Large Vision Language Models

Spaceborne inspection systems often deploy perception models prior to launch, after which updating model weights or expanding fixed label sets becomes operationally impractical. While supervised models can be integrated pre-flight, adding new semantic capabilities in orbit requires retraining and re-uploading parameters. We investigate whether prompt-driven vision--language models can enable post-launch semantic expansion, allowing new spacecraft components to be specified via natural-language prompts without modifying onboard weights. We evaluate zero-shot instance segmentation of spacecraft components under a strictly frozen, single-pass inference protocol on a test set of $129$ images of previously unseen satellites. Under fixed global thresholds and no post-processing, SAM3 achieves $0.385$ mAP@$0.5$ and $0.267$ mAP@$0.5{:}0.95$. Performance is strongly scale-dependent: large structural elements like spacecraft bodies ($0.639$ AP@$0.50$) and solar arrays ($0.598$ AP@$0.5$) localize reliably, while relatively small appendages like antennas ($0.221$ AP@$0.5$) and thrusters ($0.081$ AP@$0.5$) remain difficult. Prompt formulation influences performance, with structured prompts incorporating spatial and geometric descriptors yielding up to $82$ improvement over short category-name prompts. The model operates within the memory and compute envelope of contemporary embedded GPUs, suggesting prompt-driven grounding can provide a practical mechanism for post-launch semantic extension of dominant spacecraft structures while highlighting limitations of zero-shot localization for fine-scale components under orbital domain shift.

Action reasoning in egocentric video requires capturing fine-grained transitions of hand-object interactions, a task where general-purpose Vision-Language Models (VLMs) often struggle when operating directly on raw pixels. We propose to decouple visual perception from symbolic reasoning by converting videos into Temporal Action Graphs. In a multi-stage prompting pipeline, we first generate dense natural language narratives over short temporal windows as a semantic bottleneck, then formalize them into structured, open-vocabulary graph representations. On the EGTEA and Epic-Kitchens-100 datasets, the symbolic representation unlocks efficient in-context learning: few-shot graph demonstrations yield substantial accuracy gains over zero-shot frame and graph-based inference alike. Even in the zero-shot setting, graph-based reasoning remains competitive with pixel-based inference despite potential pretraining contamination favoring the latter. Across 11 open-weight VLMs from 6 model families ranging from 2B to 235B parameters, our findings indicate that current VLMs are more effective as symbolic reasoners than as direct visual observers. By projecting video into the language domain, we provide a scalable, fine-tuning-free alternative to end-to-end approaches that better leverages these models' latent reasoning strengths. The code will be made public.

Human visual attention plays an important role in how people perceive and respond to environments containing potential risks. This study investigates whether large vision-language models can identify the same regions of a scene that attract human attention in safety-relevant environments. Eye-tracking data were collected from ten participants viewing 33 scene images representing environments with varying levels of potential risk using Pupil Invisible wearable glasses. Gaze coordinates were mapped onto stimulus images to generate population-averaged human gaze heatmaps. In parallel, GPT-4o was prompted through the OpenAI Vision Application Programming Interface (API) to generate spatial predictions of visual attention, which were converted into saliency maps for comparison with human gaze patterns. Spatial alignment between human gaze heatmaps and model-generated saliency maps was evaluated using four complementary metrics: Pearson correlation (r = 0.515 +- 0.117), Normalised Scanpath Saliency (NSS = 0.988 +- 0.323), Kullback-Leibler divergence (KL = 1.766 +- 0.844), and Area Under the Receiver Operating Characteristic Curve using the Judd formulation (AUC-Judd = 0.806 +- 0.076). A cross-model comparison with Gemini Pro, Gemini Flash, and Claude showed that all models exceeded the AUC-Judd chance baseline of 0.5 and achieved positive NSS scores. Gemini Pro demonstrated the strongest spatial localisation according to three of the four metrics, whereas GPT-4o produced the closest distributional match to human attention as measured by KL divergence. These findings suggest that large vision-language models can identify regions that broadly correspond to where humans direct visual attention in safety-relevant scenes without requiring eye-tracking training data. The results highlight the potential of vision-language models as a scalable tool for approximating human attentional patterns.

Vision encoders for retrieval are typically trained with class-label supervision: each training pair reduces to a scalar that uniformly pushes the embedding apart or pulls it together, as if every visual attribute either differed or matched. A multimodal large language model (MLLM), shown the same pair, can articulate those attributes and use them to predict whether the images share a class. We propose \textbf{SAGA}, a framework that turns this language-grounded, attribute-aware perception into a training signal for the encoder itself. Specifically, we use Group Relative Policy Optimization (GRPO) to reward the MLLM for correct predictions on the vision encoder's tokens. Since correct predictions require those tokens to expose the specific attributes that differ or match between the pair, the gradient pushes the encoder to encode them, replacing the uniform pair-level scalar with attribute-resolved supervision. An auxiliary attention-distillation loss anchors the encoder's embedding to tokens the MLLM attended to, and a standard metric-learning loss shapes the embedding geometry for nearest-neighbour retrieval. The MLLM is frozen throughout and discarded at inference, matching the deployment cost of a metric-learning baseline. SAGA improves Recall@1 by 3 to 6 points over state-of-the-art baselines on CUB-200-2011, Cars-196, FGVC-Aircraft, and iNaturalist Aves on zero-shot image retrieval.

Existing Vision-Language-Action (VLA) models predominantly rely on explicit Chain-of-Thought (CoT) reasoning to bridge perception and action. While effective, this paradigm suffers from high computational costs and error propagation in multi-step tasks. In this paper, we propose Adaptive Variable Alignment VLA (AVA-VLA), a novel Latent Reasoning VLA framework that models reasoning as a sequence of unobservable latent variables, bypassing the need for explicit text generation. However, latent trajectories are inherently susceptible to noise interference and misalignment with downstream objectives. To address this, we introduce a Reinforcement Learning-based Denoising mechanism that treats latent state generation as a sequential decision process, optimizing reasoning trajectories via task-level rewards. Furthermore, we incorporate an Early-Exit Strategy that adaptively terminates reasoning based on state confidence, enabling a dynamic trade-off between depth and efficiency. Extensive experiments on embodied decision benchmarks demonstrate that AVA-VLA achieves a 6x inference speedup over explicit CoT methods while attaining a 98.3% average success rate on LIBERO, improving both efficiency and long-horizon stability over full-reasoning baselines.

Continual vision-language models are commonly addressed through sequential fine-tuning; however, although this paradigm enables adaptation to new environments (tasks), it inherently emphasizes the contribution of previously learned environments (tasks) at the expense of the stability required to preserve previously acquired knowledge. While existing approaches have adequately studied continual learning and catastrophic forgetting in vision-language models (VLMs), the theoretical understanding of modality-specific contributions across a sequence of environments remains largely unexplored. In this paper, we present a new theoretical perspective to understand the cross-modal (vision-language) contributions to consecutive environments. We empirically evaluate our theoretical findings on large VLMs and demonstrate their effectiveness in capturing environment-level cross-modal contributions. Our analysis provides deeper insights into continual VLMs, highlighting their contribution robustness to varying task orders and inter-task similarities, and their improved generalization performance.

Reconstructing articulated 3D objects is important for animation, gaming, and robotic simulations. Recent neural networks can estimate the articulated structure of 3D objects, but their generalization remains limited by the scarcity of annotated data for this task. To address this gap, we introduce Instruct-Particulate, a model that takes a 3D mesh together with a target kinematic specification, including part descriptions, connectivity, joint types, and optional point prompts, and predicts the corresponding kinematic part segmentation and joint motion parameters. The kinematic specification disambiguates the task and allows the model to target annotations of different granularity, thereby making it possible to use more abundant heterogeneous training data. At test time, the kinematic specification can be obtained automatically from large-scale vision-language models, so the model can be applied to any input mesh. To train our model at scale, we construct a heterogeneous dataset of more than 150,000 articulated 3D objects, extending existing publicly available collections with data obtained by partially labelling other 3D models (monolithic or already decomposed into parts) with kinematic labels by means of vision-language models. Experiments show that our model generalizes better across categories and to AI-generated meshes, enabling articulated asset reconstruction from real-world images via image-to-3D models.

Verifier reliability is not portable across tasks. A verifier-guided self-DPO pipeline with genuine held-out gains on MathVista (+9.6 points on self-training data, +8.0 held out) can be harmful on MMMU. The failure is invisible from the target-task self-training signal: over six learner-verifier configurations, MMMU self-training performance still improves by +3.52 points while held-out performance drops by 1.42 points. We call this silent negative transfer: a verifier validated as useful before can still show signatures of successful self-training after its induced update stops transferring to unseen data. Downstream failure alone cannot diagnose this: poor generalization may mean the verifier induces a wrong learning direction, or that the correct direction itself does not generalize beyond the self-training distribution. We separate these effects via gradient fidelity F, the alignment between verifier-induced and correct training directions, and gradient transferability T, the alignment between correct and held-out directions, giving a conservative Safe-Transfer Margin: positive first-order held-out alignment is certified when arccos(F) + arccos(T) < pi/2. We then introduce Asymmetric Acceptance Gating (AAG), a precision-first filter selecting preference pairs by the verifier's absolute confidence in the response receiving the positive update. On MMMU, AAG raises fidelity from 0.29 to 0.42. In a same-cell analysis, the correct direction stays positively aligned with the held-out direction (T = 0.31), yet raw verification rotates the induced update to negative held-out alignment (-0.13); AAG restores positive alignment (+0.22). Across all six MMMU configurations, AAG beats raw verifier-guided training. Verifier reliability thus means not that it worked before, but that it induces the right update on the task at hand and that this update stays useful beyond the data that generated it.

