introduce EndoBench, the first comprehensive benchmark specifically designed to assess MLLMs across the full spectrum of endoscopic practice with multi-dimensional capacities. EndoBench encompasses 4 distinct endoscopic scenarios, 12 specialized clinical tasks with 12 secondary subtasks, and 5 levels of visual prompting granularities, resulting in 6,832 rigorously validated VQA pairs from 21 diverse datasets. Our multi-dimensional evaluation framework mirrors the clinical workflow--spanning anatomical recognition, lesion analysis, spatial localization, and surgical operations--to holistically gauge the perceptual and diagnostic abilities of MLLMs in realistic scenarios. We benchmark 23 state-of-the-art models, including general-purpose, medical-specialized, and proprietary MLLMs, and establish human clinician performance as a reference standard. Our extensive experiments reveal: (1) proprietary MLLMs outperform open-source and medical-specialized models overall, but still trail human experts; (2) medical-domain supervised fine-tuning substantially boosts task-specific accuracy; and (3) model performance remains sensitive to prompt format and clinical task complexity. EndoBench establishes a new standard for evaluating and advancing MLLMs in endoscopy, highlighting both progress and persistent gaps between current models and expert clinical reasoning. We publicly release our benchmark and code.
Large-scale pretrained vision backbones have transformed computer vision by providing powerful feature extractors that enable various downstream tasks, including training-free approaches like visual prompting for semantic segmentation. Despite their success in generic scenarios, these models often fall short when applied to specialized technical domains where the visual features differ significantly from their training distribution. To bridge this gap, we introduce VP Lab, a comprehensive iterative framework that enhances visual prompting for robust segmentation model development. At the core of VP Lab lies E-PEFT, a novel ensemble of parameter-efficient fine-tuning techniques specifically designed to adapt our visual prompting pipeline to specific domains in a manner that is both parameter- and data-efficient. Our approach not only surpasses the state-of-the-art in parameter-efficient fine-tuning for the Segment Anything Model (SAM), but also facilitates an interactive, near-real-time loop, allowing users to observe progressively improving results as they experiment within the framework. By integrating E-PEFT with visual prompting, we demonstrate a remarkable 50\% increase in semantic segmentation mIoU performance across various technical datasets using only 5 validated images, establishing a new paradigm for fast, efficient, and interactive model deployment in new, challenging domains. This work comes in the form of a demonstration.
Vision GNN (ViG) demonstrates superior performance by representing images as graph structures, providing a more natural way to capture irregular semantic patterns beyond traditional grid or sequence-based representations. To efficiently adapt ViG to downstream tasks, parameter-efficient fine-tuning techniques like visual prompting become increasingly essential. However, existing prompting methods are primarily designed for Transformer-based models, neglecting the rich topological relationships among nodes and edges in graph-based representations, limiting their capacity to model complex semantics. In this paper, we propose Vision Graph Prompting (VGP), a novel framework tailored for vision graph structures. Our core insight reveals that semantically connected components in the graph exhibit low-rank properties. Building on this observation, we introduce a semantic low-rank prompting method that decomposes low-rank semantic features and integrates them with prompts on vision graph topologies, capturing both global structural patterns and fine-grained semantic dependencies. Extensive experiments demonstrate our method significantly improves ViG's transfer performance on diverse downstream tasks, achieving results comparable to full fine-tuning while maintaining parameter efficiency. Our code is available at https://github.com/zhoujiahuan1991/ICML2025-VGP.
