Multimodal tables i.e. tabular layouts interleaved with charts, maps, icons, and color encodings are ubiquitous in real applications yet remain difficult for Multimodal Large Language Models (MLLMs). Despite advances in text and image understanding, systematic evaluation of table-centric multimodal reasoning is limited. We introduce MMTabReal, a MultiModal Table Benchmark, human-curated suite of 500 real-world tables paired with 4021 question–answer pairs. MMtabReal spans four question types, five reasoning categories, and eight structural archetypes. Evaluations of state-of-the-art models reveal substantial gaps, especially in visual grounding, spatial alignment, and multi-step inference, with 20–40% performance drops relative to existing benchmarks. These results highlight the need for architectures that more tightly fuse vision with tabular structure and support explicit numeric/logical operations. MMtabReal is released for evaluation only, providing a rigorous, reproducible testbed that reflects the linguistic, structural, and reasoning complexity of real-world multimodal tables. Code and data are available at: https://coral-lab-asu.github.io/mmtabreal/
论文检索
输入标题、作者或关键词，从 3,042 篇学术成果中精准定位
Multimodal LLMs can accurately perceive numerical content across modalities yet fail to perform exact multi-digit multiplication when the identical underlying arithmetic problem is presented as numerals, number words, images, or in audio form. Because existing benchmarks often lack systematically paired instances across modalities, it remains difficult to compare genuine arithmetic limits within and across model families. We therefore introduce a controlled multimodal multiplication benchmark that factorially varies digit length, digit sparsity, representation (e.g., numerals vs. number words), and modality (text, rendered images, and audio), with paired instances from a reproducible generator. We also define arithmetic load, C, as the product of the total and non-zero digit number as a compact, mechanistically motivated proxy for operation count. Across evaluations, accuracy falls sharply as C grows, often nearing zero by C > 100. Indeed, C remains predictive of performance across modalities and models, with R^2 > 0.5, nearing the value from more complex measures of arithmetic load that count the number of intermediate arithmetic steps. A separate perception-versus-computation decomposition shows that multimodal degradation is primarily computational rather than perceptual: on matched perception checks, models are near-perfect (>99\%) across modalities even when multiplication accuracy drops substantially. Beyond measuring when models fail, we ask which procedures they are predisposed to follow. We introduce a style-controlled forced-completion loss probe that scores heuristic-specific reasoning prefixes—including columnar multiplication, distributive decomposition, and rounding/compensation. Here, distributive decomposition is favored in both text and vision modalities; heuristic-specific LoRA adapters produce near-orthogonal updates yet degrade accuracy, indicating the base model maintains a well-tuned internal router.
Radiology report generation requires precise alignment between medical imaging findings and clinically coherent textual descriptions. While current methods predominantly rely on either large vision-language models (LVLMs) for visual grounding or large language models (LLMs) for medical narrative generation, they often fail to effectively integrate multimodal clinical evidence with domain-specific knowledge. This paper proposes a novel multimodal dual-path framework that synergistically combines LVLMs and LLMs to address these limitations. Our approach establishes a dynamic fusion between LVLMs’ visual-semantic grounding capabilities and LLMs’ clinical knowledge reasoning. Specifically, we employ a structured prompting strategy that models the report generation task into three clinically meaningful sections and introduces fine-grained multi-label classification prompts to guide the models, enabling more accurate and comprehensive clinical report generation. Experiments on the public MIMIC-CXR benchmark demonstrate our framework’s superiority over state-of-the-art methods.
Can MLLMs Reason Beyond Language? VisReason: A Comprehensive Benchmark for Vision-Centric Reasoning
PDF ↗Recent multimodal large language models (MLLMs) achieve strong performance on visual reasoning benchmarks, yet it remains unclear to what extent such performance reflects reasoning directly grounded in visual evidence. We introduce VisReason, a benchmark for vision-centric reasoning in everyday scenarios where perception and inference are tightly coupled. VisReason contains 1,505 questions across 10 categories spanning perceptual, structural, and conceptual reasoning. Our evaluation shows that VisReason poses a qualitatively different challenge from existing benchmarks, exposing substantial gaps between humans and current MLLMs and revealing limited benefits from test-time reasoning strategies. VisReason offers a focused diagnostic for evaluating vision-centric reasoning beyond language.
