Large Vision Language Models

While Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities, they remain highly susceptible to embedded social biases. Existing bias evaluation protocols predominantly rely on static datasets, which provide only a superficial assessment, as their fixed test cases cannot adaptively evolve to measure the true depth and limits of model vulnerabilities. We introduce DeepBias, an adaptive framework for the in-depth probing of social biases in LVLMs with carefully designed agents. Our approach operates through a dynamic ''generation-evolution-probing'' loop. First, a generative ProposerAgent synthesizes test data and is iteratively updated via Direct Preference Optimization (DPO) based on the target LVLM's responses, exploring model-specific failure modes. Second, an autonomous skill-driven DiggerAgent rewrites each test data across multiple probing turns, adaptively selecting from a curated skill library of deepening and rewriting strategies. At each turn, this process is conditioned on the model's previous response, enabling progressively deeper biases to be exposed. Furthermore, we build a benchmark named DeepBiasBench using our framework. By employing an ensemble of five diverse state-of-the-art LVLMs as anchors, the benchmark captures vulnerabilities shared across architectures. Comprehensive experiments demonstrate the effectiveness of our framework and show that DeepBias provides a challenging benchmark for in-depth bias evaluation, establishing an evolutionary paradigm for LVLM safety assessment.

Recent advances in text-to-image (T2I) generation have led to models capable of producing highly realistic images. Yet, reliably evaluating their outputs remains challenging, especially at scale. Existing automatic evaluators, often relying on a static prompt set, struggle to capture subtle failure modes such as partial prompt misalignment, compositional errors, or visually plausible but semantically incorrect generations. In this work, we introduce DynEval, a Dynamic Evaluation framework designed to jointly assess text-to-image alignment and image quality of T2I models. To support scalable training beyond limited human-annotated data, we construct two large datasets. First, we build GenDB, a collection of 500K prompt-image pairs generated from human-written prompts drawn from DiffusionDB using a tiered prompt-model generation strategy. Second, building upon GenDB, we construct DynEvalInstruct, a 250K instruction dataset comprising prompt-image-response triplets distilled from a structured evaluation pipeline that decomposes evaluation into text-image alignment and visual quality reasoning. Using this dataset, we perform full fine-tuning of a compact evaluator through a curriculum learning strategy to effectively distill the superior evaluation capabilities of a larger teacher vision-language model, resulting in DynEval-2B and DynEval-4B. In extensive comparisons against existing evaluators across 11 benchmarks, our evaluator achieves a higher overall correlation with human judgments. Furthermore, it provides fine-grained analysis of the capabilities and failure modes of 36 T2I models across 42 subcategories and 9 semantic dimensions.

There's been a surge in adoption of video conferencing applications for both personal and business use cases. However, the bandwidth limitations faced by many users worldwide may restrict the optimal use of such applications. Although deep learning offers a solution for enhancing low bit rate videos, most models today are either hard to incorporate with modern compression standards or require specialized hardware to run such as significant GPUs making these models impractical. To address these issues, we introduce the Realtime Face Video Enhancement (RTFVE) model which can be easily incorporated with any video decoder and can run in realtime on ordinary CPUs. Experiments show that our model improves perceptual quality over the compressed video baseline at multiple low bitrate settings. The source code will be made available at https://github.com/varun-jois/RTFVE.

As mobile robots become more integrated into everyday human environments, social robot navigation is becoming essential for ensuring human comfort, safety, and trust. While reinforcement learning (RL) navigation policies provide the fast inference and reactive behavior necessary for real-time deployment, they still lack flexible semantic reasoning capabilities and often fail to generalize to complex social scenarios. Recent approaches have increasingly turned to vision-language models (VLMs) in place of RL policies to improve semantic and social reasoning in robot navigation. Nevertheless, their high computational cost and slow inference remain major barriers to real-time deployment. To overcome these limitations, we introduce HUMA (Hybrid Understanding for Multi-modal social Navigation), a hybrid architecture that dynamically balances the computational efficiency of RL policies with the deep semantic understanding of VLMs. Our approach uses a reactive RL policy to handle low-density, routine navigation tasks, while conditioning it on a post-trained high-level VLM when a human enters sensitive situations, such as the robot's proximity zone. We evaluate HUMA on the Social-MP3D and Social-HM3D benchmarks, where it achieves task success improvements of 20% and 3%, respectively, while significantly reducing personal space violations and human collisions against state-of-the-art baselines. Extensive ablation studies validate each architectural component, and real-world deployment on the Mirokaï mobile robot further demonstrates the practical viability of our approach.

Automated evaluation is essential for scaling generative 3D systems, where exhaustive human review is costly and slow. However, the reliability of an automated judge depends on the entire evaluation pipeline, not only the underlying vision-language model (VLM), but also how assets are rendered, what visual evidence is provided, how the task is specified, and how human reference labels are constructed. We introduce 3D-DefectBench, a benchmark and framework for systematic analysis of VLM-based 3D defect detection pipelines. It complements holistic ratings and pairwise preferences with nine fine-grained binary defects spanning geometry, texture, and prompt adherence, providing actionable diagnostics for generator development and judge evaluation. Using a balanced factorial design, we vary four pipeline factors, VLM, camera protocol, visual input, and prompt schema, across 84 inference designs and approximately 3.2 million scored defect decisions, followed by staged validation on a broader set of frontier models. Model choice is the largest determinant of agreement with human labels, but the remaining factors also affect performance, interact with model selection, and can change the best configuration. Within the evaluated design space, a compact six-view RGB protocol performs comparably to denser multi-view settings and inputs augmented with depth or surface normals, making it a strong cost-effective default. Under this standardized pipeline, the best of 12 VLM judges still lag behind trained human labelers, while texture agreement drops sharply when expert-consensus labels are replaced by noisier silver labels. These findings show that automated judges should be evaluated as complete pipelines and calibrated across human reference regimes, rather than benchmarked only as standalone models. We release labels, prompts, predictions, and Croissant metadata on Hugging Face.

Assembly action understanding is a key enabler for effective human-robot collaborative assembly, yet it remains challenging due to subtle motions and fine-grained hand-object interactions. We adapt vision-language models (VLMs) to this challenging domain with Compositional Context Fine-Tuning (CCFT), a method that decomposes assembly actions into semantic elements (Verb, Object, Tool) and fine-tunes VLMs to recognize each action element using templated question-answering pairs. This approach ensures near-deterministic outputs. To enable efficient and effective multi-task learning under limited data, a Layer-Partitioned Alternating Training (LP-AT) method is presented, which assigns distinct model layers to recognize specific action elements through element-specific low-rank adapters. LP-AT alternates weight updates across element-specific adapters, reducing cross-task interference while enabling per-adapter hyperparameter optimization. Furthermore, we create HA-ViD-VQA and IKEA-ASM-VQA datasets from existing assembly video datasets. Extensive experiments on these datasets demonstrate that our method consistently outperforms strong action recognition baselines while providing interpretable element-level predictions that can support diverse downstream applications.

Large Vision Language Models (LVLMs) require strong reasoning over both visual and textual input. Recent work suggests that cognitive elements, especially diverse representations and metacognition, correlate with better performance. Many of the needed perceptual functions are already provided by specialized domain-specific computer vision models, which act as the perceptual subsystem for detecting objects, localizing them, inferring states, recovering spatial layout, and reading text. The key challenge is to integrate these multi-encoder experts into a trustworthy, interpretable, and coherent representation that improves verifiability and reduces hallucinations. This is difficult because vision-language questions span different cognitive levels, yet most LVLM pipelines apply the same perception-reasoning routing regardless of the demand of each query. We propose an evidence-driven multimodal reasoning framework that utilizes a Bloom-inspired taxonomy as a hierarchical reasoning protocol. The two-stage cognitive verbalization first produces a Literal Evidence Summary by decomposing expert outputs into short, atomic evidence statements. It then performs Bloom Verbalization to turn these evidence items into a staged reasoning trace, and a lightweight Reasoning Trace Module quantitatively analyzes the trace to make evidence usage and reasoning progression explicit. Through this integration, we observed several improvements in perception and reasoning abilities. Moreover, the trace module provides quantitative evidence that different queries induce different cognitive entry levels and evidence-use trajectories that enable fine-grained analysis.

