Vision-Language Grounding

Follow this topic Ask about this topic

Momentum

44 papers in the last four weeks, up 175% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 290

Oct 8, 2026cs.CV

From What to Which: Decoding Modifier Grounding in Frozen MLLMs

As Multimodal Large Language Models (MLLMs) can describe increasingly complex visual scenes, token-level grounding becomes crucial. Yet, when an MLLM generates "the yellow banana on the left", established grounding approaches focus on what is in the image ("banana"), overlooking tokens that help describe which instance is meant ("yellow", "left"). In this work, we ask whether frozen MLLM representations contain decodable grounding information about the referred instance across generated tokens, extending to modifiers such as attributes, spatial expressions, and relational/action terms. To address this question, we introduce OTTER, a lightweight supervised probe over frozen MLLM representations that uses Optimal Transport (OT) to align generated tokens with visual regions and produce compact grounding maps. Our results show that (i) instance-discriminative visual information can be decoded from modifier tokens, with the clearest evidence for spatial terms, but (ii) is not confined to them, as contextualized object nouns also carry referential information; (iii) the recovered grounding remains informative under context perturbations, while selected regions remain relevant to generation; and (iv) the learned OT-based grounding extends beyond the controlled setting to free generation and cross-dataset transfer.

Barbara Toniella Corradini, Caterina Gallegati, Ludovica Genovese +1

AI for Good · AI for Good (AIGO), Istituto Italiano di Tecnologia, Italy · University of Siena, Italy +2

Multimodal Large Language Models Vision-Language Grounding Visual Grounding

Oct 8, 2026cs.CV

SAGE: Sink-Aware Guided Emphasis for Visual Grounding in Vision-Language Decoders

Recent large vision-language models (VLMs) pair a visual encoder with a large language model (LLM) and perform well on diverse image-text tasks, yet their reliability is often limited by decoder attention pathologies that suppress visual evidence and exacerbate hallucinations. In this paper, we revisit visual attention sinks and uncover a structured, layer-dependent behavior: across prompts, early and late decoder layers exhibit prompt-invariant attention collapse onto the same few image regions, which we term PIS (Prompt-Invariant Sinks), whereas mid layers become prompt-conditioned and drive vision-language alignment. This split suggests that treating sinks as a uniform effect is incomplete. Building on this insight, we propose SAGE (Sink-Aware Guided Emphasis), a lightweight intervention that steers decoder attention away from PIS and toward query-dependent regions of interest (ROIs) using token-aligned ROI masks derived from standard vision backbones such as CLIP, ViT, and DINOv3. Evaluated on diverse vision-encoder + decoder-only LLM VLM families, SAGE improves visual grounding, reduces hallucinations, and yields consistent gains across public downstream vision-language benchmarks, including fine-grained visual discrimination settings where localized evidence is crucial, when instantiated with backbone-derived ROI masks.

Jeonghyo Song, YoungJoon Yoo

Department of Artificial Intelligence, Chung-Ang University

Vision-Language Grounding Large Vision-Language Models VLM Hallucination Mitigation

Oct 7, 2026cs.CV

Beyond Anonymous Captions: Grounding Character Identity in Video Captioning and Question Answering

Linking people's appearance and actions to character identities is essential for understanding video narratives. We present a framework for identity-aware video captioning and person-centric question answering that combines automatic character identification, explicit spatial grounding, and task-specific adaptation. Starting from LSMDC v2 movie clips, our pipeline matches detected faces to actor reference images, tracks characters across frames, and builds inputs with identity-linked bounding boxes. A strong vision-language model generates identity-aware captions and questions, which are manually verified and filtered to create a benchmark of 750 captioned clips and 3,000 person-centric questions. We study five grounding strategies combining textual coordinates with visual face or estimated person boxes across Video-MLLM families at roughly 2B, 4B, and 8B parameters and larger frontier models. Combining visual face boxes with textual coordinates yields the most consistent performance across scales and significantly improves overall performance over coordinates alone. Smaller models tend to over-assign known identities when the queried person is not grounded, while larger models better recognize such UNIDENTIFIED cases. We introduce BAC by LoRA fine-tuning Qwen models at 2B, 4B, and 8B scales on about 32K identity-aware captioned clips. Across all scales, BAC outperforms every other evaluated model family of comparable size. BAC-8B reaches 93.20% overall QA accuracy, ranking behind only GPT-5.6 Sol among the frontier models evaluated in our study. Overall, explicitly communicating who is where, together with lightweight task-specific adaptation, substantially improves identity-aware video understanding without changing the underlying architecture. We release the benchmark, training data, code, and BAC checkpoints at https://github.com/momentslab/beyond-anonymous-captions.

Anas Filali Razzouki, Killian Steunou, Khalil Guetari +3

Télécom SudParis, Institut Polytechnique de Paris, France · Moments Lab Research, France

Video Captioning Video QA Vision-Language Grounding

Oct 7, 2026cs.RO

YUBI-STAG: Contact and Semantic-Rich Alignment for VLAs via Automated Video-Language Grounding

Vision-Language-Action (VLA) models acquire broad manipulation capabilities via large-scale pretraining, yet eliciting them through language requires fine-grained alignment between instructions and physical interactions. Existing robot demonstrations typically provide only coarse task descriptions, omitting how actions are executed, including which gripper acts, which object is contacted, and how it is grasped and moved. We introduce YUBI-STAG, a framework for Spatio-Temporal Annotation and Grounding that automatically enriches manipulation demonstrations with interaction-rich semantics to align pretrained VLAs with fine-grained manipulation language. Combining contact-object segmentation with vision-language models, YUBI-STAG annotates object identities, attributes and states, per-gripper actions, bimanual coordination, and spatially grounded interactions. To address YUBI-STAG's reliance on localized sequences and multi-stage VLM inference, we distill it into YUBI-VLM. YUBI-VLM directly recovers action structure and annotations from raw, unsegmented video in few inference calls and operates from wrist views alone. We evaluate both frameworks on YUBI-STAG-Bench across temporal, semantic, and spatial grounding tasks. YUBI-VLM retains much of YUBI-STAG's annotation accuracy with fewer inference calls and shorter runtime while generalizing to unseen manipulations. Finally, post-training VLA policies on these annotations aligns them with fine-grained language and contact-aware structure. Bimanual experiments demonstrate improved performance and instruction following, including control over object identity, acting gripper, target location, and spatial relations absent from original labels.