Current representation learning paradigms force a fundamental compromise: self-supervised methods scale to massive datasets but yield opaque features, whereas interpretable models remain bottlenecked by the need for dense human annotation. We introduce Self-Supervised Concept discOvery via Preference lEarning (\model), a label-free framework that resolves this dilemma. Instead of treating Vision-Large-Language Models (VLLMs) as static feature extractors, \model leverages them as active participants in a self-supervised preference optimization loop. By autonomously hypothesizing, validating, and reinforcing candidate visual attributes directly from raw imagery, our framework discovers novel, structured concepts without a single label. Extensive experiments across natural, medical, and physics domains demonstrate that \model successfully extracts domain-specific concepts where standard VLLMs often fail to generate. By amortizing concept discovery directly into the VLLM backbone through our self-supervised preference objective -- rather than relying on static generation and disjoint filtering -- we achieve up to a 24-point absolute improvement in downstream top-1 classification accuracy on unseen data. Our work suggest that interpretability can emerge through a model's autonomous interaction with incidental visual structures, without any human supervision.

Large Vision-Language Models (LVLMs) have achieved remarkable success across diverse multimodal tasks, yet their practical deployment remains constrained by the computational burden arising from lengthy visual tokens. While visual token pruning has emerged as a promising solution, existing methods suffer from a fundamental limitation: once tokens are pruned at a specific layer, they become inaccessible to all subsequent layers, leading to premature information loss that can compromise model performance. Through empirical studies, we observe that different layers exhibit distinct visual region focus, indicating a varying optimal token subset across layers. Motivated by this insight, we propose Adaptive Layer-wise Visual Token Selection (ALVTS), a novel framework that breaks away from the conventional static token pruning paradigm. ALVTS incorporates a lightweight token selector to identify and route important tokens for further processing, while allowing less important tokens to skip the layer, thus minimizing computational redundancy. These two streams of tokens are seamlessly reintegrated before being fed into subsequent layers, facilitating adaptive compression across the entire model. Grounded in our importance consistency constrained low-rank approximation, the proposed token selection module closely emulates the full attention mechanism, effectively capturing its essential patterns without requiring model retraining. Extensive experiments on LLaVA-1.5, LLaVA-NeXT, and Qwen2.5-VL validate the effectiveness of our method. With an 89% token compression ratio, ALVTS retains 96.7% of the original model's accuracy, achieving a superior efficiency-accuracy trade-off for LVLM inference.

Vision-language-action (VLA) policies typically inherit their vision encoder from upstream VLM releases, but it is unclear whether an encoder choice validated on a small VLA transfers to a larger backbone. We introduce a frozen-backbone grafting diagnostic: the vision tower of a released VLA is replaced by a candidate encoder under a fixed protocol (adaptive average pooling, LayerNorm, and a single trainable linear projector), with the language model and action expert frozen. Across four encoders, two LIBERO suites, two backbones (SmolVLA-450M and $π_{0.5}$-3.3B), and two-to-three seeds per cell (40 main grafting runs plus native, LoRA, pooling, and zero-/shuffled-image controls, all scored by offline action MSE), the small-backbone winner does not reliably select the large-backbone top tier: SigLIP is best on SmolVLA across both suites, while on $π_{0.5}$ DINOv2-small leads the spatial suite and the object suite is a seed-sensitive near-tie band; three of the four backbone-suite comparisons (and 11 of 12 seed-level cells) support backbone-dependent rankings. The grafting wrapper is itself non-neutral with opposite sign across backbones (+45-56% MSE on the SmolVLA native tower, -50-52% on $π_{0.5}$), so all conclusions are conditional on the fixed grafting protocol. We position frozen grafting as a cheap target-backbone diagnostic to run before committing to an encoder at scale, not as a closed-loop deployment claim.

Autonomous UAV navigation is conventionally solved by pipelines that separate perception, mapping, and planning into distinct stages, which propagates errors, accumulates latency, and requires environment-specific retuning. End-to-end generative models remove these interfaces by mapping raw observations directly to trajectories, but inherit a subtle failure mode: trained on clean data, they cannot recognise when an observation is unreliable, and treat degraded regions such as glass, mirrors, and overexposed surfaces as valid evidence for planning. We present a reliability-aware diffusion planner for 3D UAV navigation. It conditions trajectory generation on the observation together with a scene-level reliability heatmap that marks where perception cannot be trusted, produced by a lightweight network that distils the open-vocabulary reasoning of a vision-language model within the real-time planning budget. To generalise to unseen environments without retraining, we steer the denoising process with a differentiable two-stage ESDF cost that treats physical obstacles from depth and virtual obstacles from highly unreliable regions on equal footing. In simulation and on a real quadrotor, our planner produces markedly safer trajectories than a state-of-the-art diffusion baseline, reducing the obstacle-violation rate from 40.3% to 9.6% and raising the mean reliability of traversed regions from 0.588 to 0.925. Ablating the reliability term alone drops mean reliability from 0.898 to 0.783, confirming it as the decisive component, while distillation runs the framework up to 2 times faster than the full vision-language model.

End-to-end navigation policies trained on large simulation corpora degrade sharply when transferred to out-of-distribution scenes, categories, or goal modalities. Modular pipelines such as Modular GOAT are bottlenecked by closed-set object detection recall, while 3D snapshot-memory systems (e.g. 3D-Mem) accumulate dense, view-dependent representations that are heavy to maintain. We present AnyGoal, a training-free multi-robot architecture that places a Vision-Language Model (VLM) at the core of frontier-based exploration and coordinates agents through a shared 2D Gaussian Bayesian Value Map (BVM). The BVM maintains a per-pixel (mu, sigma^2) posterior over goal relevance, updated via precision-weighted fusion of VLM scores through a depth-cone mask, and is never reset between subtasks, yielding lifelong evidence accumulation. Frontiers are ranked by a convex blend of a VLM-as-judge softmax and a Bayesian UCB term on the BVM. A greedy allocator with spatial-separation penalty and commitment hysteresis distributes frontiers across agents without a centralized controller. On the full GOAT-Bench val unseen split (360 episodes, 2,669 subtasks), our dual-agent system achieves 52.4% Subtask SR at 12.7% SPL--state of the art under the strict physical regime (discrete 0.25 m steps, no teleportation, 42 deg HFOV) and a +27.5 pp improvement over Modular GOAT (24.9%). Single-agent AnyGoal achieves 41.9% Subtask SR, showing gains arise from the decision architecture. A four-way perception ablation shows that open-vocabulary detectors shift the dominant failure mode from exploration to goal verification.

Diabetic Retinopathy (DR) is an aggressive retinal disease and a leading cause of global blindness, yet its clinical management is currently hindered by the black-box nature of diagnostic AI. While deep learning models achieve high classification accuracy, there is a critical lack of explainability methods capable of detailing the exact anatomical landmarks and lesion distributions that lead to a clinical decision for DR. Therefore, we propose HSQ-VLM, a novel quadrant segmentation pipeline on fundus images that utilizes a Landmark-Anchored Cartesian Cross-Attention mechanism to unify visual feature extraction with structured clinical reasoning. Unlike traditional methods that rely on arbitrary image partitioning, our pipeline implements 4-quadrant Topological Latent Partitioning (TLP) to dynamically align retinal features with a fovea-centered coordinate system. This allows the Vision-Language Model to generate natural language reports that quantify pathology with anatomical precision. On a dataset of 3,500 high-resolution fundus images, this innovative methodology achieved a lesion detection sensitivity of 99.6% for hemorrhages and 96.4% for microaneurysms, while demonstrating a significant reduction in boundary-ambiguity errors compared to standard segmentation baselines.

On-policy distillation (\textsc{OPD}) has recently become a prominent post-training recipe by combining two desirable ingredients: on-policy student trajectories and dense teacher supervision. However, how this hybrid changes a model's parameters remains unclear. Across several language and vision-language model pairs and \textsc{OPD} use cases, our analysis yields two main findings. On sparsity, \textsc{OPD} updates are small and coordinate-sparse. They are distributed across layers, with the largest relative movement usually appearing in FFN modules. This sparse structure is operationally useful: training only the discovered subnetwork nearly recovers full-training performance. The sparse support does not remove the need for adaptive optimization: SGD, previously reported to be competitive in \textsc{RLVR}, underperforms AdamW in our \textsc{OPD} optimizer ablation, suggesting that dense teacher supervision preserves useful momentum structure and heterogeneous second-moment scales. On geometry, the updates are numerically full-rank but spectrally concentrated; they lie mostly away from the principal singular subspaces of the source weights and fall disproportionately on coordinates where the source weights are close to zero. These findings suggest that dense teacher supervision does not turn \textsc{OPD} into ordinary dense parameter rewriting; instead, \textsc{OPD} retains important geometric signatures of on-policy post-training.