Deploying AI-based visual inspection in manufacturing is hard because requirements change often, new defect types appear, and large labeled datasets are rarely available. We propose answer-conditioned chain-of-thought (CoT) distillation for rapidly adapting small vision-language models (VLMs) to new industrial tasks using minimal labeled data. A frontier VLM receives each training image along with its correct label and generates a justified visual explanation. A 3B-parameter model is then fine-tuned on these reasoning-augmented examples via LoRA. By conditioning on correct answers, we ensure all training reasoning is directed toward the correct conclusion, which is critical because frontier models score as low as 24.1% on our hardest task. We validate on four industrial classification tasks spanning three image modalities using only 18 to 30 labeled images per task. Across 4 seeds per task (32 training runs), our method outperforms direct fine-tuning on all 16 seed-task combinations, with mean improvements of +1.7 to +4.4 percentage points. A controlled equal-budget experiment confirms the improvement comes from reasoning quality, not additional training steps. An unconditioned baseline demonstrates that with out answer-conditioning, wrong reasoning degrades performance by 17.8 percentage points. On weld radiograph classification, the fine-tuned 3B model outperforms GPT-4.1 by 10.0pp using just 24 training images.

Zero-shot object-goal navigation aims to enable an intelligent agent to explore and navigate to objects of unknown categories in an unfamiliar environment without specific target training. In zero-shot navigation tasks, pre-trained large models are usually employed to leverage their prior knowledge for guiding the agent's navigation. However, existing zero-shot object-goal navigation methods based on large language models (LLMs) merely utilize LLMs as flat reasoning tools to directly associate objects or regions. They lack the hierarchical spatial cognition modeling of human-like room semantics to object localization, which leads to strong blindness in exploration, insufficient accuracy in semantic association, and failure to fully unleash the common-sense reasoning potential of LLMs. This paper proposes an LLM-driven hierarchical room-to-object (HRO) framework for zero-shot object-goal navigation, which guides the agent to explore and navigate to the target object in a coarse-to-fine manner. Experiments on Gibson and HM3D datasets verify that our HRO framework achieves superior success rate and generalization over existing LLM-based methods, underscoring LLMs' strong potential for zero-shot object-goal navigation.

Visual Language Navigation foundation models aim to unify deep reasoning for grounded spatial decisions with broad versatility for diverse embodied tasks. Current approaches typically achieve this integration via monolithic policies that map observations directly to actions, yet they often suffer from coordinate drift and poor handling of long-tail semantics. Furthermore, these black-box mappings lack interpretability, hindering the simultaneous achievement of generality, robustness, and transparency. We present ABot-N1, a step toward a general Visual Language Navigation foundation model, that addresses these challenges by decoupling cognition from control via a slow-fast architecture guided by dual visual-language signals. More specifically, a slow vision-language reasoner performs explicit Chain-of-Thought reasoning while producing a pixel goal. This compact set of image-space anchor points serves as a universal interface for diverse tasks, including point-goal, object-goal, poi-goal, instruction-following, and person-following. Subsequently, a fast action expert leverages both the textual cues and the pixel guidance to generate continuous waypoints at the native control frequency. By bridging high-level intents and low-level control through pixel-grounded anchors paired with explicit linguistic traces, our approach ensures robust, generalizable, and interpretable navigation across simulation and real-world benchmarks. ABot-N1 establishes new state-of-the-art records, delivering massive gains specifically in urban-scale navigation: boosting POI arrival by 35.0% (to 77.3%) and achieving 95.4%/92.9% SR in complex indoor and outdoor scenes. It also maintains superior robustness across object-reaching, person-following, and instruction-following tasks. New Point-Goal/POI-Goal benchmarks are released as open source to advance the field of urban-scale navigation.

Deploying billion-parameter Vision-Language-Action (VLA) models on industrial hardware requires fine-tuning to bridge the embodiment gap. Full Fine-Tuning (FFT) provides maximal plasticity but requires data centre-grade GPUs. We present a systematic study of Low-Rank Adaptation (LoRA) for $π_0$, a flow-matching VLA, evaluated on four precision assembly tasks with a UR5e robotic manipulator. Across a sweep of LoRA ranks (r=8 to 256), allocation strategies, and component-freezing ablations, we find no statistically significant advantage of FFT over certain LoRA configurations. Performance saturates at r=32, and uniform allocation across the Vision-Language-Model (VLM) backbone and action expert proves sufficient. Freezing the VLM or restricting the vision encoder to LoRA significantly degrades performance, indicating that embodiment adaptation requires both semantic and visual plasticity. These results suggest that LoRA at r=32 with full vision encoder fine-tuning is a practical approach, reducing static peak VRAM from 36.2 to 10.8 GiB (parameters and optimizer states, activation memory excluded) without detectable performance loss.

Gaze target estimation aims to infer the position of a person's gaze within a scene. Within mainstream design logic, multi-branch methods require extra supervision and annotations, while streamlined designs prioritize low-level visual saliency over true gaze intent. The former leads to a high annotation burden and hinders domain transfer, whereas the latter causes misalignment between predicted attention and actual gaze targets. To address this issue, we propose TextGaze, a unified cross-modal architecture that leverages a Large Vision-Language Model (LVLM) as scalable semantic guidance to balance the two design paradigms. The model extracts visual features from a frozen encoder and utilizes an LVLM to obtain gaze-aligned textual cues. We design a transformer-based fusion module with hierarchical text supervision to preserve task semantics. Lightweight decoding heads enable the joint prediction of gaze heatmaps and in-/out-of-frame status. We evaluate our method on four mainstream datasets, and the results show competitive performance across key metrics with robust cross-dataset generalisation without extra fine-tuning. Overall, we provide a streamlined alternative to traditional designs and highlight the potential of LVLMs as accessible auxiliary guidance for gaze estimation.

Vision language models (VLMs) have made remarkable progress in visual reasoning during the last decade. Most evaluations have used simple scenes (MS-COCO) that do not showcase complex human interactions or behaviors, only a handful of non-curated human descriptions as a benchmark, and have not focused on understanding the model's error types. Here, we introduce the Complex Social Behavior (CSB) dataset, containing 100 images depicting complex social interactions/behaviors. We analyze the progression of scene descriptions over a decade (2017-2025) of VLMs (four pre-Multimodal Large Language Models, MLLMs, and five MLLMs). We evaluate the accuracy of the models and 20 human descriptions relative to a gold standard on the CSB dataset and on a sample from MS-COCO. We analyzed five visual-cognitive error types: object detection, recognition, hallucination, scene understanding, and spatial dependence. The CSB dataset showed a more pronounced improvement than MS-COCO in scene description accuracy, with pre-MLLMs achieving much lower accuracy than the bottom-ranked human descriptions and MLLMs attaining accuracies similar to the top-ranked human descriptions. We show that MLLMs have eliminated the gap in scene description accuracy between simpler MS-COCO scenes and scenes depicting complex behaviors (CSB). MLLMs have almost eliminated all error types in our tested datasets, except for occasionally relying on different image regions for scene descriptions than humans do (spatial dependence error). We also show that detection, recognition, and hallucination errors have the highest impact on scene description accuracy. Together, our findings provide a more thorough evaluation of how visual language models have advanced over the last decade.

Foundation models are reshaping computational pathology, yet their capabilities remain shaped by pretraining objectives, data sources, and spatial scales, fragmenting complementary expertise across separate backbones. Here we present ALICE, a unified foundation model trained through multi-stage agglomerative distillation that sequentially distills eight vision-only, vision-language, and slide-level teacher models into dedicated modules of a single backbone. ALICE is pretrained on 24,985,184 tile-level pathology images and 155,604 high-resolution images, and evaluated across 21 task scenarios, 96 downstream tasks, and 48 data sources, spanning region-of-interest tissue analysis, vision-language multimodal evaluation, and whole-slide clinical assessment. In all three evaluation settings, ALICE achieved the best average rank among task-matched pathology foundation models. These results demonstrate that agglomerative distillation can consolidate complementary capabilities from specialized models into a unified backbone for broad computational pathology applications. The model is available at https://github.com/WonderLandxD/ALICE.

Vision-Language Models (VLMs) are the perceptual backbone of embodied AI, but their energy footprint on edge hardware remains poorly understood. Existing efficiency efforts focus predominantly on reducing visual tokens, implicitly treating visual processing as the dominant energy cost. We overturn this implicit assumption through the first systematic energy profiling of on-device VLM inference, spanning five models across three architecture families, four input resolutions, and two hardware platforms (NVIDIA RTX 3070 and Jetson Orin NX). Our analysis yields three findings. First, average inference power is a model-intrinsic constant, invariant to input resolution, image complexity, and prompt type, with less than 5% variation across all conditions. This means that all energy variation across inputs must arise from variation in inference time, not from variation in power draw. Second, each output token costs 11 to 39x more wall-clock time than each input token due to the compute-bound and memory-bound asymmetry between prefill and decode, making output token count the dominant driver of both latency and energy. Third, image complexity, measured by the number of objects in an image, induces up to 4.1x energy differences at identical resolution. This variation arises not from increased visual processing cost, but from differences in output length. These findings expose a fundamental limitation of visual token pruning: even removing all visual tokens saves at most 10% of total energy for fixed-token models. Across models spanning 1 billion to 8 billion parameters, controlling output length saves up to 97% of total energy, with the energy dominance of decoding growing stronger at larger model scale. In short, the true energy bottleneck in edge VLM inference is not what the model sees, but how much it says.