Masatoshi Tateno, Takehiko Ohkawa, Yueh-Hua Wu +4

AI Robot Association (AIRoA) · The University of Tokyo · Institute of Science Tokyo

Vision-Language Grounding VLMs for Robotics Language-Conditioned Robot Manipulation Vision-Language-Action Models

Oct 7, 2026cs.CV

Visual Evidence Under Cross-Examination: Evaluating and Controlling Decision-Level Evidence Use in Vision-Language Models

Vision-language models increasingly reason through crops, regions, and tool-produced observations. Yet an observation can influence the answer without benefiting the candidate it supports. We study candidate-bound visual contribution: valid evidence should help, invalidating its supporting relation should remove its additional effect, and valid rebinding should redirect that effect to the newly supported candidate. We introduce CROSS-Bench, a benchmark of 28,000 decision problems, with matched invalidation and rebinding tests on a dedicated evaluation subset. Our RIVET interface preserves evidence identity and uncertainty, composes a candidate-conditioned response, and separately controls its strength. Shared-evidence experiments show that task accuracy and evidence ownership can diverge. Under matched capacity and training, RIVET increases normalized effect transfer from 0.512 to 0.651 where clean evidence has a positive effect. The advantage persists on common evaluation examples and across repeated decision-layer fits. With evidence predicted from raw inputs, RIVET improves CROSS-Bench accuracy by an average of 5.70 pp across four frozen backbones, relative to the same models without auxiliary evidence. These results separate the utility of visual evidence from the candidate-specific destination of its effect.

Huiyao Zhang, Jin Bai, Zilong Su +6

Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences · University of Chinese Academy of Sciences · University of Science and Technology of China

VLM Evaluation Faithfulness in VLMs VLM Interpretability Vision-Language Grounding

Oct 7, 2026cs.CV

Spatial Latent Reasoning for Embodied Reference Understanding

Pointing-gesture visual grounding requires connecting hand geometry with the visual identity and extent of a referred object. A central challenge for continuous latent reasoning is how to organize these complementary cues into useful intermediate supervision. We propose Spatial Latent Reasoning (SLR), a framework that structures this supervision around an ordered sequence of geometric and visual states. A spatial ray state is supervised by fingertip position and pointing direction, followed by four states aligned with target-region features. To construct the visual targets, we introduce parity pooling, which applies polyphase grouping to average region tokens on four interleaved spatial supports. All states are generated recurrently during training and inference; auxiliary annotations are required only during training. On EgoPoint-Ground, the framework improves mIoU over same-backbone supervised fine-tuning by 2.8, 17.5, and 21.1 percentage points on Qwen3.5-4B, Qwen2.5-VL-7B, and Qwen3-VL-8B, respectively, with improvements on both hard subsets. On YouRefIt, it achieves 77.6% precision at IoU 0.5, a numerical margin of 5.2 percentage points over the reported state of the art under differing evaluation protocols. Ablations support joint geometric and visual supervision on the standard and similar-object sets, and favor parity over three alternative pooling operators on the standard set. These results support task-structured supervision for continuous pointing grounding. We will release the code and supporting materials.

Ling Li, Jianhui Zhong, Wei Liu +3

Tsinghua University · Dalian University of Technology · University of Science and Technology of China

Vision-Language Grounding Continuous Latent Reasoning Embodied Reasoning

Oct 6, 2026cs.CV

GeoPID: Decomposing and Steering Visual Information in Vision-Language Models

While recent vision-language models (VLMs) have shown outstanding performance across diverse applications, they tend to under-use visual information and over-rely on textual context. In this work, we propose \textsc{GeoPID}, a training-free framework that analyzes multimodal information within VLMs from a geometric perspective. \textsc{GeoPID} decomposes information into Redundant, Modality-Unique, and Synergistic components through the geometric relationships between visual and textual representation subspaces. Through an extensive analysis across 22 VLMs and 14 benchmarks, we confirm that correct predictions exhibit stronger vision-unique components when questions strongly require visual grounding. Building on this geometric analysis, we introduce a targeted intervention technique that selectively amplifies visual representations along the vision-unique subspace during inference. As a result, visual grounding capabilities were enhanced without any additional model parameter updates, achieving an average relative accuracy gain of 7.63%.

Seulgi Kim, Zhixiong Zhang, Xinwei Zhang +2

Georgia Institute of Technology · Work done as an intern at Amazon. · Amazon

Vision-Language Grounding

Oct 5, 2026cs.LG

Decoupling What from Where: How Should a Small GUI Grounding Model Receive the Action Type?