Aligning Vision-Language Models (VLMs) with safety standards is essential to mitigate risks arising from their multimodal complexity, where integrating vision and language unveils subtle threats beyond the reach of conventional safeguards. Inspired by the insight that reasoning across modalities is key to preempting intricate vulnerabilities, we propose a novel direction for VLM safety: multimodal reasoning-driven prompt rewriting. To this end, we introduce VLMGuard-R1, a proactive framework that refines user inputs through a reasoning-guided rewriter, dynamically interpreting text-image interactions to deliver refined prompts that bolster safety across diverse VLM architectures without altering their core parameters. To achieve this, we devise a three-stage reasoning pipeline to synthesize a dataset that trains the rewriter to infer subtle threats, enabling tailored, actionable responses over generic refusals. Extensive experiments across five benchmarks with six VLMs reveal that VLMGuard-R1 outperforms four baselines. In particular, VLMGuard-R1 achieves a remarkable 43.59% increase in average safety across five models on the SIUO benchmark.
Short-form news videos increasingly shape public perception through strategic framing, yet existing verification methods largely overlook the communicative intent underlying such content. By emphasizing surface semantics, current models struggle to separate stylistic presentation from factual evidence, which leads to shortcut learning and brittle generalization. To address this limitation, we propose the Origin–Objective–Means (OOM) framework, a theory-grounded representation of communicative intent that captures creator stance, audience need activation, and communication strategy. We validate OOM through large-scale human annotation, revealing distinct and consistent lexical and structural patterns across intent dimensions. Building on this representation, we operationalize intent as an explicit semantic condition rather than a prediction target. Concretely, we introduce Intent-Guided Prompting (IGP) to condition LLM reasoning and intent-conditioned multimodal detection framework (ICMD), which injects intent into multimodal detectors via feature-wise modulation. Experiments on FakeSV and FakeTT show that modeling intent as an intermediate condition consistently improves accuracy and robustness across diverse vision–language backbones, while substantially reducing reliance on spurious stylistic correlations.
Typical large vision-language models (LVLMs) apply autoregressive supervision primarily to textual responses, without fully exploiting causal learning over rich visual inputs. As a result, these models often emphasize vision-to-language alignment while potentially overlooking fine-grained visual information. While prior work has explored autoregressive image generation, effectively leveraging autoregressive visual supervision to enhance image understanding remains an open challenge. In this paper, we introduce Autoregressive Semantic Visual Reconstruction (ASVR), which enables joint learning of visual and textual modalities within a unified autoregressive framework. ASVR trains models to autoregressively reconstruct the semantic content of input images, which consistently enhances multimodal comprehension. Notably, we show that even when provided with continuous image features as input, models can effectively reconstruct discrete semantic tokens, resulting in stable and consistent improvements across various multimodal understanding benchmarks. ASVR delivers significant performance gains and scalability across varying data scales, visual input, visual supervision and model architectures. In particular, ASVR generally improves baselines by 2-3% across 14 multimodal benchmarks.
Multimodal Large Language Models (MLLMs) are increasingly adopted as autonomous agents in interactive environments, yet their ability to proactively address safety hazards remains insufficient. We introduce SafetyALFRED, built upon the embodied agent benchmark ALFRED, augmented with six categories of real-world kitchen hazards. While existing safety evaluations focus on hazard recognition through disembodied question answering (QA) settings, we evaluate eleven state-of-the-art models from the Qwen, Gemma, and Gemini families on not only hazard recognition, but also active risk mitigation through embodied task planning. Our experimental results reveal a significant alignment gap: while models can accurately recognize hazards in QA settings, average mitigation success rates for these hazards are low in comparison. Our findings demonstrate that static evaluations through QA are insufficient for physical safety, advocating for a paradigm shift toward benchmarks that prioritize multi-step corrective actions in embodied context.
B-APO: Bias-Targeted Adversarial Preference Optimization for Debiasing Multimodal Large Language Models
PDF ↗Multimodal Large Language Models (MLLMs) often suffer from modality bias, where the model disproportionately relies on one modality while neglecting critical information from others. Existing debiasing methods via modality masking create biased responses by completely removing an entire modality, forming an extreme and static training environment. However, real-world multimodal bias often emerges under subtle perturbations (e.g., mild occlusion, noisy instructions), where both modalities are present but the model is tempted to rely on spurious shortcuts. We propose B-APO (Bias-Targeted Adversarial Preference Optimization), which casts debiasing as a bias-targeted min-max game: we generate hard negatives by applying small adversarial perturbations in the latent space to maximally induce language-vision-prior reliance, and then perform preference alignment to enlarge the margin between clean and adversarial responses. This encourages the model to anchor on true cross-modal evidence even under the most adversarial conditions. Extensive experiments on bias and hallucination benchmarks demonstrate that B-APO achieves superior debiasing performance while maintaining general capabilities.
