Overview

Visual grounding studies how systems identify the image regions or objects referred to by language, often producing boxes, points, or masks. Common approaches include aligning text and visual features, selecting among detected objects, using attention or high-resolution crops, and training with localization annotations or reinforcement-learning rewards. The field spans referring-expression benchmarks such as RefCOCO, fine-grained spatial reasoning, medical and remote-sensing images, video, and embodied tasks such as navigation and manipulation. A central challenge is that correct answers do not prove a model used visual evidence: systems still struggle with precise localization, changing scenes, and reliable visual dependence while balancing accuracy, efficiency, and robustness.

Latest papers

167 papers21 papers in the last four weeks, down 30% on the four weeks before. 0.1% of all new papers.

Oct 5, 2026

Visual Grounding Safety in Vision-Language Models

Vision-language models (VLMs) are increasingly trained to generate structured outputs like points and bounding boxes that downstream interfaces, agents, and robots can act on, yet safety alignment of this output channel has not been systematically analyzed. We study visual grounding safety by repurposing three safety benchmarks spanning direct harm (VLSU), social bias (BBQ-V), and situational safety (Asimov-2.0) into 15,401 matched pairs of harmful requests that differ only in the requested output: a free-text answer (VQA) or a grounding (point or bounding box). Across five VLMs, models that refuse a harmful request posed as a question often comply when the same request asks for a grounding: averaged over models, grounding refusal trails VQA refusal by 31-59 percentage points, depending on the domain, and safety system prompts do not close this gap. We propose a fine-tuning approach that combines grounding-form refusals with capability grounding data and self-distilled benign data to counter over-refusal. For Qwen3-VL-8B and VisionReasoner-7B, it improves grounding refusal by 77-95 percentage points on VLSU and BBQ-V and by 64-85 points on the held-out Asimov-2.0 domain, while also improving VQA refusal, preserving grounding capability, and keeping over-refusal limited. Representation analysis shows that fine-tuning moves harmful requests toward each model's refusal direction, most strongly for grounding, while leaving benign requests near the harmless reference.
Oct 3, 2026

AgroGround: Multi-Granularity Grounded Recognition in Agriculture

Agricultural visual models are typically evaluated for either recognition or localization, but reliable diagnosis requires identifying what is present and localizing the evidence. Agricultural visual question answering (VQA) datasets carry rich semantic labels but rarely link them to image regions, and adding such annotations by hand is costly at scale. We introduce AgroGround, a large-scale dataset for grounded agricultural recognition: identifying plant diseases and other agricultural targets and localizing their image regions. An automated pipeline converts the labels of eight agricultural VQA datasets into annotations for disease lesions and whole objects, producing 794,850 instruction examples. Healthy images provide negative supervision for disease queries, teaching the model to return empty predictions. We fine-tune a shared vision-language model on known-target grounding instructions combined with instructions requiring both recognition and localization. We evaluate predicted identities, regions, joint correctness, and healthy-image abstention on 1,480 human-verified images disjoint from all training data. Grounding-only fine-tuning reduces recognition accuracy from 51.8% to 29.1%, while adding recognition-and-localization instructions raises it to 72.6%. With images and annotations held fixed, combining the two formats raises joint accuracy from 19.2% to 43.3% at comparable grounding. Healthy negatives raise abstention on healthy images to 95.0%, and reinforcement learning improves lesion-level grounding. The resulting 2B model exceeds its annotation teacher in grounding F1 on our benchmark and on the external PlantSeg test set. AgroGround establishes a benchmark for grounded agricultural recognition, measuring joint correctness of identity and localization along with abstention on healthy images. The code is available at https://github.com/AB-Abdulla/AgroGround.
Oct 1, 2026

Same Reward, Different Skills: When Multimodal RL Learns to Look

Reinforcement learning with verifiable rewards (RLVR) improves vision-language benchmark scores even without visual information during training. With images at test, blind-trained models recover roughly half of the real-image gain at 3B and nearly four fifths at 7B. Prolonged real-image training can erode grounding while benchmark gains persist. Both findings expose the same gap: an image in the prompt is not an image in the learning signal. Our design rule, visual resolvability, asks that visual evidence be necessary for a correct answer and that the task remain learnable. We test it on counterfactual coordinate scenes in which the question stays fixed and the target is never named, so a correct answer requires finding the target in the image. With standard GRPO and correctness-and-format rewards, a 7B model raises its accuracy at finding the target (discovery) from 0.425 to 0.875 on held-out scenes denser than any it trained on, and it improves on question types it never trained on. Two controls locate the source of the gain. Replacing test images with gray canvases drops discovery to zero; training on gray canvases instead, at matched step 30 and in each of four seeds, yields essentially none of the gain even when the model is then tested with real images. The learned skill carries over to grounding tasks built independently of the training corpus. A caption that answers the training question, added to the same images, reward and budget, cuts the gain by nearly two thirds. Changing what reward requires changes what RL learns.
Oct 1, 2026