A GUI agent decides which action to take and where to take it; we ask how a small grounding model should receive the action type. Fine-tuning Qwen2-VL-2B with LoRA on Android in the Wild, we compare a flat baseline with five ways of supplying the type under matched data, compute, and decoding: an auxiliary loss, a hard-routed action word, an additive learned embedding, a prepended learned token, and the type written into the prompt. With five seeds, an episode-clustered bootstrap, and seed-level paired tests, the ranking on a mixed stream is clear: the auxiliary loss, the additive embedding, and the prompt word each gain five to seven [email protected] points over the baseline, while hard routing and the prepended token are not distinguishable from it. Much of that gain is protection from a preprocessing choice of ours rather than a spatial prior. Our serializer clamps the off-screen touch point AITW records for type events to the origin; that class degrades the baseline's click grounding, and removing it lifts the baseline by nearly seven points, after which no mechanism's hit rate beats it and the intervals exclude a two-point effect, though the auxiliary loss still shortens the average miss; on a stream of taps and swipes none helps. Whether this generalizes beyond one serialization is open. For deployment, the pipeline's margin over the baseline with predicted rather than gold types is not established (+0.016, 95% interval [-0.017, +0.052]), and a wrong type collapses every model conditioned at inference. The prepended token does not help at the shared learning rate, where its rows barely move from initialization; trained ten times faster it reaches the level of the other three, with a margin three seeds do not establish. We also document a silent failure: injecting conditioning through inputs_embeds makes Qwen2-VL fall back to 1-D positions for image tokens, costing nine points.

Aadi Chauhan, Arthur Ilyasov

Stanford University

GUI Grounding Mobile GUI Agents Vision-Language Grounding

Oct 5, 2026cs.CV

Readout Blindness: VLM Scores Miss the Spatial Direction Their Frozen Encoders Retain

CLIP-like vision-language models remain a cornerstone of multimodal systems, yet their scores stay near chance on directed spatial relations, such as whether one object is left of another. We call this failure readout blindness and analyze, theoretically and empirically, why deployed scores miss the direction: when scoring rules treat the subject and object symmetrically, direction cancels regardless of encoder training. Guided by this analysis, we introduce Antisymmetric Displacement Readout (ADR), which aligns caption words with image patches in the frozen features and scores each relation by the signed displacement between matched object centroids. Notably, ADR succeeds without additional training or learned parameters, thereby demonstrating that directional information remains in the frozen encoder. However, text and world priors can inflate accuracy, so we further introduce prior deflation, which measures the benefit of the image-text pairing as the grounded gain over a null that pairs each item with an unrelated image. Extensive experiments across encoder families show that ADR substantially improves over deployed scores, which remain near chance on most direction-balanced sets even for fine-tuned encoders. Compared with more complex readouts, ADR outperforms the evaluated MLLM likelihood readouts and is competitive with their chat inference at a small fraction of the computation. These results support our claim that directional information can be recovered from frozen features by an appropriate readout. Our implementation and evaluation kit will be publicly available.

Guangyuan Li, Tianming Du, Yan Jiang +2

ELLIS Institute Finland · Aalto University · University of Oulu +1

VLM Evaluation Vision-Language Grounding Representation Probing

Oct 5, 2026cs.RO

Encoded but Not in Control: Revealing the Grounding Gap in Vision-Language Robot Policies

Instruction following is central to language-conditioned robot policies: language should determine what to do when the same scene permits multiple valid actions. Yet successful execution alone cannot establish whether a policy follows the instruction or infers the task from the scene. We study this ambiguity through scene-preserving instruction interventions, using valid target substitutions, arbitrary nouns, and unrelated sentences while holding the scene fixed. We evaluate vision-language-action (VLA) policies and world-action models (WAMs) in simulation and in real-world experiments. Our analysis addresses three questions: (a) Does task success imply instruction following? When instructions request a different visible object, all evaluated policies predominantly approach and pick up the incorrect original target associated with the scene. (b) Is this failure caused by language insensitivity? Instruction perturbations affect task performance. A layerwise action lens shows intermediate action predictions respond to these perturbations. Linear probes accurately recover instructed targets, indicating modified instructions are encoded despite rarely determining target selection. (c) Why does encoded language fail to control action? Attention analysis indicates weak instruction-token contributions to action generation. Target-token attention can remain focused on the original object, revealing a mismatch between target encoding and visual grounding. UMAP and shared non-negative matrix factorization show target information remains accessible within representations increasingly organized by scene identity. Our findings expose a grounding gap concealed by nominal success and provide a diagnostic framework. They further establish a concrete criterion for progress: policies should reliably follow valid changes in user intent, even when they conflict with scene-favored behavior.

Shaohan Jiang, Jiahang Cao, Qiduo He +9

HKU · CUHK(SZ) · Shanghai AI Lab +3

Vision-Language Grounding Vision-Language-Action Models Reasoning for VLA Models

Oct 5, 2026cs.AI

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.

Erfan Shayegani, Kundan Krishna, Yue Dong +3

University of California, Riverside · Work done during internship at Apple. · Apple

VLM Evaluation Vision-Language Grounding Visual Grounding

Oct 4, 2026cs.CV

Answer with Evidence: Consistency-Aware Grounded Visual Question Answering for Roadside Traffic Scenes

Roadside traffic reasoning requires every free-form textual claim to be backed by visual evidence. Existing grounded multimodal large language models (MLLMs) frequently exhibit say-point mismatch, in which the textual answer contradicts the bounding boxes the model localizes. Evaluation metrics that score answers and boxes separately leave this failure unpenalized. We trace the mismatch to the conventional answer-then-ground factorization, which commits to a numerical claim before any object is enumerated. To measure it, we build RoadSceneVQA-G, a benchmark of 34.7K question-answer pairs in which every free-form answer is linked to the set of boxes that witnesses it, and we propose the Answer-Grounding Consistency (AGC) evaluation suite. To address it, we introduce Enumerate-then-Answer (EtA), which reverses the generation order so that answer-evidence agreement becomes a property of the output structure, and Enumeration-Consistent Policy Optimization (ECPO), a reinforcement learning stage that uses the union of multiple rollouts as a recall teacher without ground-truth boxes. EtA raises say-point consistency from 26.6% to 93.7% and grounding F1 from 52.2% to 73.0%, and ECPO further increases F1 to 75.6% without per-box supervision. On gRefCOCO, the same framework outperforms the strongest compared method, indicating that it transfers beyond traffic scenes. The project is available at https://github.com/GuanRunwei/RoadSceneVQA-G.