This paper argues that a systemic lack of Agency constrains the implicit reasoning capabilities of current Vision-Language Models (VLMs). Implicit reasoning refers to the ability to autonomously discover and utilize hidden visual evidence to bridge information gaps, rather than merely relying on explicitly specified targets. This capacity underlies human visual understanding and everyday reasoning. We argue that this limitation arises from a tendency to approach visual reasoning primarily as passive semantic retrieval, rather than as active, situated reasoning that depends on autonomous visual exploration. As a result, most existing benchmarks primarily assess Passive Capacity, leaving this aspect of reasoning largely unmeasured. To address this gap, we introduce the Visual Implicit Reasoning Diagnosing Benchmark (V-IRD), which targets this missing quadrant by requiring models to derive answers strictly through autonomous visual analysis. Our results show that, despite strong retrieval abilities, prominent VLMs struggle to utilize reference objects and to attend to visual evidence that requires self-directed inquiry. Simply put, strong semantic recognition does not equate to active visual exploration, revealing a critical gap in current VLMs. More information can be found at https://haoychen.github.io/Implicit-Reasoning/

This paper presents Custom ZeroCLIP, a retrieval-augmented vision-language framework for zero-shot captioning of Indonesian traditional garments. The dataset contains 3,800 expert-annotated images from all 38 Indonesian provinces. Using a province-level inductive zero-shot protocol, the model is trained on 24 seen provinces, validated on 6 seen provinces, and evaluated on 8 unseen provinces. The framework combines a frozen CLIP ViT-B/32 image encoder, a CLIP text encoder, a BERT text encoder, and an LSTM caption decoder. During inference, unseen-province labels and captions are unavailable, and retrieval uses only captions from training provinces. No unseen-province image, label, or caption is used during training, validation, or retrieval-bank construction. Custom ZeroCLIP achieves a CLIPScore of 0.8536, BLEU-4 of 0.3342, and METEOR of 0.4859, outperforming existing baselines. Ablation results show that retrieval improves cultural vocabulary recovery with a 19.3% METEOR gain, while human evaluation confirms stronger cultural accuracy and fluency. The results demonstrate the effectiveness of retrieval-augmented domain adaptation for culturally grounded caption generation in low-resource heritage settings. The dataset is publicly available at https://github.com/AnugrahAidinYotolembah/Traditional-Indonesian-Clothing-Captioning-Dataset.

Letting a vision-language model (VLM) think longer at test time has driven much recent progress. A natural way to bring this to spatial grounding is visual self-correction: the model predicts a bounding box, sees it rendered on the image, and refines it over several steps. We build a faithful instance of this idea, Iterative Visual Thinking (IVT), with a two-phase recipe: a supervised warm-up in which the base model's own predictions serve as realistic errors that a teacher VLM turns into corrective reasoning traces (yielding training data without human annotation), followed by GRPO with a simple IoU reward. Measured the way such systems are usually reported, it works: the trained model surpasses the single-shot base by +2.4pp Acc@0.5. We show this gain is a measurement mirage. The reported number silently keeps, per sample, the trajectory step closest to the ground-truth box: an oracle that needs the very answer it predicts. Re-scored under deployable, label-free stopping rules the improvement vanishes, and the best policy is not to iterate at all: stopping at step 0 matches the base and beats every shippable rule. The cause is a verification failure, since the model can generate a better box somewhere in its trajectory but cannot identify it. Self-verification confidence correlates only weakly with correctness (r about 0.22), and a counterfactual overlay shows the loop reacts to the presence of a rendered box rather than its correctness. We distill the lesson into an honest-trajectory evaluation protocol: accuracy under fixed label-free policies plus an explicit oracle-shippable gap.

Vision-Language Models (VLMs) have achieved impressive results on general vision-language tasks, yet they suffer from hallucination, imprecise localization, and prohibitive computational cost when applied to dedicated OCR scenarios. This paper presents PP-OCRv6, a lightweight OCR system that combines architectural innovation with data-centric optimization. PP-OCRv6 redesigns the backbone, detection neck, and recognition neck around a unified MetaFormer-style building block with structural reparameterization, decoupling spatial token mixing from channel mixing and supporting both tasks through task-specific stride configurations. Three model tiers (medium, small, tiny) share the same block primitives, covering deployment scenarios from server to edge. On our in-house benchmarks, PP-OCRv6_medium achieves 83.2% recognition accuracy and 86.2% detection Hmean, outperforming PP-OCRv5_server by +5.1% and +4.6% respectively while surpassing Qwen3-VL-235B, GPT-5.5, and Gemini-3.1-Pro with orders of magnitude fewer parameters. The tiny tier achieves 3.9$\times$ faster inference than PP-OCRv5_mobile on Intel Xeon CPU while maintaining comparable accuracy.

Visualization-based malware detection maps raw binary bytes to grayscale images and applies learned visual classifiers, providing an evasion-resistant and disassembly-free alternative to conventional analysis pipelines. However, executable packing remains a critical failure mode: packed binaries produce high-entropy images that obscure the structural patterns these models rely on. Because packing is also prevalent in benign software (e.g., for compression or copy protection), packing state alone is not a reliable indicator of maliciousness, and existing approaches do not address this challenge within a unified supervised framework. We present ViPER, a Vision-based Packing-Aware Encoder for Robust malware detection. ViPER builds on a LoRA-adapted ViT-B/14 backbone with a dual-head architecture that jointly learns malware classification and packing detection. A packing-aware gating mechanism conditions malware predictions on the inferred packing state, enabling distinct decision boundaries for packed and unpacked inputs. To address packing label skew during training, we employ frequency-weighted losses with stratified sampling over joint class-packing strata. Evaluated on 200,000 Windows PE byteplot images, ViPER achieves a balanced accuracy of 0.8521, ROC-AUC of 0.9260, and AUPR of 0.9279, outperforming representative state-of-the-art baselines across all primary metrics, while attaining a packing detection AUC of 0.9949.

Multi-label recognition with frozen Vision-Language Models (VLMs) is brittle under distribution shift: standard zero-shot inference scores labels independently, ignoring co-occurrence structure and producing incoherent label sets where dominant concepts suppress weaker but compatible labels. We introduce Bayesian Conditional Priors (BCP) Estimation, a gradient-free test-time adaptation method that injects label dependency without tuning the backbone. BCP views zero-shot logits as a proxy for marginal posteriors under a fixed image-text likelihood and attributes shift-induced errors mainly to a mismatched label prior. For each test image, it selects a high-confidence anchor label and applies an anchor-conditioned Bayesian refinement. This update is closed-form in logit space and admits a pointwise mutual information (PMI) interpretation, explicitly promoting compatible labels and suppressing incompatible ones. BCP operates without target annotations by estimating anchor-conditioned priors online from the unlabeled test stream via lightweight second-order co-occurrence statistics, adding negligible overhead beyond a single forward pass. Across standard multi-label benchmarks and multiple CLIP backbones, BCP consistently outperforms strong TTA baselines, e.g., improving RN50 average mAP from 57.31 to 69.22 and ViT-B/16 from 62.61 to 71.79.

While recent vision-language models (VLMs) demonstrate strong multimodal understanding, they remain limited in spatial reasoning tasks that require active evidence acquisition and multi-step visual interaction. This limitation suggests that relying solely on implicit visual representations from vision encoders is insufficient for recovering fine-grained spatial evidence. We introduce PERception-Interaction-reason Agent (PERIA), a tool-augmented visual agent for spatial reasoning tasks across map reasoning, visual probing, and vision reconstruction. PERIA uses two lightweight tool families: vision perception tools for exposing textual, symbolic, and spatial evidence, and vision interaction tools for manipulating visual context, tracing paths, and verifying spatial relations. To train PERIA, we develop a unified recipe that combines supervised tool-use trajectory synthesis, composite rewards, and Observation-Relaxed Group-in-Group Policy Optimization (OR-GIGPO) for effective multi-tool behavior. Experiments on 13 benchmarks from 8 datasets show that PERIA-8B improves over the Qwen3-8B backbone by 10.0% on in-distribution benchmarks and 4.4% on out-of-distribution benchmarks, while outperforming previous state-of-the-art baselines of similar size by 7.0%-14.8%. It also achieves performance comparable to much larger models such as Qwen3-VL-235B-A22B-Thinking and GPT-5, demonstrating the effectiveness of PERIA in enhancing spatial reasoning capabilities.

Vision-language models (VLMs) are increasingly used to detect whether AI-generated images contain visible artifacts, yet their ability to analyze such artifacts remains poorly understood. A correct image-level decision can still hide important failures: a model may correctly flag an artifact while relying on the wrong visual cue, selecting the wrong region, or describing a defect that the image does not support. To evaluate these behaviors directly, we introduce SalArt-VQA, a diagnostic benchmark for fine-grained SALient ARTifact understanding in AI-generated images. SalArt-VQA contains 950 images and 3,681 human-authored multiple-choice questions spanning artifact images, matched real reference images, and paired generated reference images. Four aligned question types evaluate presence detection, semantic localization, spatial grounding, and evidence-grounded defect identification, while the reference splits test calibration and abstention when the annotated defect is absent. Across 20 VLMs, SalArt-VQA reveals failures that image-level detection accuracy hides: the strongest model reaches 99.37% detection recall on artifact images but answers all four artifact-side questions correctly on only 53.26% of images. Comparing artifact images with artifact-free references reveals a sensitivity-calibration tradeoff: sensitive models often make unsupported artifact claims, while conservative models avoid false alarms largely by missing real artifacts. These results show that high artifact detection accuracy alone does not imply grounded artifact understanding. SalArt-VQA exposes these hidden failure modes and provides a fine-grained evaluation of whether VLM artifact claims are supported by local visual evidence.