Text-guided medical image segmentation leverages clinical semantics to improve lesion delineation, yet many existing models bind cross-modal fusion, supervision, and decoder design into a task-specific architecture. Such tight coupling makes it difficult to reuse language guidance modules across heterogeneous vision and text backbones, and often requires redesigning the network when the encoder pair changes. This paper presents BTHA, a backbone-transferable hierarchical adapter framework for text-guided medical image segmentation. BTHA is built around a stable feature-level interface: given multi-scale visual features and a text representation, it injects semantic guidance through shape-preserving adapters while maintaining the decoder-side tensor contract. To make this interface effective, we introduce a Hierarchical Coarse-to-Fine Supervision Strategy that decomposes learning into global image-text alignment, multi-scale auxiliary localization, and boundary-aware final mask refinement. We further design a Scale-Adaptive Gated Semantic Guidance (SAGSG) adapter, where resolution-specific gates adaptively control textual injection and channel recalibration suppresses redundant cross-modal responses. Evaluations across diverse vision and text backbones show that the same adapter and supervision design remains effective across convolutional and transformer-based visual encoders as well as different language encoders. Experiments on four public datasets further demonstrate that BTHA improves strong text-guided baselines with modest computational overhead.

Pre-trained Vision-Language Models (VLMs) such as CLIP achieve strong zero-shot generalization, but their performance degrades sharply under adversarial perturbations. Existing test-time adaptation methods typically rely on sample-level confidence heuristics, overlooking the intrinsic distributional structure of the data. This sample-centric approach limits robustness, as it fails to distinguish confident adversarial mispredictions from true semantic consistency. In this work, we observe that adversarial distortion is structurally brittle: while holistic representations are corrupted, semantic integrity is often preserved in the distribution of augmented views. Motivated by this insight, we propose RITA, a Robust test-tIme prompt-TAdaptation framework that shifts from sample-level estimates to distribution-level alignment. Specifically, RITA employs optimal transport to align the distribution of augmented visual features with textual prototypes, mitigating adversarial outliers and rectifying cross-modal semantic misalignment. Furthermore, we introduce a dynamic cache to progressively accumulate reliable cues from the test stream for online refinement. Extensive experiments demonstrate that RITA significantly improves adversarial robustness without compromising clean accuracy.

Test-time scaling (TTS) reliably improves reasoning in large language models, but whether it transfers to small open vision-language models remains unclear. We examine this on EXAMS-V, a multilingual visual multiple-choice benchmark, comparing self-consistency, describe-then-reason with PRM-guided beam search, and two post-hoc selectors across Qwen2.5-VL-7B-Instruct and Qwen3.5-4B. What matters is the conditions under which TTS runs, not the search or verification machinery. The largest factor is parseability: an early prompt format left many chains reasoning correctly yet never committing to an answer letter, which a standard answer cue and a guided repair step largely remove. A larger decoding budget removes the rest: raising the per-chain token limit from 1k to 2k recovers 3.7 pp, whereas sampling more chains (8 to 16) adds only 0.15 pp. Once chains have room to finish, elaborate methods contribute little: PRM-guided beam search trails plain self-consistency by 0.39 pp at over eight times the cost, and neither a training-free generative critic nor a trained multimodal PRM beats majority vote across both policies. The largest gain comes instead from the policy model itself (+11.4 pp). Our best configuration reaches 84.1% on the held-out ImageCLEF 2026 test split, ranking first on the Visual MCQ leaderboard.

We present a novel integrated architecture for robust online 3D Gaussian splatting, real-time VR exploration, and speech-driven Vision-Language-Model interaction. Unlike methods assuming clean depth or external poses, our system combines ORB-SLAM3-based pose estimation with online Gaussian reconstruction for noisy real-world data. A VR pipeline enables immersive exploration of incremental reconstructions; a semantic module transcribes voice commands, generates scene descriptions, and records points of interest. Against state-of-the-art online Gaussian splatting methods, we improve image quality on our dataset (+14.5% PSNR, +8.6% SSIM, -14.3% LPIPS) and TUM-RGBD (+11.7% PSNR, +7.8% SSIM, -21.6% LPIPS), with comparable or superior frame rates via quality-speed configurations. We achieve an 88% VLM object-recognition rate.

Large Language Models are reshaping how software is developed and maintained. They are typically deployed in production using inference engines such as vLLM, which can efficiently serve pre-trained, highly configurable models. While prior work has focused on model architectures and hardware acceleration, the impact of inference engine configuration on energy consumption, performance, and output quality remains poorly understood. In this paper, we present a large-scale controlled study of three selected vLLM configuration options: attention kernel type, prefix caching, and chunked prefill. We evaluate all combinations of these configurations across 5 open-weight LLMs and 5 diverse inference tasks, totaling $9,000$ runs and $93,600$ measures. We analyze energy consumption, latency, and accuracy, and examine both main effects and interaction effects between configuration options and tasks. Our results show that the studied configuration options significantly impact energy and performance, mainly driven by attention type and prefix caching, while chunked prefill has a limited effect under the default vLLM serving configuration and evaluated workloads. These effects are highly model- and workload-dependent, and no configuration is universally optimal. We further show that model choice dominates global trade-offs, while configuration tuning provides local improvements along the Pareto frontier. Unexpectedly, inference options can also affect model accuracy.

Sign language translation (SLT) converts continuous sign videos into spoken language text. Gloss-free approaches leverage pre-trained visual encoders and language models but rely on implicit cross-modal alignment from translation supervision alone. We present VTaMo, a framework that introduces explicit multi-granularity alignment at three levels: (1) local alignment via entropy-regularized optimal transport with a learnable null token for fine-grained frame-to-token correspondences; (2) global alignment via a learnable orthogonal transformation that calibrates embedding space geometry through Earth Mover's Distance; and (3) position-aligned contrastive learning for discriminative token-level representations. Experiments on Phoenix-2014T, CSL-Daily, How2Sign, and OpenASL demonstrate consistent state-of-the-art performance, with ablations confirming the complementary contributions of each component. Code is available at https://github.com/junyi2005/vtamo.

Recent advancements in LVLMs necessitate robust benchmarks for complex, visually grounded reasoning. A critical limitation is identified in many document understanding benchmarks: visual content is often reducible to text, enabling high performance without genuine visual grounding. To address this limitation, OmniMapBench is introduced to foster visual-centric reasoning for map documents. The benchmark comprises 2,096 manually annotated question-answer pairs across 1,603 map documents from nine categories. It is designed to probe a hierarchy of skills, ranging from perception to multi-step visual reasoning. To quantify benchmark properties, a simple yet effective benchmark-level metric is proposed: the Visual Dependency Index (VDI), defined as the accuracy drop when images are replaced with question-agnostic descriptions. OmniMapBench exhibits higher VDI than established benchmarks, which quantitatively validates its focus on irreducible visual reasoning. Comprehensive evaluations of 25 leading LVLMs are conducted on OmniMapBench. A significant performance gap is observed, with the top-performing model achieving only 75.03% accuracy. This result underscores the challenges posed by OmniMapBench to current LVLMs. This work aims to catalyze progress in visual-centric reasoning for document understanding of LVLMs. The dataset and code are publicly available at https://github.com/SIGMME/OmniMapBench.

Vision-Language Models (VLMs) have achieved success using homogeneous Transformers to process multimedia data. Recent studies show that heterogeneous structures interleaving efficient mechanisms, like linear attention, improve both performance and inference latency over homogeneous designs. However, these efforts rely on handcrafted static mixing patterns, which are sub-optimal and difficult to adapt to specific hardware. To bridge this gap, we propose Multi-Objective Search for Adaptive Inter-layer Composition (MOSAIC), a hardware-aware search method that automatically transforms homogeneous models into optimized heterogeneous architectures. MOSAIC integrates diverse efficiency mechanisms--including linear, sparse, and low-rank operators--into a unified search space. By formulating the selection as a multi-objective Mixed Integer Programming (MIP) problem, our method identifies optimal configurations that maximize downstream performance under strict hardware latency constraints. To mitigate performance degradation from structural transitions, we introduce a two-stage parameter recovery process: global off-policy distillation to stabilize internal representations, followed by a dual-teacher on-policy distillation leveraging a 235B oracle for knowledge expansion and the original 4B teacher for distributional stability. We validate MOSAIC through MOSAIC-4B, derived from Qwen3-VL-4B-Instruct. Results demonstrate that MOSAIC-4B matches the baseline's performance across multiple benchmarks while requiring less than 2% of the original training cost. Furthermore, it substantially improves inference efficiency, achieving 1.76x prefilling and 2.54x decoding speedups.