Runwei Guan, Rongsheng Hu, Shangshu Chen +9

The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · Jiangnan University, Wuxi, China · Central China Normal University, Wuhan, China +6

Autonomous Driving Benchmarks Visual Question Answering Vision-Language Grounding RL Fine-Tuning

Oct 4, 2026cs.CV

Recurrent Latent Visual Search for GUI Grounding

GUI grounding is a critical capability for GUI agents powered by vision-language models, helping them execute user instructions by locating the corresponding elements in screenshots. Single-step grounding struggles with small elements and dense layouts, motivating multi-step visual search. However, existing approaches commonly rely on textual reasoning misaligned with visual space or costly multi-round interactions with external visual tools. To make multi-step visual search an explicit spatial process within the model, we propose ReLaViS, which performs Recurrent Latent Visual Search in a single interaction round. At each step, a spatial search head uses the hidden state to query the screenshot's visual tokens, producing a spatial search distribution that explicitly represents the search focus. This distribution then aggregates the visual tokens into latent visual evidence, which is recurrently fed back as the next input embedding to condition subsequent search. We further introduce a GUI-aware coarse-to-fine inductive bias through trajectories constructed from flat element annotations, supervising search from the global interface through intermediate element groups to the target. Built on Qwen2.5-VL-7B, ReLaViS improves ScreenSpot-Pro accuracy by 3.1 percentage points to 56.3% with only a 3.5% increase in inference FLOPs and outperforms the matched single-step baseline on all five benchmarks.

Kaiyu Wu, Beichen Zheng, Weiyao Huang +1

Sun Yat-sen University

GUI Grounding Vision-Language Grounding Visual Search

Oct 4, 2026cs.CV

Look Where You Say You're Looking: Self-Grounded Attention for Visual Reasoning

We introduce Self-Saliency, a method for training Vision-Language Models (VLMs) to increase the alignment between their visual attention and the image regions mentioned in their reasoning. Self-Saliency uses a grounding model to localize the objects mentioned in each reasoning step and treats the resulting areas as supervision for the model's visual attention. Previous work on steering visual attention determines target image regions based solely on the image and question. In contrast, we show that conditioning the target regions on the model's generated reasoning improves downstream performance. For proper evaluation, we build a unified, broad suite of 25 visual reasoning benchmarks, where we reproduce the results of previous methods. We find that Self-Saliency significantly outperforms both prior attention-steering methods and baselines that ground image-level text, achieving both a better average rank and a better mean score. Post-training analysis shows that the model primarily adapts its reasoning text to existing attention patterns, producing shorter steps that refer to larger regions. Nevertheless, when controlling for generated text, attention to grounded regions increases significantly across the relevant layer. Finally, we identify a consistent geometric bias in VLM visual attention toward the image border. However, our ablations show that Self-Saliency's gains cannot be explained by simply aligning attention with the center of the image, highlighting the importance of aligning visual attention with the regions mentioned in the model's reasoning.

Uri Berger, Gal Chechik, Gal Dalal

NVIDIA Research · The Hebrew University of Jerusalem · University of Melbourne +1

Vision-Language Grounding VLM Reasoning

Oct 1, 2026cs.CV

VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations

Existing synthetic image evaluators typically provide only a scalar quality score and do not identify the image regions that support it. We introduce VIEScore2, a unified evaluator for image generation and editing tasks with optional conditioning images. VIEScore2 represents an image as an N x N grid and jointly predicts quality scores and defect locations in a single model pass. Its text-native grid representation provides a common interface for heterogeneous spatial supervision and enables directly verifiable post-training objectives. We train on 38K examples spanning score-only, localization-only, and joint supervision across generation and editing tasks. Starting from supervised fine-tuning, we further apply GRPO to improve defect localization using rewards that combine cell-level Dice overlap, score accuracy, and output-format validity. A parameter-free parser converts the structured predictions into readable explanations. On the primary suite, VIEScore2 achieves an overall-score SRCC of 0.601, compared with 0.491 for Gemini-3-Flash, the strongest zero-shot general-purpose VLM baseline under matched inputs. For defect localization, VIEScore2 outperforms both general-purpose VLMs and specialized spatial evaluators on three of six benchmarks in per-image grid IoU and ranks among the top three on five, including datasets beyond its training sources.