Vision-Language Models (VLMs) often struggle in Taiwanese Mandarin environments due to region-specific orthographic and cultural context. We introduce VisTW, a comprehensive benchmark featuring (i) multiple-choice questions (3,795 academic questions) and (ii) free-form generation evaluation (141 Taiwanese-context free-form pairs). Beyond standard accuracy, we investigate character mixing— the unintended production of Simplified Chinese characters under Taiwanese-Mandarin-style prompts—and propose a human-grounded purity penalty derived from perceptual thresholds measured from users. Our evaluation reveals substantial character contamination (3%–19%) across state-of-the-art VLMs. We find that Gemini-3-Pro significantly outperforms the strongest open-weight baseline, Qwen3 235B MoE, by up to 22 percentage points on dialogue tasks once the purity penalty is applied. These results highlight orthographic consistency as a vital, yet overlooked, dimension for localized multimodal evaluation and deployment.
Recent work has increasingly explored neuron-level interpretation in vision-language models (VLMs) to identify neurons critical to final predictions. However, existing neuron analyses generally focus on single tasks, limiting the comparability of neuron importance across tasks. Moreover, ranking strategies tend to score neurons in isolation, overlooking how task-dependent information pathways shape the write-in effects of feed-forward network (FFN) neurons. This oversight can exacerbate neuron polysemanticity in multi-task settings, introducing noise into the identification and intervention of task-critical neurons. In this study, we propose HONES (**H**ead-**O**riented **N**euron **E**xplanation **S**teering), a gradient-free framework for task-aware neuron attribution and steering in multi-task VLMs. HONES ranks FFN neurons by their causal write-in contributions conditioned on task-relevant attention heads, and further modulates salient neurons via lightweight scaling. Experiments on four diverse multimodal tasks and two popular VLMs show that HONES outperforms existing methods in identifying task-critical neurons and improves model performance after steering. Our source code is released at: https://github.com/petergit1/HONES.
Can unified vision–language models (VLMs) perform forward dynamics prediction (FDP), i.e., predicting the future state (in image form) given the previous observation and an action (in language form)? We find that VLMs struggle to generate physically plausible transitions between frames from instructions. Nevertheless, we identify a crucial asymmetry in multimodal grounding: fine-tuning a VLM to learn inverse dynamics prediction (IDP)—effectively captioning the action between frames—is significantly easier than learning FDP. In turn, IDP can be used to bootstrap FDP through two main strategies: 1) weakly supervised learning from synthetic data and 2) inference time verification. Firstly, IDP can annotate actions for unlabelled pairs of video frame observations to expand the training data scale for FDP. Secondly, IDP can assign rewards to multiple samples of FDP to score them, effectively guiding search at inference time. We evaluate the FDP resulting from both strategies through the task of action-centric image editing on Aurora-Bench with two families of VLMs. Despite remaining general-purpose, our best model achieves a performance competitive with state-of-the-art image editing models, improving on them by a margin of 15% on real-world subsets according to GPT4o-as-judge, and achieving the best average human evaluation across all subsets of Aurora-Bench.
Automatic evaluators such as reward models play a central role in the alignment and evaluation of large vision–language models (LVLMs). Despite their growing importance, these evaluators are almost exclusively assessed on English-centric benchmarks, leaving open the question of how well these evaluators generalize across languages. To answer this question, we introduce MM-JudgeBench, the first large-scale benchmark for multilingual and multimodal judge model evaluation, which includes over 60K pairwise preference instances spanning 25 typologically diverse languages. MM-JudgeBench integrates two complementary subsets: a general vision–language preference evaluation subset extending VL-RewardBench, and a chart-centric visual–text reasoning subset derived from OpenCQA, enabling systematic analysis of reward models (i.e., LVLM judges) across diverse settings. We additionally release a multilingual training set derived from MM-RewardBench, disjoint from our evaluation data, to support domain adaptation. By evaluating 22 LVLMs (15 open-source, 7 proprietary), we uncover substantial cross-lingual performance variance in our proposed benchmark. Our analysis further shows that model size and architecture are poor predictors of multilingual robustness, and that even state-of-the-art LVLM judges exhibit inconsistent behavior across languages. Together, these findings expose fundamental limitations of current reward modeling and underscore the necessity of multilingual, multimodal benchmarks for developing reliable automated evaluators.