Vision-language-action models (VLAs) inherit semantic capabilities from pretrained VLMs, yet large-scale post-training on robot data and architectural modifications can reshape the backbone so extensively that it becomes difficult to isolate what the VLM contributes to control. Directly converting pretrained VLMs into VLAs with minimal architectural change offers a more transparent path to understanding how VLM capabilities transfer across model scales. The core obstacle is output-distribution mismatch: predicting actions as bare numeric token sequences moves generation away from the VLM's pretrained language distribution, degrading the capabilities we seek to preserve. To address this, we propose CLAP (Causal Language-Action Prediction), which prepends each numeric action sequence with a natural-language action description, causally conditioning precise action-token prediction on a language-action plan without modifying the backbone architecture. With single-epoch fine-tuning alone, 2B CLAP achieves 90.8% on LIBERO (+14.9 pt over VLA-0) and improves robustness on LIBERO-PRO under language, object, and spatial perturbations. We will release CLAP at 0.8B, 2B, and 4B as an open-weight, multi-scale compact VLA family from a single VLM lineage, enabling controlled analysis of VLM-to-VLA capability transfer.

Recent benchmarks for VLMs largely assess single- or limited-view perception, leaving untested the core cognitive ability to integrate observations across viewpoints into a coherent, world-centric (allocentric) 3D mental model. We introduce MultiView-Bench, a diagnostic benchmark expressly designed to evaluate multi-view integration for holistic 3D scene comprehension. Unlike existing datasets that focus on pixel-level mapping or camera-relative navigation, MultiView-Bench requires models to decouple object positioning from transient perspectives and ground them in a fixed global coordinate system. This capability serves as a prerequisite for VLMs before being deployed for downstream tasks such as mechanical part assembly. Our systematic evaluation of frontier VLMs reveals consistent failure modes: strong performance on 2D planar relations from a single image, but marked difficulty with 3D spatial relations and with aggregating information across views. We further identify biases in VLMs, such as struggles with unconventional axis directions and sensitivity to object colorways and texture variations. Acknowledging these limitations, we propose ViewNavigator, a multi-agent framework that actively selects informative viewpoints, perceives, and fuses multi-view evidence, improving diverse base models on MultiView-Bench even under a strict budget-matched comparison (and by 3-5x for the full agent).

Recent advances in Vision-Language Models, Large Language Models, and Multimodal Large Language Models have improved autonomous driving tasks such as scene understanding, decision making, trajectory prediction, and visual question answering. However, evaluating whether these models can reliably reason about safety-critical incidents remains challenging. To address this gap, we present AUTOPILOT-VQA, an incident-centric visual question answering benchmark for dashcam video understanding. The dataset evaluates different systems through structured questions designed around real-world driving incidents and near-incidents. The benchmark covers diverse safety-relevant categories, including weather and lighting conditions, traffic environment, road layout, road surface state, signage, involved entities, accident occurrence, impact location, and avoidability-related reasoning. By requiring models to answer grounded questions about both contextual scene properties and event-level incident details, AUTOPILOT-VQA moves beyond object recognition toward temporally grounded, safety-aware reasoning. The dataset is released as part of the AUTOPILOT CVPR 2026 competition and provides a standardized benchmark for assessing the reliability of autonomous driving systems in different scenarios. Our benchmark support developments for more interpretable, robust, and safety-conscious vision-language systems for real-world autonomous driving.

Language-conditioned manipulation requires both precise contact-rich control and robust reasoning over language, scenes, and long horizons. End-to-end Vision-Language-Action (VLA) models provide strong local visuomotor skills, but they are trained on in-distribution task trajectories and often fail under deployment perturbations such as semantic retargeting, goal re-binding, spatial-layout shifts, and unstable local contacts. LLM coding agents provide complementary semantic and compositional reasoning, but purely analytic primitives struggle with irregular grasping, constrained placement, and articulated-object interaction. We present Harness VLA, a memory-augmented agentic framework that exposes a frozen VLA as a retryable contact-rich primitive and composes it with a small fixed library of analytic primitives for grounding, staging, transport, navigation, and release. Rather than expanding the skill library, the harness learns the operating range of these fixed primitives from task-specific execution traces, global success rules, and failure models. By lifting semantic re-grounding, non-contact execution, and VLA re-staging to the planner while reserving the frozen VLA for local contact-rich phases, Harness VLA extends pretrained VLAs beyond their original trajectory distribution without finetuning. Across perturbed tabletop, household kitchen, and clean-to-randomized bimanual manipulation, Harness VLA improves over the strongest relevant baselines by 38.6 and 25.4 percentage points on LIBERO-Pro and RoboCasa365, respectively, and reaches 58.4% on RoboTwin C2R. Real-world demonstrations on dual-Franka robots further show target redirection, grasp recovery, and new task compositions with the same frozen VLA. Code is available at https://github.com/RLinf/RPent.

Vision-Language Navigation (VLN) enables UAV autonomous navigation in unknown environments by mapping language instructions to real-time visual inputs. Compared with GPS-dependent or pre-programmed navigation, VLN supports intuitive human-machine interaction and stronger environmental adaptability, requiring tight integration of high-level semantic reasoning and low-latency flight control.Existing methods suffer from structural misalignment between global multimodal understanding and sequential action generation, causing jittery trajectories and severe decision latency for long-horizon aerial navigation. To solve this issue, we propose FSD-VLN, a fast-slow dual-system architecture disentangling semantic reasoning and low-latency flight command generation.The framework has two asynchronous branches: a slow stream extracting stable semantic priors from pre-trained vision-language models, and a Diffusion Transformer (DiT) fast stream modeling cross-temporal action distributions to produce consistent flight outputs. We further introduce a time-aware adaptive optimizer to stabilize long-sequence training and reduce gradient oscillation.Large-scale low-altitude simulation experiments show FSD-VLN achieves up to 2X higher navigation success rates on unseen scenes than SOTA methods, while cutting single-action inference delay and total task runtime by over 50%. Our work validates the benefit of decoupled semantic-control modeling and provides a practical paradigm for long-horizon aerial VLN.

Vision-language alignment, the stage that bridges pretrained vision encoders and large language models, is widely treated as a form of pretraining requiring full-parameter updates. We challenge this view and investigate what happens when low-rank adaptation is applied to the LLM during this stage instead. We find that low-rank alignment not only reduces computational costs but also outperforms full-parameter alignment on most benchmarks. To understand this phenomenon, we systematically characterize the implicit biases introduced by low-rank adaptation during alignment. Empirically, we find that low-rank alignment shifts model behavior from hallucinatory to conservative and preserves per-token linear separability of visual features that full-parameter alignment disrupts, a phenomenon we term LS-curse. Geometrically, low rank aligned models exhibit more homogeneous and structurally stable visual representations, maintaining modality-specific knowledge rather than prematurely fusing entity-level semantics. Theoretically, we establish two theorems showing that low-rank alignment induces preferences for parameter subspaces with flat gradients and feature subspaces robust to perturbations, providing a principled explanation for the observed structure-preserving behavior. Extensive experiments cover ablation over 100 alignment configurations, three families of low-rank operators, and various rank, encoder, and other settings.

Long-horizon robot planning requires jointly reasoning over semantic task structure and geometric feasibility. To successfully execute a task, a robot must decompose goals, select task-relevant objects, and sequence actions, while ensuring that plans satisfy spatial constraints such as limited free space and object collisions. In this work, we propose APIVOT, a VLM-based planner that adaptively interleaves language and visual thoughts for long-horizon planning. APIVOT learns to leverage language for semantic reasoning, while using visual thoughts as imagined future states for internal verification of geometric feasibility. On long-horizon kitchen tasks, APIVOT outperforms general-purpose VLMs and prior planning frameworks, achieving the largest gains in spatially constrained settings. We find that APIVOT learns meaningful modality selection behavior, demonstrating that adaptive interleaving of vision-language thoughts improves both planning success and reasoning efficiency.

Hallucinations in vision language models (VLMs) are commonly treated as semantic errors, yet they often arise from partial or ambiguous visual evidence. Prior work mainly focuses on detecting or suppressing hallucinations at generation time, leaving the subsequent reasoning stage largely unexplored. In this work, we study Post Hallucination Reasoning (PHR), the stage in which hallucinated semantics enter the model's inference context and influence downstream predictions. To systematically investigate PHR, we introduce HIVE, Hallucination Inference and Verification Engine, an evaluation infrastructure that enables controlled comparisons between faithful and hallucinated captions. Across nine tasks and nine models, we observe structured modality dependent patterns: hallucinated captions often improve accuracy on vision language tasks, while text only tasks exhibit limited or unstable effects. Further analyses show that hallucinated cues broaden semantic coverage and reshape reasoning dynamics while preserving stable inference. These findings highlight that hallucinated semantics may influence downstream reasoning once they enter the model's inference context. Understanding this post hallucination stage is important for improving the reliability and interpretability of multimodal reasoning systems. Code is publicly available at https://github.com/hefengcs/HIVE.

