Multimodal Large Language Models

Although Multimodal Large Language Models (MLLMs) have advanced rapidly, they still face notable challenges in fine-grained multi-image understanding, often exhibiting spatial hallucination, attention leakage, and failures in object constancy. In addition, existing approaches typically rely on expensive human annotations or large-scale chain-of-thought (CoT) data generation. We propose Compositional Grounded Contrast (abbr. CGC), a low-cost full framework for boosting fine-grained multi-image understanding of MLLMs. Built on existing single-image grounding annotations, CGC constructs compositional multi-image training instances through Inter-Image Contrast and Intra-Image Contrast, which introduce semantically decoupled distractor contexts for cross-image discrimination and correlated cross-view samples for object constancy, respectively. CGC further introduces a Rule-Based Spatial Reward within the GRPO framework to improve source-image attribution, spatial alignment, and structured output validity under a Think-before-Grounding paradigm. Experiments show that CGC achieves state-of-the-art results on fine-grained multi-image benchmarks, including MIG-Bench and VLM2-Bench. The learned multi-image understanding capability also transfers to broader multimodal understanding and reasoning tasks, yielding consistent gains over the Qwen3-VL-8B base model on MathVista (+2.90), MuirBench (+2.88), MMStar (+1.93), MMMU (+1.77), and BLINK (+1.69).

Understanding social dominance in animal behavior is critical for neuroscience and behavioral studies. In this work, we explore the capability of Multimodal Large Language Models(MLLMs) to analyze raw behavioral video of mice and predict their dominance hierarchy. We introduce MTT-Bench, a novel benchmark comprising annotated videos of pairwise mouse interactions for Mouse Tube Test analysis. Building on existing MLLM architectures, we fine-tune these models to perform zero-shot inference on unseen behavioral sequences, predicting social dominance without explicit labels during testing. Our framework demonstrates promising results, showing high agreement with tube test rankings. This work opens a new direction for applying foundation models to ethology and social behavior analysis, without the need to design domain-specific models.

Multimodal large language models (MLLMs) have advanced static visual--spatial reasoning, yet they often fail to preserve long-horizon spatial coherence in embodied settings where beliefs must be continuously revised from egocentric observations under environmental change. We introduce SpaMEM (Spatial Memory from Action Sequences), a large-scale diagnostic benchmark that isolates the mechanics of spatial belief evolution via action-conditioned scene transformations (spawn, place, remove) over long interaction horizons. SpaMEM is built on a physically grounded dataset with 10,601,392 high-fidelity images across four modalities (RGB, depth, instance, semantic segmentation), collected from 25,000+ interaction sequences in 1,000 procedurally generated houses. We formalize embodied spatial reasoning as a three-level hierarchy with 15 diagnostic tasks: Level 1 measures atomic spatial perception from single observations; Level 2 probes temporal reasoning with oracle textual state histories to factor out perceptual noise; and Level 3 requires end-to-end belief maintenance from raw visual streams under the same task dimensions. We further evaluate both short-term (step-wise) updates and long-term (episodic) reconstruction. Benchmarking representative open-source VLM families reveals a consistent stacked bottleneck: coordinate-consistent grounding remains a hard ceiling, and the sharp collapse from Level 2 to Level 3 exposes a pronounced symbolic scaffolding dependency, where models succeed with text-based bookkeeping but struggle to sustain robust visual memory. SpaMEM provides a granular diagnostic standard and motivates explicit mechanisms for state representation, belief revision, and long-horizon episodic integration. A subset of SpaMEM is publicly available at https://huggingface.co/datasets/mill-ct-liao/SpaMEM.

