Large Vision Language Models

Semi-supervised few-shot learning (SSFSL) resembles real-world applications such as auto-annotation, as it aims to learn a model from a few labeled and abundant unlabeled task-specific examples to annotate the unlabeled ones. Despite the availability of powerful open-source Vision-Language Models (VLMs) and open-world data, existing SSFSL literature largely neglects these resources. In contrast, the related area few-shot learning (FSL) has already exploited them to boost performance. Arguably, to solve real-world auto-annotation, SSFSL should leverage such open resources. To bridge this gap, we explore established SSL methods to finetune a VLM. Unexpectedly, they significantly underperform FSL baselines that do not use unlabeled data. Our in-depth analysis reveals the root cause of failure: VLMs produce flat distributions of softmax probabilities, resulting in zero utilization of unlabeled data and weak supervision signals. To address this challenge, we propose an embarrassingly simple solution that uses temperatures to sharpen the softmax output, which not only increases the confidence scores of pseudo-labels to improve the utilization of unlabeled data, but also strengthens training supervision for effective finetuning. Furthermore, we exploit task-relevant open data, e.g., those retrieved from VLMs' publicly available pretraining set. To mitigate the imbalance and domain gaps in retrieved data, we employ a stage-wise training strategy. Building on the successful finetuning of VLMs and the exploitation of open data, we present a simple yet effective SSFSL method, Stage-Wise Finetuning with Temperatures (SWIFT). Across five benchmarks, SWIFT outperforms recent FSL and SSL methods by $\sim$5 accuracy points. SWIFT even rivals supervised learning, which finetunes a VLM assuming unlabeled data having ground-truth labels!

Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in generalizing across diverse robotic manipulation tasks. However, deploying these models in unstructured environments remains challenging due to the critical need for simultaneous task compliance and safety assurance, particularly in preventing potential collisions during physical interactions. In this work, we introduce a Vision-Language-Safe Action (VLSA) architecture, named AEGIS, which contains a plug-and-play safety constraint (SC) layer formulated via control barrier functions. AEGIS integrates directly with existing VLA models to improve safety with theoretical guarantees, while maintaining their original instruction-following performance. To evaluate the efficacy of our architecture, we construct a comprehensive safety-critical benchmark SafeLIBERO, spanning distinct manipulation scenarios characterized by varying degrees of spatial complexity and obstacle intervention. Extensive experiments demonstrate the superiority of our method over state-of-the-art baselines. Notably, AEGIS achieves over 50% improvement in obstacle avoidance rate while substantially increasing the task success rate by nearly 10%. All benchmark datasets, code, and supplementary materials are publicly available at https://vlsa-aegis.github.io/.

How does irrelevant information (i.e., distractors) affect test-time scaling in vision-language models (VLMs)? Prior work on text-only language models has shown that textual distractors can intensify inverse scaling, causing models to reason longer but less effective reasoning traces. In this work, we investigate whether similar phenomena arise in multimodal settings. We introduce Idis (Images with distractors), a visual question-answering dataset that systematically varies distractors along semantic and numerical dimensions. Our analyses reveal that visual distractors affect reasoning VLMs in a fundamentally different way from textual distractors: although inverse scaling still emerges, visual distractors reduce accuracy without increasing reasoning length. We further show that attribute counts extracted from reasoning traces provide key insights into how distractors interact with reasoning length and accuracy. As a sanity check, we propose a simple prompting strategy that mitigates distractor-driven predictions in reasoning vision-language models.

Spatial reasoning is a critical capability for intelligent robots, yet current vision-language models (VLMs) still fall short of human-level performance in video-based spatial reasoning. This gap mainly stems from two challenges: a semantic-geometric misalignment that prevents consistent 3D understanding, and the absence of persistent memory to retain 3D representation and understanding across frames. To address these limitations, we present VLM$^2$, a Vision-Language Model with persistent Memory for spatial reasoning with a view-consistent, 3D-aware representation purely from 2D videos. Specifically, we incorporate a dual-memory module consisting of a working memory that operates as a sliding window to focus on immediate context, and an episodic memory that consolidates and stores critical information across frames. This design enables bounded and efficient spatial reasoning under a fixed computational cost. Extensive experiments on multiple benchmarks show that VLM$^2$ achieves state-of-the-art performance among video-based models, significantly advancing the frontier of visual-spatial intelligence.

In this work, we define Foresight Intelligence as the capability to anticipate and interpret future events-an ability essential for applications such as autonomous driving, yet largely overlooked by existing research. To bridge this gap, we introduce FSU-QA, a new Visual Question-Answering (VQA) dataset specifically designed to elicit and evaluate Foresight Intelligence. Using FSU-QA, we conduct the first comprehensive study of state-of-the-art Vision-Language Models (VLMs) under foresight-oriented tasks, revealing that current models still struggle to reason about future situations. Beyond serving as a benchmark, FSU-QA also enables the assessment of world models by measuring the semantic coherence of their generated predictions, quantified through performance gains when VLMs are augmented with such outputs. Our experiments further demonstrate that FSU-QA can effectively enhance foresight reasoning: even small VLMs fine-tuned on FSU-QA surpass much larger, advanced models by a substantial margin. Together, these findings position FSU-QA as a principled foundation for developing next-generation models capable of truly anticipating and understanding future events. Furthermore, beyond model performance, we examine whether WM-generated predictions remain semantically consistent by using VLM-based proxy judges, and validate this evaluation protocol through shuffled control experiments. Fine-tuning models on FSU-QA leads to substantial improvements in foresight understanding, demonstrating the dataset's effectiveness and offering a principled foundation for future research.

Visual in-context learning (VICL) solves visual tasks by conditioning on a few input-output demonstrations without any model training. Recent advances in large vision-language models (VLMs) have shown promising VICL capability when the demonstration pair and the query belong to the same vision task, but real use cases often provide mismatched examples, making it unclear whether a VLM should imitate the demonstrated transformation or infer a new one from the query. This raises a fundamental question: Can VLMs perform cross-task VICL where demonstration and query differ? In the paper, we study this cross-task VICL setting and propose T2T-VICL, a collaborative prompt-transfer framework, which converts mismatched visual demonstrations into implicit textual guidance without explicitly naming the tasks. To do so, a large teacher VLM first generates structured descriptions of visual changes and task differences between task pairs, from which we construct a dataset of diverse implicit cross-task relations. We then distill this capability into a lightweight student VLM that produces content-dependent prompts from a task-A demonstration pair and a task-B query. The generated prompt is used to guide a frozen image-editing VLM, and a score-based inference strategy is introduced to rank multiple candidates. Experiments on 12 low-level vision tasks and over 20 evaluated cross-task pairs show that T2T-VICL consistently improves task-aware alignment over fixed prompting and often also improves image fidelity, revealing both the potential and limits of cross-task VICL. Our code is available on GitHub.

