Vision-Language Grounding

Vision-Language-Action (VLA) models achieve strong performance in robotic manipulation by leveraging pre-trained vision-language backbones. However, in downstream robotic settings, they are typically fine-tuned with limited data, leading to overfitting to specific instruction formulations and leaving robustness to paraphrased instructions underexplored. To study this gap, we introduce LIBERO-Para, a controlled benchmark that independently varies action expressions and object references for fine-grained analysis of linguistic generalization. Across seven VLA configurations (0.6B-7.5B), we observe consistent performance degradation of 22-52 pp under paraphrasing. This degradation is primarily driven by object-level lexical variation: even simple synonym substitutions cause large drops, indicating reliance on surface-level matching rather than semantic grounding. Moreover, 80-96% of failures arise from planning-level trajectory divergence rather than execution errors, showing that paraphrasing disrupts task identification. Binary success rate treats all paraphrases equally, obscuring whether models perform consistently across difficulty levels or rely on easier cases. To address this, we propose PRIDE, a metric that quantifies paraphrase difficulty using semantic and syntactic factors. Our benchmark and corresponding code are available at: https://github.com/cau-hai-lab/LIBERO-Para

Remote sensing visual grounding (RSVG) aims to localize specific targets in remote sensing images using natural language expressions. However, existing methods are restricted to single-sensor domains, i.e., either optical or synthetic aperture radar (SAR), limiting their real-world applicability. In this paper, we introduce the Cross-Domain RSVG (CD-RSVG) task and construct OptSAR-RSVG, the first large-scale benchmark dataset for this setting. To tackle the challenges of cross-domain feature modeling, computational inefficiency, and fine-grained semantic discrimination, we propose OptiSAR-Net++. Our framework features a patch-level Low-Rank Adaptation Mixture of Experts (PL-MoE) for efficient cross-domain feature decoupling. To mitigate the substantial computational overhead of Transformer decoding frameworks, we adopt a CLIP-based contrastive paradigm and further incorporate dynamic adversarial negative sampling, thereby transforming generative regression into an efficient cross-modal matching process. Additionally, a text-guided dual-gate fusion module (TGDF-SSA) and a region-aware auxiliary head are introduced to enhance semantic-visual alignment and spatial modeling. Extensive experiments demonstrate that OptiSAR-Net++ achieves SOTA performance on both OptSAR-RSVG and DIOR-RSVG benchmarks, offering significant advantages in localization accuracy and efficiency. The model and dataset have been made publicly available at https://github.com/JunDong-dev/OptiSAR-Net-PlusPlus.

Many multimodal tasks, such as image captioning and visual question answering, require vision-language models (VLMs) to bind objects with their properties and spatial relations. Yet it remains unclear where and how such associations are computed within VLMs. In this work, we show that VLMs rely on two concurrent mechanisms to represent spatial variable binding. In the language model backbone, intermediate layers represent content-independent spatial relations on top of visual tokens corresponding to objects. However, this mechanism plays only a secondary role in shaping model predictions. Instead, the dominant source of spatial information originates in the vision encoder, whose representations encode the layout of objects and are directly exploited by the language model backbone. Notably, this spatial signal is distributed globally across visual tokens, extending beyond object regions into surrounding background areas. We validate the generalization of our findings to complex natural images from the COCO dataset, where globally amplifying the vision-derived spatial representations across all image tokens corrects spatial variable binding failures across models of various sizes. Together, our results clarify how spatial variable binding is computed within VLMs and highlight the central role of vision encoders in enabling it.

Precise spatial understanding in Earth Observation is essential for translating raw aerial imagery into actionable insights for critical applications like urban planning, environmental monitoring and disaster management. However, Multimodal Large Language Models exhibit critical deficiencies in fine-grained spatial understanding within Remote Sensing, primarily due to a reliance on limited or repurposed legacy datasets. To bridge this gap, we introduce a large-scale dataset grounded in verifiable cadastral vector data, comprising 3.8 million annotated objects across 510k high-resolution images with 135 granular semantic categories. We validate this resource through a comprehensive instruction-tuning benchmark spanning seven spatial reasoning tasks. Our evaluation establishes a robust baseline using a standard LLaVA architecture. We show that while current RS-specialized and commercial models (e.g., Gemini) struggle in zero-shot settings, high-fidelity supervision effectively bridges this gap, enabling standard architectures to master fine-grained spatial grounding without complex architectural modifications.