Sign language research has achieved significant progress due to the advances in large language models (LLMs). However, the intrinsic ability of LLMs to understand sign language, especially in multimodal contexts, remains underexplored. To address this limitation, we introduce CNSL-bench, the first comprehensive Chinese em{National Sign Language benchmark designed for evaluating multimodal large language models (MLLMs) in sign language understanding. The proposed CNSL-bench is characterized by: 1) Authoritative grounding, as it is anchored to the officially standardized \textit{National Common Sign Language Dictionary, mitigating ambiguity from regional or non-canonical variants and ensuring consistent semantic definitions; 2) Multimodal coverage, providing aligned textual descriptions, illustrative images, and sign language videos; and 3) Articulatory diversity, supporting fine-grained analysis across key manual articulatory forms, including air-writing, finger-spelling, and the Chinese manual-alphabet. Using CNSL-bench, we extensively evaluate 21 open-source and proprietary up-to-date MLLMs. Our results reveal that, despite recent advances in multimodal modeling, current MLLMs remain substantially inferior to human performance, exhibiting systematic disparities across input modalities and manual articulatory forms. Additional diagnostic analyses suggest that several performance limitations persist beyond improvements in reasoning and that instruction-following robustness varies substantially across models.

Model Construction is a foundational practice in science learning that relies on visualization and interactivity. Large Language Models, increasingly augmented with multimodal capabilities, have been integrated in education contexts to support learning. However, these tools lack visual interactivity that is required by some learning contexts. We introduce Text to Multimodal Model (T2MM), a robust, dynamic LLM supported architecture that assists in model construction within the open inquiry ecology-based modeling software Virtual Experimental Research Assistant (VERA). T2MM accounts for the current context of the learner's model and creates interactive models, rather than static images, enabling the model to remain responsive to manual adjustment. To measure technical feasibility, we evaluate T2MM through a custom procedurally generated dataset of natural language learner modeling requests and target models within the VERA system. T2MM outperforms a baseline model generation architecture implemented through LLM-supported full code generation, common in the literature, across all measured success metrics. Our contribution not only outlines LLM integration into a inquiry-based learning modeling tool, but also describes a possible architecture through which more interactive multimodal LLM tools can be created.

Protein-ligand bioactivity data published in the literature are essential for drug discovery, yet manual curation struggles to keep pace with rapidly growing literature. Automated bioactivity extraction remains challenging because it requires not only interpreting biochemical semantics distributed across text, tables, and figures, but also reconstructing chemically exact ligand structures (e.g., Markush structures). To address this bottleneck, we introduce BioMiner, a multi-modal extraction framework that explicitly separates bioactivity semantic interpretation from ligand structure construction. Within BioMiner, bioactivity semantics are inferred through direct reasoning, while chemical structures are resolved via a chemical-structure-grounded visual semantic reasoning paradigm, in which multi-modal large language models operate on chemically grounded visual representations to infer inter-structure relationships, and exact molecular construction is delegated to domain chemistry tools. For rigorous evaluation and method development, we further establish BioVista, a comprehensive benchmark comprising 16,457 bioactivity entries curated from 500 publications. BioMiner validates its extraction ability and provides a quantitative baseline, achieving an F1 score of 0.32 for bioactivity triplets. BioMiner's practical utility is demonstrated via three applications: (1) extracting 82,262 data from 11,683 papers to build a pre-training database that improves downstream models performance by 3.9%; (2) enabling a human-in-the-loop workflow that doubles the number of high-quality NLRP3 bioactivity data, helping 38.6% improvement over 28 QSAR models and identification of 16 hit candidates with novel scaffolds; and (3) accelerating protein-ligand complex bioactivity annotation, achieving a 5.59-fold speed increase and 5.75% accuracy improvement over manual workflows in PoseBusters dataset.

Charts are widely used to present complex information. Deriving meaningful insights in real-world contexts often requires interpreting multiple related charts together. Research on understanding multi-chart images has not been extensively explored. We introduce PolyChartQA, a mid-scale dataset specifically designed for question answering over multi-chart images. PolyChartQA comprises 534 multi-chart images (with a total of 2,297 sub-charts) sourced from peer-reviewed computer science research publications and 2,694 QA pairs. We evaluate the performance of nine state-of-the-art Multimodal Language Models (MLMs) on PolyChartQA across question type, difficulty, question source, and key structural characteristics of multi-charts. Our results show a 27.4% LLM-based accuracy (L-Accuracy) drop on human-authored questions compared to MLM-generated questions, and a 5.39% L-accuracy gain with our proposed prompting method.