CoEvolve: Construct-to-Edit Visual Grounding with Bidirectional State Refinement

Visual grounding localizes an object described by language with a bounding box. Most multimodal grounding models compress target identification, spatial reasoning, and boundary estimation into one terminal prediction. Free-form rationales make reasoning linguistically explicit but do not necessarily expose measurable, editable spatial states. Intermediate localization errors are therefore difficult to diagnose and correct, allowing incorrect region choices and imprecise boundaries to persist in the final box. We introduce CoEvolve, a construct-to-edit framework that separates grounding into explicit state construction and state editing. Region-Evolution Reinforcement (RER) organizes grounding analysis into a progressive semantic--spatial trajectory, with each reasoning step committing to an explicit candidate region. Bidirectional Denoising Refiner (BDR) treats the reasoning text as fixed semantic context and refines the trajectory's coordinate fields through bidirectional same-position reconstruction. Geometry- and behavior-level objectives provide target geometry and edit-preference signals for consolidating reliable candidates, preserving accurate inputs, or correcting toward annotations. Evaluations cover natural-image and remote-sensing grounding. With a 9B backbone, CoEvolve rivals models up to 241B parameters in grounding accuracy. Under controlled corruption, a single BDR pass improves mean box overlap by over 27 percentage points, demonstrating strong recovery from substantial localization errors. State-source comparisons further support the complementarity of explicit state construction and source-matched editing. The project is at https://sundongwei.github.io/CoEvolve_Project/.
Sep 29, 2026

LEGO-OPD: Factorized Teacher Composition for Multimodal On-Policy Distillation

Multimodal on-policy distillation (OPD) aims to improve visual grounding while preserving the strong reasoning capabilities of language models. Recent multi-teacher approaches combine LLM and VLM teachers to provide complementary supervision. However, directly using a VLM's full predictive distribution entangles its visual grounding signal with its own language prior, preventing the grounding information from being transferred independently. Conversely, increasing the strength of visual supervision can improve perception but may overemphasize visual evidence and degrade language reasoning. To address this trade-off, we introduce LEGO-OPD, which selectively composes factors from a Language Expert and a Grounding expert into One teacher distribution for multimodal OPD. Under a generalized Bayesian formulation, the language expert provides a prior over candidate tokens, while the grounding expert contributes a visual likelihood that updates this prior, rather than transferring its complete predictive distribution. This factorized composition allows language reasoning and visual grounding to be controlled independently. We further introduce adaptive calibration to determine how strongly the visual likelihood should update the language prior at each decoding prefix. Specifically, LEGO-OPD uses the grounding expert's image-induced prediction shift as a prefix-dependent reference, preventing both insufficient and excessive visual supervision. Experiments with Qwen3 models show that LEGO-OPD consistently outperforms the evaluated single- and multi-teacher OPD baselines on both multimodal and text-only reasoning tasks. Moreover, it improves the initial student's visual perception while preserving text-only reasoning.
Sep 29, 2026

DSPO: Diversity-aware Subjective Policy Optimization for Robust Emotional Reasoning

Reinforcement Learning has significantly advanced the complex reasoning capabilities of MLLMs. However, prevailing RL algorithms suffer a severe failure in emotion reasoning tasks. These methods heavily rely on deterministic hard-label supervision and point-wise isolated evaluation, creating a fundamental gap with the inherently subjective and continuously distributed nature of human emotions. Furthermore, unlike explicit physical objects, emotional states are deeply implicit within visual cues. This abstract nature exacerbates visual hallucinations in MLLMs, leading to plausible yet ungrounded emotional evidence. To address these limitations, we propose Diversity-Aware Subjective Policy Optimization (DSPO), a reinforcement learning framework that jointly promotes subjective affective coverage and visual grounding. First, we construct a context-grounded emotional distribution prior in the VAD space by combining the lexical prior of the annotated emotion with image-specific contextual information. Based on this prior, we introduce a Distribution-Aligned Emotional Diversity Reward (DEDR), which measures the leave-one-out marginal contribution of each candidate emotion within a rollout. DEDR rewards candidates whose inclusion brings the predicted affective set closer to the context-grounded prior, thereby preserving plausible subjective interpretations without encouraging unconstrained dispersion. We further develop Counterfactual Visual Intervention Gating (CVIG), which masks the visual region highlighted in the reasoning process and uses the resulting candidate-wise probability changes to reduce the weights of interpretations unsupported by visual evidence. Extensive experiments demonstrate that DSPO achieves state-of-the-art performance across multiple public benchmarks, especially on the cross-domain performance, i.e., improving +10.8% on average cross-domain accuracy than EMO-R3.
Sep 28, 2026

FigAct: Turning Scientific Figures into Active Canvases for Explanation

Scientific figures are designed to communicate information visually, yet MLLMs typically explain them by translating their visual content back into text. This requires readers to manually map the resulting explanations back to the figure. Inspired by how people present visual information, we introduce FigAct, a framework that transforms static scientific figures into question-conditioned visual presentations by acting directly on their existing graphical elements. Like a human presenter, FigAct generates a sequence of short narrations, grounds each narration in the corresponding visual evidence, and applies visual actions to guide the viewer's attention. We develop a hierarchical search strategy for efficient element localization, reducing token usage by approximately 40×\times. We further train FigAct-8B using three task-specific rewards for grounding accuracy, search efficiency, and rendering quality. We further build a human-verified benchmark from figures in real-world scientific papers to evaluate the ability of MLLMs to generate grounded visual explanations. Our results demonstrate the effectiveness of FigAct and show that treating scientific figures as presentation canvases makes explanations clearer and easier to follow.
Sep 28, 2026