Large Vision-Language Models (LVLMs) have achieved strong performance across medical imaging tasks, yet they remain prone to factual inconsistencies, poor visual grounding, and misalignment with clinically meaningful feedback. Existing post-training alignment approaches, including Direct Preference Optimization (DPO) and its variants, face three critical limitations in the medical domain: (1) sequence-level reward signals treat clinically critical tokens identically to generic filler text; (2) reliance on static supervised fine-tuning references as preferred responses introduces an off-policy distribution shift, steering optimization toward stylistic artifacts over clinical correctness; and (3) alignment objectives lack explicit visual grounding constraints, leaving models insensitive to subtle yet diagnostically decisive pathological features. Our method leverages a bidirectional token-wise KL regularizer alongside a visual-contrastive grounding objective that pairs clean and lesion-corrupted images to penalize responses generated without adequate visual evidence. Together, these components form a fine-grained, on-policy alignment framework that constructs preference pairs by minimally editing model-generated outputs, correcting only clinically erroneous spans while preserving the original linguistic style. Extensive experiments across medical imaging tasks and clinical text generation benchmarks validate the effectiveness of our approach.

Vision-Language-Action (VLA) models that couple pretrained Vision-Language Models (VLMs) with continuous action experts have achieved strong manipulation performance, yet generalization to out-of-distribution (OOD) language instructions remains poor. A known challenge is the structural imbalance in VLA data, where language is far less diverse than visual and action content, making policies prone to visual shortcuts. While discrete-action methods mitigate this through vision-language co-training, continuous action experts lack such protection: they start from random initialization and learn entirely from imbalanced data, producing noisy gradients that corrupt the VLM and fail to exploit its language capability. We address this from a Bayesian perspective, factorizing the policy into a language-agnostic Vision-Action (VA) prior and a language-conditioned VLA likelihood, and propose APT, a two-stage training method emphasizing Action expert PreTraining. In Stage 1, the action expert is pretrained as a VA prior on vision-action pairs from a frozen VLM, bypassing the language imbalance. In Stage 2, language tokens are injected through a gated fusion mechanism that integrates VLM features while preserving the learned visuomotor prior. APT applies to mainstream VLA architectures, including the $π$ and GR00T-style architectures. Comprehensive experiments validate that APT achieves consistent gains on unseen instructions and compositional tasks. Project Page: https://xukechun.github.io/papers/APT/

High-stakes clinical use of large vision-language models (LVLMs) requires reasoning that is grounded in visual evidence and clinical knowledge, not just correct final answers. We introduce OpenMedReason, a large-scale, open multimodal medical reasoning corpus comprising approximately 450K image-question-answer instances whose reasoning traces are primarily derived from curated biomedical, human-authored scientific articles. OpenMedReason provides high-fidelity supervision beyond synthetic chains of thought, covering diverse medical domain vision modalities such as radiological scans, microscopic images, visible light photographs, charts, and others. We complement it with OpenMedReason-Bench, a held-out benchmark that allows fine-grained evaluation of LVLMs along three complementary axes of capability, including perception, medical knowledge, and rationale, enabling diagnostic evaluation beyond final-answer accuracy. OpenMedReason is a rich training resource that exhibits its effectiveness in both supervised fine-tuning (SFT) and reinforcement-based alignment. Training with OpenMedReason yields a 20% average improvement in VQA accuracy over the base model and achieves performance within 4.2% of the strongest comparable-scale medical LVLMs. Fine-grained performance analysis confirms that the gains are not concentrated in any single axis: OpenMedReason improves perception, medical knowledge, and rationale jointly, and its reasoning traces are preferred over those of the base model in 86.1% of pairwise comparisons. We release the code and dataset at huggingface.co/datasets/neginb/OpenMedReason.

Vision-language-action (VLA) models inherit a shared synchronous clock from vision-language pretraining, processing every input at one rate. This is misaligned with physical interaction, where a high-frequency modality changes at hundreds of hertz, vision evolves more slowly, and language stays constant across an episode. A synchronous VLA oversamples slow modalities, undersamples fast ones, and caps action generation at the lowest effective frequency. We hypothesize that decoupling temporal processing per modality, letting each update and retain information at its own sensor rate, yields stronger representations and more robust control. We present DAM-VLA, which maintains per-modality latent buffers refreshed at sensor rates and read continuously by the action head, integrating new high-frequency modalities through gated cross-attention that leaves the pretrained backbone intact. Across seven contact-rich real-world manipulation tasks, DAM-VLA more than doubles the average success rate of the strongest synchronous baseline (95.2% vs.\ 40.95%) while sustaining smooth, reactive 100,Hz control. Project website: \href{https://intuitive-robots.github.io/DAM-VLA/}{intuitive-robots.github.io/DAM-VLA/}

Sign language translation (SLT) converts sign language video into spoken language text and holds significant promise for improving accessibility and enabling communication between signing and non-signing communities. While large weakly-aligned datasets have enabled pre-training at scale and gloss-free methods have reduced reliance on expert annotation, high-quality parallel sign video-text pairs for fine-tuning remain scarce, limiting generalisation on long-tail vocabulary and unseen constructions. We propose a corpus augmentation approach that requires no additional human annotation, external sign-language video corpora, or generative video models, relying only on the existing gloss-annotated training corpus and an LLM for sentence generation: per-gloss clips are extracted from training videos via CTC forced-alignment, novel gloss-sentence pairs are generated by a corpus-anchored LLM, and synthetic sequences are assembled through random sentence sampling and clip assignment. The resulting synthetic RGB video-text pairs are architecture-agnostic at the downstream training stage and can be consumed directly by RGB-based SLT models, or converted into pose or feature representations by pipelines that derive such inputs from video. Sincan et al. re-evaluated five recent gloss-free methods under strictly identical conditions; the largest verified gain over the GFSLT-VLP baseline was only 0.98 BLEU-4. Our augmentation, applied within the same framework, achieves +2.92 BLEU-4 without any change to architecture or training protocol. We further identify that synthetic data harms vision-language pretraining despite improving its objectives, and that optimising clip transitions for visual smoothness is counter-productive under L2-based criteria; we propose that abrupt boundaries may act as a form of implicit regularisation. Code is available at https://github.com/robizso/slt-datagen.

We propose a new paradigm for long video understanding by treating a long video as a Neural Knowledge Representation (NKR). NKR represents video contents neither as a stream of tokens nor pre-organized databases, but as an individual small portion of network weights attached to the VLM backbone. The NKR weights are optimized to encapsulate the video's semantic content via a novel Agentic Knowledge Distillation (AKD) process, where an agent automatically synthesizes dense descriptions and question-answer pairs to distill the video's knowledge into the NKR. While AKD serves as a comprehensive, one-time encoding phase, the resulting NKR transforms the video into a portable, reusable asset. At inference, the lightweight NKR is mounted onto a frozen Vision-Language Model (VLM), enabling direct, query-based understanding without reloading or re-encoding the original video. This approach decouples video length from inference cost, offering high amortized efficiency for multi-turn video understanding. Experiments on the LVBench benchmark show our method achieves performance comparable to state-of-the-art approaches while reducing end-to-end latency by over two orders of magnitude, opening new possibilities for interactive long-video understanding.

A vision encoder compresses image pixels into semantic embeddings, implicitly acting as a privacy boundary by preserving semantic content while attenuating pixel-local detail required for exact text recovery. Encoder-free vision-language models (VLMs) remove this boundary by routing image patches directly into the language-model token stream, thereby exposing an architectural privacy attack surface: intermediate visual tokens become a pre-output side channel. Under a token-access adversary, decoders invert visual-token streams from two encoder-free VLMs, Gemma4 and Fuyu, recovering recognizable image structure and readable held-out access codes, whereas matched encoder-based controls localize target regions but recover no exact strings. Within-model ablations show that the operative factor is spatial sampling fidelity of the visual-token grid, especially character-direction sampling density, rather than token or value count. The leakage is not limited to exported tokens: Gemma4 layer-0 key-value cache tensors are directly invertible, placing the side channel within KV caches commonly persisted by production serving stacks for decoding efficiency. The attack survives clutter, realistic document degradation, and zero-shot transfer to public document images, and it resists value-level defenses such as additive noise and quantization. Effective mitigation must therefore reduce spatial sampling, making removal of the vision encoder a first-class privacy decision in VLM deployment.