Xianda Du, Max Ku, Weiming Ren +5

University of Waterloo · National Taiwan University · Nanyang Technological University +1

VLM Evaluation Image Editing Evaluation Vision-Language Grounding Image Generation Evaluation

Sep 30, 2026cs.AI

R-GroundBench: A Diagnostic Benchmark for R-Group Groundingin Markush Molecular Editing

Recent advances in AI for scientific discovery enable molecular understandingand design, yet reasoning over incomplete chemical representations remainsunclear.Markush structures, which encode molecular families through variable R-groupplaceholders (\textit{R\textsubscript{1}}, \textit{R\textsubscript{2}}, \textit{X}, etc.), are ubiquitous in pharmaceutical patents and requiregrounding across molecular, textual, and chemical information.However, existing molecule-language benchmarks focus on fully specifiedmolecules, leaving R-group grounding largely unevaluated.We introduce R-GroundBench:, a diagnostic benchmark built from real patent Markushstructures, featuring a Multiple-Choice (VQA) track with controlled difficultyand modality splits, and an open-ended Generation track.Our results reveal a substantial gap between recognition andmolecular grounding.While models achieve over 90% accuracy on Easy VQA, performance drops to56--66% on Hard VQA when shortcuts are controlled.Chemical-domain VLMs also remain unreliable, achieving only 25.7--46.2% on HardVQA despite domain-specific pretraining.Moreover, Generation Exact Match remains below 20% for most models and below8% when visual input is required.These findings reveal that current AI systems lack reliable grounding andexecution for Markush editing, highlighting challenges for AI-drivenscientific discovery.

Xin Wang, Zichuan Ying, Xinna Lin +8

Westlake University · The University of Hong Kong · Shanghai Innovation Institute +5

Vision-Language Grounding Drug Discovery

Sep 30, 2026cs.CV

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop control. Yet vision-language-action (VLA) and world-action models (WAMs) take perception from general-purpose vision-language and video-generation backbones, which still fail in these settings. We introduce GroundingPI, a 4B grounding foundation model that generates points and boxes as quantized coordinates in a shared vocabulary. Training combines multimodal and spatial pretraining, supervised fine-tuning, and reinforcement learning with GRPO, using supervision from public datasets and dedicated data engines. Against 44 baselines across 34 grounding benchmarks spanning 11 perceptual capabilities, GroundingPI establishes a new state of the art, averaging 73.68%, above the larger GPT-6 Astra (71.54%). As a downstream visual backbone, GroundingPI improves performance on robotic manipulation and autonomous driving. On RoboTwin 2.0, it outperforms every mainstream backbone we evaluate in all four out-of-distribution settings, by up to 24.8% relative to the strongest backbone. On RoboCasa-GR1, GroundingPI trained with 50% of the demonstrations outperforms those baselines trained with 75%. On nuScenes, used as the visual backbone, GroundingPI attains an average open-loop L2 error of 0.296 m. We systematically analyze GroundingPI's pretraining in scale and data composition. Downstream autonomous driving and robotic manipulation improve as the pretraining is scaled. Analyzing the data recipe across these 11 perceptual capabilities shows dense grounding's substantial benefits for both, and OCR's potential as a catalyst for perceptual learning. These results support grounding as a perceptual foundation, and dedicated perceptual pretraining as a promising direction for foundation models of physical intelligence.

Qize Yu, Lianrui Fan, Boyu Chen +23

XPeng Inc. · Peking University · The University of Hong Kong +4

Vision-Language Grounding VLMs for Robotics Robotic Perception Fine-Grained Visual Perception

Sep 30, 2026cs.CV

GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed

Autoregressive (AR) grounding models serialize spatial predictions, introducing sequential latency and imposing a causal order on output tokens. We view grounding as visual evidence extraction: objects, locations, and spatial relations are jointly constrained by the image and query, yet their dependencies do not imply an intrinsic left-to-right generation order. This distinction makes bidirectional diffusion a natural fit, allowing spatial hypotheses to emerge in parallel and be jointly refined through iterative denoising. We introduce GroundAnything, a 4B-parameter grounding foundation model that reconciles fast parallel decoding with precise localization through blockwise denoising. Training combines grounding pretraining from public datasets and dedicated data engines, direct AR-to-diffusion conversion with joint AR and diffusion objectives, supervised fine-tuning, and GRPO-based reinforcement post-training. Across 30 grounding benchmarks, our autoregressive variant, GroundAnything-VLM, establishes a new overall state of the art among similarly sized models at 72.42%, remaining competitive with GPT-6 Astra (71.35%). With entropy-guided decoding, GroundAnything also surpasses the prior state of the art at this scale, averaging 61.75% versus 53.32% for the fast MTP-based LocateAnything model. We further explore decoding strategies, showing that an optional self-speculative mode achieves a

4.51\times

speedup over the AR counterpart with a 0.74 percentage-point drop in COCO F1mIoU. Infrastructure experiments show that progressive inference optimizations translate parallel decoding into practical speedups. These support efficient visual grounding in latency-sensitive real-world systems.

Qize Yu, Lianrui Fan, Bowen Ping +19

XPeng Inc. · Peking University · The University of Hong Kong +4

Efficient VLM Inference Vision-Language Grounding Parallel Decoding Diffusion Language Models

Sep 30, 2026cs.CV

Distill the Visual Evidence, Not Just the Answer: Cross-World On-Policy Distillation for Vision-Language Models

A central goal of vision-language model (VLM) distillation is to transfer both the teacher's language capabilities and its visual understanding. However, existing methods primarily supervise the student's output, leaving visual understanding implicit. Our analysis reveals that a student can match the teacher's answer without relying on the same visual evidence, raising the question: how can we ensure the student responds to the visual information that actually determines the answer? To this end, we propose \textbf{Cross-World On-Policy Distillation (CW-OPD)}, which explicitly supervises the student's response to changes in visual evidence. For each example, CW-OPD constructs two visual worlds that share the question and scene context but differ in answer-critical evidence, yielding different answers. We perform on-policy distillation in both worlds and distill the teacher's cross-world belief transition, encouraging the student to match not only \emph{what} the teacher predicts but also \emph{why} its prediction changes with the evidence. A gradient analysis shows that this term is invariant to errors shared by both worlds and supplies a corrective signal invisible to endpoint matching alone. In this way, CW-OPD makes reliance on the relevant visual evidence an explicit distillation target rather than an implicit consequence of output matching. To diagnose whether a model truly grounds its answers in visual evidence, we introduce CWBench, which measures cross-world consistency via Cross-World Pair Accuracy (CWPA). Experiments on Qwen3.5-4B show that CW-OPD outperforms the strongest baseline by \textbf{1.2} points on average, and the 4B student exceeds DeepSeek-V4.1 (552B) by \textbf{22.4} CWPA points on CWBench. Code is released in https://github.com/baokou-fw2/CWAD.