Look Before You Judge: Training-Free Region Mining for Grounded and Explainable Deepfake Detection

Multimodal large language models (MLLMs) can explain deepfake verdicts in natural language, but such explanations are not necessarily visually grounded in the visual evidence underlying the prediction. A model may describe plausible artifacts inferred from language priors rather than from image evidence. Existing grounding methods improve visual reliance through decoding or attention interventions, but they generally strengthen grounding over the entire image, making them ill-suited for forensic artifacts that are subtle, spatially localized, and image-dependent. We propose Look Before You Judge, a training-free framework that formulates explainable deepfake detection as a sequential evidence acquisition process. Instead of directly predicting image authenticity from holistic visual reasoning, our framework first identifies image-specific candidate evidence regions by contrasting the MLLM's decoder-to-visual attention between an original image and its Gaussian-blurred counterpart. The identified regions are then inspected individually, and the resulting local evidence is integrated with the global image context before reaching a final verdict. The framework operates without manipulation masks, external forensic models, or parameter updates, making it directly applicable to off-the-shelf MLLMs. Across five open-source MLLMs on TriDF and MMTD-Set, our framework improves detection accuracy by up to 12.8%, reduces CHAIR by up to 33.4% and hallucination rate by up to 21.3%, and outperforms representative training-free decoding and attention methods.
Sep 27, 2026

Probe to Act: Elevating Browser-Use Agent via Active Visual Probing

Browser-use agents require seamless alignment between structured web metadata and visual information, while preserving relevant context across long interactions. Existing interfaces often rely on either screenshot-level action prediction or static Set-of-Marks overlays, leaving the model to resolve dense DOM-pixel alignment before every operation. We introduce Probe to Act (P2A), an active probing framework for the browser-agent loop that moves this alignment into decision time. P2A addresses an asymmetric bridge between symbolic DOM hypotheses and screenshot layout by rendering on-demand symbolic DOM structure back into pixels. Before committing a state-changing browser operation, the agent can issue lightweight probes to translate DOM handles into pixel evidence, map screen regions back to DOM candidates, register visual-only targets, and commit verified notes. These interleaved processes naturally produce evidence-based memory: only probed, acted-on, or explicitly committed observations are kept across steps, preserving only decision-critical evidence in long-horizon contexts. P2A can be used as a prompting strategy for proprietary models under the standard DOM+SoM interface, and can be distilled into open-weight models through cold-start synthesis and self-bootstrapped SFT. Across three browser-use benchmarks, P2A shows clear gains on task success rate for both proprietary and fine-tuned models; on VisualWebArena, for example, it improves Gemini-3-Pro from 54.1% to 61.2% and Qwen3-VL-8B from 24.6% to 32.9%, while matching the costly full-observation history (∼\sim3×\times) at only ∼\sim1.2×\times the peak retained input context of action-only history.
Sep 27, 2026

FORUM: Frozen Outputs Reconciled Using Model Agreement for Visual Grounding

Frozen multimodal large language models (MLLMs) now solve standard referring expression comprehension with a single prompted call, yet on adversarial benchmarks with same-category distractors and negation, even the largest models are confidently wrong, and resampling repeats the error. Models built from different data and architectures rarely fall for the same confounder, so their agreement is a strong label-free signal of the correct target. We present FORUM, a training-free test-time fusion of frozen MLLMs guided by two fixed geometric rules: agreement-based selection keeps the region supported by the most distinct models, and medoid localization returns an actual member box instead of a coordinate average, so one loose prediction cannot shift the answer. Fusing three open MLLMs, FORUM surpasses the 397B-parameter published reference by a relative 5% in mean accuracy on the adversarial Ref-Adv-s benchmark, and a plain averaging ensemble by 15%. The gains transfer to standard RefCOCO+, and a balanced lineup with no dominant member still surpasses the 397B model by 5%.
Sep 27, 2026

FocusDrive: Reasoning with Visual Focus for Autonomous Driving

Driving decisions depend on both where to focus and how to act on what is seen. Effective driving reasoning must establish which objects matter, where they are, and how they inform the intended action. Text-based rationales can describe a driving response while leaving its correspondence to specific visual evidence implicit. Visual focus provides a concrete starting point for this connection by identifying what matters in the scene and where it is. We propose FocusDrive, a structured multimodal reasoning framework that organizes end-to-end planning around explicit visual focus. It pairs descriptions of decision-relevant objects with image-patch references, bringing explicit visual focus into the reasoning that generates driving plans and trajectories. We first assess this focus representation through driver gaze prediction, then investigate its role in planning reasoning using driving-focus annotations within existing NAVSIM training scenes. Experiments on W3DA and NAVSIM demonstrate competitive gaze prediction and end-to-end planning performance, with FocusDrive improving over text-based chain-of-thought. These results support visual focus as an effective link between scene understanding and driving action.
Sep 26, 2026