Text-to-3D generation has advanced rapidly, yet state-of-the-art models, encompassing both optimization-based and feed-forward architectures, still face two fundamental limitations. First, they struggle with coarse semantic alignment, often failing to capture fine-grained prompt details. Second, they lack robust 3D spatial understanding, leading to geometric inconsistencies and catastrophic failures in part assembly and spatial relationships. To address these challenges, we propose VLM3D, a general framework that repurposes large vision-language models (VLMs) as powerful, differentiable semantic and spatial critics. Our core contribution is a dual-query critic signal derived from the VLM's Yes or No log-odds, which assesses both semantic fidelity and geometric coherence. We demonstrate the generality of this guidance signal across two distinct paradigms: (1) As a reward objective for optimization-based pipelines, VLM3D significantly outperforms existing methods on standard benchmarks. (2) As a test-time guidance module for feed-forward pipelines, it actively steers the iterative sampling process of SOTA native 3D models to correct severe spatial errors. VLM3D establishes a principled and generalizable path to inject the VLM's rich, language-grounded understanding of both semantics and space into diverse 3D generative pipelines.

The rapid progress of vision--language models (VLMs) has sparked growing interest in robotic control, where natural language can express the operation goals while visual feedback links perception to action. However, directly deploying VLM-driven policies on aerial manipulators remains unsafe and unreliable since the generated actions are often inconsistent, hallucination-prone, and dynamically infeasible for flight. In this work, we present AERMANI-VLM, the first framework to adapt pretrained VLMs for aerial manipulation by separating high-level reasoning from low-level control, without any task-specific fine-tuning. Our framework encodes natural language instructions, task context, and safety constraints into a structured prompt that guides the model to generate a step-by-step reasoning trace in natural language. This reasoning output is used to select from a predefined library of discrete, flight-safe skills, ensuring interpretable and temporally consistent execution. By decoupling symbolic reasoning from physical action, AERMANI-VLM mitigates hallucinated commands and prevents unsafe behavior, enabling robust task completion. We validate the framework in both simulation and hardware on diverse multi-step pick-and-place tasks, demonstrating strong generalization to previously unseen commands, objects, and environments.

The rapid digitization of histopathology slides has opened new opportunities for computational tools in clinical and research workflows. Content-based slide retrieval can help pathologists identify morphologically and semantically related precedent cases, supporting expert diagnosis and example-based education. Effective retrieval of whole-slide images (WSIs), however, remains challenging because gigapixel slides contain abundant irrelevant content, focal diagnostic patterns and slide-level semantic information that must be represented at a practicable search cost. Here we present PathSearch, a retrieval framework that combines fine-grained attentive mosaics with slide-level embeddings aligned through vision-language contrastive learning. Trained on 6,926 slide-report pairs, PathSearch captures both fine-grained morphological cues and high-level semantic patterns to enable accurate and flexible retrieval. The framework supports two key functionalities: (1) mosaic-based image-to-image (I2I) retrieval, ensuring accurate and efficient slide search; and (2) multimodal retrieval, where text queries can directly retrieve relevant slides. PathSearch was evaluated on eight tasks comprising 5,021 evaluation slides, spanning malignancy assessment on frozen and hematoxylin and eosin (H&E)-stained slides, lymph-node metastasis detection, tumor subtyping, mixed-gallery rare-cancer retrieval, and hepatocellular carcinoma (HCC) risk stratification. Internal and external experimental results demonstrate that PathSearch consistently outperforms the strongest existing methods without compromising multimodal accuracy. A multi-center reader study further demonstrated increases in task-level mean diagnostic accuracy, confidence, and inter-observer agreement with PathSearch's support. Together, these results support the effectiveness of PathSearch across diverse retrieval tasks and evaluation settings.

Open-vocabulary object detection (OVD) aims to recognize and localize object categories beyond the training set. Recent approaches leverage vision-language models to generate pseudo-labels using image-text alignment, allowing detectors to generalize to unseen classes without explicit supervision. However, these methods depend heavily on single-step image-text matching, neglecting the intermediate reasoning steps crucial for interpreting semantically complex visual contexts, such as crowding or occlusion. In this paper, we introduce MSPL, a framework that incorporates multi-step visual reasoning into the pseudo-labeling process for OVD. It decomposes complex scene understanding into three interpretable steps-object localization, category recognition, and background grounding-where these intermediate reasoning states serve as rich supervision sources. Extensive experiments on standard OVD evaluation protocols demonstrate that MSPL achieves state-of-the-art performance with superior pseudo-labeling efficiency, outperforming the strong baseline by 9.4 AP50 for novel classes on OV-COCO and improving box and mask APr by 3.2 and 2.2, respectively, on OV-LVIS. Code and models are available at https://github.com/hchoi256/mspl.

Large Vision Language Models (VLMs) excel at general visual reasoning but experience significant performance degradation when deployed in novel domains that exhibit substantial distribution shifts from their pretraining data. Existing domain adaptation methods rely on finetuning standard VLM components; however, depending on which components are updated, these approaches either limit the model's ability to learn domain-specific representations or cause catastrophic forgetting of previously acquired capabilities. We introduce Vision Contextualized Probing (VisCoP), a parameter-efficient adaptation framework that augments the VLM vision encoder with a compact set of learnable visual probes. By learning domain-specific visual representations through these probes while requiring only minimal updates to pretrained model components, VisCoP effectively adapts to new domains without sacrificing existing knowledge. We evaluate VisCoP across three challenging adaptation settings: cross-view (exocentric to egocentric), cross-modal (RGB to depth), and cross-task (human understanding to robot control). Across all scenarios, VisCoP consistently outperforms existing domain adaptation strategies, achieving superior target-domain performance while preserving the pretrained VLM's capabilities on the source domain. These results demonstrate that lightweight visual probing provides an effective and robust solution for adapting VLMs under substantial distribution shifts. Code, models, and evaluation protocols are available at https://github.com/dominickrei/VisCoP.

Large pretrained vision encoders are central to multimodal intelligence, powering applications from on-device vision processing to vision-language models. Since these applications often demand real-time processing of massive visual data, reducing the inference cost of vision encoders is critical. Quantization offers a practical path, but it remains challenging even at 8-bit precision due to so-called outliers. In this work, we propose $\textit{RegCache}$, a training-free algorithm that mitigates outliers in large-scale pretrained vision encoders and serves as a plug-in module that can be applied on top of other quantization methods. RegCache introduces outlier-prone yet semantically meaningless prefix tokens to the vision encoder, which prevent other tokens from having outliers. Notably, we observe that outliers in vision encoders behave differently from those in language models, motivating two technical innovations: middle-layer prefixing and token deletion. Experimental results show that our method consistently improves quantized model performance across various vision encoders, particularly in extremely low-bit regimes (e.g., 4-bit).