Yuanhao Sun, Huawei Ji, Jiaxin Ding +2

Shanghai Jiao Tong University, Shanghai, China

Counterfactual Evaluation of VLMs VLM Distillation Vision-Language Grounding On-Policy Distillation

Sep 30, 2026cs.CV

SpatialCORE: Confidence-Aware Grounded Spatial Reasoning in Large Vision--Language Models

Large Vision-Language Models (LVLMs) have made remarkable progress across visual perception tasks, yet spatial reasoning remains a persistent weakness, especially for questions that require reasoning over visual space. Recent spatial-reasoning methods incorporate generated grounding, where models predict bounding boxes, masks, or other localization outputs for task-relevant objects as part of their reasoning trace. However, these approaches typically optimize final-answer correctness alone, allowing correct answers to be rewarded even when the model does not reason from confidently localized task-relevant objects. We introduce SpatialCORE (Spatially COnfident REasoning), a post-training framework that turns the model's own confidence in generated grounding into a learning signal for spatial reasoning. Its central idea is to reinforce grounding that is both accurate and confident, encouraging the model to reason from confidently localized task-relevant objects. SpatialCORE realizes this through a self-regulating spatial reward that weights each predicted bounding box's matching quality by its coordinate-token confidence. An answer gate further ties grounding optimization to final-answer correctness. SpatialCORE achieves state-of-the-art results among open-source and specialized spatial reasoning models across diverse benchmarks, and transfers effectively in zero-shot settings to unseen data distributions. The source code is available at https://github.com/rafiibnsultan/SpatialCORE.

Rafi Ibn Sultan, Xiangyu Zhou, Md. Sajid Alam Chowdhury +4

Department of Computer Science, Wayne State University · Department of Radiation Oncology, Henry Ford Health · Department of Electrical and Computer Engineering, The Ohio State University +1

Visual Spatial Reasoning Large Vision-Language Models Vision-Language Grounding RL for VLMs

Sep 29, 2026cs.CV

Composition, Not Conversation: VLMs Lose the Scene, Not the Thread

Vision-language models (VLMs) increasingly reason over visual evidence that is cropped, segmented, retrieved, or revealed over time. Yet most VQA benchmarks present the complete image and question at once. We ask what models lose when the same information is fragmented. We introduce Layered-VQA, with 93 scenes and 300 questions. Each image is decomposed into ordered RGBA layers that exactly recompose the original scene, and each question is annotated with supporting, minimal-sufficient, and distractor layers. We evaluate eleven open-weight VLMs from 3B to 32B parameters and two proprietary models with a scale of 187,200 conversations, graded by 1.74M open-model cross-judgments. We find three consistent failures. Loss in Composition: fragmenting the question has a small effect, but fragmenting the scene substantially reduces accuracy; recomposing the same layers largely restores performance. Oracle Inversion: even oracle-selected sufficient evidence can perform worse than the complete scene. Loss in Grounding: as more evidence is required, grounding degrades much faster than answer accuracy. Together, these results show that having the right visual evidence is not enough. How that evidence is composed and presented determines whether models can use and ground it. The right evidence is not enough: VLMs need the scene it came from.

L. D. M. S. Sai Teja, Ufaq Khan, N. Siva Gopala Krishna +5

NIT Silchar · MBZUAI · BML Munjal University +1

VLM Evaluation Visual Question Answering Vision-Language Grounding VLM Reasoning

Sep 29, 2026cs.CV

Seeing Is Not Addressing: Auditing Linguistic Access to Frozen Visual Geometry

Visual distinctions are often finer than those reflected in linguistic conceptualization. Vision-language models exhibit a similar asymmetry: a distinction can remain discriminable in frozen image geometry while being weakly addressable through the native text interface. We study this gap by separating visual discriminability from linguistic addressability in text-to-image retrieval. Using FactorAtlas, a fully crossed testbed of 23,040 images spanning shape, hue, pattern, and nuisance variation, we compare both readouts on held-out images of the same distinctions. We then derive image-side contrasts that separate each value from its alternatives for matched visual grounding, and test whether this reduces the native-text access gap across factors and models. Direction-specific and visual-absence controls tie these gains to the relevant visual contrast; the gains persist after global alignment and extend to compositional retrieval and natural images. Together, these results show that visual discriminability and linguistic addressability need not coincide, and that matched visual grounding can probe and reduce the resulting access gap.