InterTab: Interleaved Visual-Structure Alignment for Multi-Modal Table Reasoning

Table images preserve structural information that are often lost in text serialization, and reasoning over them requires locating relevant rows, columns, and cells step by step. Current multimodal large language models (MLLMs) encode the whole image once before reasoning, so they cannot pick up row-, column-, and cell-level evidence as the question unfolds. Encoder-side table structure and generic interleaved visual chain-of-thought still do not bind each reasoning step to that structure. We propose InterTab, an Interleaved structure-aware framework for CoT reasoning over Table images, interleaves chain-of-thought with tool calls that crop structure-aligned table regions. First, we build InterTab-22K, includes reasoning trajectories in which each step is tied to both a structural location and a bounding box. InterTab is trained in two stages: supervised structure-aware alignment (SSA) on InterTab-22K teaches the model to interleave reasoning with structure-aligned crops, and active localization optimization (ALO) further optimizes answer correctness, localization IoU, and output format, while penalizing missing or excessive tool calls. Experiments on nine table benchmarks show that InterTab improves the average accuracy of its backbone from 68.28% to 73.17% and achieves the best average performance among all compared methods. Code and data will be released soon.
Sep 25, 2026

Enhancing Visual Reasoning in Chest X-Ray Report Generation Using Reinforcement Learning

Medical report generation has made significant progress with the rise of modern vision-language models and the growing availability of large-scale medical datasets. However, hallucinations remain a major challenge, largely due to the limitations of supervised fine-tuning (SFT), which prioritizes lexical similarity to reference reports rather than clinical correctness. While reinforcement learning has shown strong performance in domains with verifiable rewards such as mathematics and code generation, its application to open-ended medical tasks remains limited. Existing work focuses on evaluating final answers, overlooking the model's reasoning, despite evidence that flawed reasoning can degrade overall performance. In this study, we propose a framework that verifies the model's reasoning process by integrating anatomical regions, bounding boxes, and region-level textual descriptions. We design spatial and factual reward mechanisms to ensure that the model's reasoning is both visually grounded and factually accurate. Starting from Qwen3-VL-8B-Instruct as our base model, we adapt it to the medical domain using supervised fine-tuning, introduce reasoning capability through a cold-start SFT stage, and refine it with reinforcement learning. We find that RL provides performance gains beyond those achievable through SFT alone, and that jointly verifying both reasoning steps and final outputs yields larger improvements than verifying either in isolation. We further identify multiple modes of reward hacking in the RL stage. Finally, the model's structured think traces enhance interpretability, making its outputs easier to audit for clinical use.
Sep 23, 2026

GeoNLI - A Natural Language Interpreter for Satellite Imagery

Multi-modal multitasking models have shown strong performance on remote sensing datasets. However, because these models are trained on heterogeneous data and vary across tasks, designing a unified model that performs well in captioning, visual question answering (VQA), and visual grounding remains challenging. In this work, we evaluate several models on the VRS Bench and NWPU-VHR-10 datasets. The EarthMind model demonstrates strong results in both captioning and VQA. For grounding, we propose multiple pipelines - RemoteSAM-SAM-v1, RemoteSAM-SAM-v2, and DiffuSAM - and ultimately adopt a majority-voting ensemble across EarthMind, RemoteSAM, SAM3, Falcon, RemoteSAM-SAM3-v1, RemoteSAM-SAM3-v2, and DiffuSAM predictions. Our unified, modular pipeline integrates advanced SAM variants with multimodal LLMs to jointly perform captioning, VQA, and grounding. It achieves 82% accuracy on captioning and 83.32% on VQA, with 90.94%, 52.04%, and 92.06% for binary, numeric, and semantic question types respectively. For grounding, it attains 64.94% accuracy. By combining diverse VLMs with our custom RemoteSAM-SAM3 models through ensemble majority voting, the system delivers more accurate and consistent remote-sensing understanding than task-specific approaches.
Sep 23, 2026

AnchorReasoning: A Visual Grounding and Causal Reasoning Dataset in Long-Tail Autonomous Driving Scenarios

Vision-language models (VLMs) offer a promising approach to long-tail autonomous driving, but existing driving datasets provide limited supervision for connecting decision-critical visual evidence with reasoning and planning. We introduce AnchorReasoning, a visually grounded reasoning dataset built on WOD-E2E, containing 416,119 annotated frames and 395,379 decision-critical elements across four major categories and 19 fine-grained types. Each frame is organized as a visually grounded chain-of-thought (VG-CoT) that links decision-critical element identification and localization, element attributes and implications, driving-action rationale, and action and trajectory planning. We further develop a curriculum supervised fine-tuning strategy that progressively learns these hierarchical capabilities, together with an object-size-aware grounding metric for evaluating localization quality. Experiments across eight general-purpose, embodied-AI, and AV-specific backbones show that VG-CoT supervision improves grounded reasoning and trajectory prediction. Across models, 5-s ADE and FDE decrease by 7.84 and 11.86, while RFS Frame and Cluster improve by 1.66 and 1.70. These gains are achieved with 18.5 fewer reasoning tokens and 0.32 s/frame lower inference latency on average, demonstrating the value of visually grounded, decision-focused supervision for VLM reasoning and planning in long-tail autonomous driving.
Sep 23, 2026