Multimodal Large Language Models (MLLMs) achieve strong vision-language reasoning, but long visual contexts enlarge the KV cache and increase decoding latency. Existing compression methods rely on observation window attention for stable token-importance estimation, yet this aggregation can dilute sparse visual evidence and discard answer-critical tokens under aggressive compression. Therefore, we identify last-query attention as a complementary source for recovering such evidence, but its answer-irrelevant signals can mislead retention. We propose BACON, a plug-and-play method that calibrates observation window attention with last-query evidence and suppresses isolated noise via intra-layer coherence and inter-layer persistence. Across diverse benchmarks, models, budgets, and compression methods, BACON improves multimodal KV compression by 7.5% on average under the most aggressive budget, with gains up to 30.9%. Our project page is available at https://ryu1ion.github.io/official_BACON/

Open-vocabulary scene sketch semantic segmentation aims to assign dense semantic labels to sparse line drawings based on flexible category vocabularies specified at inference time, without relying on pixel-level annotations during training. Unlike natural images, sketches lack texture and color cues, making semantic understanding heavily dependent on stroke layout and spatial configuration, a challenge that renders single-layer vision-language features inherently unstable. Our key observation is that attention maps from different Vision Transformer layers encode complementary spatial cues: shallow layers capture global structural layouts, while deeper layers focus on local stroke intersections and object parts. This suggests that cross-layer aggregation provides a more robust structural prior than any individual layer alone. Leveraging this insight, we propose a structure-aware framework built upon \textbf{L}ayer-wise \textbf{A}ccumulated \textbf{S}tructural \textbf{A}ttention (\textbf{LASA}), which aggregates multi-layer attention to guide hierarchical semantic alignment under weak supervision and refine predictions during inference. Experiments on FS-COCO, SFSD, and FrISS show that LASA improves mIoU by $+3.43$, $+8.01$, and $+15.74$ over the prior weakly supervised baselines, demonstrating consistent gains in both segmentation accuracy and spatial coherence. Our source code will be made publicly available.

Visual causal reasoning is essential for understanding and intervening in the physical world, requiring identification of causal variables from visual inputs and reasoning over intervention effects. Despite recent progress, large vision--language models (VLMs) remain brittle at such tasks, especially for interventional and counterfactual queries over multi-image inputs. Most existing explorations inject causal knowledge via textual prompts, leaving causal mechanisms external to model execution and limiting reliable control during inference. To address this problem, we propose BridgeVLM, which internalizes visual causal reasoning by inducing a causal graph from multi-image inputs and converting it into structured Causal Tokens executed by RAMP layers injected into the LLM decoder for causal message passing. We further introduce a unified training interface M3S for fine-grained causal supervision from different granularities (local/global level). BridgeVLM achieves 54.4% accuracy on intervention tasks on CausalVLBench (vs. 33.2% with prompt-level supervision), improves results on Causal3D from 43.6% to 49.0%, and substantially improves causal structure learning on CausalVLBench ($F_1$: 33.4% $\rightarrow$ 75.1%).

Understanding multi-label images remains a challenging task in computer vision. With the rapid progress of vision-language multimodal learning, vision-language models (VLMs) enable zero-shot recognition without labeled data. However, due to their intrinsic design, these models often prioritize the most iconic object and omit other contextual positives. This intrinsic bias conflicts with the nature of multi-label learning, thereby limiting their applicability. In this work, we propose an unsupervised framework that adapts VLMs from iconic recognition toward inclusive understanding, enabling label-free multi-label image recognition. Our approach consists of two key stages, cutting'' and sewing'': In the cutting stage, we present the multi-sampling response estimator to prevent the model from concentrating only on one single object. In the second sewing stage, the multi-object blend adaptation is introduced to adjust the labels to better conform to the multi-label distribution while preserving the intrinsic characteristics of the original model within only one epoch. Extensive experiments show that our framework significantly outperforms existing unsupervised approaches on four public datasets, even surpassing several representative weakly supervised baselines. These results demonstrate the potential of adapting pre-trained VLMs for more comprehensive visual understanding without manual annotations. Our code is publicly available at https://github.com/iCVTEAM/TailorCLIP.

Frozen vision-transformer (ViT) foundation-model embeddings increasingly serve as the substrate for downstream chest-radiography (CXR) pipelines, yet where small-scale, low-contrast signal is retained or lost in the frozen forward pass has not been systematically quantified across architectures, pretraining domains, and objectives. We probed five frozen ViTs (RAD-DINO, DINOv2-B/14, DINOv3 ViT-7B, BiomedCLIP, MedSigLIP) and a frozen DINO-pretrained ResNet-50 architectural control across three large CXR cohorts (NIH-CXR14, MIMIC-CXR, Emory-CXR; aggregate pool n=492,724) and ChestX-Det10 (n=3,543; 1,462 small-lesion bounding boxes across Calcification, Nodule, Mass). Each model was evaluated with a small-scale-perturbation panel and a region-aware bounding-box-stratified probe on real lesions, comparing three pooling modes from the same forward pass: classification token (CLS), patch-mean (mean over all final-layer patch tokens), and bounding-box-restricted patch-local. On the perturbation panel, CLS embeddings sat at the chance floor (area under the ROC curve [AUC] 0.500-0.524); patch-mean was indistinguishable from CLS on iso-blur and reticular-fine cells but rose with CLS on larger directional-blur footprints, while disease AUC on globally decided tasks ranged 0.642-0.913. Patch-local probes recovered AUC ~1.0 from the same forward pass (per-model mean improvement +0.412 to +0.488); the ResNet-50 control reproduced the chance floor. On ChestX-Det10, image-level CLS classification showed within-class small-versus-large stratum gaps up to +0.243 AUC; bounding-box-level patch-local pooling on the same forward pass recovered AUC >= 0.899 on every (model x class) cell. Frozen ViT embeddings silently suppress small-scale signal at the global-aggregation step; the signal is recoverable from patch tokens conditional on a region of interest.

Modern Vision-Language Models (VLMs) benefit from chain-of-thought prompting and test-time scaling, but these gains often come with prohibitive inference cost due to large visual contexts and long decoding chains. We view this cost through two coupled axes: Visual Context Scaling (VCS), which controls how much visual evidence is passed to the language model, and Visual Reasoning Scaling (VRS), which controls how much inference-time reasoning search is performed. Existing methods typically optimize one axis at a time, leaving the joint allocation of compute across these axes underexplored. We introduce Adaptive Visual Inference Scaling (AVIS), a lightweight policy that adapts both VCS and VRS per query. AVIS realizes VCS through Key Diversity Visual (KDV) pruning, a training-free $O(N)$ key-based rule for removing redundant visual tokens before prefilling, and realizes VRS through adaptive self-consistency, using a learned difficulty predictor to select the number of reasoning rollouts. AVIS is deployment-friendly and compatible with shared-prefill inference, where all rollouts reuse a single prefilling pass and KV cache. Across diverse image and video reasoning benchmarks, AVIS improves the accuracy--compute trade-off relative to VCS-only and VRS-only baselines, and remains effective on top of RL post-trained VLMs while keeping compute and latency low.

Vision-language models like CLIP can provide rich semantic priors for open-vocabulary object detection. However, jointly integrating both textual and visual knowledge into detection architectures remains challenging. In this paper, we propose VL-DINO, an open-vocabulary detector that enhances DINO through more effective exploitation of CLIP's vision-language knowledge. Specifically, a Query-guided Positive Sample Construction (QPSC) module is first developed to construct additional high-quality positive samples, enabling the vanilla DINO framework to better accommodate mixed training across heterogeneous data sources while providing more vision-language alignment signals, thereby incorporating richer textual knowledge during training. A Visual Semantic Encoder (VSE) module is then introduced to distill CLIP visual knowledge into backbone-extracted features, producing fused features for subsequent encoder refinement. Based on the fused features, an Object-Region Semantic Alignment (ORSA) module extracts object-centric region features and aligns them with the corresponding textual embeddings, further incorporating textual cues. In the zero-shot setting, VL-DINO-T and VL-DINO-L achieve 36.3 and 38.1 AP on the LVIS benchmark, respectively, consistently outperforming prior advanced approaches. Extensive experiments demonstrate the effectiveness and competitive performance of the proposed design.