As Vision Language Models (VLMs) are deployed across safety-critical applications, understanding and controlling their behavioral patterns has become increasingly important. Existing behavioral control methods face significant limitations: system prompting approaches could easily be overridden by user instructions, while applying activation-based steering vectors requires invasive runtime access to model internals, precluding deployment with API-based services and closed-source models. Finding steering methods that transfer across multiple VLMs is still an open area of research. To this end, we introduce universal visual input based steering for output redirection (VISOR++), to achieve behavioral control through optimized visual inputs alone. We demonstrate that a single VISOR++ image can be generated for an ensemble of VLMs to emulate each of their steering vectors. By crafting universal visual inputs that induce target activation patterns, VISOR++ eliminates the need for runtime model access while remaining deployment-agnostic. This means that when an underlying model supports multimodal capability, model behaviors can be steered by inserting an image input replacing runtime steering vector based interventions. We first demonstrate the effectiveness of the VISOR++ images on open-access models such as LLaVA-1.5-7B and IDEFICS2-8B along three alignment directions: refusal, sycophancy and survival instinct. Both the model-specific steering images and the jointly optimized images achieve performance parity closely following that of steering vectors for both positive and negative steering tasks. We also show the promise of VISOR++ images in achieving directional behavioral shifts for unseen models including both open-access and closed-access ones. Furthermore, VISOR++ images are able to preserve 99.9% performance on 14,000 unrelated MMLU evaluation tasks.

Large vision-language models (LVLMs) have achieved impressive performance across a wide range of vision-language tasks, while they remain vulnerable to backdoor attacks. Existing backdoor attacks on LVLMs aim to force the victim model to generate a predefined target pattern, which is either inserted into or replaces the original content. We find that these fixed-pattern attacks are relatively easy to detect, because the attacked LVLM tends to memorize such frequent patterns in the training dataset, thereby exhibiting overconfidence on these targets given poisoned inputs. To address these limitations, we introduce TokenSwap, a more evasive and stealthy backdoor attack that focuses on the compositional understanding capabilities of LVLMs. Instead of enforcing a fixed targeted content, TokenSwap subtly disrupts the understanding of object relationships in text. Specifically, it causes the backdoored model to generate outputs that mention the correct objects in the image but misrepresent their relationships (i.e., bags-of-words behavior). During training, TokenSwap injects a visual trigger into selected samples and simultaneously swaps the grammatical roles of key tokens in the corresponding textual answers. However, the poisoned samples exhibit only subtle differences from the original ones, making it challenging for the model to learn the backdoor behavior. To address this, TokenSwap employs an adaptive token-weighted loss that explicitly emphasizes the learning of swapped tokens, such that the visual triggers and bags-of-words behavior are associated. Extensive experiments demonstrate that TokenSwap achieves high attack success rates while maintaining superior evasiveness and stealthiness across multiple benchmarks and various LVLM architectures.

Class-Incremental Learning (CIL) aims to endow models with the ability to continuously adapt to evolving data streams. Recent advances in pre-trained vision-language models (e.g., CLIP) provide a powerful foundation for this task. However, existing approaches often rely on simplistic templates, such as "a photo of a [CLASS]", which overlook the hierarchical nature of visual concepts. For example, recognizing "cat" versus "car" depends on coarse-grained cues, while distinguishing "cat" from "lion" requires fine-grained details. Similarly, the current feature mapping in CLIP relies solely on the representation from the last layer, neglecting the hierarchical information contained in earlier layers. In this work, we introduce HiErarchical Representation MAtchiNg (HERMAN) for CLIP-based CIL. Our approach leverages LLMs to recursively generate discriminative textual descriptors, thereby augmenting the semantic space with explicit hierarchical cues. These descriptors are matched to different levels of the semantic hierarchy and adaptively routed based on task-specific requirements, enabling precise discrimination while alleviating catastrophic forgetting in incremental tasks. Extensive experiments on multiple benchmarks demonstrate that our method consistently achieves state-of-the-art performance.

Speech and audio encoders developed over years of community effort are routinely excluded from video understanding pipelines, not because they fail, but because benchmarks never required listening. We audit 10 video benchmarks and find items largely solvable from visual cues alone: a single-frame probe answers about 76% of AVQA without audio, suggesting poor measurement of audio-visual reasoning. Building on LLaVA-OneVision, we attach a speech/audio encoder and compare five compressor architectures under 25-fold token reduction (25 Hz to 1 Hz). Across 10 benchmarks, with and without filtering, audio yields clear gains on tasks requiring speech comprehension or cross-modal grounding, while vision-centric suites remain largely unaffected. Our results show that speech encoders play a larger role in video understanding than current benchmarks suggest. We will open-source our work at https://github.com/naver-ai/unimambamia-av.

Recent advances in pre-training vision-language models (VLMs), e.g., contrastive language-image pre-training (CLIP) methods, have shown great potential in learning out-of-distribution (OOD) representations. Despite showing competitive performance, the prompt-based CLIP methods still suffer from: i) inaccurate text descriptions, which leads to degraded accuracy and robustness, and poses a challenge for zero-shot CLIP methods. ii) limited vision-language embedding alignment, which is one important factor affecting generalization performance. To tackle the above issues, this paper proposes a novel Conditional Domain prompt Learning (CoDoL) method, which utilizes readily-available domain information to form prompts and contributes to improved vision-language embedding alignment, which we identify as one factor underlying the observed OOD generalization gains. To capture both instance-specific and domain-specific information, we further propose a lightweight Domain Meta Network (DMN) to generate input-conditional tokens for images in each domain. Extensive experiments on four OOD benchmarks (PACS, VLCS, OfficeHome, and DigitDG) validate the effectiveness of our proposed CoDoL method in terms of empirically improves vision-language embedding alignment across four DG benchmarks, which we present as a contributing factor (rather than the sole cause) of the observed OOD gains.