A Unified Framework and Dataset for Oriented Object Visual Grounding in Remote Sensing

Visual grounding in remote sensing images aims to locate objects described by referring expressions. Most existing methods predict horizontal bounding boxes, which are often inaccurate for objects with arbitrary orientations. To address this limitation, we introduce O2^2-VG, a family of models for oriented object visual grounding with three complementary designs. Specifically, O2^2-VG-Trans is a cross-modality transformer for oriented object visual grounding. It establishes a strong discriminative foundation for the model family. Building upon it, O2^2-VG-Uni predicts universal oriented proposals for possible foreground objects without specific text prompts. It also supports object retrieval through cached proposal embeddings. Using these universal oriented proposals as input prompts, O2^2-VG-VLM is an autoregressive vision-language model. It generates oriented box token blocks in parallel through multi-token prediction. In addition, we construct DIOR-R-RSVG, a dataset for oriented object visual grounding in remote sensing images. It provides image, expression, and oriented box triplets for training and evaluation. Together, the O2^2-VG family provides a flexible framework that spans discriminative transformers and generative vision-language models. It achieves superior performance across multiple benchmarks. Code is available at https://github.com/wokaikaixinxin/ai4rs and https://github.com/wokaikaixinxin/Eagle_o2_vg.
Sep 22, 2026

Pro-Bench: Prompt-Robust Open-Vocabulary Visual Grounding Across Real-World Heterogeneous Environments

Open-vocabulary visual grounding enables robots to localise task-relevant entities from natural-language queries without dependence on predefined perceptual taxonomies. However, existing benchmarks largely rely on short category labels and web-scraped imagery, leaving it unclear whether open-vocabulary models can robustly ground diverse queries and visual conditions under real deployments. We introduce Pro-Bench, a prompt-conditioned benchmark for open-vocabulary visual grounding in heterogeneous, real-world environments. Pro-Bench includes 13k+13k+ RGB frames from independent robotic domains (subterranean, industrial, indoor, outdoor, urban), with 74.5k74.5k manual instance annotations and 515515 target queries covering categorical, attributive, relational, affordance, state, part-whole, negative, and compositional semantics. We benchmarked 1616 open-vocabulary model configurations in strict zero-shot inference, measuring localisation accuracy across IoU thresholds, end-to-end inference latency, prompt-induced performance variation, and target recovery consistency. Our results show that prompt-robustness is strongly architecture-dependent. Most model configurations (10/1610/16) perform best with short category labels, whereas free-form queries yield the highest accuracy for only one. Moreover, similar aggregate mAP can conceal substantial differences in consistent target recovery across reformulations. Pro-Bench enables systematic evaluation of these gaps and supports prompt-robust visual grounding. Pro-Bench: https://pro-bench.github.io/.
Sep 21, 2026

MM-VeriRec: Failure-Guided Fusion for Verifiable Agentic Multimodal Recommendation

Images often carry recommendation constraints that text metadata only hints at. A movie may need to look dark, a product may need a minimal style, and a visually impossible request should be rejected. Agentic multimodal recommenders must reason over text-image evidence, decide when visual evidence is decisive, and abstain when no valid action exists. We introduce MM-VeriRec, a verifiable multimodal recommendation protocol and failure-guided fusion method for hidden visual constraints, image-text mismatch, and impossible-task abstention. MM-VeriRec builds tasks from real movie-poster and product-image datasets, verifies each recommendation with deterministic visual attributes, and converts failures into actionable labels: text-trap following, visual ignorance, and false acceptance. Fusion should not merely concatenate modalities, but should diagnose which modality failed and route to the appropriate repair. Across MM-ML 1M and Amazon Reviews datasets, stronger text and vision embeddings improve retrieval but do not remove these failure modes, whereas failure-guided fusion does. The adaptive attribute gate reads the same tags the verifier checks and its scores are verifier-aligned upper bounds testing whether the taxonomy routes to the correct repair. More informative is transfer under a non-aligned gate: an independently derived leave-one-out CLIP detector still reaches 0.7028 and 0.6111 visual-grounded success, above both a VBPR baseline and plain fusion. The text-versus-visual gap reproduces across two LLM families, and the repair that helps differs by domain. MM-VeriRec is both a benchmark and a practical diagnostic loop for trustworthy agentic multimodal recommendation.
Sep 21, 2026