Medical image segmentation is a crucial and time-consuming task in clinical care, where mask precision is extremely important. The Segment Anything Model (SAM) offers a promising approach, as it provides an interactive interface based on visual prompting and edition to refine an initial segmentation. This model has strong generalization capabilities, does not rely on predefined classes, and adapts to diverse objects; however, it is pre-trained on natural images and lacks the ability to process medical data effectively. In addition, this model is built for 2D images, whereas a whole medical domain is based on 3D images, such as CT and MRI. Recent adaptations of SAM for medical imaging are based on 2D models, thus requiring one prompt per slice to segment 3D objects, making the segmentation process tedious. They also lack important features such as editing. To bridge this gap, we propose RadSAM, a novel method for segmenting 3D objects with a 2D model from a single prompt. In practice, we train a 2D model using noisy masks as initial prompts, in addition to bounding boxes and points. We then use this novel prompt type with an iterative inference pipeline to reconstruct the 3D mask slice-by-slice. We introduce a benchmark to evaluate the model's ability to segment 3D objects in CT images from a single prompt and evaluate the models' out-of-domain transfer and edition capabilities. We demonstrate the effectiveness of our approach against state-of-the-art models on this benchmark using the AMOS abdominal organ segmentation dataset.
Vision Large Language Models (VLLMs) exhibit promising potential for multi-modal understanding, yet their application to video-based emotion recognition remains limited by insufficient spatial and contextual awareness. Traditional approaches, which prioritize isolated facial features, often neglect critical non-verbal cues such as body language, environmental context, and social interactions, leading to reduced robustness in real-world scenarios. To address this gap, we propose Set-of-Vision-Text Prompting (SoVTP), a novel framework that enhances zero-shot emotion recognition by integrating spatial annotations (e.g., bounding boxes, facial landmarks), physiological signals (facial action units), and contextual cues (body posture, scene dynamics, others' emotions) into a unified prompting strategy. SoVTP preserves holistic scene information while enabling fine-grained analysis of facial muscle movements and interpersonal dynamics. Extensive experiments show that SoVTP achieves substantial improvements over existing visual prompting methods, demonstrating its effectiveness in enhancing VLLMs' video emotion recognition capabilities.
Recent advancements in multimodal large language models (MLLMs) have broadened the scope of vision-language tasks, excelling in applications like image captioning and interactive question-answering. However, these models struggle with accurately processing visual data, particularly in tasks requiring precise object recognition and fine visual details. Stringent token limits often result in the omission of critical information, hampering performance. To address these limitations, we introduce \SysName, a novel visual prompting mechanism designed to enhance MLLM performance while preserving essential visual details within token limits. \SysName features three key innovations: a prompt-aware strategy that dynamically highlights relevant image regions, a spatial-preserving orchestration schema that maintains object integrity, and a budget-aware prompting method that balances global context with crucial visual details. Comprehensive evaluations across multiple datasets demonstrate that \SysName consistently outperforms baseline methods, achieving up to a $26.9\%$ improvement in accuracy while significantly reducing token consumption.
Large Vision Language Models (LVLMs) often suffer from object hallucination, which undermines their reliability. Surprisingly, we find that simple object-based visual prompting -- overlaying visual cues (e.g., bounding box, circle) on images -- can significantly mitigate such hallucination; however, different visual prompts (VPs) vary in effectiveness. To address this, we propose Black-Box Visual Prompt Engineering (BBVPE), a framework to identify optimal VPs that enhance LVLM responses without needing access to model internals. Our approach employs a pool of candidate VPs and trains a router model to dynamically select the most effective VP for a given input image. This black-box approach is model-agnostic, making it applicable to both open-source and proprietary LVLMs. Evaluations on benchmarks such as POPE and CHAIR demonstrate that BBVPE effectively reduces object hallucination.
Visual prompting techniques are widely used to efficiently fine-tune pretrained Vision Transformers (ViT) by learning a small set of shared prompts for all tokens. However, existing methods overlook the unique roles of different tokens in conveying discriminative information and interact with all tokens using the same prompts, thereby limiting the representational capacity of ViT. This often leads to indistinguishable and biased prompt-extracted features, hindering performance. To address this issue, we propose a plug-and-play Token Coordinated Prompt Attention (TCPA) module, which assigns specific coordinated prompts to different tokens for attention-based interactions. Firstly, recognizing the distinct functions of CLS and image tokens-global information aggregation and local feature extraction, we disentangle the prompts into CLS Prompts and Image Prompts, which interact exclusively with CLS tokens and image tokens through attention mechanisms. This enhances their respective discriminative abilities. Furthermore, as different image tokens correspond to distinct image patches and contain diverse information, we employ a matching function to automatically assign coordinated prompts to individual tokens. This enables more precise attention interactions, improving the diversity and representational capacity of the extracted features. Extensive experiments across various benchmarks demonstrate that TCPA significantly enhances the diversity and discriminative power of the extracted features. The code is available at https://github.com/zhoujiahuan1991/ICML2025-TCPA.