We introduce TableVista, a comprehensive benchmark for evaluating foundation models in multimodal table reasoning under visual and structural complexity. TableVista consists of 3,000 high-quality table reasoning problems, where each instance is expanded into 10 distinct visual variants through our multi-style rendering and transformation pipeline. This process encompasses diverse scenario styles, robustness perturbations, and vision-only configurations, culminating in 30,000 multimodal samples for a multi-dimensional evaluation. We conduct an extensive evaluation of 29 state-of-the-art open-source and proprietary foundation models on TableVista. Through comprehensive quantitative and qualitative analysis, we find that while evaluated models remain largely stable across diverse rendering styles, they exhibit pronounced performance degradation on complex structural layouts and vision-only settings, revealing that current models struggle to maintain reasoning consistency when structural complexity combines with visually integrated presentations. These findings highlight critical gaps in current multimodal capabilities, providing insights for advancing more robust and reliable table understanding models.
Thinking Like a Botanist: Challenging Multimodal Language Models with Intent Driven Chain-of-Inquiry
PDF ↗Vision evaluations are typically done through multi-step processes. In most contemporary fields, experts analyze images using structured, evidence-based adaptive questioning. In plant pathology, botanists inspect leaf images, identify visual cues, infer diagnostic intent, and probe further with targeted questions that adapt to species, symptoms, and severity. This structured probing is crucial for accurate disease diagnosis and treatment formulation. Yet current vision-language models are evaluated on single-turn question answering. To address this gap, we introduce PlantInquiryVQA, a benchmark for studying multi-step, intent-driven visual reasoning in botanical diagnosis. We formalize a Chain of Inquiry framework modeling diagnostic trajectories as ordered question-answer sequences conditioned on grounded visual cues and explicit epistemic intent. We release a dataset of 24,964 expert-curated plant images and 138,078 question-answer pairs annotated with visual grounding, severity labels, and domain-specific reasoning templates. Evaluations on top-tier Multimodal Large Language Models reveal that while they describe visual symptoms adequately, they struggle with safe clinical reasoning and accurate diagnosis. Importantly, structured question-guided inquiry significantly improves diagnostic correctness, reduces hallucination, and increases reasoning efficiency. PlantInquiryVQA provides a foundation for training diagnostic agents that reason like expert botanists rather than static classifiers.
Time series captioning, the task of describing time series in natural language, requires numeric and temporal reasoning, trend interpretation, and contextual understanding. Existing benchmarks, however, often rely on fully synthetic or generic captions, and typically neglect metadata and visual representations. We introduce CaTS-Bench, a comprehensive benchmark for Context-aware Time Series reasoning across 11 diverse domains, centered on a gold-standard evaluation set of 1746 human-rewritten captions that measure how effectively models translate numeric trends into immediately interpretable narratives. To address the scarcity of human-annotated data, we also propose a scalable pipeline for generating high-fidelity synthetic captions, the quality of which we validate. We evaluate leading Vision-Language Models on our benchmark, revealing that even proprietary models struggle to capture numeric nuances in temporal descriptions, while finetuning open-source models on synthetic data yields substantial performance gains. Finally, we release a diagnostic suite of 910 multiple-choice questions and use tailored numeric metrics to gauge time-series-specific reasoning capabilities, establishing CaTS-Bench as a reliable foundation for grounded, multimodal text generation in numeric domains.
Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning and has become a standard post-training paradigm for contemporary language and vision-language models. However, the RLVR recipe introduces a significant risk of capability regression, where models forget foundational skills after prolonged training without employing regularization strategies. We empirically confirm this concern, observing that open-source reasoning models suffer performance degradation on core capabilities such as perception and faithfulness. While imposing regularization terms like KL divergence can help prevent deviation from the base model, these terms are calculated on the current task, thus they do not guarantee broader knowledge. Meanwhile, commonly used experience replay across heterogeneous domains makes it nontrivial to decide how much training focus each objective should receive. To address this, we propose RECAP—a replay strategy with dynamic objective reweighting for general knowledge preservation. Our reweighting mechanism adapts in an online manner using short-horizon signals of convergence and instability, shifting the post-training focus away from saturated objectives and toward underperforming or volatile ones. Our method is end-to-end and readily applicable to existing RLVR pipelines without training additional models or heavy tuning. Extensive experiments on benchmarks based on Qwen2.5-VL-3B and Qwen2.5-VL-7B demonstrate the effectiveness of our method, which not only preserves general capabilities but also improves reasoning by enabling more flexible trade-offs among in-task rewards.