DeCo: Efficient Decouple-to-Couple Learning for Multi-Task Visual Grounding

Multi-task visual grounding requires models to jointly understand linguistic semantics and perform accurate visual localization and segmentation. Despite the success of multimodal large language models, effectively adapting them to multiple grounding objectives remains challenging. Existing methods commonly enforce task cooperation through shared representations, while overlooking the intrinsic conflict between task-oriented feature interests. In this paper, we introduce DeCo\textbf{DeCo}, an efficient De\textbf{De}couple-to-Co\textbf{Co}uple learning framework that resolves this dilemma through a two-stage paradigm: task-specific representation decoupling followed by complementary prior coupling. Specifically, we first propose Task-aware Semantic Decoupling (TSD) to route shared visual cues into individual features under salient word-level guidance, alleviating representation interference between localization and segmentation. Furthermore, we observe that segmentation naturally provides informative localization priors due to dense supervision. Based on this insight, we introduce Hybrid Prior Coupling (HPC), which integrates sentence-level semantic prior with mask-derived spatial prior for enhanced grounding. Built upon a frozen multimodal encoder, DeCo requires lightweight trainable parameters while achieving strong generalization across multiple grounding objectives. Extensive experiments on RefCOCO/+, G-Ref, ReferIt, Flickr, DIOR-RSVG, SARVG1.0, RRSIS-D, RIS-LAD, and RefDIOR demonstrate that DeCo achieves state-of-the-art performance on both natural and remote sensing benchmarks. The code and models are available at https://github.com/xiaoqiang-lu/DeCo.
Sep 20, 2026

Layer-Aware Position Embeddings for Visual Token Pruning in Multimodal Large Language Models

Multimodal large language models (MLLMs) incur substantial computational overhead due to the reliance on hundreds of visual tokens to represent images. While token pruning has emerged as a promising approach to reduce the inference cost of MLLMs, existing methods typically reassign position embeddings to the retained tokens using either sparse or continuous position embeddings, each introducing distinct limitations. Sparse position embeddings tend to decrease the attention value allocated to visual tokens, thereby degrading the perception capability of MLLMs, whereas continuous position embeddings disrupt the original spatial correspondence of visual tokens, leading to weakened grounding capability. To mitigate this issue, we perform layer-wise analysis of the language decoder and observe that intermediate layers play a critical role for maintaining the grounding capability of MLLMs under token pruning. Based on this observation, we propose a layer-aware position embedding strategy, which switches to sparse position embeddings at grounding-sensitive layers while maintaining continuous position embeddings elsewhere. Extensive experiments across representative pruning methods and diverse benchmarks demonstrate that our approach improves the comprehensive multimodal performance of pruned MLLMs compared with standard sparse and continuous position embeddings.
Sep 19, 2026

A Design-Intent-Preserving Agent Harness for Parametric CAD Modeling

Parametric CAD modeling requires not only matching the target shape, but also preserving design intent under parameter edits. However, most existing methods focus on improving static shape generation accuracy, while the dependencies that govern later edits are often overlooked. To tackle this issue, we present DIP-CAD, a design-intent-preserving agent harness for generating parametric CAD models from images. DIP-CAD combines vision-language model reasoning with CAD kernel operations to establish dependencies that encode the design intent. In parametric CAD, these dependencies are mainly established through geometry references in modeling commands and constraints in parametric sketches. At the command level, ID-based explicit geometry reference binds modeling commands to selected faces, edges, or vertices. At the sketch level, a local-coordinate bridge ensures accurate sketch placement, providing the basis for correctly establishing sketch constraints. Constraints among sketch primitives and constraints to external projected geometry further preserve both internal sketch relationships and dependencies on existing geometry. To provide a more comprehensive data foundation for parametric CAD modeling tasks, we introduce the Geometry Explicit Reference Dataset (GERD), whose structured data format links stepwise modeling commands to intermediate CAD models through explicit geometry references. On GERD-EVL and a DeepCAD test subset, DIP-CAD improves mIoU for static model generation by 11.1% and 5.6%, respectively. In parameter-editing evaluations, the corresponding mIoU improvements are 7.0% and 4.2%. Case studies further demonstrate how parameter edits drive shape updates while preserving design intent.
Sep 17, 2026

MaskHarness-WAM: Instance-Grounded Harnessing for Long-Horizon Robot Manipulation

Long-horizon robot manipulation requires not only stable local visuomotor control, but also continuous target tracking and reliable task progress assessment throughout execution. This challenge becomes particularly critical when multiple objects share identical appearances and must be manipulated in a prescribed order. In such scenarios, relying solely on a limited-horizon manipulation policy is often insufficient to determine which instance should be operated on and when the task should transition to the next stage. To address this challenge, we propose MaskHarness-WAM, an instance-grounded harness for long-horizon manipulation. The proposed system connects high-level task planning with low-level manipulation policies through target masks, while leveraging visual feedback for subtask scheduling and continuous execution. Since each subtask corresponds to a different target instance, the low-level policy requires a newly established initial target mask under the updated scene at each subtask transition. The harness continuously re-observes the environment, generates, and verifies the target mask at subtask boundaries, thereby updating the instance-level spatial condition provided to the low-level policy. Furthermore, the system advances the manipulation process by switching target instances according to the verified completion status of each subtask. Experiments on a real robot platform demonstrate that MaskHarness-WAM substantially outperforms limited-horizon policies on sequential multi-object manipulation, showing its effectiveness in extending local manipulation skills to reliable long-horizon execution.
Sep 15, 2026

SAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination Mitigation

Multimodal large language models (MLLMs) have made strong progress on visual question answering and image captioning, yet they still produce fluent claims about objects, attributes, or relations that are not grounded in the image. Many remedies either modify decoding at test time, which adds latency, or fine tune with preferences such as DPO variants, which teach which answer is preferred but not when the model's own answer is unreliable. We argue that calibrated self assessment is the missing signal. We introduce Savor, a training framework that (i) augments the output schema with token and answer confidence, (ii) optimises the policy with a Group Relative Policy Optimisation (GRPO) objective that penalises calibration error and poor abstention decisions, and (iii) uses the learned confidence at inference time to revisit visual evidence only when the model is uncertain. Experiments on POPE, HallusionBench, AMBER and MMHal-Bench across two recent backbones (InternVL3-8B and Qwen3-VL-8B) show that Savor reduces hallucination while preserving general capability on MME and MMBench, with lower Expected Calibration Error than DPO and decoding baselines.
Sep 2, 2026

TempoGround: State-Aware Streaming Visual Grounding with Vision-Language Models

Visual grounding maps language referents to spatial targets and is central to open-vocabulary perception with vision-language models. Existing methods have made substantial progress on single-frame and video-based visual grounding, yet under streaming inputs they still suffer from identity drift, cross-frame inconsistency, and fragile localization under partial occlusion. To address these issues, we present TempoGround, a VLM-native framework that detects cross-frame object correspondence and explicitly models object presence states, thereby enabling accurate and consistent visual grounding under streaming inputs. The key is a curriculum prediction mechanism guided by state-aware cross-frame correspondence: TempoGround resolves 2D instance association, predicts whether each object newly enters, continues in, or leaves the view, decodes the 2D box, and then lifts it to a camera-frame 3D box. As token-level supervision alone cannot capture the geometric objectives of streaming grounding, we further introduce Streaming Grounding Reinforcement (SGR), which optimizes TempoGround with verifiable Grounding, Identity, and Consistency rewards, jointly reinforcing persistent localization and temporally consistent predictions. We carefully design a three-stage training strategy and train TempoGround on large-scale data. We evaluate visual grounding under causally streaming inputs on multiple challenging benchmarks: TempoGround improves [email protected] and [email protected] by 4.4 and 0.5 on average, and [email protected] and AP_3D by 6.2 and 7.5, respectively. These results demonstrate that TempoGround provides a practical foundation for visual grounding under streaming inputs.
Sep 1, 2026

Part Grounding, Not Action Knowledge: Locating the Bottleneck in VLM Affordance Prediction

Benchmarks agree that vision-language models reason poorly about low-level manipulation, but an aggregate accuracy score does not say which step fails. We separate two steps that affordance questions conflate: identifying which part of an object to act on, and knowing what action that part requires. Across 19 articulated objects we asked eight models, spanning three developers, what motion a robot should apply. Under an open prompt, push was produced once in 64 evaluations where it was correct, despite being correct for 8 of 19 objects and appearing in the offered label set every time. Inspecting the outputs showed why: models described a different part than the one being scored, e.g. explaining how to pick up a camera rather than press its button. Naming the target part raises action accuracy by 0.32 to 0.63 for every model, from 0.158-0.474 to 0.684-0.947, and push recall from 0-1/8 to 7-8/8. No model beats a constant answer that ignores the image under the open prompt; once the part is named, all eight do. Asked to describe the same part in free prose with no label set, models produce pressing language for 6 to 8 of 8. These results are hard to reconcile with missing action knowledge, and instead point to part grounding as the dominant bottleneck, a pattern that holds across all three model families and does not diminish with capability. Naming the part supplies the grounding variable, so this bounds what a perfect part detector would offer rather than demonstrating a general model of mechanics. Two supporting results agree: on real photographs only three of eight models localize grasp points better than a constant baseline, and on rendered objects none do. We also document two measurement errors of our own, a threshold that let a constant baseline score 0.929 and a labelling rule wrong on 4 of 19 objects, both caught only by testing our numbers against trivial alternatives.
Aug 31, 2026

Semantic-Spatial Discriminability Enhancement for Generalized Visual Grounding

Generalized Visual Grounding (GVG) task aims to localize targets in an image based on referring expressions, extends the classical visual grounding paradigm by integrating multi-target and non-target scenarios. Previous methods typically rely on global semantic matching or coarse-grained region interactions for localization, where the discriminative cues are primarily derived from sentence-level semantics or regional context. In complex multi-target scenarios, such approaches tend to confuse visually similar targets, making it difficult to establish stable instance-level decision boundaries. To address these limitations, this paper proposes a novel Semantic-Spatial Discriminability Enhancement (SSDE) framework for generalized visual grounding, which aims to enhance the discriminative ability on fine-grained semantics and spatial localization, improving both cross-modal understanding and instance-level grounding. Specifically, to enhance the semantic discriminability of query representations at the fine-grained level, we propose a Semantic Discriminability Enhancement (SeDE) module, which leverages spatially guided cross-attention to disentangle fine-grained target-relevant visual attributes and integrates them with the textual subject semantics. Furthermore, to strengthen the spatial discriminability of the referred targets, we introduce a Spatial Discriminability Enhancement (SpDE) module, which models an instance center density map to characterize the spatial distribution of targets, and explicitly constructs instance separation structures in the spatial domain by employing them as an auxiliary supervision signal. Extensive experiments show that SSDE achieves superior performance on ten datasets across both classic and generalized visual grounding tasks.
Aug 26, 2026