Traditionally, continual learning has assumed access to labeled data, yet many real-world applications -- such as lifelong robotics -- require models to adapt continuously from unlabeled streams. This has led to the development of continual self-supervised learning (CSSL), a rapidly growing area that lacks a dedicated, systematic review. In this work, we present a comprehensive survey of CSSL for vision, with connections to emerging vision-language settings. First, we analyze existing evaluation protocols and highlight inconsistencies that hinder fair comparison. We then examine why self-supervised objectives exhibit improved robustness to catastrophic forgetting, relating this to task-agnostic representations and smoother loss landscapes. Next, we organize existing methods into a unified taxonomy based on their forgetting-mitigation strategies, including distillation, replay, regularization, architectural approaches, model merging, and objective-level adaptation. Finally, we identify open challenges such as scalability and the need for fast adaptability. We argue that advancing CSSL requires moving beyond small-scale benchmarks towards continual pre-training paradigms for large-scale systems.

Vision Language Models (VLMs) and Vision Language Action (VLA) models have shown promise in robotic control. Yet, they face significant challenges regarding explainability, generalization, and compute requirements. This paper presents a Multi-Agent System (MAS) architecture that addresses these limitations by deploying specialized agents on onboard hardware - eliminating dependence on external compute. The system controls a multi-purpose autonomous mobile manipulator in a simulated industrial warehouse, fulfilling five task categories: safety inspection, warehouse maintenance, warehouse search, package quality verification, and responding to human requests. Compact VLMs (3-20B parameters) are used throughout, with fine-tuning applied to improve package inspection accuracy. A novel "Megamind" orchestration agent mitigates context retention issues inherent to long-horizon planning with smaller models. The system was validated in a hardware-in-the-loop simulation using an AMD Ryzen(TM) AI mini PC. Results demonstrate that a fully onboard MAS architecture is a viable, cost-efficient alternative to cloud-dependent deployments, with strong potential for real-world transfer. The simulation environment has been released as open source under the Apache 2.0 licence.

Reliable confidence estimation remains a key limitation of test-time adaptation in vision-language models (VLMs), where prompt tuning improves zero-shot accuracy but often degrades calibration due to entropy-driven overconfidence. Prior approaches mitigate this using LLM-derived class attributes and contrastive regularization, yet treat attributes independently, ignoring their relational structure. We propose ARGTCA, which represents (class, attribute) pairs as nodes in a Symbolic Attribute Graph and trains a Graph Attention Network (GAT) using contrastive objectives to produce structurally informed embeddings that capture inter-attribute dependencies. We introduce two attribute selection strategies: ARGTCA-DIV for intra-class diversity and ARGTCA-DISC for inter-class discrimination. Experiments across nine benchmarks show that ARGTCA-DIV reduces average Expected Calibration Error (ECE) by approximately ~37% over baselines, while ARGTCA-DISC consistently performs as the second-best variant, reducing average ECE by approximately ~17% over baselines. These results suggest that modeling symbolic attribute interactions provides a principled approach for reliable test-time adaptation in VLMs.

Fast Radio Bursts (FRBs) are millisecond-duration radio transients whose automated detection increasingly relies on highly specialized deep learning models. These detectors achieve exceptional performance, but they require large task-specific training datasets and cannot be redefined without retraining. In this work, we evaluate whether small, open-weight, locally run generalist Vision-Language Models (VLMs) can detect FRBs in dynamic spectra under a zero-shot, prompt-only regime, with no fine-tuning and no labeled examples, returning structured decisions with a natural-language justification. From a controlled set of 3000 simulated L-band dynamic spectra containing FRBs, structured Radio Frequency Interference (RFI), and noise, we draw a balanced binary benchmark of 2000 samples and compare two such VLMs (Gemma 4 2B and 4B), sample by sample, against the state-of-the-art specialized detector SwinYNet. At the default threshold, Gemma 4 2B reaches an accuracy of 93.65%, with no statistically significant difference from SwinYNet (92.90%), while showing a significantly lower false-positive rate on structured RFI (6.4% vs. 25.0%) and no false positives on pure noise. SwinYNet retains a perfect probabilistic ranking on this benchmark (ROC-AUC of 1.0000 vs. 0.9482), a ceiling that the zero-shot VLM approaches from general-purpose pretraining alone. Rewriting the prompt alone reconfigures the same models for three-class FRB/RFI/noise classification on the full set of 3000 spectra, where they reach up to 86% accuracy without a single false FRB.

Current Vision-Language Models (VLMs) often struggle to handle complex visual tasks that require consistent and fine-grained reasoning. Recent methods aim to train models to facilitate self-reflective reasoning, i.e., reviewing and improving the generated reasoning. However, they require large volumes of annotated data and lack explicit reflective behavior during test time. By contrast, humans perform explicit and efficient self-reflection through mechanisms such as backward prediction, i.e., predicting which current states are likely to precede a given future state. Inspired by neuroscience, this work proposes a novel solution to address these challenges. We first observe and investigate the phenomenon that mainstream VLMs can perform backward prediction, similar to the human brain. A label-free training framework named Brain-inspired Unsupervised Self-reflection (BUS) is proposed to leverage and exploit backward prediction capability to enhance reflective reasoning in complex visual tasks. BUS enables self-verification of reflective reasoning based on backward prediction, providing explicit learning signals under unsupervised conditions. In this way, BUS eliminates reliance on annotated data while improving reasoning performance. Designed as a model-agnostic plug-in, our framework is compatible with popular fine-tuning methods, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL). Initialized from Qwen3-VL-8B, it improves HR-Bench-8K (+8.0%), HR-Bench-4K (+7.7%), V* Bench (+6.3%), and MME-RealWorld-Lite (+5.8%), proving backward prediction is key to advancing reflective reasoning.

Infrared vision-language models are increasingly used for perception under low-light and adverse visual conditions, yet their robustness to localized structured perturbations remains underexplored. Existing infrared adversarial studies mainly focus on object detectors, leaving the security of infrared vision-language models less systematically examined. We present InfraQR, a QR-inspired structured patch attack for infrared vision-language models. Unlike localized attacks that attach perturbations to the target object, InfraQR places a compact structured patch along image boundaries and optimizes learnable grid cells through surrogate CLIP-style encoders. The resulting patch has a near-binary structured appearance, but is not required to be a valid or machine-readable QR code. We evaluate InfraQR on infrared classification, caption transfer, and question-answer-aware visual question answering (VQA) tasks. On a 300-image infrared benchmark, InfraQR sharply reduces the accuracy of multiple CLIP-style classifiers, including reducing OpenAI CLIP accuracy from 98.67% to 0.70%. The generated adversarial images also transfer to black-box captioning and VQA models, causing semantic degradation in captions and more error-prone answers under GPT-5.4-based evaluation. These results show that infrared vision-language models remain vulnerable to structured edge-placed perturbations, motivating further study of cross-task robustness beyond direct object occlusion.

Visual navigation policies built on large pretrained models have so far followed a common recipe: a dedicated visual encoder, a bespoke action head, and training on thousands of hours of cross-embodiment datasets. We ask whether this recipe is necessary. In this paper, we introduce GemNav, a visual robot navigation policy that adapts a frozen Multimodal Large Language Model (MLLM) for short-to-medium horizon waypoint navigation using Low-Rank Adaptation (LoRA) on the language tower alone, with no auxiliary visual encoder and no continuous regression head. Waypoints and categorical navigation signals share a single discrete token vocabulary generated by the language-model head, and a soft-decoded auxiliary loss recovers the metric structure that pure cross-entropy training discards. On a single 8.7-hour open corpus, roughly three orders of magnitude smaller than competing training sets, the policy transfers zero-shot to four physically distinct unseen environments and stops within 0.25-0.42m of the goal across 20 real-world trials covering an open carpark, an obstacle carpark, a long outdoor chemical yard, and an indoor warehouse. Conditioning on short image histories improves offline metrics but yields no robot benefit, pointing to a ceiling on what temporal context adds once pretrained vision features are in place. These results indicate that discrete-token adaptation of frozen MLLMs can provide a data-efficient, deployable alternative for foundation model robot navigation.

How can pretrained Vision-Language-Action (VLA) models retain long-horizon visual histories with high-frequency updates without sacrificing efficiency? Existing approaches rely on external memory management, which restrains either the memory horizon or the reactiveness of pretrained policies. To this end, we present NativeMEM, a VLA policy that features long-term and real-time updated memory. At its core is an efficient memory encoding scheme, Native Memory Compression, which repurposes the VLA's own vision encoder to compress each historical frame from each camera view into a single token. Appended to the input sequence, these memory tokens enable the pretrained VLA to attend over long-term history with negligible latency overhead, requiring neither an external planner nor a freshly initialized memory module. To align the memory tokens with the pretrained policy, we first develop a generic memory tokenizer under the supervision of a frozen VLA on memory-demanding data, and then unfreeze the VLA for task-specific fine-tuning. NativeMEM consistently outperforms prior methods, boosting success rates from 32.4% to 84.0% in simulation and up to 98.7% on real robots, while maintaining low inference latency and GPU memory usage. Notably, NativeMEM exhibits high data efficiency by achieving competitive results with prior arts using only 20% of the training data.