Personalized object detection aims to adapt a general-purpose detector to recognize user-specific instances from only a few examples. Lightweight models often struggle in this setting due to their weak semantic priors, while large vision-language models (VLMs) offer strong object-level understanding but are too computationally demanding for real-time or on-device applications. We introduce MOCHA (Multi-modal Objects-aware Cross-arcHitecture Alignment), a distillation framework that transfers multimodal region-level knowledge from a frozen VLM teacher into a lightweight vision-only detector. MOCHA extracts fused visual and textual teacher's embeddings and uses them to guide student training through a dual-objective loss that enforces accurate local alignment and global relational consistency across regions. This process enables efficient transfer of semantics without the need for teacher modifications or textual input at inference. MOCHA consistently outperforms prior baselines across four personalized detection benchmarks under strict few-shot regimes, yielding a +10.1 average improvement, with minimal inference cost.

Existing plant-disease datasets target classification and detection, leaving vision-language models unable to support interactive, reasoning-based diagnosis. To address this, we present PlantExpertVQA, a large-scale visual question answering (VQA) dataset designed to advance vision-language models for agricultural decision-making. It is compiled from 45 open-source datasets, including the widely used PlantVillage corpus, and comprises 765,186 high-quality question-answer (QA) pairs grounded over 150,841 images spanning 38 crop species and 89 disease conditions. Questions are organized into 3 levels of cognitive complexity and 9 distinct categories. Each was phrased following expert guidance and generated via an automated two-stage pipeline: template-based QA synthesis from image metadata, followed by multi-stage linguistic re-engineering. The dataset was iteratively reviewed by domain experts for scientific accuracy and relevance. We find that current frontier vision-language models, including recent open-source instruction-tuned multimodal LLMs, perform poorly on PlantExpertVQA. However, parameter-efficient fine-tuning of a compact 2B-parameter model on a small fraction of the dataset yields substantial improvements across all question categories, demonstrating its effectiveness for domain adaptation.

Inspired by human categorization, visual reasoning about object properties, such as physical attributes and functions, involves identifying and recognizing low-level details and higher-level abstractions. While current visual question answering (VQA) studies consider multiple object properties, such as size, they typically blend perception and reasoning and lack representativeness with respect to reasoning levels and image categories, making it unclear whether and how vision-language models (VLMs) recognize and reason about depicted objects. To this end, we introduce a systematic evaluation framework comprising images of three representative types, three reasoning levels of increasing complexity, and four object property dimensions, informed by prior work on commonsense knowledge representation and reasoning. We develop a procedure to instantiate this framework in two VQA object-reasoning benchmarks: OPTICS-CNT, comprising 360 images paired with 1,080 multi-level, count-based questions, and OPTICS-CMP, comprising 2.1k comparison questions. Experiments with 12 state-of-the-art VLMs in zero-shot settings reveal significant limitations relative to humans, with the best-performing model achieving below 40% counting and 70% comparison accuracy. While newer reasoning models perform better, a 20% gap to human performance remains. VLMs struggle particularly with photographic images, counterfactual reasoning, physical and functional properties, and higher counts. We make the OPTICS benchmark data and code available to support future scalable benchmarking methods, generalized annotation guidelines, and advanced reasoning VLMs.

Vision Language Models (VLMs) are increasingly being used in a broad range of applications, bringing their security and behavioral control to the forefront. While existing approaches for behavioral control or output redirection, like system prompting in VLMs, are easily detectable and often ineffective, activation-based steering vectors require invasive runtime access to model internals--incompatible with API-based services and closed-source deployments. We introduce VISOR (Visual Input-based Steering for Output Redirection), a novel method that achieves sophisticated behavioral control through optimized visual inputs alone. By crafting universal steering images that induce target activation patterns, VISOR enables practical deployment across all VLM serving modalities while remaining imperceptible compared to explicit textual instructions. We validate VISOR on LLaVA-1.5-7B across three critical alignment tasks: refusal, sycophancy and survival instinct. A single 150KB steering image matches steering vector performance within 1-2% for positive behavioral shifts while dramatically exceeding it for negative steering--achieving up to 25% shifts from baseline compared to steering vectors' modest changes. Unlike system prompting (3-4% shifts), VISOR provides robust bidirectional control while maintaining 99.9% performance on 14,000 unrelated MMLU tasks. Beyond eliminating runtime overhead and model access requirements, VISOR exposes a critical security vulnerability: adversaries can achieve sophisticated behavioral manipulation through visual channels alone, bypassing text-based defenses. Our work fundamentally re-imagines multimodal model control and highlights the urgent need for defenses against visual steering attacks.

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

Semantic scene understanding in robotics requires representations that are both metric-accurate and queryable via natural language in real-time. While recent Vision-Language Models enable powerful 2D image-text alignment, their integration into real-time 3D mapping systems remains challenging due to their requirements on ground truth poses, computational cost, and memory constraints. We present VLEM (Vision-Language Embedding Mapping), a real-time framework for integrating pixel-aligned 2D vision-language embeddings from various backends into a globally consistent, metric-accurate 3D representation, requiring only a raw RGB-D stream. Compared to ConceptFusion, Open-Fusion, and RayFronts, VLEM provides better open-set segmentation performance and a more compact representation. We further demonstrate VLEM's versatility in interactive real-time robotic manipulation tasks and mobile mapping scenarios.

While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities across diverse domains, their application to specialized anomaly detection (AD) remains constrained by domain adaptation challenges. Existing Group Relative Policy Optimization (GRPO) based approaches suffer from two critical limitations: inadequate training data utilization when models produce uniform responses, and insufficient supervision over reasoning processes that encourage immediate binary decisions without deliberative analysis. We propose a comprehensive framework addressing these limitations through two synergistic innovations. First, we introduce a multi-stage deliberative reasoning process that guides models from region identification to focused examination, generating diverse response patterns essential for GRPO optimization while enabling structured supervision over analytical workflows. Second, we develop a fine-grained reward mechanism incorporating classification accuracy and localization supervision, transforming binary feedback into continuous signals that distinguish genuine analytical insight from spurious correctness. Comprehensive evaluation across multiple industrial datasets demonstrates substantial performance improvements in adapting general vision-language models to specialized anomaly detection. Our method achieves superior accuracy with efficient adaptation of existing annotations, effectively bridging the gap between general-purpose MLLM capabilities and the fine-grained visual discrimination required for detecting subtle manufacturing defects and structural irregularities.