Video Temporal Grounding (VTG) localizes the temporal boundaries of query-relevant moments in long, untrimmed videos, making video-language-model prohibitively expensive. While recent training-free token pruning has shown success in video question answering, naively applying these objectives to VTG causes drastic degradation, as VTG crucially depends on boundary-sensitive evidence and cross-frame reasoning chains. We therefore identify two VTG-specific pruning principles: evidence retention, which keeps query-critical patches especially around event boundaries, and connectivity strength, which preserves cross-frame connectivity for long-range evidence aggregation. Building on these insights, we propose SemVID, a training-free pruning framework that constructs a compact yet coherent token subset with complementary semantic roles. SemVID first allocates per-frame budgets by balancing query relevance and inter-frame variation to avoid over-pruned segments, and then selects three types of tokens: object tokens for diverse query-critical evidence, motion tokens to capture meaningful transitions and serve as cross-frame relays, and context tokens for scene continuity. Extensive experiments show that SemVID achieves a strong accuracy-efficiency trade-off, retaining up to 95.4% mIoU with only 12.5% visual tokens and delivering up to a 5.8x prefill speedup, consistently outperforming prior methods under the same budgets. Our code is available at https://github.com/JiaqiLi404/SemVID

In real scenarios, videos can span several minutes or even hours. However, existing research on spatio-temporal video grounding (STVG), given a textual query, mainly focuses on localizing targets in short videos of tens of seconds, typically less than one minute, which limits real-world applications. In this paper, we explore Long-Form STVG (LF-STVG), which aims to locate targets in long-term videos. Compared with short videos, long-term videos contain much longer temporal spans and more irrelevant information, making it difficult for existing STVG methods that process all frames at once. To address this challenge, we propose an AutoRegressive Transformer architecture for LF-STVG, termed ART-STVG. Unlike conventional STVG methods that require the entire video sequence to make predictions at once, ART-STVG treats the video as streaming input and processes frames sequentially, enabling efficient handling of long videos. To model spatio-temporal context, we design spatial and temporal memory banks and apply them to the decoders. Since memories from different moments are not always relevant to the current frame, we introduce simple yet effective memory selection strategies to provide more relevant information to the decoders, significantly improving performance. Furthermore, instead of parallel spatial and temporal localization, we propose a cascaded spatio-temporal design that connects the spatial decoder to the temporal decoder, allowing fine-grained spatial cues to assist complex temporal localization in long videos. Experiments on newly extended LF-STVG datasets show that ART-STVG significantly outperforms state-of-the-art methods, while achieving competitive performance on conventional short-form STVG. Our code is at: https://github.com/HengLan/ART-STVG.

Crop monitoring is essential for precision agriculture, but current systems lack high-level reasoning. We introduce a novel, modular framework that uses a Vision Language Model (VLM) to guide robotic task planning by actively querying heterogeneous data sources, including enriched RGB camera feeds and 2D semantic occupancy maps, interleaved with robotic action primitives. We contribute a comprehensive benchmark for short- and long-horizon crop monitoring tasks in monoculture and polyculture environments. Our results show that while zero-shot VLMs perform robustly for short-horizon tasks (achieving 87% success, comparable to human experts), success drops significantly to under 10% for complex long-horizon, multi-target tasks. Despite this decline, task completion rates remain above 76% under noiseless conditions. Critically, the system degrades when relying on noisy semantic maps, demonstrating a key limitation in current VLM context grounding for sustained robotic operations. This work offers a deployable framework and critical insights into VLM capabilities and shortcomings for complex agricultural robotics.

While Vision-Language Models (VLMs) have achieved notable progress in computational pathology (CPath), the gigapixel scale and spatial heterogeneity of Whole Slide Images (WSIs) continue to pose challenges for multimodal understanding. Existing alignment methods struggle to capture fine-grained correspondences between textual descriptions and visual cues across thousands of patches from a slide, compromising their performance on downstream tasks. In this paper, we propose PathFLIP (Pathology Fine-grained Language-Image Pretraining), a novel framework for holistic WSI interpretation. PathFLIP decomposes slide-level captions into region-level subcaptions and generates text-conditioned region embeddings to facilitate precise visual-language grounding. By harnessing Large Language Models (LLMs), PathFLIP can seamlessly follow diverse clinical instructions and adapt to varied diagnostic contexts. Furthermore, it exhibits versatile capabilities across multiple paradigms, efficiently handling slide-level classification and retrieval, fine-grained lesion localization, and instruction following. Extensive experiments demonstrate that PathFLIP outperforms existing large-scale pathological VLMs on four representative benchmarks while requiring significantly less training data, paving the way for fine-grained, instruction-aware WSI interpretation in clinical practice.