Infrared remote-sensing imagery captures intensity structure, object-background contrast, and illumination-invariant cues often invisible in RGB imagery. Yet, most remote-sensing vision-language resources and models focus on visible-band semantics, leaving infrared vision-language understanding underexplored. We introduce MonoIR-RS, a large-scale infrared remote-sensing vision-language dataset and benchmark that couples IR-aware data construction with CLIP-style contrastive adaptation and VLM instruction tuning. Built from the same source pool and split as FusionRS, MonoIR-RS retains the infrared image as the model-facing modality, yielding 600,000 synthesized infrared images and 59,032 retained IR-aware caption records. The model experiments use this retained language-supervision subset, whose captions rewrite supervision around grayscale structure and infrared-style contrast instead of RGB appearance. We show that the synthesized infrared imagery is markedly closer to real thermal imagery than a grayscale conversion on the AVIID benchmark. We fine-tune five CLIP backbones and six VLM backbones, and calibrate them against zero-shot behavior: IR-aware adaptation lifts CLIP mean recall by up to 12.8 points and drives VLM captioning IR-cue coverage to 100% while reducing residual RGB-color leakage to near zero. By isolating the infrared modality from RGB-IR dual-modal learning, MonoIR-RS offers a controlled, reproducible testbed for aligning infrared remote-sensing evidence with language.

In this report, we present Pelican-VLA 0.5, a unified VLA model that integrates vision-language understanding, future-frame generation, and action prediction within a single architecture. Pelican-VLA 0.5 achieves attention-level generalization: without object annotations, segmentation masks, attention supervision, or task-specific fine-tuning, its action pathway already focuses on the manipulation-relevant object and contact region. This behavior persists across unseen scenes and unseen robot embodiments, and is substantially stronger than in other open-source VLA baselines. We verify that this ability originates from the learnable Bottleneck Token inserted between perception and action: by routing task-relevant visual information through a compact bottleneck, the tokens interface induces manipulation-centric attention during pre-training and remains effective across different policy structures, including a MoT-style architecture.

Vision-language models (VLMs) are increasingly deployed on infrared (IR) remote sensing imagery in security-critical settings, yet their adversarial robustness remains unexamined. We present AirflowAttack, to our knowledge the first adversarial attack for IR remote-sensing VLMs and the first to weaponize thermal-airflow turbulence as the perturbation prior. A lightweight generator synthesizes a single input-agnostic perturbation regularized toward physically plausible airflow patterns. Optimized on one surrogate CLIP model, it attains a mean zero-shot scene-classification attack success rate (ASR, the fraction of samples whose top-1 class changes) of 48.5% across five diverse CLIP backbones, far exceeding four IR-specific physical baselines (27.7--37.0%). Applied to six state-of-the-art VLMs, it cuts scene-classification accuracy by up to 38.2% relative, yet paradoxically makes some models more confident in their IR analysis, confabulating the perturbation as genuine thermal evidence such as temperature gradients and convection. Ablations show the airflow prior raises physical plausibility at no measurable cost to attack success. Together with a benchmark spanning eleven models and four tasks, these findings expose critical vulnerabilities in the rapidly expanding IR VLM ecosystem.

Traffic signs are crucial components of road safety, serving as visual tools under all lighting conditions. The Manual on Uniform Traffic Control Devices (MUTCD) specifies daytime visual factors such as legibility and color contrast, and nighttime retroreflectivity requirements. Traditional assessment methods rely on manual inspections, which the Federal Highway Administration (FHWA) notes are subjective, labor-intensive and pose safety concerns, while retroreflectometers are expensive and unaffordable for smaller agencies. Most existing studies focus on either daytime factors or nighttime retroreflectivity but rarely integrate both aspects comprehensively. This study develops a novel framework that systematically evaluates traffic signs through integrated daytime-nighttime assessment. The methodology employs three fine-tuned Vision Language Models (VLMs) for daytime visual performance assessment across four key factors: legibility, color, surface and shape integrity, and surrounding environment conditions. VLM predictions are converted to numerical scores through sentiment analysis and Contrastive Language-Image Pre-Training (CLIP) scoring, while nighttime performance is assessed using LiDAR-derived retroreflectivity following established calibration procedures. The framework integrates these components into a comprehensive Sign Condition Index (SCI) for maintenance guidance. Evaluation results demonstrated that LLaVA and Qwen outperformed InternVL, achieving bidirectional cosine similarity scores of 0.67-0.76 across all factors. Among 462 validated traffic signs, 68 were flagged by the proposed framework as requiring immediate replacement due to inadequate retroreflectivity performance. This research provides a cost-effective alternative to traditional manual inspections for comprehensive traffic sign condition assessment.

Accurate breast cancer classification from mammography requires effective integration of complementary information from craniocaudal (CC) and mediolateral oblique (MLO) views, which provide a more complete characterization of breast abnormalities. However, existing multi-view learning approaches typically rely on feature-level aggregation or single-stage cross-attention, which can entangle view-specific and shared representations and restrict interaction to limited network depths. To address these limitations, we propose a token-centric dual-view learning framework that unifies prompt-based adaptation and cross-view fusion within a frozen vision transformer backbone. The framework reformulates inter-view interaction as structured token-level communication, where dedicated fusion tokens explicitly encode bidirectional information exchange between CC and MLO views via cross-attention, serving as intermediate carriers of cross-view dependencies rather than relying on direct feature fusion. Unlike conventional methods that apply fusion at a single layer, fusion modules are inserted at multiple transformer depths, enabling progressive and repeated interaction across the encoder hierarchy. Fusion tokens are reintegrated into the token sequence and refined by subsequent transformer layers, facilitating hierarchical propagation of complementary information while preserving view-specific structure. Experiments on VinDr-Mammo and CMMD datasets demonstrate consistent improvements over linear probing, prompt-only adaptation, and conventional fusion baselines. On the VinDr-Mammo BI-RADS classification task, the framework achieves 50.40% F1-score and 0.8090 AUC, including a 0.10 AUC improvement over a dual-view fusion baseline in the binary setting. Ablation studies further validate the effectiveness of token-based fusion and multi-depth interaction design.

3D dense captioning, an emerging vision-language task, aims to generate descriptive sentences for each object in the 3D scene. Despite the impressive results achieved by previous methods, they suffer from two limitations. First, current research often employs global rigid transformations, such as rotation, to augment scenes without changing their spatial layouts. However, diverse spatial layouts are crucial for training a 3D dense captioning model to describe spatial relations between objects. Second, previous works mainly focus on the design of the caption generation pipeline while utilizing a simple network architecture for other components, i.e., backbone and detection head, which is crucial for extracting rich semantic information for captioning. In this paper, we propose PVCap to alleviate the aforementioned problems. Our PVCap consists of PseudoCap and VoxelCapNet. Specifically, PseudoCap employs a random mixing technique on instances within the dataset, generating numerous pseudo frames with diverse spatial layouts at the instance level. By utilizing a teacher-student framework, PseudoCap obtains pseudo caption labels for these pseudo frames. This data augmentation approach significantly increases the number of training samples and enhances the model's ability to describe the environment effectively. Regarding VoxelCapNet, we introduce a robust caption network that utilizes voxel features and adapts the caption head to the voxel-based network architecture. Our VoxelCapNet can serve as a competitive baseline for future research on 3D dense captioning. Extensive experiments are conducted on two prevalent benchmarks, i.e., ScanRefer and Nr3D. Notably, our method surpasses current state-of-the-art by 11.41% and 13.99% in CIDEr@0.5IoU, respectively. Codes will be made publicly available.

Existing construction-site Vision-Language Model (VLM) studies have primarily adapted pretrained VLMs through direct QA-style fine-tuning from a single global image, but we argue that this paradigm remains limited in operational range, reliability under reduced-resolution inputs, and inference efficiency. To address these limitations, we propose AVA-VLM, an Adaptive Visual Attention-Vision Language Model that follows a human-inspired coarse-to-fine strategy: it first reasons over a low-resolution global image and requests a high-resolution local crop only when detailed inspection is needed. We further introduce a region-aware Chain-of-Thought dataset that teaches when to inspect, where to crop, and how to use local evidence. Experiments show that, for violation identification, AVA-VLM improves overall F1 from 62.0 to 75.1 while using only 30.6% of the baseline visual-token budget; for long-distance PPE-violation cases, F1 improves from 16.0 to 63.6. These results demonstrate AVA-VLM's improved robustness to distant and reduced-resolution visual evidence with substantially lower visual-token usage.