Large language models (LLMs) have demonstrated remarkable capabilities across diverse language tasks, motivating their extension to vision-language models (VLMs) for multimodal understanding. However, billion-parameter VLMs incur substantial memory and computational costs that hinder deployment in resource-constrained settings. Post-training quantization (PTQ) compresses models and accelerates inference without retraining, yet remains underexplored for VLMs. We identify two intrinsic VLM activation properties in PTQ: (1) visual over-representation, where vision tokens are excessive and often redundant, and (2) the modality gap separating text and vision tokens in the latent feature space. Prior methods largely overlook these properties, leading to quantization performance degradation. To address this mismatch, we propose SalQ-VLM, an importance-aware PTQ framework that prioritizes salient tokens and suppresses redundant vision tokens during calibration. We derive a gradient-driven importance factor that captures token-level importance variance and is theoretically grounded in the relationship among loss perturbation, activation errors, and output gradients. SalQ-VLM obtains this factor through a single lightweight block-wise gradient-caching pass and incorporates it into the layer-wise reconstruction objective. Because SalQ-VLM modifies only calibration, it adds no inference-time operations and remains compatible with existing high-performance kernels. Extensive evaluations across benchmarks and backbones show that SalQ-VLM consistently outperforms strong PTQ baselines, especially under ultra-low-bit quantization. Notably, it improves MME-RealWorld accuracy by 16.45% under INT2g128 quantization.

Large Vision-Language Models (LVLMs) recently achieve significant breakthroughs in understanding complex visual-textual contexts. However, hallucination issues still limit their real-world applicability. Although previous mitigation methods effectively reduce hallucinations in photographic images, they largely overlook the potential risks posed by stylized images, which play crucial roles in critical scenarios such as game scene understanding, art education, and medical analysis. In this work, we first construct a dataset comprising photographic images and their corresponding stylized versions with carefully annotated caption labels. We then conduct head-to-head comparisons on both discriminative and generative tasks by benchmarking 13 advanced LVLMs on the collected datasets. Our findings reveal that stylized images tend to induce significantly more hallucinations than their photographic counterparts. To address this issue, we propose Style-Aware Visual Early Revision SAVER, a novel mechanism that dynamically adjusts LVLMs' final outputs based on the token-level visual attention patterns, leveraging early-layer feedback to mitigate hallucinations caused by stylized images. Extensive experiments demonstrate that SAVER achieves state-of-the-art performance in hallucination mitigation across various models, datasets, and tasks.

We investigate whether socioeconomic indicators, like household wealth, leave recoverable informational imprints in both satellite imagery (capturing features like buildings and roads) and Internet-sourced text (reflecting historical, cultural, and narratives of neighborhoods). Using DHS data from African neighborhoods (clusters), we pair high-resolution Landsat images with textual descriptions generated by LLMs conditioned on location/year, plus text retrieved by an LLM-driven AI Search Agent from web sources. We develop a multimodal framework that predicts household wealth (International Wealth Index; IWI) via five pipelines: (i) a vision model on satellite images, (ii) an LLM using only location and year, (iii) an AI agent that searches and synthesizes web text, (iv) a joint image-text encoder, and (v) an ensemble of all signals. Our framework yields three contributions. First, evaluations show that fusing vision and agent/LLM-generated text improves on vision-only baselines in wealth prediction (e.g., R-squared of 0.77 vs. 0.63 on out-of-sample splits), with LLM-internal knowledge (artificial neural memory) proving surprisingly predictive in out-of-country/time generalization. Second, we find suggestive evidence of partial representational alignment: fused embeddings from vision and language modalities correlate moderately (median cosine similarity across modalities of about 0.60 after alignment). This pattern is broadly consistent with the Platonic Representation Hypothesis, but does not by itself establish convergence to a single shared latent representation. Because agent-retrieved data yields only marginal and unstable gains across splits, our evidence for the Agent-Induced Novelty Hypothesis is limited. Third, we release a large-scale multimodal dataset of about 60,000 DHS clusters, each linked to satellite images, LLM-generated descriptions, and AI-agent-retrieved texts.

A common belief in multimodal research is that the perceptual weaknesses of vision--language models can be compensated by stronger language reasoning (e.g., chain-of-thought, in-context learning, or external tools). We challenge this assumption. We argue that for a broad class of visual tasks hard to specify in language, failures stem from a structural fatality where the temporal decision of \textit{when} to reason strictly dictates the spatial constraint of \textit{where} reasoning takes place. When visual reasoning is deferred to language generation, current architectures do not merely delay computation; they displace it from the continuous visual representation to a discrete textual space. Consequently, the sequential Perception-then-Reasoning'' paradigm degenerates perception into a passive, one-off feature encoding process, rendering it functionally equivalent to Reasoning-in-Text-Space'', where task-critical spatial signals are collapsed before reasoning begins. We substantiate this claim with the Turing Eye Test (TET): tasks that must be resolved in \emph{visual space} and are hard to verbalize; results show text-only reasoning cannot remedy these perceptual failures. Our findings suggest rethinking the architectural divide: shifting from reasoning \textit{about} perception to reasoning \textit{within} perception. This facilitates actively reasoning-driven perception that operates directly on pixel-level visual representations, rather than within a collapsed textual space.

Recent advancements in vision-language models (VLMs) have leveraged large language models (LLMs) to achieve performance on par with closed-source systems like GPT-4V. However, deploying these models in real-world scenarios, particularly on resource-constrained devices, remains challenging due to their substantial computational demands. This has spurred interest in distilling knowledge from large VLMs into smaller, more efficient counterparts. A key challenge arises here from the diversity of VLM architectures, which are built on different LLMs and employ varying token types-differing in vocabulary size, token splits, and token index ordering. To address this challenge of limitation to a specific VLM type, we present Generation after Recalibration (GenRecal), a general-purpose distillation framework for VLMs. GenRecal incorporates a Recalibrator that aligns and adapts feature representations between heterogeneous VLMs, enabling effective knowledge transfer across different types of VLMs. Through extensive experiments on multiple challenging benchmarks, we demonstrate that GenRecal significantly improves baseline performances, eventually outperforming large-scale open- and closed-source VLMs.

Natural-language manipulation instructions specify the task goal but leave the underlying robot trajectory unspecified. We present AntiGrounding, a visual action-selection framework built around a dual geometric-visual trajectory interface. After feasibility filtering, each retained short trajectory is both an explicit motion plan for execution and a rendered prompt for instruction-conditioned vision-language model (VLM) evaluation. Structured multi-view visual question answering (VQA) scores safety, task alignment, efficiency, and physical plausibility; weighted view fusion aggregates the trajectory scores. These scores guide subsequent translational trajectory proposals; separate orientation and gripper controls coordinate interaction. An initialized digital twin provides the planning state and validates selected segments before the real robot executes the same waypoint sequences. Across eight real-world manipulation tasks, AntiGrounding with a single GPT-6 Astra evaluator achieves 71.25% overall success, compared with 50.00% for pi0.5 and 47.50% for a PIVOT-style visual proposal-selection baseline using the same evaluator under the reported deployment protocol. Component ablations and evaluator-sensitivity analyses examine trajectory evaluation, proposal search, orientation control, and evaluator choice. The interface connects general-purpose multimodal reasoning to executable trajectories, with performance bounded by digital-twin fidelity and physical interaction.