Mining hard, safety-critical scenes from driving logs is bottlenecked by the absence of difficulty labels, and no single proxy, collision risk, trajectory ambiguity, or semantic rarity suffices to find such scenes on its own. We present SceneMiner, a unified, camera-only bird's-eye-view pipeline that emits complementary mining signals from a frozen vision-language backbone in a single forward pass, with no LiDAR or radar: a retrieval embedding for text-prompted scenario search, a multi-label scene-tag distribution, and a continuous physics-based risk score (a motion forecast is a byproduct, not a contribution). Building such a multi-head model exposes our central finding, a failure mode we term cross-task interference: adding or upgrading one head shifts a shared activation stream and degrades weight-frozen sibling heads, so freezing parameters alone is insufficient. Our contribution, identity-preserving multi-task fine-tuning, removes this interference by zero-initializing every new sub-module and freezing every parameter that feeds the shared stream. The mining heads are thereby preserved bit-identically while training only ~102k parameters. The tagging head reaches mAP 0.4614 (micro-F1 0.5557) on 20 scene tags by pooling each scene into 32 visual tokens, and the embedding head supports text-prompted retrieval, validated qualitatively. Code is available at: https://anonymous.4open.science/r/sceneminer_anonymous-64E5

A global shortage of trained sonographers limits prenatal ultrasound screening in low- and middle-income countries, where over half of pregnant women receive no skilled sonography. Current deep learning approaches address detection, segmentation, or classification in isolation, each demanding a separate model and expert-specified labels at inference. We present FADA, a unified vision-language model built on Qwen3.5-VL that performs clinical interpretation, classification, detection, and segmentation through a single interpretation-first pipeline without external labels. FADA distills knowledge from four domain-specific foundation models (FetalCLIP, UltraSAM, USF-MAE, UltraFedFM) via offline pre-computed feature caching. Selective distillation, which applies feature alignment only to annotation tasks while interpretation relies on standard fine-tuning, consistently outperforms full distillation across most evaluation axes. The recommended variant, FADA-SKD, achieves 0.8820 mean Dice for segmentation, 0.7671 mAP@0.50 for detection, and 100% structured interpretation compliance. Expert sonographer validation across 237 images confirms clinically acceptable outputs in both autonomous and human-in-the-loop modes, with 73.5% of interpretations scoring perfectly under clinician guidance. The system is trainable on a single consumer GPU and deployable without cloud connectivity. We validate edge deployment by running the compressed 0.8B model on a commodity smartphone (Qualcomm Snapdragon 7 Gen 1, 12 GB RAM) using llama.cpp with GGUF quantization, completing the full 5-phase pipeline in approximately 60 seconds entirely offline. This establishes a practical pathway for integrating AI-assisted fetal assessment with portable ultrasound devices, directly addressing diagnostic access gaps in resource-constrained settings. Code, models, and data are available at https://github.com/mahmoodphd/FADA.

Vision-Language Models (VLMs) demonstrate strong performance on general multimodal reasoning benchmarks, yet their ability to perform engineering reasoning remains largely unexplored. Unlike general visual question answering, engineering problem solving requires interpreting technical diagrams, selecting governing physical principles, and maintaining physically consistent multi-step reasoning. These capabilities are increasingly important for AI systems used in engineering education, scientific assistance, and technical decision-making, where reasoning failures may produce physically invalid yet superficially plausible solutions. Existing benchmarks primarily evaluate final answers and provide limited assessment of intermediate reasoning processes. We introduce EngVQA, a multimodal benchmark for evaluating engineering reasoning across 5 engineering subjects containing 696 problems. We introduce an 8-stage automatic evaluation framework for assessing VLM-generated solutions. The framework independently evaluates each stage of the solution, enabling fine-grained analysis of reasoning failures. We benchmark multiple state-of-the-art open and closed source VLMs on our evaluation framework and demonstrate substantial limitations in current engineering reasoning capabilities. Human evaluation shows strong agreement with our automated framework, achieving a Pearson correlation of 0.975 and a mean absolute error of 0.67 on a 10-point grading scale. Our results highlight the importance of process-oriented evaluation for reliable assessment of multimodal engineering reasoning systems.

Remote sensing vector mapping aims to generate structured maps of geospatial entities, such as buildings, roads, and water bodies, from remote sensing imagery. In practice, vector maps usually contain multiple category layers and heterogeneous entity structures, requiring a unified model for diverse mapping needs. However, existing methods typically represent vector objects as polygons or graphs, making them suitable only for specific categories: polygons poorly capture topological relations, while graphs often blur instance boundaries. We observe that language, as a natural medium for human communication, offers a flexible and expressive representation that can accommodate heterogeneous map elements, including geometry, semantics, and topolog. Motivated by this insight, we propose Vector Map as Language (VecLang), a unified paradigm that reformulates multiclass vector mapping as structured text generation. VecLang encodes the common elements of different geospatial entities into a GeoJSON-like vector language, enabling cross-category modeling within a shared textual format. To generate this language reliably, we design a progressive vision-language mapping framework that first localizes vectorization units and then generates structured map elements. We further introduce Hierarchical Vector Language Optimization, which uses reinforcement learning to improve syntax validity, content fidelity, and map executability. We also build VecMap-Bench with 54K images and 800K instances, supporting training and evaluation across standard and generalization settings. Extensive experiments demonstrate that VecLang handles both single-class and multiclass vector mapping while achieving strong cross-dataset and open-vocabulary generalization. The model and dataset are publicly available at https://github.com/yyyyll0ss/VecLang.

3D vision-language segmentation aims to segment target objects in 3D scenarios according to the linguistic instructions and visual observations. Prior art heavily relies on the coarse superpoint representation to reduce the computation complexity, which suffers from poor segmentation quality and messy object boundaries. In this paper, we propose the SEGment-And-select (SEGA3D) paradigm for 3D visionlanguage segmentation that directly operates on the fine-grained visual information and is free from the superpoint dependency. Specifically, we first leverage a mask candidate generator to provide fine-grained categorical mask candidates, substantially improving the quality of candidate masks over the superpoint counterparts. Then, a Large Language Model (LLM) is utilized to generate the semantic and spatial information based on the linguistic description and visual features. The LLM output and visual features are fed to the Semantic-Spatial Selector (SSS) to produce the top-ranking mask candidates. Eventually, the Loopback Verification Module (LVM) is designed to yield the segmentation mask from the selected candidate masks. Our SEGA3D attains competitive performance on ScanRefer, ScanNet and Matterport3D benchmarks. Notably, our SEGA3D surpasses the top-performing counterpart by 8.3 mIoU and 5.3 mIoU on ScanNet and Matterport3D, respectively. Codes will be available upon publication.

Zero-shot vision-and-language navigation in continuous environments (VLN-CE) has recently become feasible with large vision-language models (VLMs). However, existing methods typically rely on learned waypoint predictors to propose navigable actions. This severely limits the model's action space and fails to leverage depth inputs effectively. Moreover, memory is commonly handled by accumulating long textual or visual histories with substantial irrelevant context, or by retrieving cross-episode experiences, which weakens the zero-shot setting. In this paper, we rethink zero-shot VLN-CE as an agentic interface between the VLM and the environment, and present AgenticNav, a lightweight navigation harness that exposes action, depth, and memory as callable tools. Instead of choosing from predicted waypoints, the action tool allows the VLM to directly select a target pixel in RGB observations, converting it into executable motion. Depth is exposed through an on-demand pixel-depth tool, enabling the VLM to request precise metric distances only where they matter. For memory, AgenticNav provides a compact map image summarizing the historical trajectory, paired with a recall tool that allows the VLM to selectively revisit past visual observations without overwhelming the prompt context. On the R2R-CE benchmark, AgenticNav establishes new state-of-the-art (SOTA) performance among zero-shot methods given the same VLM backbone. Real-world validation further highlights its zero-shot generalization compared to prior methods. Ablations show that our action tool design outperforms traditional waypoint predictors, and that depth tool and agentic memory further contribute to navigation performance.

Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness. A key property is cross-model transferability, which enables transfer-based black-box attacks. However, existing attacks often rely heavily on the surrogate model, causing cross-model performance drops. One reason is that adversarial optimization may follow surrogate model responses more than input semantics, making the update direction effective on the surrogate but less transferable to unseen targets. We refer to this dependency as surrogate-specific bias. Motivated by this observation, DeBias-Attack improves transferability by correcting surrogate-specific bias in adversarial optimization directions. It maintains two perturbation branches. The main branch optimizes a perturbation on the original image and obtains the adversarial gradient used to disrupt image-text alignment. The reference branch optimizes a perturbation on a weak-semantic image constructed from the dataset mean image with small Gaussian noise resampled at each iteration. Since this weak-semantic image contains little clear visual content, its optimization reflects surrogate responses more than image semantics, and its reference gradient estimates surrogate-specific bias. DeBias-Attack removes the aligned projection of the main gradient on the reference gradient before updating the adversarial image, then performs context-aware text substitution using the updated adversarial image. DeBias-Attack is the first transfer-based VLP attack that corrects surrogate-specific bias through gradient correction. Experiments show strong performance across VLP models, downstream tasks, and open-source and closed-source multimodal large language models.

The cost signal that constrained-RL algorithms optimize against is almost always reactive: the simulator emits a non-zero cost only after a collision has begun, and the Lagrange multiplier of PPO-Lagrangian grows only after the episode budget has been exceeded. At race speeds, where collisions are instantaneous and irreversible, any safety mechanism that waits for cost to accumulate is structurally too late. We present VLM-Safe-RL, a framework that integrates a frozen vision-language model into the CMDP Lagrangian update as an anticipatory cost term. The framework comprises four contributions: (i) Decoupled Dual-Path CLIP, independent reward/cost paths that respect the CMDP's factorization; (ii) VLM-Lagrange, an augmented multiplier update that incorporates a per-step VLM cost as an anticipatory term; (iii) Confidence Gating, a Bayes-optimal weight derived from a logistic noise model on the CLIP margin; and (iv) VLMPPOLag, the composed algorithm. On Safety-Gymnasium FormulaOne L2, our principal evaluation ($n{=}5$ seeds, $10^{6}$ steps, budget $d_{\text{lim}}{=}25$) VLMPPOLag$+$Conf is the only configuration in our default budget comparison that simultaneously retains substantive return ($J_r{\approx}40$) and holds cost within budget on a majority of seeds; the five constraint-aware baselines (PPOLag, CPO, CPPOPID, CPO-CLG, PPOLag-RND) each fail at least one requirement. The mechanism generalizes to held-out MetaDrive Medium (catastrophe rate $41\%{\to}26\%$, 95% bootstrap CI $[-26,-5]$,pp) and shows directionally consistent transfer to Bullet Safety-Gym; we report honestly where it does not (MetaDrive Easy/Hard, Qwen2-VL backbone) and trace the Hard failure to a Lagrangian-regulation pathology rather than the VLM signal itself. To our knowledge, this is the first work to use frozen VLM signals as an anticipatory cost term inside the CMDP Lagrangian update.

Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks. However, these policies offer no guarantees against collisions with task-irrelevant objects in the scene. Existing safety filters sidestep this problem by querying a vision-language model (VLM) to identify obstacles and their locations. This, however, is too slow to run in the control loop and can only be invoked at episode initialization, leaving the filter unable to track moving obstacles. We discover that a small number of attention heads within a VLA model reliably localize the object the policy intends to approach. These heads can be exploited within a training-free safety framework that obtains the active target from the attention heads at every step, treats the remainder of the scene as obstacles, and feeds these into a Control Barrier Function (CBF) filter. Together with a lightweight real-time object tracker, this allows for collision avoidance for non-static obstacles. We evaluate our framework on SafeLIBERO, which we extend with moving obstacles. On the original static benchmark, our method performs comparably to an oracle that uses privileged simulator state to identify the target, emulating a VLM-based identification step run once at episode initialization. On the dynamic variant, where the oracle's init-time target assignment becomes stale, our method substantially outperforms it by 43%, on average. Our findings suggest that the perceptual signals needed for real-time safety filtering are already present within VLA policies and can be exploited without additional training or heavy auxiliary models.

Vision-language-action (VLA) policies provide strong priors for language-conditioned manipulation, but remain brittle in off-nominal states requiring targeted recovery. We propose ReCoVLA -- a failure-conditioned residual recovery framework that keeps a pretrained VLA policy frozen, uses an external vision-language model (VLM) to infer the failure mode and recovery stage, and compiles a structured reward from task-relevant components. Rather than using the VLM to generate actions or rewards directly, ReCoVLA uses it as a semantic reward selector: it predicts a recovery descriptor and reward mask for in-simulation residual-policy training, followed by zero-shot sim-to-real deployment of the trained recovery policies. This decouples high-level failure understanding from low-level corrective control to support different VLAs. Experiments across short-horizon, long-horizon, and contact-rich manipulation tasks show that ReCoVLA outperforms the tested baselines on average. In simulation, our reward compiler improves average success from 36.7% for the fine-tuned $π_{0.5}$ baseline to 66.7%. In physical zero-shot sim-to-real experiments, ReCoVLA achieves the best average performance, with 61.7% success.

Multilingual dictionaries are among the most valuable documentary resources for low-resource and endangered languages, yet many remain available only as scans. For many decades, their digitization and conversion into a machine-readable format was nearly impossible due to language-specific scripts, complex multi-column layouts full of entries with abbreviations and cross-references. Recent vision-language models offer a promising solution, but it is unclear how well they preserve characters, markup, and process lexicographic structure. We introduce MUDIDI, a two-stage framework for multi-lingual dictionary digitization. Stage One evaluates the quality of character recognition and markup preservation; Stage Two focuses on dictionary entry segmentation with subsequent mapping into a machine-readable lexicographic schema, SIL's Multi-Dictionary Formatter. We also release a dataset that consists of human-annotated lexicographic entries collected from 30 public-domain dictionaries featuring diverse writing systems, language families, and formats. We benchmark OCR systems, general-purpose Large Language Models (LLMs), and Vision Language Models (VLMs) on the dataset, demonstrating superior performance of LLMs across most writing systems and languages in both stages, and provide practical guidelines on improving the results for more challenging scenarios. Finally, we show that supplementing additional information, such as dictionary introduction, to the LLMs can improve the quality of the digitized dictionary. Github: https://github.com/naarm-nlp/mudidi

Two-stage post-training -- a Stage-1 warm-start (supervised fine-tuning, SFT, or on-policy distillation, OPD) followed by Stage-2 reinforcement learning (RL) -- is increasingly used for vision-language models (VLMs). We ask what Stage-1 actually controls in a small-data study using Qwen2.5-VL-7B with a same-modality 72B VLM teacher for OPD. First, the three warm-starts reach a narrow $53$--$54\%$ band on Geometry3K internal validation, consistent with the narrow range reported by recent specialized methods; this setup provides little evidence that Stage-1 changes the in-domain endpoint. Second, a matched-recipe, early-stopped SFT improves out-of-domain MathVista by $+2.1$ points, reversing the $-9.5$-point drop of an over-trained variant. The clearest difference is the \emph{entropy regime}: OPD enters RL with substantially higher policy entropy than either SFT initialization, and the separation remains visible through the available trajectories. At the in-domain initialization, OPD also has higher answer diversity and pass@16 ($+2.0$ to $+5.2$ points over SFT), although problem-level bootstrap intervals show that the smaller contrast is uncertain. The advantage is absent after RL (endpoint pass@16 values within $1.1$ points) and on MathVista (six models within $1.2$ points). Our contribution is therefore a bounded empirical characterization: Stage-1 is strongly associated with the entropy regime in this setup, but the downstream payoff is small, localized, and not evidence that OPD is a better RL warm-start.

Vision-language models (VLMs) with varying performance and resource requirements are widely deployed, making it difficult for users to select the most appropriate one among numerous VLM candidates. Existing work reveals the performance paradox phenomenon in language models and focuses on routing methods to solve it. However, developing a router for VLM selection is still a critical yet challenging problem, which primarily faces: 1) lack of specialized data, 2) ineffective feature representation, and 3) rigid model space and costly adaptation. In this paper, we construct a multimodal dataset for VLM selection, containing the outputs of seven mainstream VLMs on 32,626 unique image-text queries. We then propose ARMS, a router for VLM selection. ARMS enhances input signals with VLM profiles, employs a simple but effective architecture to improve representations of queries and VLM capabilities. To improve ARMS' adaptation to new VLMs, we propose two extension training strategies: incremental training and independent training. Experimental results on both in-distribution and out-of-distribution test sets demonstrate the effectiveness of ARMS. In particular, using our training strategy, ARMs (only 800M in size) can adapt to a broader VLM space and defeat commercial models like GPT-4o that are hundreds of times larger in scale. Our code, models, and datasets are available in the anonymous repository.

Semiconductor lithography inspection requires reliable detection of small pattern defects such as bridge, burr, pinch, and contamination. In this study, we propose a two-stage vision-language framework that combines initial defect detection with prediction refinement. In the first stage, Qwen3-VL is fine-tuned with LoRA as a vision-language adapter to predict defect counts, defect categories, and normalized bounding boxes from lithography images. However, direct fine-tuning may still produce common test-time errors, including false positives, missed defects, and incorrect defect types. To address this limitation, the second stage trains a refinement module using first-stage prediction failures and their corrected labels, allowing the model to review and revise initial outputs. By learning from cases where the initial adapter fails, the refinement process improves defect inference beyond single-stage fine-tuning.

Reasoning Vision-Language Models (VLMs) achieve strong performance on complex multimodal tasks, but reliable real-world application requires handling visual inputs that are messier than clean, curated benchmarks. Existing works mainly evaluate such reliability of VLMs through input corruptions, such as noise, blur and weather effects, which make visual evidence harder to perceive. This leaves a critical reliability failure mode underexplored: a model may perceive the evidence correctly, yet reason from plausible but irrelevant and distracting evidence and propagate this mistake to its final answer. To address this gap, we introduce \textbf{Distract-Bench}, a benchmark for evaluating VLM robustness to \textbf{semantic visual distractions}, defined as meaningful but task-irrelevant visual cues added to inputs while preserving the ground-truth answer. We comprehensively evaluate eight leading open-source and two closed-source VLMs across conventional vision corruptions and Distract-Bench. Our results show that Distract-Bench exposes a robustness failure distinct from vision corruptions: reasoning VLMs largely track their non-reasoning base models under perceptual degradation, but show consistently lower robustness to semantic distractions. Further analysis shows that these distractions often enter the reasoning process of VLMs, are treated as evidence, and lead to incorrect answers. Together, these findings reframe robustness evaluation for reasoning VLMs, shifting the focus from degraded perception to distractions for reliable real-world visual reasoning. Our data and code are available at https://github.com/Yizheng-Sun/Distract-Bench.

Images can be segmented based on visual cues (i.e., texture segmentation) or into objects (i.e., semantic segmentation). We propose a new category of sub-semantic image segmentation that blurs the line between the two. In sub-semantic image segmentation, language is not used to name whole objects. Instead, it is used to partition an image into stable appearance patterns that can be described by language. To do that, we couple a general-purpose vision-language model to SAM 3, a promptable segmentation backbone whose native text pathway can ground rich descriptions into masks. Simple coupling fails for a number of reasons that we identify in the paper, and we overcome them by introducing DETECTURE that resolves three concrete failure modes -- language leakage between texture regions, prompt competition inside the segmentation backbone, and semantic distortion at the language-to-mask interface. Since there is no dataset of sub-semantic image segmentation, we introduce one, termed TextureADE. The new dataset is derived from the ADE20K dataset using a system we designed. We compare DETECTURE to a number of baselines and find that it achieves the strongest performance on several datasets using different metrics. Code is available at https://github.com/Scientific-Computing-Lab/TextureDetecture.