Pre-trained Vision-Language Models (VLMs) like CLIP have proven highly effective as foundation models for various downstream applications. However, prompt learning in VLMs encounters a performance-generalization dilemma: while prompts can be tuned to achieve high accuracy on seen distributions, this tuning process often undermines their generalizability to unseen data. The limited set of learnable prompts, which contextualize and condition the input to steer it toward the task within the pretrained VLM, tends to overfit the training data, leading to a trade-off between task-specific performance and preserving generalization. To address this dilemma, we introduce SAMPLe (Sharpness-Aware Minimization Prompt Learning), a plug-in sharpness-aware optimizer that enhances prompt generalizability by accounting for loss landscape sharpness. Unlike conventional methods, SAMPLe balances exploration and exploitation by satisfying objective function constraints at each step, dynamically adapting to the current optimization state based on the local curvature and gradient properties. This approach reduces overfitting on seen distributions and improves adaptability to unseen data, preserving the generalization potential of pre-trained VLM models. We integrate SAMPLe into multiple prompt learning frameworks, including CoOp, CoCoOp, MaPLe, TCP, and Co-Prompt, demonstrating its effectiveness across diverse methods. Experiments show that SAMPLe elevates prompt learning frameworks and consistently outperforms existing optimizers across diverse settings, establishing itself as a robust, model-agnostic solution for prompt learning.

While recent Vision-Language-Action (VLA) models show promise toward generalist manipulation policies, they struggle with long-horizon tasks due to their Markovian nature-relying solely on current observations. Hierarchical dual-system methods address this but suffer from a gap between high-level planning semantics and low-level execution kinematics. We introduce Cortex, a bidirectionally aligned embodied agent framework with a customized planning interface that conveys executable and tractable subtask plans from high-level VLM to low-level VLA. Specifically, we standardize manipulation subtasks into 32 canonical skill primitives and inject tractability principles, such as representative object attributes and improved trajectory reachability, into the data generation pipeline. This enables automatic annotation of over 4k hours of open-source video data and generation of 30 hours of simulation data. We further devise an event-balanced sampling strategy to construct training data for fine-tuning the framework to better handle planning ambiguity during subtask transitions, enhanced by carefully designed harness engineering from task contexts to skill constraints during inference. Both open-loop VLM and closed-loop system evaluations demonstrate Cortex's efficacy, e.g., it outperforms monolithic baselines by 3.1% on Libero-long and 4.1% on RoboTwin. Notably, Cortex's generalist VLM enables zero-shot completion of unseen real-world long-horizon tasks, such as multi-stage chemistry experiments, by simply combining with a fine-tuned VLA-a capability infeasible through VLA fine-tuning alone.

Open-vocabulary 3D scene understanding aims to segment 3D scenes beyond predefined categories by transferring semantic knowledge from vision-language models. Existing methods have advanced this task by lifting language-aligned 2D features into 3D, yet they often rely on context-independent semantic representations, leaving object relationships underexplored for contextual refinement. We propose RelGraphOV, a relationship-aware framework that uses 3D scene graphs to enhance open-vocabulary 3D understanding. Our method constructs relational scene graphs from multi-view observations by leveraging vision-language reasoning to infer object relationships and prune geometrically implausible connections, without manual relationship annotations. To aggregate relational context while avoiding feature interference, we introduce an Adaptive Gated Dual-Stream Contextual GAT that separates dense geometric features and semantic CLIP embeddings, performs edge-guided message passing, and adaptively fuses complementary semantics. A hierarchical contrastive objective further promotes instance-level consistency and category-level discrimination. Experiments on ScanNetV2, ScanNet200, ScanNet$++$, and Replica demonstrate strong performance and generalization ability. Project Page: https://cxavireh.github.io/relgraphov-projectpage

Whether a hyperbolic representation model uses its geometry cannot be inferred from curvature alone: what matters is the dimensionless operating point $\sqrt{c}ρ$ and whether the radial and cone mechanisms are operational there. We develop necessary-condition diagnostics and audit three published hyperbolic vision-language families -- MERU, HyCoCLIP, and PHyCLIP -- across released checkpoints and matched interventions. All converged checkpoints remain near-Euclidean ($H(u)\approx1$; none reaches $\sqrt{c}ρ>1$), and releasing the curvature floor changes $c$ and norms without leaving this regime or substantially degrading downstream performance. Entailment cones are inactive or saturated, and graded traversal fails under controlled readouts, including the models' native distance metrics. External parent-child ordering shows no shuffle-controlled pair-specific radial signal at quantified sensitivity; the only surviving pair-specific signal, a statistically detectable but small residual on the GRIT box-to-full-caption relation, remains non-operative under the evaluated readouts. Taxonomy correlations show no detectable norm contribution beyond cosine, and coarse-retrieval gains co-vary with box/compositional supervision without establishing an active radial mechanism. Gradient diagnostics expose a low-curvature, wide-cone shortcut in the entailment objective. A closed-form aperture identity places the saturation edge at $\sqrt{c}ρ\le2K$: with the floor released, all trained relation-level parent means lie at or below this edge, leaving the parent cones fully or nearly saturated. Entailment-off runs pass the edge and continue contracting. The shortcut is the dominant accelerator of collapse, not its sole cause. These audited formulations do not show an operative radial/cone mechanism under our diagnostics. We distill the audit into a five-number geometry report for hierarchy claims.

Large-scale Vision-Language Models like CLIP have demonstrated impressive open-set localization capabilities at the image level. However, adapting this capability to pixel-level dense prediction poses challenges due to global feature biases. In this paper, we introduce CLIPix, a simple yet effective framework that repurposes CLIP to perform pixel-level localization. By tracing back CLIP's classification process, CLIPix identifies object-specific attentive regions and repurposes them as pixel-level localization cues. To address noise introduced by global biases, we propose a Noise-Resistant Correction strategy, refining these cues for more precise segmentation. Additionally, we introduce a Localization Embedding strategy to integrate both localization and enriched detail information, enabling accurate, high-resolution segmentation. Our approach preserves CLIP's generalization strength and unlocks its potential for segmenting arbitrary objects. Extensive experiments on the PASCAL and COCO datasets demonstrate that CLIPix achieves state-of-the-art performance, underscoring its effectiveness.

Charts and images appear together throughout scientific publications, yet most computational work does not characterize their coherence. We argue that a chart, its accompanying image, and the caption that links them form a multimodal unit, and that the inferential work required to read it varies systematically. To capture this variation, we develop a typology of reasoning gaps, R1 through R5, that characterizes how chart, image, and text jointly convey a scientific claim, and the interpretive work this demands of the reader. Some pairs restate the same data, while in other pairs, charts are used to quantify a structure the image localizes, project image content onto an external variable, audit an image-based claim, or jointly construct a frame that neither panel can establish alone. The typology is anchored in the grounding theory of communication and was derived bottom-up, with a neuroscience expert, from a corpus of 79 traumatic brain injury papers and 32 chart-image pairs. Crucially, the levels provide a systematic mechanism for identifying where grounding succeeds or breaks down, rather than leaving it to subjective inference. We show this in a study in which a domain expert and three non-experts judge vision-language model (VLM) descriptions of 25 pairs: the level predicts where their judgments align and where they diverge, isolating the points at which contextual knowledge, not the figure, carries coherence. This typology thus offers figure designers a systematic way to balance text against chart-image pairs, bridging the expert-to-non-expert divide in reading a scientific takeaway.

Adverse driving conditions, such as bad weather, remain a principal barrier to autonomous driving because they degrade two things at once: what the vehicle can perceive and what it can physically do. Human drivers cope by anticipation, reasoning about the scene and re-budgeting speed, following distance, and steering before grip or sight is lost, whereas current autonomous driving systems at best react after the fact. This paper proposes VLM-CASE, a framework that gives an autonomous vehicle this anticipatory capacity while keeping its motion bounded by a formal safety model at all times. A vision-language model (VLM), fine-tuned with low-rank adaptation (LoRA), reasons about the scene from the front-camera image and reports the road surface and visibility conditions. This output parametrizes a context-adaptive safety envelope (CASE), derived from physical limits and the guarantees of responsibility-sensitive safety, that couples braking and steering through a shared friction budget. A model predictive controller then drives freely within the envelope, while the VLM runs asynchronously so it never blocks the real-time control loop. We validate the framework in closed-loop CARLA simulation on tasks that demand both lateral and longitudinal control, across a range of weather, road-surface, and lighting conditions. The resulting controller, VLM-CASE-MPC, completes all trials, outperforming a conventional MPC baseline and a state-of-the-art VLM-integrated controller. Ablations confirm that the gains come from context adaptation, with the friction and visibility adaptations proving complementary. Furthermore, the framework is controller-agnostic and pairs with almost any low-level controller, offering a promising direction for safe autonomous driving. The dataset and supplementary materials for VLM-CASE are available at https://github.com/ytj254/VLM-CASE.