Satellite imagery differs from natural images in viewpoint, resolution, scale variation, and the prevalence of small objects -- demanding both region-level spatial reasoning and holistic scene understanding. Existing remote-sensing approaches are fragmented: dual-encoder retrieval models scale well but cannot interleave modalities, whereas generative assistants support grounding, yet are inefficient for retrieval. Benchmarks mirror this split: interleaved evaluations mainly target generative assistants, while cross-modal retrieval benchmarks target dual encoders. To bridge this gap, we introduce \textbf{RSMEB}, a unified remote sensing benchmark that evaluates cross-modal and interleaved retrieval across 21 tasks under a single ranking protocol, enabling comprehensive comparison of retrieval models on region- and geo-aware capabilities as well as conventional retrieval. As a strong reference baseline, we present \textbf{VLM2GeoVec}, an instruction-conditioned, single-encoder interleaving formulation tailored to remote sensing that packs image, text, bounding-box, and geo-coordinate tokens into one sequence and learns a unified embedding via contrastive training. Across RSMEB, VLM2GeoVec achieves $\textbf{26.6\%}$ P@1 in region-caption retrieval ($\textbf{+25}$ percentage points), $\textbf{32.5\%}$ in referring-expression retrieval ($\textbf{+19}$), and $\textbf{17.8\%}$ in semantic geo-aware retrieval (\textbf{>3}$$\times prior best), while remaining competitive in conventional scene classification and text--image retrieval in zero-shot settings. Together, the proposed suite and reference baseline standardize evaluation and deliver a unified embedder for scalable retrieval and region-/geo-aware grounding. The code, the model checkpoints, and the data are available at https://github.com/emasa/VLM2GeoVec.

The rapid advancement of long-context vision language models (LCVLMs) has led to a significant expansion of their context windows. However, an extended context window does not guarantee the effective utilization of the context, posing a critical challenge for real-world applications. Current evaluations of such long-context faithfulness in multimodal settings remain limited to short contexts. To bridge this gap, we introduce MMLongCite, the first benchmark evaluating the faithfulness of LCVLMs via multimodal citation generation. MMLongCite features 2,280 examples across 8 tasks and diverse modalities (image, video, interleaved), with context lengths scaled from 16K to 128K tokens. To test spatial localization capabilities of LCVLMs, we also introduce MMLongCite-HR, evaluating fine-grained visual grounding amidst dense pixel spaces. Through extensive benchmarking of cutting-edge LCVLMs, we provide a systematic analysis of current multimodal citation capabilities. Our results reveal a significant discrepancy between answer correctness and citation faithfulness. We also conduct attention pattern investigations and in-depth error analyses to reveal the underlying phenomena of failures in LCVLMs. MMLongCite establishes a rigorous foundation for diagnosing and advancing the faithfulness of LCVLMs. We hope our findings provide meaningful insights to drive further improvements in the long-context capabilities of LCVLMs.

Multimodal large language models (MLLMs) often miss small details and spatial relations in cluttered scenes, leading to errors in fine-grained perceptual grounding. We introduce AttWarp, a lightweight method that allocates more resolution to query-relevant content while compressing less informative areas, all while preserving global context. At test time, the approach uses an MLLM's cross-modal attention to perform rectilinear warping of the input image, reallocating spatial resolution toward regions the model deems important, without changing model weights or architecture. This attention-guided warping preserves all original image information but redistributes it non-uniformly, so small objects and subtle relationships become easier for the same model to read while the global layout remains intact. Across five benchmarks (TextVQA, GQA, DocVQA, POPE, MMMU) and four MLLMs (LLaVA, Qwen-VL, InternVL, and InstructBLIP), AttWarp consistently improves accuracy, strengthens compositional reasoning, and reduces hallucinations, outperforming four competitive baselines that manipulate raw images at test time. Together, these results show that attention-guided warping prioritizes information relevant to the query while preserving context, and that the same MLLMs perform better when given such warped inputs.