We present BLUE, a minimal method for better language use in vision-language-action (VLA) models for autonomous driving (AD). Through extensive analysis, we reveal that language matters on only a small fraction of routes, but on those routes it can greatly improve or degrade performance. Generating language at every frame is therefore inefficient, since most computation is spent on frames that do not benefit from language. We further show that pretrained VLA hidden states potentially already encode whether language will benefit a given frame, even though scene complexity and kinematic features alone struggle to predict this. Based on this finding, BLUE trains a lightweight gate on frozen VLA hidden states to decide per frame whether to activate language generation or predict actions directly, without modifying the backbone or requiring additional human annotation. With just a 0.11M-parameter gate, BLUE sets a new state of the art on both benchmarks, achieving 76.2% success rate on Bench2Drive and 36 driving score on Longest6 v2, while delivering 2.54x inference speedup and 8.9% success rate improvement over the backbone. BLUE provides a practical path toward efficient language-augmented AD, showing that VLA models can retain the benefits of language at a fraction of the cost. Our code, data, logs and checkpoints are fully available on https://github.com/George-Ling3/BLUE.

Modern Vision-Language-Action (VLA) models must bridge pretrained vision-language reasoning and precise continuous robot control. Existing action tokenizers discretize actions primarily for reconstruction, producing codes that preserve motion geometry but provide only weak semantic supervision to the backbone. We therefore formulate action tokenization not as mere compression, but as semantic interface learning between multimodal reasoning and executable control. To this end, we introduce X-Tokenizer, a lightweight encoder-Semantic Residual Quantization (SRQ)-decoder architecture that provides a shared action interface across diverse robotic arm embodiments. Its key component, SRQ, imposes an asymmetric structure on residual vector quantization: the first level is trained with Masked Action Modeling (MAM) to form a discrete action language that captures coarse motion intent, while deeper levels remain reconstruction-oriented residuals that preserve fine-grained details. To further align action tokens with multimodal semantics, X-Tokenizer is pretrained with contrastive alignment to the representation space of a pretrained foundation model and with next-frame vision-language feature prediction. Pretrained on 2.4M trajectories (2.0B action frames), a single frozen X-Tokenizer plugs into a mixed discrete-continuous VLA as a representation-shaping supervision signal. X-Tokenizer achieves top real-world aggregate and strong RoboTwin 2.0 simulation results. Outperforming FAST in multimodal grounding (+13.5%) and long-horizon tasks (+8.25), it shows that action tokenizers serve as semantic interfaces for VLA pretraining beyond mere action compression.

Reward models play a pivotal role in reinforcement learning (RL) and multi-modal trajectory selection for autonomous driving. However, acquiring such rewards typically relies on hand-crafted rule-based objectives or perception ground truth, which hinders generalization for data-scaling. While Vision-Language Models (VLMs) have demonstrated feasibility as reward models in other domains, their effectiveness in driving tasks remains underexplored. In this work, we bridge this gap by (1) introducing DriveReward, a reasoning trajectory evaluation dataset rigorously labeled via temporally-grounded visual guidance, and augmented with counterfactual driving behaviors., (2) alongside a specialized Vision-Language Reward Model. To address the scarcity of failure cases in conventional datasets, we propose a counterfactual data annotation scheme to construct cases encompassing diverse driving styles and erroneous behaviors. Evaluations on our proposed benchmark reveal that even leading open-source and proprietary VLMs fail to excel across all tasks, highlighting significant room for improvement in existing models. Building on these findings, we subsequently tailor a specialized 1B reward model that outperforms larger VLMs on task-specific reward alignment. Finally, we validate our reward model's effectiveness by integrating it into RL finetuning and multi-modal trajectory scoring across multiple baselines, achieving performance comparable to rule-based reward calculations in both open-loop and closed-loop evaluation.

Vision-language models (VLMs) pretrained on large-scale image-text pairs demonstrate strong image-level understanding, but are primarily optimized for global alignment and do not explicitly encode fine-grained anatomical structure, limiting their suitability for spatially precise tasks such as segmentation. We introduce CheXanatomy, a framework that integrates explicit anatomical knowledge into a pretrained VLM through autoregressive token-space supervision. Instead of adding task-specific decoder heads, the model is trained to generate anatomical segmentation masks via next-token prediction. To enable scalable supervision, we synthesize realistic chest radiographs from CT volumes and forward-project CT segmentation labels to obtain anatomically consistent 2D masks. We evaluate the approach on synthetic and real chest radiographs against a U-Net baseline, including ablations on model scale, input resolution, and vision encoder fine-tuning. Autoregressive anatomical supervision achieves performance comparable to specialized convolutional models in-distribution and demonstrates improved geometric robustness under domain shift to real CXR data. In addition, anatomy-pretrained models exhibit improved sample efficiency when adapting to novel localization tasks under limited supervision. Larger models and higher input image resolution improve performance, while vision encoder fine-tuning has limited effect. These results show that embedding anatomical structure directly into the generative objective promotes spatially grounded representations and supports anatomy-aware medical vision-language modeling.

Perceptual uncertainty is a central challenge for heterogeneous robot teams operating in unstructured outdoor environments, where no single viewpoint affords reliable scene understanding. Perceptual uncertainty, arising from sources such as occlusions, manifests differently across robot viewpoints depending on scene structure. Detecting and resolving sources of perceptual uncertainty requires both scene-based contextual reasoning and capability-aware robot allocation. While vision-language models provide strong semantic priors for both, they are computationally prohibitive for onboard inference and lack calibrated uncertainty quantification. We introduce Co-GLANCE, a real-time onboard perception and decision-making system for uncertainty resolution in heterogeneous robot teams. Co-GLANCE distills the semantic reasoning capabilities of a vision-language model into an end-to-end model for occlusion segmentation and robot allocation, eliminating the need for cloud-based inference. To quantify perceptual uncertainty, Co-GLANCE combines conformal prediction with selective abstention to provide statistically valid coverage guarantees for segmentation, robot allocation, and detection outputs. These calibrated uncertainty estimates directly trigger active perception, dispatching the most appropriate robot to acquire informative viewpoints and resolve uncertainty. Across real-world scenarios, Co-GLANCE outperforms cloud-based vision-language model baselines in occlusion segmentation and robot allocation accuracy by 25% and 36%, respectively, while reducing per-frame inference latency 350x. We also release an air-ground dataset for future research. Code, videos, and dataset available at https://co-glance.github.io/ .

Long-horizon robot operation requires spatio-temporal memory to record the environment state and recall it for downstream reasoning. Scene graphs and retrieval-augmented systems ground VLM descriptions to persistent 3D entities with rich semantic descriptions. However, VLM captions are noisy and viewpoint-inconsistent, and existing systems treat them as an oracle with no mechanism to detect unreliable stored descriptions. We introduce object-level semantic uncertainty for multi-view VLM memory: a score that measures object-centric cross-view semantic scatter of captions and identifies semantically unresolved objects. Then, we include our uncertainty scores in an advanced spatial-semantic memory system, that we dub UQ-DAAAM. UQ-DAAAM uses this score to actively refine uncertain objects under a fixed query budget by selecting high-quality views and fusing the resulting multi-view captions into a single object description. We also derive probabilistic guarantees showing that higher-quality candidate views (as selected by our approach) are more likely to reduce uncertainty. Our experiments show that uncertainty quantification can make embodied 4D memory systems more reliable and more effective. In particular, on the OC-NaVQA benchmark, UQ-DAAAM achieves substantially larger uncertainty reduction and better spatio-temporal question answering performance than baselines.

Vision-language models (VLMs) enable visual recognition from semantic class descriptions, which makes them attractive when target annotations are scarce or unavailable. Most deployment pipelines, however, first choose a single VLM and then adapt that model to the unlabeled target set. This single-backbone paradigm hides a critical assumption: the selected VLM is already compatible with the target domain. In realistic cross-domain deployment, several general-purpose and domain-specialized VLMs may be plausible, yet no instance-level target labels are available to identify the reliable ones. Deployment therefore requires a coupled solution for model selection, target adaptation, and prediction integration. We revisit this problem from a system-level multi-VLM perspective. Our central observation is that the three decisions above depend on the same latent object: a trustworthy sample-class structure in the target set. Different VLMs may encode different transfer biases and produce conflicting predictions, but their outputs can still provide complementary evidence for estimating this structure. We propose One Stone, Three Birds, a training-free framework based on self-adaptive optimal transport. Given a pool of frozen candidate VLMs, OSTB estimates a consensus sample-to-class transport plan without updating VLM parameters. The learned transport structure is then reused for all deployment objectives: model selection is performed by ranking the combined semantic and visual reliability induced by the consensus plan; target adaptation is obtained by fitting transport-conditioned visual classifiers; and ensembling is implemented through reliability-aware probabilistic integration. Extensive experiments on natural-image, remote-sensing, and medical-pathology benchmarks show that OSTB improves model ranking, adaptation stability, and ensemble robustness under heterogeneous candidate pools.