Despite the impressive performance of vision-language models (VLMs) on downstream tasks, their ability to understand and reason about causal relationships in visual inputs remains unclear. Robust causal reasoning is fundamental to solving complex high-level reasoning tasks, yet existing benchmarks often include a mixture of reasoning questions, and VLMs can frequently exploit object recognition and activity identification as shortcuts to arrive at the correct answers, making it challenging to truly assess their causal reasoning abilities. To bridge this gap, we introduce VQA-Causal and VCR-Causal, two new benchmarks specifically designed to isolate and rigorously evaluate VLMs' causal reasoning abilities. Our findings reveal that while VLMs excel in object and activity recognition, they perform poorly on causal reasoning tasks, often only marginally surpassing random guessing. Further analysis suggests that this limitation stems from a severe lack of causal expressions in widely used training datasets, where causal relationships are rarely explicitly conveyed. We additionally explore fine-tuning strategies with hard negative cases, showing that targeted fine-tuning can improve model's causal reasoning while maintaining generalization and downstream performance. Our study highlights a key gap in current VLMs and lays the groundwork for future work on causal understanding.

Currently, a prevalent approach for enhancing Vision-Language Models (VLMs) performance is to encode both the high-resolution version and the thumbnail of an image simultaneously. While effective, this method generates a large number of image tokens. When combined with the widely used Rotary Position Embedding (RoPE), its long-term decay property hinders the interaction between high-resolution tokens and thumbnail tokens, as well as between text and image. To address these issues, we propose ID-Align, which alleviates these problems by reordering position IDs. In this method, high-resolution tokens inherit IDs from their corresponding thumbnail token while constraining the overexpansion of positional indices. Our experiments conducted within the LLaVA-Next framework demonstrate that ID-Align achieves significant improvements, including a 6.09% enhancement on MMBench's relation reasoning tasks and notable gains across multiple benchmarks. Our code is available at the following link: https://github.com/zooblastlbz/ID-Align.

Many decision-making tasks, where both accuracy and efficiency matter, still require human supervision. For example, tasks like traffic officers reviewing hour-long dashcam footage or researchers screening conference videos can benefit from concise summaries that reduce cognitive load and save time. Yet current vision-language models (VLMs) often produce verbose, redundant outputs that hinder task performance. Existing video caption evaluation depends on costly human annotations and overlooks the summaries' utility in downstream tasks. We address these gaps with Video-to-text Information Bottleneck Evaluation (VIBE), an annotation-free method that scores VLM outputs using two metrics: grounding (how well the summary aligns with visual content) and utility (how informative it is for the task). VIBE selects from randomly sampled VLM outputs by ranking them according to the two scores to support effective human decision-making. Human studies on LearningPaper24, SUTD-TrafficQA, and LongVideoBench show that summaries selected by VIBE consistently improve performance-boosting task accuracy by up to 61.23% and reducing response time by 75.77% compared to naive VLM summaries or raw video.

Worldwide image geolocalization-the task of predicting GPS coordinates from images taken anywhere on Earth-poses a fundamental challenge due to the vast diversity in visual content across regions. While recent approaches adopt a two-stage pipeline of retrieving candidates and selecting the best match, they typically rely on simplistic similarity heuristics and point-wise supervision, failing to model spatial relationships among candidates. In this paper, we propose GeoRanker, a distance-aware ranking framework that leverages large vision-language models to jointly encode query-candidate interactions and predict geographic proximity. In addition, we introduce a multi-order distance loss that ranks both absolute and relative distances, enabling the model to reason over structured spatial relationships. To support this, we curate GeoRanking, the first dataset explicitly designed for geographic ranking tasks with multimodal candidate information. GeoRanker achieves state-of-the-art results on two well-established benchmarks (IM2GPS3K and YFCC4K), significantly outperforming current best methods.

Despite the impressive capabilities of Large Vision-Language Models (LVLMs), they remain susceptible to hallucinations, where generated content is inconsistent with the input image. Existing training-free hallucination mitigation methods often suffer from unstable performance and high sensitivity to hyperparameter settings, which limits their practicality and broader adoption. In this paper, we propose Decoding with Inter-layer Consistency via Layer Aggregation (DCLA), a training-free decoding mechanism that requires no retraining, fine-tuning, or access to external knowledge bases. Specifically, DCLA constructs a dynamic semantic reference by aggregating representations from previous layers and uses it to correct semantically deviated layers, thereby enforcing inter-layer consistency. Experiments across seven LVLMs and multiple benchmarks demonstrate the generality of DCLA: it surpasses standard decoding by 28.58 MME points on LLaVA1.5-7B and 42.6 MME points on Qwen2.5-VL, while improving POPE accuracy by 2.74 percentage points in the strongest setting.

Rapid advances in vision-language models (VLMs) have generated growing interest in their application to autonomous driving. A prevailing assumption is that successive VLM generations will continually improve driving performance and eventually outperform state-of-the-art methods. To systematically examine this assumption, we introduce LightEMMA, a longitudinal framework for evaluating the autonomous driving performance of VLMs. LightEMMA uses a lightweight, unified evaluation protocol that assesses each model's intrinsic driving capability without model-specific fine-tuning, architectural changes, or prompt engineering. Using this protocol, we evaluate 15 models from five major families on the challenging nuScenes prediction benchmark. Empirical findings show that, despite increased model scale and enhanced general reasoning capabilities, successive VLM generations do not consistently achieve better driving performance. Further analysis of driving scenarios reveals recurring failure modes, including overreliance on historical actions and difficulty reconciling conflicting visual cues. These findings highlight the need for domain-specific adaptation to improve the safety of VLM-based autonomous driving systems. The source code is available at https://github.com/michigan-traffic-lab/LightEMMA.

Vision-Language Models (VLMs) have demonstrated exceptional performance in various multi-modal tasks. Recently, there has been an increasing interest in improving the personalization capabilities of VLMs. To better integrate user-provided concepts into VLMs, many methods use positive and negative samples to fine-tune these models. However, the scarcity of user-provided positive samples and the low quality of retrieved negative samples pose challenges for existing techniques. To reveal the relationship between sample and model performance, we systematically investigate the amount and diversity impact of positive and negative samples (easy and hard) on VLM personalization tasks. Based on the detailed analysis, we introduce Concept-as-Tree (CaT), which represents a concept as a tree structure, thereby enabling the data generation of positive and negative samples with varying difficulty and diversity, and can be easily extended to multi-concept scenarios. With a well-designed data filtering strategy, our CaT framework can ensure the quality of generated data, constituting a powerful pipeline. We perform thorough experiments with various VLM personalization baselines to assess the effectiveness of the pipeline, alleviating the lack of positive samples and the low quality of negative samples. Our results demonstrate that CaT equipped with the proposed data filter significantly enhances the capabilities of VLMs across personalization benchmarks. To the best of our knowledge, this work is the first controllable synthetic data pipeline for VLM personalization.