One-shot controllable video editing (OCVE) is an important yet challenging task, aiming to propagate user edits that are made -- using any image editing tool -- on the first frame of a video to all subsequent frames, while ensuring content consistency between edited frames and source frames. To achieve this, prior methods employ DDIM inversion to transform source frames into latent noise, which is then fed into a pre-trained diffusion model, conditioned on the user-edited first frame, to generate the edited video. However, the DDIM inversion process accumulates errors, which hinder the latent noise from accurately reconstructing the source frames, ultimately compromising content consistency in the generated edited frames. To overcome it, our method eliminates the need for DDIM inversion by performing OCVE through a novel perspective based on visual prompting. Furthermore, inspired by consistency models that can perform multi-step consistency sampling to generate a sequence of content-consistent images, we propose a content consistency sampling (CCS) to ensure content consistency between the generated edited frames and the source frames. Moreover, we introduce a temporal-content consistency sampling (TCS) based on Stein Variational Gradient Descent to ensure temporal consistency across the edited frames. Extensive experiments validate the effectiveness of our approach.
Vision-language models (VLMs) have demonstrated impressive zero-shot transfer capabilities in image-level visual perception tasks. However, they fall short in 3D instance-level segmentation tasks that require accurate localization and recognition of individual objects. To bridge this gap, we introduce a novel 3D Gaussian Splatting based hard visual prompting approach that leverages camera interpolation to generate diverse viewpoints around target objects without any 2D-3D optimization or fine-tuning. Our method simulates realistic 3D perspectives, effectively augmenting existing hard visual prompts by enforcing geometric consistency across viewpoints. This training-free strategy seamlessly integrates with prior hard visual prompts, enriching object-descriptive features and enabling VLMs to achieve more robust and accurate 3D instance segmentation in diverse 3D scenes.
Recent advances in the visual-language area have developed natural multi-modal large language models (MLLMs) for spatial reasoning through visual prompting. However, due to remote sensing (RS) imagery containing abundant geospatial information that differs from natural images, it is challenging to effectively adapt natural spatial models to the RS domain. Moreover, current RS MLLMs are limited in overly narrow interpretation levels and interaction manner, hindering their applicability in real-world scenarios. To address those challenges, a spatial MLLM named EarthGPT-X is proposed, enabling a comprehensive understanding of multi-source RS imagery, such as optical, synthetic aperture radar (SAR), and infrared. EarthGPT-X offers zoom-in and zoom-out insight, and possesses flexible multi-grained interactive abilities. Moreover, EarthGPT-X unifies two types of critical spatial tasks (i.e., referring and grounding) into a visual prompting framework. To achieve these versatile capabilities, several key strategies are developed. The first is the multi-modal content integration method, which enhances the interplay between images, visual prompts, and text instructions. Subsequently, a cross-domain one-stage fusion training strategy is proposed, utilizing the large language model (LLM) as a unified interface for multi-source multi-task learning. Furthermore, by incorporating a pixel perception module, the referring and grounding tasks are seamlessly unified within a single framework. In addition, the experiments conducted demonstrate the superiority of the proposed EarthGPT-X in multi-grained tasks and its impressive flexibility in multi-modal interaction, revealing significant advancements of MLLM in the RS field.