Vision-language models (VLMs) have advanced multimodal perception, demonstrated by open-vocabulary object detection with simple language queries. State-of-the-art VLMs still struggle to handle complex queries involving descriptive attributes and relational clauses. To address this problem, we propose restructuring linguistic representations according to the hierarchical relations within sentences for language-based object detection. A key insight is that textual tokens should be disentangled into core components-objects, attributes, and relations-and aggregated into hierarchically structured sentence-level representations. Building on this principle, we introduce the TaSe (Talk in Pieces, See in Whole) framework with three main contributions: (1) a hierarchical synthetic captioning dataset spanning three tiers from category names to descriptive sentences; (2) the three-component disentanglement module guided by a novel disentanglement loss function, transforms text embeddings into subspace compositions; and (3) aggregating disentangled components into hierarchically structured embeddings guided by the proposed hierarchical objectives. Experimental results under the OmniLabel benchmark show a 24% performance improvement, demonstrating the importance of linguistic compositionality.

Most existing approaches to referring segmentation achieve strong performance only through fine-tuning or by composing multiple pre-trained models, often at the cost of additional training and architectural modifications. Meanwhile, large-scale generative diffusion models encode rich semantic information, making them attractive as general-purpose feature extractors. In this work, we introduce a new method that directly exploits features (attention scores) from diffusion transformers for downstream tasks, requiring neither architectural modifications nor additional training. To systematically evaluate these features, we extend benchmarks with vision-language grounding tasks spanning both images and videos. Our key insight is that stop words act as attention magnets: they accumulate surplus attention and can be filtered to reduce noise. Moreover, we identify global attention sinks (GAS) emerging in deeper layers and show that they can be safely suppressed or redirected onto auxiliary tokens, leading to sharper and more accurate grounding maps. We further propose an attention redistribution strategy, where appended stop words partition background activations into smaller clusters, yielding sharper and more localized heatmaps. Building on these findings, we develop RefAM, a simple training-free grounding framework that combines cross-attention maps, GAS handling, and redistribution. Across zero-shot referring image and video segmentation benchmarks, our approach achieves strong performance and surpasses prior methods on most datasets, establishing a new state of the art among training-free methods, without task-specific training or architectural modification. For video, we localize the referent from the spatio-temporal features of a video diffusion transformer via a first-frame query that is then propagated; we therefore do not explicitly resolve temporal (which-frame) expressions.

We introduce VMMU, a Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark designed to evaluate how vision-language models (VLMs) interpret and reason over visual and textual information beyond English. VMMU consists of 2.5k multimodal questions across 7 tasks, covering a diverse range of problem contexts, including STEM problem solving, data interpretation, rule-governed visual reasoning, and abstract visual reasoning. All questions require genuine multimodal integration, rather than reliance on text-only cues or OCR-based shortcuts. We evaluate a diverse set of state-of-the-art proprietary and open-source VLMs on VMMU. Despite strong Vietnamese OCR performance, proprietary models achieve only 66% mean accuracy. Further analysis shows that the primary source of failure is not OCR, but instead multimodal grounding and reasoning over text and visual evidence. Code and data are available at https://vmmu-bench.github.io/

Video Temporal Grounding (VTG) aims to localize specific video segments corresponding to natural language queries. While recent Large Vision-Language Models (LVLMs) employ Reinforcement Learning to generate Chains-of-Thought (CoT), they typically rely solely on outcome-based supervision. Consequently, this often leads to hallucinations, where the reasoning process becomes disconnected from the visual content and the final prediction. Existing attempts to mitigate this by relying on external supervision from larger models or separate reward models are computationally expensive and prone to rigid patterns. To address these challenges, we propose TAR (Temporal Anchor-Constrained Reasoning), a framework that introduces the temporal anchor (T-anchor) as a transparent and auditable checkpoint mechanism. T-anchor enforces progressive refinement within the CoT, compelling the model to continuously ground its intermediate thoughts in visual evidence and iteratively calibrate temporal predictions, thereby significantly enhancing the faithfulness and autonomy of the reasoning process and final accuracy. Furthermore, we introduce a bootstrapping paradigm that automatically harvests high-quality CoT data using only a standard 7B model, eliminating the dependency on ultra-large models. Extensive experiments demonstrate that TAR achieves state-of-the-art performance and generates faithful, autonomous, and progressively refined reasoning traces.