Recent advancements in Large Language Models (LLMs) and Vision-Language Models (VLMs) have made them powerful tools in embodied navigation, enabling agents to leverage commonsense and spatial reasoning for efficient exploration in unfamiliar environments. Existing LLM-based approaches convert global memory, such as semantic or topological maps, into language descriptions to guide navigation. While this improves efficiency and reduces redundant exploration, the loss of geometric information in language-based representations hinders spatial reasoning, especially in intricate environments. To address this, VLM-based approaches directly process ego-centric visual inputs to select optimal directions for exploration. However, relying solely on a first-person perspective makes navigation a partially observed decision-making problem, leading to suboptimal decisions in complex environments. In this paper, we present a novel vision-language model (VLM)-based navigation framework that addresses these challenges by adaptively retrieving task-relevant cues from a global memory module and integrating them with the agent's egocentric observations. By dynamically aligning global contextual information with local perception, our approach enhances spatial reasoning and decision-making in long-horizon tasks. The proposed method surpasses previous state-of-the-art approaches by a significant margin on both the HSSD and HM3D benchmarks and demonstrates strong performance on a real robot.

The advances in Vision-Language models (VLMs) offer exciting opportunities for robotic applications involving image geo-localization - the problem of identifying the geo-coordinates of a place based on visual data only. In robotics, such capabilities are particularly relevant to the global re-localization stage of the kidnapped robot problem, where a robot must recover its pose without prior knowledge of its location. Recent work has focused on using a VLM as embedding extractor for geo-localization. However, the most sophisticated VLMs may only be available as black boxes that are accessible through an API, and come with a number of limitations: there is no access to training data, model features and gradients; retraining is not possible; and the number of predictions may be limited by the API. The potential of state-of-the-art VLMs as a stand-alone, zero-shot geo-localization systems at planet scale using a single text-based prompt is largely unexplored. To bridge this gap, this paper undertakes the first systematic study, to the best of our knowledge, to investigate state-of-the-art generative VLMs as stand-alone, zero-shot geo-localization systems in a black-box setting with realistic constraints. We consider three main scenarios for this thorough investigation: a) fixed text-based prompt; b) semantically-equivalent text-based prompts; and c) semantically-equivalent query images. Beyond standard accuracy, we introduce model consistency as a metric to account for the auto-regressive and probabilistic nature of generative VLMs. Our findings reveal that while VLMs demonstrate strong coarse-level localization and navigation priors, fine-grained localization degrades significantly under realistic variations, highlighting reliability challenges for deploying generative VLMs in robust, open-world robotic navigation systems.

Large-scale Vision-Language Models (VLMs) have achieved notable progress in aligning visual inputs with text. However, their ability to deeply understand the unique physical properties of non-RGB vision sensor images remains limited. In this paper, we revisit and analyze these limitations and introduce a novel, cost-efficient paradigm that significantly advances sensor image understanding-without requiring extensive training data or any modifications to the existing VLM architectures. Specifically, we propose Sensor-Aware Attributes Fine-Tuning (SAFT) with the Diverse Negative Attributes (DNA) optimization, which leverages minimal sensor-specific data to enable robust learning of non-RGB characteristics and overcome RGB-centric biases inherent in current VLMs. In addition, we present VS-TDX-the first comprehensive, public benchmark designed to rigorously evaluate VLMs' sensor-specific understanding across diverse and realistic scenarios. Through extensive experiments on VLMs and various sensor modalities, we validate that our method consistently delivers superior performance and generalization under resource-constrained and architecture-invariant settings. Our approach provides a practical advance towards scalable deployment of VLMs in increasingly sensor-diverse real-world environments.

Global geolocation, which seeks to predict the geographical location of images captured anywhere in the world, is one of the most challenging tasks in the field of computer vision. In this paper, we introduce an innovative interactive global geolocation assistant named GaGA, built upon the flourishing large vision-language models (LVLMs). GaGA uncovers geographical clues within images and combines them with the extensive world knowledge embedded in LVLMs to determine the geolocations while also providing justifications and explanations for the prediction results. We further designed a novel interactive geolocation method that surpasses traditional static inference approaches. It allows users to intervene, correct, or provide clues for the predictions, making the model more flexible and practical. The development of GaGA relies on the newly proposed Multi-modal Global Geolocation (MG-Geo) dataset, a comprehensive collection of 5 million high-quality image-text pairs. GaGA achieves state-of-the-art performance on the GWS15k dataset, improving accuracy by 4.57% at the country level and 2.92% at the city level, setting a new benchmark. These advancements represent a significant leap forward in developing highly accurate, interactive geolocation systems with global applicability.

Large Vision-Language Models (LVLMs) have achieved remarkable performance on multimodal tasks but remain highly vulnerable to small adversarial perturbations in input images. Existing attacks typically target the vision encoder's final output embeddings, implicitly treating the encoder as a uniform attack surface, while a systematic analysis of which internal components are most vulnerable has remained largely unexplored. We show such analysis is essential, as adversarial vulnerability in LVLM vision encoders is structurally concentrated rather than uniformly distributed. Building on this, we propose Vision Encoder Vulnerable-Component-Targeted Universal Adversarial Perturbation (VEV-UAP), a task-agnostic and cost-efficient attack framework. Through a component- and layer-wise analysis of attention mechanisms, we identify the value components in middle layers as critical vulnerabilities that strongly influence downstream language model behavior. VEV-UAP selectively targets these components to generate a single universal perturbation shared across images, without involving textual inputs or the language model during optimization. Experiments across multiple LVLMs and tasks show VEV-UAP achieves state-of-the-art attack success rates with reduced computational overhead. Moreover, a single VEV-UAP transfers across LVLMs sharing the same vision encoder, even when paired with different language models, making it a practical framework for scalable robustness evaluation.