In complex domains like interior design, user requests are often ambiguous and multimodal. Professional designers address this by asking strategic clarification questions based on hierarchical priorities, a capability lacking in current Vision-Language Models (VLMs). When fine-tuned on dialogue data, existing models often exhibit modality forgetting, overfitting to textual patterns while neglecting visual cues and thus producing hallucinated or visually irrelevant questions. To bridge this gap, we introduce VIDA (Visual Intent-driven Design Assistant), an assistant designed to generate proactive, visually grounded, and strategically prioritized clarification questions. Instead of standard fine-tuning, we propose a strategy-aware alignment framework that evolves from imitation learning to value-driven reinforcement. We utilize Group Sequence Policy Optimization to strictly enforce expert protocols, ensuring the model not only mimics fluent speech but also adheres to optimal inquiry strategies. Crucially, we design a novel hierarchical reward mechanism with Dynamic Intent Binding to align the assistant with professional prioritization standards. To facilitate this research, we construct and release InteriorClarify, a multimodal benchmark dataset comprising 1,016 real-world consultation cases annotated with this three-tier intent hierarchy. Extensive experiments demonstrate that VIDA sets a new state-of-the-art, improving the Strategic Alignment Score (SAS) by 20.59% over SFT baselines and effectively restoring visual grounding capabilities lost during standard fine-tuning.
When Meaning Travels: A Granular Lens on Hybrid-MoE’s Role in Idiomatic Understanding for Language Models
PDF ↗In the contemporary epoch of multilingual education, learning idioms provides a fascinating gateway towards creativity, cultural values, historical context, and diverse perspectives inherent to various linguistic traditions. This paper showcases the navigation of retaining figurative and cultural semantics in low-resource Southeast Asian languages such as Hindi, Bengali, and Thai, where culturally rich idioms pose significant obstacles for computational modelling and cross-linguistic transfer due to their deep metaphorical complexity. To tackle such complexity, we present Varnika (वर्णिका) , a reconstructed multimodal idiom corpus comprising 3,533 multilingual idioms, enriched with seven idiomatic tones aligned with both textual and visual representations. Additionally, to infer informative idiomatic understanding, we introduce a Hybrid Mixture-of-Experts (HybridMoE) framework that embeds multiple idiomatic expert opinions while mitigating expert sparsity by integrating outputs from both selected and unselected experts through controlled hybridisation, further augmented with Idiomatic Property Signals via masked multimodal embeddings. To analyse the performance across multiple dimensions, we propose the IDIO-TONE and Idiomatic Validation Score, a three-stage evaluation pipeline measuring (i) literal translation fidelity, (ii) visual- semantic alignment, and (iii) idiomatic meaning retention. Empirical evaluations highlight that HybridMoE achieves 5–6% performance gains across advanced vision language models, demonstrating improved representation of figurative language and culturally embedded meaning in multilingual multimodal settings. Resources are available at (https://github.com/sarmistha-D/Hybrid_MOE).
Vision-Language Models (VLMs) have shown strong generalization across multimodal tasks, but their capacity to handle sign language translation (SLT), which requires fine-grained spatiotemporal reasoning and linguistic understanding, remains unclear. In this study, we evaluate whether small VLMs (with \leq3B parameters) can perform SLT effectively. We perform supervised fine-tuning on four publicly available multilingual SLT datasets, including one German (DGS), two American (ASL), and one Indian (ISL), applying parameter-efficient LoRA to the language decoder while keeping the vision encoder frozen and training only the connector. To evaluate translation quality, we propose entity- and semantics-aware metrics tailored for SLT. We highlight the data imbalance issues present in the above widely used SLT datasets. Our analysis highlights the limitations in applying general-purpose VLMs to SLT, unlike their applicability in other tasks, and provides insights to inform future development of VLMs for SLP, which is essential for building inclusive AI applications.