Unified models for robot manipulation aim to equip one policy with both the semantic priors of pretrained VLMs and the physical dynamics learned through future prediction. In practice, existing designs tend to erode the semantics of the pretrained backbone, suffer interference among heterogeneous objectives, and learn future prediction from scratch in pixel space, leaving the dynamics priors of pretrained video generators unexploited. We present InternVLA-A1.5, which builds the policy on a native VLM backbone that keeps training on VQA and subtask prediction, and attaches a lightweight unified expert for continuous action generation. Future prediction is recast as a latent-querying problem, where a small set of learnable foresight tokens condenses the task-relevant future into a compact latent code under the supervision of a frozen pretrained video generation model, so the policy inherits world-model dynamics priors without ever learning pixel-level generation. The video branch is discarded at inference, keeping real-time control. Pretrained on 1.2M robot episodes and 3M multimodal samples, InternVLA-A1.5 achieves the best overall results on all six simulation benchmarks. In the real world, the preserved semantics deliver the strongest compositional generalization on held-out instruction bindings, and the two designs together sustain long-horizon execution.

We present HunyuanOCR-1.5, a lightweight end-to-end OCR-specialized vision-language model. HunyuanOCR unifies document parsing, text spotting, information extraction, text-image translation, and multi-image document understanding within a single end-to-end VLM. Building upon the lightweight architecture of HunyuanOCR-1.0, HunyuanOCR-1.5 does not redesign the backbone, but systematically improves both efficiency and capability. For efficiency, we adapt DFlash to OCR decoding, significantly reducing the latency of long structured outputs such as dense documents, tables, and formulas while preserving output distribution. Powered by DFlash, HunyuanOCR-1.5 achieves a 6.37x Transformer inference speedup and a 2.14x speedup under vLLM, delivering the fastest inference among lightweight OCR VLMs. For capability, we propose Agentic Data Flow, an agent-driven data construction system that transforms model weaknesses into executable data requirements and autonomously performs material search, quality verification, and pipeline development. It substantially improves long-tail capabilities in ancient-script OCR, fine-grained chart and table parsing, multi-image text-centric QA, low-resource multilingual parsing, and document hallucination evaluation. HunyuanOCR-1.5 ranks among the top-tier end-to-end OCR solutions on OmniDocBench v1.6 while achieving new performance milestones across these long-tail tasks. Combined with an upgraded pretraining and post-training recipe, HunyuanOCR-1.5 further extends its capability in high-resolution, long-context, and multi-task scenarios. Experiments demonstrate faster inference, broader OCR capability coverage, and the deployment advantages of a lightweight end-to-end model. We will release the model weights and training code to support future research and real-world OCR applications.

Reasoning segmentation aims to predict pixel-wise masks for targets given complex language queries. Existing approaches leverage Multimodal Large Language Models (MLLMs) for vision-language reasoning and generate intermediate target cues (e.g., points or boxes) to guide a segmentation model. However, compressing rich reasoning into sparse cues often introduces ambiguity and noise, preventing these cues from accurately preserving the reasoning intent. While multiple complementary cues can enrich target information, existing methods typically feed them jointly into a single segmentation process, allowing ambiguous or erroneous cues to affect the entire prediction. Therefore, we propose DGSeg, a reasoning segmentation framework that learns to fuse predictions guided by semantic and spatial cues. Specifically, the MLLM jointly reasons about both target identity and spatial location, producing complementary semantic and spatial cues that are fed into separate segmentation branches. Their predictions are adaptively integrated by a lightweight dynamic gating module trained with relative branch-quality supervision to suppress noisy or conflicting regions. Extensive experiments demonstrate that DGSeg consistently outperforms strong baselines on multiple benchmarks and achieves 69.6% and 67.3% gIoU on the challenging ReasonSeg validation and test splits. Code is available at https://github.com/RZZeng/DGSeg.

This report presents our solutions to the QoMEX 2026 Grand Challenge on Video Quality Assessment for Asymmetric Encoded Videos, comprising a full-reference (FR) model, CompressedVQA-AEV-FR, and a no-reference (NR) model, CompressedVQA-AEV-NR. The FR approach leverages a Swin-B backbone to extract multi-stage similarity statistics between reference and distorted videos for quality prediction. For the NR setting, our model employs complementary frame-level encoders based on SigLIP2 and Swin-B, followed by temporal mean pooling and cross-fold ensembling to estimate perceptual quality without reference data. Our CompressedVQA-AEV-FR achieves first place in the FR track of QoMEX 2026 Grand Challenge, while CompressedVQA-AEV-NR secures fourth place in the NR track, demonstrating the effectiveness of our proposed models. The code is available at https://github.com/sunwei925/CompressedVQA-AEV.

Vision-Language Models (VLMs) have demonstrated impressive capabilities across different tasks, but their computational cost is dominated by the large number of visual tokens fed to the language model. Existing token reduction methods rely on attention-based scores or pairwise similarity, without an explicit semantic representation of each token. We introduce TORINO (TOken Reduction via Interpretable coNcept Overlap), a plug-and-play framework for adaptive visual token reduction in VLMs that requires no fine-tuning of the underlying model. TORINO leverages Sparse Autoencoders (SAEs) to project visual tokens into an interpretable latent space where token relationships can be analyzed through shared concept activations. Specifically, we define concept overlap as the degree of agreement between active SAE latents and use it to group tokens that share semantic content. Reduction within each group is then performed by either pruning or merging, providing a unified framework that preserves semantically important visual information while removing redundancy. Unlike fixed-budget approaches, TORINO dynamically adapts the reduction rate to input complexity, allowing different images to retain different numbers of tokens. Experiments across multiple vision-language benchmarks show that TORINO achieves favorable efficiency-accuracy trade-offs, reducing the number of visual tokens with minimal performance loss.

While Large Vision-Language Models (VLMs) demonstrate remarkable generic capabilities, their clinical reasoning in specialized domains like ocular surface diseases (OSDs) is severely hindered by a paucity of high-fidelity, multimodal instruction-tuning data. To dismantle this data bottleneck, we introduce IRIS, an Intelligent Recognition and Interaction System tailored for fine-grained OSD understanding via external eye photography. First, we curate IRIS-120K, the largest and most comprehensive OSD visual question-answering (VQA) dataset to date. Crucially, to overcome the semantic shallowness of conventional image-caption pairs, we propose a synergistic data generation paradigm to explicitly inject clinical priors. Our data engine operates via a dual-branch framework: 1) a Topic Finding Tree (TFT) that hierarchically anchors visual features to precise anatomical and pathological concepts, enforcing rigorous medical deduction logic; and 2) a Scene-driven strategy that synthesizes role-adaptive clinical dialogues to ensure pragmatic generalization. By explicitly aligning a compact 4B-parameter VLM on this structurally enriched corpus, IRIS achieves state-of-the-art performance, comprehensively outperforming both generalist and specialized medical VLMs with up to 34B parameters. Our findings underscore that structured knowledge injection profoundly prevails over sheer parameter scaling, unlocking the potential for resource-efficient, expert-level AI deployment on mobile edge devices for scalable OSD screening. Code, datasets, and model weights will be publicly released by this repo.

Large Vision-Language Models (LVLMs) have shown strong multimodal understanding and spatial grounding, but their computational cost limits real-time robotic control. In contrast, lightweight models are suitable for edge deployment but often suffer from "spatial blindness", namely weak native spatial prediction ability. Training Vision-Language-Action (VLA) models on mixed human demonstrations can also degrade policy performance due to highly diverse behaviors. To address these limitations, we propose XS-VLA, a two-stage framework for efficient and spatially grounded robotic manipulation. First, we distill spatial semantic knowledge from Qwen3-VL-4B into the SmolVLM2-0.25B backbone by fine-tuning on curated coarse-grained spatial descriptions, turning the lightweight model into a spatially grounded engine. Second, we use this enhanced backbone to condition a Latent Flow Matching policy. Unlike deterministic controllers, our policy combines a Conditional Variational Autoencoder (CVAE) with Flow Matching dynamics to model complex multimodal action distributions. On the LIBERO benchmark, XS-VLA achieves state-of-the-art performance among models with fewer than 0.5B parameters. It improves average success rates by up to 7.2 percent, including a 23 percent gain on LIBERO-Long, over the SmolVLA 0.25B baseline, and outperforms the larger 2.2B vanilla SmolVLA. Ablations show that spatial tuning and generative latent flow control substantially improve lightweight VLA performance, delivering a 3.2 times speedup in mission execution over the previous lightweight flow matching policy.