PointRL: Learning Point-Level Vision-Language Grounding from Verifiable Annotation Evidence

Vision-language models (VLMs) increasingly rely on point coordinates as a compact and executable interface for visual grounding in GUI interaction, robotic manipulation, and interactive visual systems. However, learning reliable pointing behavior remains difficult because the supervision space is inherently non-unique: many coordinates may be valid within the same target region, while multi-instance instructions require target coverage, count consistency, and duplicate suppression. This work presents PointRL, a verifiable reinforcement learning framework that learns point-level grounding from existing heterogeneous annotation evidence. PointRL converts bounding boxes, masks, and instance labels into pointing instructions, while retaining their target supports, instance membership, and set constraints as hidden verifier evidence, i.e., annotations kept outside the prompt and used by a deterministic checker to score predictions. The proposed reward evaluates parseability, point validity, instance coverage, cardinality consistency, and redundant or missing predictions. On PointArena, PointRL improves the overall accuracy of Qwen3.5-4B from 56.11% to 65.58%. Further evaluations on RoboSpatial, BLINK, and Ref-Adv show same-backbone gains on the evaluated external benchmarks, suggesting that verifiable point-level feedback may benefit spatial grounding in these settings.
Aug 25, 2026

ReGround-Surg: Reliability-Guided Anchor Grounding for Referring Surgical Video Segmentation

Referring surgical video segmentation requires segmenting a target instrument or tissue region across video frames according to a natural language expression. Recent Segment Anything Model 2 (SAM2) based two-stage methods (e.g., ReSurgSAM2) first ground the referred target in an initial or selected frame, then propagate the selected mask via tracking. Although effective, their performance is highly sensitive to the quality of the initial grounded mask: once an incorrect anchor is selected, subsequent tracking tends to propagate the error. This issue is especially challenging in surgical videos due to visually similar instruments, occlusion, and complex tissue-tool interactions. To address this issue, we propose ReGround-Surg, a lightweight reliability-guided anchor grounding framework to improve SAM2-based referring surgical video segmentation. It first predicts a text-conditioned spatial reliability map from the referring expression and current-frame visual features. The map is then reused in two complementary branches: a Gated Side Adapter enhances expression-relevant visual regions before text-to-vision fusion, while a Reliability-Weighted Vision-to-Text Attention module suppresses off-target visual evidence during prompt-token aggregation. Experiments on Ref-EndoVis17 and Ref-EndoVis18 show consistent improvements over state-of-the-art methods across three evaluation splits with negligible speed reduction. Code is publicly available at https://github.com/JiaxinWen1/ReGround-Surg.
Aug 25, 2026

PlaceSeek: Human-Centered Geospatial Retrieval of Urban Outdoor Places via Semantic Grounding and Affective Alignment

People search for urban outdoor places not only by category or function, but also by what activities a place can support and how it is perceived. Existing geospatial retrieval remains largely POIcentric and metadata-driven, making it difficult to satisfy openended, affective, or activity-oriented needs. We present PlaceSeek, a human-centered outdoor place retrieval framework that maps natural-language queries to geolocated street-view imagery. PlaceSeek introduces an intent-aware retrieval mechanism that decomposes user queries into functional and affective sub-intents. A Semantic Grounding Module verifies whether candidate street-view results contain the physical evidence needed to support the intended activity, while an Affective Alignment Module re-ranks physically valid candidates using a LoRA-adapted vision-language model trained on human urban perception judgments. We evaluate PlaceSeek on 31,956 street-view locations in Milan across 10 naturallanguage queries annotated by five human evaluators. PlaceSeek achieves 88.0% Precision@5, a mean match score of 3.39/4.0, and 0.920 nDCG@5, outperforming CLIP, fine-tuned CLIP, SigLIP, and a VQA-based baseline. Ablation results show that physical grounding is essential for retrieval validity, while affective alignment improves ranking quality among physically valid candidates. These findings highlight that complex urban spatial queries require modeling both verifiable visual evidence and human perceptual preferences. PlaceSeek provides a potential framework for human-centered nextgeneration geospatial retrieval systems.
Aug 25, 2026

When Seeing Is Not Enough: Benchmarking Interactive Visual Grounding in LVLMs

Visual grounding is typically evaluated as a one-shot mapping from an informative referring expression to a visual target. This formulation misses a central property of real-world reference: initial referring expressions are often incomplete or ambiguous, requiring participants to establish shared understanding through interaction. We introduce a controlled evaluation framework for interactive visual grounding in large vision-language models (LVLMs), varying how much target information is provided upfront and how much must be acquired through dialogue. Across four human-grounded visual contexts and four interaction protocols, current LVLMs perform significantly below task-level human baselines. Interaction can help when follow-up questions refine or repair an initial target description. Performance is lowest when no initial description is provided and target information must be acquired through questions, indicating that proactive question-driven grounding remains difficult. LVLMs are also poorly calibrated, often reporting confidence that exceeds their empirical accuracy. Follow-up studies confirm these patterns across varied description sources (human versus AI), reasoning efforts, repeated interactions, description providers, and visual contexts. Overall, interactive visual grounding remains challenging, requiring visual matching, information seeking and synthesis.