Video understanding has shown remarkable improvements in recent years, largely dependent on the availability of large scaled labeled datasets. Recent advancements in visual-language models, especially based on contrastive pretraining, have shown remarkable generalization in zero-shot tasks, helping to overcome this dependence on labeled datasets. Adaptations of such models for videos, typically involve modifying the architecture of vision-language models to cater to video data. However, this is not trivial, since such adaptations are mostly computationally intensive and struggle with temporal modeling. We present TP-CLIP, an adaptation of CLIP that leverages temporal visual prompting for temporal adaptation without modifying the core CLIP architecture. This preserves its generalization abilities. TP-CLIP efficiently integrates into the CLIP architecture, leveraging its pre-trained capabilities for video data. Extensive experiments across various datasets demonstrate its efficacy in zero-shot and few-shot learning, outperforming existing approaches with fewer parameters and computational efficiency. In particular, we use just 1/3 the GFLOPs and 1/28 the number of tuneable parameters in comparison to recent state-of-the-art and still outperform it by up to 15.8% depending on the task and dataset.
The goal of this paper is to enhance pretrained Vision Transformer (ViT) models for focus-oriented image retrieval with visual prompting. In real-world image retrieval scenarios, both query and database images often exhibit complexity, with multiple objects and intricate backgrounds. Users often want to retrieve images with specific object, which we define as the Focus-Oriented Image Retrieval (FOIR) task. While a standard image encoder can be employed to extract image features for similarity matching, it may not perform optimally in the multi-object-based FOIR task. This is because each image is represented by a single global feature vector. To overcome this, a prompt-based image retrieval solution is required. We propose an approach called Prompt-guided attention Head Selection (PHS) to leverage the head-wise potential of the multi-head attention mechanism in ViT in a promptable manner. PHS selects specific attention heads by matching their attention maps with user's visual prompts, such as a point, box, or segmentation. This empowers the model to focus on specific object of interest while preserving the surrounding visual context. Notably, PHS does not necessitate model re-training and avoids any image alteration. Experimental results show that PHS substantially improves performance on multiple datasets, offering a practical and training-free solution to enhance model performance in the FOIR task.
Multimodal social interaction understanding (MMSI) is critical in human-robot interaction systems. In real-world scenarios, AI agents are required to provide real-time feedback. However, existing models often depend on both past and future contexts, which hinders them from applying to real-world problems. To bridge this gap, we propose an online MMSI setting, where the model must resolve MMSI tasks using only historical information, such as recorded dialogues and video streams. To address the challenges of missing the useful future context, we develop a novel framework, named Online-MMSI-VLM, that leverages two complementary strategies: multi-party conversation forecasting and social-aware visual prompting with multi-modal large language models. First, to enrich linguistic context, the multi-party conversation forecasting simulates potential future utterances in a coarse-to-fine manner, anticipating upcoming speaker turns and then generating fine-grained conversational details. Second, to effectively incorporate visual social cues like gaze and gesture, social-aware visual prompting highlights the social dynamics in video with bounding boxes and body keypoints for each person and frame. Extensive experiments on three tasks and two datasets demonstrate that our method achieves state-of-the-art performance and significantly outperforms baseline models, indicating its effectiveness on Online-MMSI. The code and pre-trained models will be publicly released at: https://github.com/Sampson-Lee/OnlineMMSI.
Differentially private (DP) synthetic data has become the de facto standard for releasing sensitive data. However, many DP generative models suffer from the low utility of synthetic data, especially for high-resolution images. On the other hand, one of the emerging techniques in parameter efficient fine-tuning (PEFT) is visual prompting (VP), which allows well-trained existing models to be reused for the purpose of adapting to subsequent downstream tasks. In this work, we explore such a phenomenon in constructing captivating generative models with DP constraints. We show that VP in conjunction with DP-NTK, a DP generator that exploits the power of the neural tangent kernel (NTK) in training DP generative models, achieves a significant performance boost, particularly for high-resolution image datasets, with accuracy improving from 0.644$\pm$0.044 to 0.769. Lastly, we perform ablation studies on the effect of different parameters that influence the overall performance of VP-NTK. Our work demonstrates a promising step forward in improving the utility of DP synthetic data, particularly for high-resolution images.