Woosang Jeon, Jiwon Yang, Soo Chung +1

Seoul National University

Vision-Language Models Vision-Language Grounding Modality Gap in VLMs Vision-Language Retrieval Fine-Grained Visual Perception

Sep 29, 2026cs.CV

How Medical VLMs Underutilize Their Vision Encoders: A Dermatology Perspective

Medical Vision-Language Models (VLMs) show significant promise for clinical image understanding, offering accurate diagnosis with interpretable reasoning. However, a critical performance gap exists between their strong vision encoders and the full multimodal model: in dermatology, the MedSigLIP encoder outperforms MedGemma by an average of 10.26 percentage points even when both use zero target-task labels; few-shot linear probing provides further evidence of strong visual representations. This gap motivates an investigation of how visual information is used in end-to-end diagnosis and why plausible-sounding predictions can lack grounding in image evidence. Using dermatology as our primary testbed, we systematically investigate three hypotheses for this phenomenon. We further provide a mechanistic analysis of the model's internal attention patterns, showing that a simple describe-then-decide prompting strategy increases vision attention by 30-40% during generation. Task-specific fine-tuning improves dermatology classification but reduces cross-domain medical question-answering performance in our evaluation. To address these challenges, we combine label-free prompting with low-label encoder-assisted reranking while keeping the VLM frozen. We validate the interventions across five VLM backbones in dermatology and provide supporting representation and attention analyses across additional medical modalities.

Janet Wang, Yunbei Zhang, Xiao Wang +1

Tulane University · Oak Ridge National Laboratory

Medical Diagnosis VLM Interpretability Vision-Language Grounding Medical VLMs Modality Gap in VLMs

Sep 28, 2026cs.CV

AnswerMap: Faithful Spatial Interpretability of VLMs from Answer Posteriors

When a VLM answers a visual query, current interpretability tools rely on text rationales, which use a mismatched modality, or on internal read-outs, which originate too early to reflect the final output and require white-box access to the model. We introduce AnswerMap, a training-free, task-agnostic, black-box visual rationale constructed from the output head. The image is cut into K row and K column bands, each shown alone to the frozen model along with the query in the format of a yes/no relevance question. The outer product of the row and column ``yes'' posteriors gives the query-conditioned spatial map. Crucially, by defining a fixed read-out R (e.g., expectation, maximum) on top of AnswerMap, we can derive continuous outputs like location natively. This bypasses the reliance on discrete text tokens for continuous-output tasks and guarantees an image-dependent answer by construction. However, a rationale can be confabulated, so we validate AnswerMap across four models and three query distributions with two tests: (a) agreement with the model's own generated point and (b) deletion of the map's region. The map lands where the model points (AUC 0.85 against 0.38 for attention), and deleting its region flips 53% of correct answers (against 19% for attention's). Beyond establishing faithfulness, we demonstrate the map's task-agnostic utility through three distinct read-outs: its maximum flags hallucinated objects without generation, its expectation localizes correctly when the model's own pointing fails, and its top-mass region, fed back as a crop, fixes half of the model's wrong answers. AnswerMap thus offers a new lens on VLM interpretability and, through its read-outs, a new output interface for visual tasks beyond text tokens.

Mohamed Eltahir, Fardows Adam, Duaa M. Tahir +6

King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia · Department of Computer Science, Edge Hill University, Ormskirk, England

Vision-Language Models VLM Interpretability Vision-Language Grounding

Sep 26, 2026cs.CV

EyeVQA: Benchmarking Ophthalmic Vision-Language Models from Recognition to Spatial Grounding

Vision-language models (VLMs) have shown increasing potential for medical image understanding, yet their capabilities in ophthalmic imaging remain insufficiently characterized. Existing ophthalmic datasets are typically designed for individual diseases or specialized tasks, making it difficult to systematically evaluate whether VLMs can move beyond disease recognition toward comparative reasoning and fine-grained spatial grounding. We introduce EyeVQA, a unified visual question answering benchmark for comprehensive evaluation of ophthalmic VLMs. EyeVQA is constructed from 21 available ophthalmic datasets and contains 20,000 question-answer pairs spanning six disease groups and seven question types: Single-Choice, Multi-Select, Variable-Select, True-False, Ranking, Point Location, and Bounding Box. Gold answers are deterministically derived from source-provided diagnoses, severity grades, clinical findings, segmentation masks, bounding boxes, and anatomical landmarks, enabling reproducible evaluation without relying on model-generated annotations. Notably, 44.5% of the questions require reasoning across multiple images, extending evaluation beyond conventional single-image medical VQA. We benchmark fourteen representative general-purpose, scientific, and medically specialized VLMs under a unified zero-shot protocol. The best-performing model only achieves an overall score of 62.8, while substantial gaps remain in spatial grounding and cross-task generalization. These results highlight the limitations of current VLMs in comprehensive ophthalmic visual understanding and establish EyeVQA as a diagnostic benchmark for developing more reliable and spatially grounded ophthalmic multimodal models. The project page is available at https://github.com/PKUTHM/EyeVQA.

Gujie Shao, Zixun Xie, Xuechun Xing +7

VLM Evaluation Medical VQA Vision-Language Grounding Medical Image Benchmarks

Sep 24, 2026cs.CV

GHOST-Q: Towards Studying Grounding Hallucinations Overlooked Under Same-score TradeOffs in Quantized VLMS

Post-training quantization of vision--language models (VLMs) is typically assessed through aggregate task accuracy and memory savings, but preserving a headline score does not guarantee preservation of visual grounding behavior. We present GHOST-Q, a cross-precision controlled evaluation of three 8B VLM families under FP16, INT8, and NF4 across utility and hallucination-sensitive benchmarks. Rather than comparing only aggregate accuracy, we pair FP16 and quantized predictions item by-item to quantify how compression redistributes grounding successes and failures. Five of six quantized variants preserve MMStar accuracy within

\pm2

percentage points, yet 10 of 36 paired effects remain significant after false-discovery-rate correction, nine on hallucination-sensitive conditions. Same-device A100 profiling further demonstrates that substantial memory reduction does not necessarily mean lower inference latency. Finally, an open-ended AMBER audit reveals strong generation budget censoring whose severity varies by architecture and precision. These results show that quantized VLMs should be evaluated jointly for aggregate utility, grounding reliability, generation behavior, and realized deployment efficiency.