Forensic deepfake analysis demands more than binary classification: investigators need region-grounded natural language explanations they can verify against the image. Multimodal large language models (MLLMs) are a natural fit, but pretrained MLLMs fail systematically, producing globally coherent text that misses the small localized cues defining manipulations. We argue this is an inductive bias problem rather than a capacity issue: the image-text contrastive objective training MLLM visual encoders optimizes for whole-image semantic summaries, not patch-level forensic detail. The same mismatch explains why prior deepfake reasoning methods target either face manipulation or fully AI-generated content, never both. We propose FORGE, which addresses the mismatch by routing a second visual stream into the language model from a Vision-Only Model (VOM) trained on dense patch prediction rather than image-text alignment. The MLLM's native encoder and the VOM operate on a shared patch grid, which lets us interleave their tokens with preserved spatial correspondence; we show this beats naive concatenation. A two-stage adapter training protocol (generic image-caption alignment, then joint task-specific optimization) prevents the localized stream from overfitting to training-domain manipulations. Across face-manipulated and fully synthetic content, FORGE produces region-referential explanations answering fine-grained attribute queries ("Does the eyes/nose/mouth look real or fake?") and substantially outperforms in-domain baselines on cross-domain evaluations; region-specific evaluation and human studies confirm explanation faithfulness.

Vision and Language Navigation (VLN) requires an embodied agent to traverse complex environments by following natural language instructions, demanding accurate alignment between visual observations and linguistic guidance. To address these challenges, we propose a fine grained instruction guided graph reasoning framework (FIGR) that enhances both spatial representation and instruction understanding during navigation. Specifically, an observation graph interaction mechanism is introduced to disentangle angular and visual cues while strengthening directed edge representations through geometric embedding, enabling more reliable spatial reasoning within the navigation graph. The key detail guidance module is implemented as Adaptive Open Vocabulary Guidance (AOVG), where a contextual role parser dynamically identifies location, object, spatial relation, and other contextual cues. This design avoids exact string matching and supports previously unseen entities and compositional expressions. For multilingual instructions, a Multilingual Semantic Adapter (MSA) maps language-specific representations into a shared navigation-semantic space. By jointly integrating structured graph reasoning with instruction critical semantic cues, the proposed approach significantly improves the agent ability to follow complex navigation instructions. On the validation-unseen splits, FIGR achieves 67 SPL on R2R and 64.8 sDTW on RxR, exceeding SPENav by 1 percentage point in SPL and PRET by 2.4 points in sDTW, respectively.

Coastline detection in remotely sensed imagery is commonly formulated as pixel-wise segmentation, even though coastlines used in coastal monitoring are ultimately represented as geometric curves and defined by geomorphic proxies such as vegetation lines, dune toes, or cliff edges. We revisit coastline extraction from a representation perspective and formulate the task as geometric boundary localization, where a thin coastline boundary is localized directly as a curve rather than derived from a segmentation mask. Using the New Zealand Coastal Change Dataset (NZCCD) and LINZ aerial imagery, we develop CoastlineVLM-7B, a vision-language model built on the GeoChat-7B/LLaVA-1.5 architecture that jointly performs coastline presence detection, proxy-type classification, and direct coastline grounding as an ordered polyline. We compare it against U-Net, UNet++, DeepLabV3+, and SegFormer trained using one-pixel-wide coastline masks and evaluate localization using tolerance- and distance-based geometric metrics. On the West Coast test set, U-Net provides stronger local boundary proximity, showing better tolerance scores and lower Chamfer and Modified Average Hausdorff distances, while CoastlineVLM-7B achieves the lowest Hausdorff and Earth Mover's distances, indicating reduced worst-case deviation and stronger global structural correspondence. Ablation studies show that geometric localization is driven primarily by direct coastline-grounding supervision and that GeoChat initialization provides a stronger starting representation than generic LLaVA-1.5 initialization. Zero-shot evaluation on the Australian VCMP dataset shows reduced performance for U-Net and CoastlineVLM-7B, but CoastlineVLM-7B achieves better geometric localization than U-Net. These results show that direct ordered-polyline grounding can be used as an alternative formulation for representing and localizing coastline geometry.