Vision-language Models (VLMs) are essential for contextual understanding of both visual and textual information. However, their vulnerability to adversarially manipulated inputs presents significant risks, leading to compromised outputs and raising concerns about the reliability in VLM-integrated applications. Detecting these malicious prompts is thus crucial for maintaining trust in VLM generations. A major challenge in developing a safeguarding prompt classifier is the lack of a large amount of labeled benign and malicious data. To address the issue, we introduce VLMGuard, a novel learning framework that leverages the unlabeled user prompts in the wild for malicious prompt detection. These unlabeled prompts, which naturally arise when VLMs are deployed in the open world, consist of both benign and malicious information. To harness the unlabeled data, we present an automated maliciousness estimation score for distinguishing between benign and malicious samples within this unlabeled mixture, thereby enabling the training of a binary prompt classifier on top. Notably, our framework does not require extra human annotations and is robust to realistic prompt variations, offering strong flexibility and practicality for real-world applications. Extensive experiments show that VLMGuard achieves superior detection results, improving AUROC by 5.39% on average over the state-of-the-art method. Disclaimer: This paper may contain offensive examples; reader discretion is advised. Code is available at: https://github.com/radiolab-ntu/vlmguard.

As Visual Language Models (VLMs) become increasingly embedded in everyday applications, ensuring they can recognise and appropriately handle privacy-sensitive content is thus essential to protect users. To this end, we conduct a comprehensive evaluation of twelve state-of-the-art VLMs and identify limitations in their understanding of visual privacy. However, existing privacy-related datasets often suffer from label inconsistencies, limiting their reliability. To address this, we introduce two compact, high-quality benchmarks, PrivBench and PrivBench-H, that focus on commonly recognised visual privacy categories aligned with the General Data Protection Regulation (GDPR). Additionally, we present PrivTune, an instruction-tuning dataset specifically curated to improve privacy sensitivity. We obtain multiple Privacy VLMs by fine-tuning off-the-shelf VLMs on only a few hundred samples from PrivTune, which leads to substantial gains on all benchmarks, surpassing even GPT-4, while maintaining strong performance on other tasks. Our findings show that privacy-awareness in VLMs can be substantially improved with minimal data and careful dataset design, setting the stage for safer, more privacy-aligned AI systems.

We describe our entry to the EgoLongQA track of the Wearable-AI Challenge in ECCV 2026, which placed first in the <=2B parameter division with 0.8279 on the held-out test set. Our system is a single 2B vision-language model that answers multiple-choice questions about ten-minute egocentric videos in one greedy forward pass; It is obtained by distilling the junior perception module of a tool-using agentic pipeline, not the agent itself into a small student, using teacher traces filtered to those that answered correctly. it reaches 89% of the accuracy of the large agentic pipeline using 1.1% of its parameters. This raises a 27.1% base model to 81.4% on our held-out questions. The 2B backbone has 2.2132B parameters and therefore over the divisional limit, to make the entry admissable we prune the multilingual embedding table from 248,320 to 143,469 rows, reaching 1.9985B with provably identical logits on retained rows.

Humans effortlessly perceive the present while remembering the past, yet streaming VLMs often trade off real-time perception against long-term memory. Prior work shows that shortening the context can sharpen current-scene perception at the expense of long-range recall. To reconcile these abilities, we introduce StreamTTT, which writes long-range history into online-updated fast weights outside the attention context. This leaves a short sliding key-value cache dedicated to recent evidence, mitigating attention dilution. We train StreamTTT jointly on offline long-video QA and a newly constructed real-time QA corpus. On OVO-Bench, under each model's reported input protocol, StreamTTT-4B outperforms the same-scale SimpleStream-4B by 0.6 points in real-time perception and 5.3 points in backward tracing. It also surpasses the larger SimpleStream-8B by 0.73 points on StreamingBench's Real-Time Visual Understanding (RTVU) subset. Our code is publicly available at https://github.com/zeyun-zhong/StreamTTT.

We present ABACUS, a unified vision-language model that jointly addresses object counting, crowd counting, referring-expression counting, and count-faithful image generation within a single 3B-parameter model. ABACUS introduces three contributions: density-aware adaptive zooming paired with an objectness map from multi-head self-attention decomposition to spatially ground count predictions; a boundary-aware count policy trained via GRPO with nested local, boundary, and global rewards to eliminate over- and undercounting at crop boundaries; and a cycle-consistent GRPO strategy in which the frozen understanding branch scores generated candidates on count-deviation and aesthetic quality, closing the understanding-generation synergy gap without any external critic or annotation. ABACUS achieves state-of-the-art results across seven benchmarks spanning object counting (FSC-147, CARPK), crowd counting (ShanghaiTech A/B), referring-expression counting (REC-8K), count-faithful generation (CoCoCount, T2I-CompBench, GenEval), and count reasoning (CountQA), surpassing both task-specific specialists and larger generalist models. Project page is at https://mondalanindya.github.io/pages/ABACUS.

We present Lunima-OmniLV (abbreviated as OmniLV), a universal multimodal multi-task framework for low-level vision that addresses over 100 sub-tasks across four major categories: image restoration, image enhancement, weak-semantic dense prediction, and stylization. OmniLV leverages both textual and visual prompts to offer flexible and user-friendly interactions. Built on Diffusion Transformer (DiT)-based generative priors, our framework supports arbitrary resolutions -- achieving optimal performance at 1K resolution -- while preserving fine-grained details and high fidelity. Through extensive experiments, we demonstrate that separately encoding text and visual instructions, combined with co-training using shallow feature control, is essential to mitigate task ambiguity and enhance multi-task generalization. Our findings also reveal that integrating high-level generative tasks into low-level vision models can compromise detail-sensitive restoration. These insights pave the way for more robust and generalizable low-level vision systems.

Metric questions about video require vision-language models to use supplied real-world references to convert visual measurements into physical units. Yet we find that current models use this scale information only partially. When every world-space quantity in a prompt is rescaled by a common factor, the video remains equally valid and the correct answer changes by exactly that factor, but model predictions move only part of the way and accuracy remains concentrated near the familiar scale of the depicted objects. Across eight vision-language models, this under-response persists over four orders of magnitude. The same models recover the correct closed-form scaling laws when the identical physics is asked in a scale-free form, indicating that the main deficit lies in metric grounding rather than physical mechanism knowledge. We use this exact scaling relation as supervision without requiring metric annotations. Under a common rescaling of the supplied world-space quantities, the correct metric answer must change by the same factor. EquiSD exploits this constraint by projecting a model's own prediction onto the scale-equivariant family and fine-tuning the model on the resulting targets. It requires no ground-truth answers and only one model query per training video. On held-out simulated videos, EquiSD increases a 3B model's median response slope from 0.66 to 0.94 and improves mean relative accuracy by 9.2 points across scales. The learned relation generalizes to unseen world scales and transfers without adaptation to real QuantiPhy videos, where accuracy increases by 6.4 points. These results show that an exact physical symmetry can provide label-free supervision for improving metric grounding in vision-language models.