Saim Rehman, Muhammad Shafique

eBRAIN Lab, Division of Engineering, New York University Abu Dhabi (NYUAD), Abu Dhabi, UAE

VLM Evaluation VLM Quantization Vision-Language Grounding Post-Training Quantization

Sep 23, 2026cs.CV

Small yet Assistive: Spatially-Aware Post-Training for Low Vision

An estimated 1 billion people worldwide live with vision impairment, yet current vision-language models (VLMs) produce descriptions too vague for safe navigation by blind and low-vision (BLV) users. Large VLMs can generate high-quality audio-description-compliant narrations but cannot run on mobile devices; small VLMs offer competitive latency but lack spatial detail, directional cues, and hazard awareness for navigational assistance. We present Smol-VL-BLV, a compact VLM for blind and low-vision users that closes this gap using a 500M decoder transformer model and two post-training mechanisms: (1) teacher-student distillation and (2) Group Relative Policy Optimization (GRPO) with a composite BLV reward targeting directional language, metric distances, and hazard detection. Because multi-stage post-training can induce catastrophic forgetting, we add a lightweight finetuning stage after the last stage GRPO finetuning to recover general descriptive quality while preserving BLV-specific spatial grounding. Our best model substantially outperforms the baseline across various benchmarks, including tasks: VQA, BLV captioning, OCR, and latency. Compared with the baseline for relative improvement, it improves the Spatial score gain of 19.3%, and the Social score gain of 14.8%. It also increases OCR-Bench by 101.5%, and raises TextVQA accuracy by 44.2%. These results show that BLV-focused post-training improves both accessibility-specific spatial grounding and general visual-text reasoning. Deployed on a mid-range Android smartphone via Mixed-Precision Quantization, the model remains approx. 450 MB and runs entirely on-device, offline and without network dependency, generating descriptions with latency dependent on host hardware capabilities. Our model, dataset, and code is publicly released at https://smol-vl-blv.github.io/Smol-VL-BLV-website/

Rishabh Choudhary, Shreyansh Raj, Umesh Goyal +6

Indian Institute of Technology Mandi · Mohamed bin Zayed University of Artificial Intelligence

Vision-Language Models VLM Adaptation Vision-Language Grounding

Sep 23, 2026cs.CV

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 O

^2

-VG, a family of models for oriented object visual grounding with three complementary designs. Specifically, O

^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, O

^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, O

^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 O

^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.

Zeyu Ding, Yong Zhou, Jiaqi Zhao +5

School of Computer Science and Technology/School of Artificial Intelligence, the Mine Digitization Engineering Research Center of the Ministry of Education, and Jiangsu Provincial Industrial Technology Engineering Center for Intelligent Sensing and Emergency IoT in Underground Space, China University of Mining and Technology, Xuzhou 221116, China · School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON K1N 6N5, Canada

Remote Sensing Image Understanding Vision-Language Grounding Visual Grounding Remote Sensing Benchmarks Remote Sensing Visual Grounding

Sep 23, 2026cs.CV

What Looks Like a Capability Limit in Vision-Language Models Is a Readout Limit

Benchmarks for vision-language models offer their answer choices in some convention: a letter, a color name, a pixel coordinate. That convention is treated as neutral. We find it is not, and that the limits a benchmark reports can belong to the readout rather than to the model. On 200 COCO photographs, Qwen3-VL-4B picks the correct one of nine locations for a named object 68.5% of the time when the locations are given in English and 20.0% when the same locations are given as pixel coordinates. Chance is 11.1%. The cost arises when the answer options are coordinates; giving the model a coordinate in the question instead costs 3.5 points and is not significant. The gap holds on a 4x4 grid, under 8-bit rather than 4-bit quantization, and in every slice by object size, boundary distance and category. It also decides which model wins. Two models that tie under English names differ by 39 points in one coordinate system and by 54 in the other, in opposite directions. On the color task, three of the four open models capable of the task show the penalty; on photographs, two of three open models do, and so does Gemini, at 11.1 points on parseable answers (p = 1e-4). GPT-4o does not. To ask whether a model reads a coordinate at all, we attach the wrong name to each one and record which the model follows. Color options written as hue angles are followed below chance; a normalized pixel convention is followed at four times chance. This tells apart conventions a model can use from ones it cannot, though it did not predict accuracy on two untried conventions. Five models also name the same color wheel five different ways, so a fixed answer vocabulary is not neutral across models either. Five times during this work we measured a capable model as incapable because our scorer and the model disagreed about what an answer looks like. We report each case. They are the phenomenon in miniature.

Alfredo F. Frontera Del Valle

Columbia University

VLM Evaluation Vision-Language Grounding

Sep 22, 2026cs.CV

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 \textbf{Pro-Bench}, a prompt-conditioned benchmark for open-vocabulary visual grounding in heterogeneous, real-world environments. Pro-Bench includes

13k+

RGB frames from independent robotic domains (subterranean, industrial, indoor, outdoor, urban), with

74.5k

manual instance annotations and

515

target queries covering categorical, attributive, relational, affordance, state, part-whole, negative, and compositional semantics. We benchmarked

16

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 (

10/16

) 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/.

Linus Nwankwo, Muslim Alaran, Christian Rauch +2

Chair of Cyber-Physical Systems, Montanuniversität Leoben, Austria. · Department of Design Engineering and Mathematics, Middlesex University, London, UK.

Vision-Language Grounding Visual Grounding Robotic Perception