Large Multimodal Models (LMMs) such as LLaVA are typically trained with an autoregressive language modeling objective, providing only indirect supervision to visual tokens. This often yields weak internal visual representations and brittle behavior under distribution shift. Inspired by recent progress on latent denoising for learning high-quality visual tokenizers, we show that the same principle provides an effective form of visual supervision for improving internal visual feature alignment and multimodal understanding in LMMs. We propose a latent denoising framework that corrupts projected visual tokens using a saliency-aware mixture of masking and Gaussian noising. The LMM is trained to denoise these corrupted tokens by recovering clean teacher patch features from hidden states at a selected intermediate LLM layer using a decoder. To prevent representation collapse, our framework also preserves the teacher's intra-image similarity structure and applies intra-image contrastive patch distillation. During inference, corruption and auxiliary heads are disabled, introducing no additional inference-time overhead. Across a broad suite of standard multimodal benchmarks, our method consistently improves visual understanding and reasoning over strong baselines, and yields clear gains on compositional robustness benchmarks (e.g., NaturalBench). Moreover, under ImageNet-C-style non-adversarial common corruptions applied to benchmark images, our method maintains higher accuracy and exhibits reduced degradation at both moderate and severe corruption levels. Our code is available at https://github.com/dhruvashp/latent-denoising-for-lmms.

We introduce MMTR-Bench, a benchmark designed to evaluate the intrinsic ability of Multimodal Large Language Models (MLLMs) to reconstruct masked text directly from visual context. Unlike conventional question-answering tasks, MMTR-Bench eliminates explicit prompts, requiring models to recover masked text from single- or multi-page inputs across real-world domains such as documents and webpages. This design isolates the reconstruction task from instruction-following abilities, enabling a direct assessment of a model's layout understanding, visual grounding, and knowledge integration. MMTR-Bench comprises 2,771 test samples spanning multiple languages and varying target lengths. To account for this diversity, we propose a level-aware evaluation protocol. Experiments on representative MLLMs show that the benchmark poses a significant challenge, especially for sentence- and paragraph-level reconstruction. The homepage is available at https://mmtr-bench-dataset.github.io/MMTR-Bench/.

We present a novel framework for automatically evaluating building conditions nationwide in the United States by leveraging large language models (LLMs) and Google Street View (GSV) imagery. By fine-tuning Gemma 3 27B on a modest human-labeled dataset, our approach achieves strong alignment with human mean opinion scores (MOS), outperforming even individual raters on SRCC and PLCC relative to the MOS benchmark. To enhance efficiency, we apply knowledge distillation, transferring the capabilities of Gemma 3 27B to a smaller Gemma 3 4B model that achieves comparable performance with a 3x speedup. Further, we distill the knowledge into a CNN-based model (EfficientNetV2-M) and a transformer (SwinV2-B), delivering close performance while achieving a 30x speed gain. Furthermore, we investigate LLMs' capabilities for assessing an extensive list of built environment and housing attributes through a human-AI alignment study and develop a visualization dashboard that integrates LLM assessment outcomes for downstream analysis by homeowners. Our framework offers a flexible and efficient solution for large-scale building condition assessment, enabling high accuracy with minimal human labeling effort.

Multi-spectral imagery is a valuable input signal for Remote Sensing applications, such as land-use and land-cover classification and environmental monitoring. However, generalist Large Multi-modal Models (LMMs) are typically trained on RGB images, limiting their applicability to the RGB domain. At the same time, training multi-spectral multi-modal models is expensive and produces uniquely specialized models. To address this, we propose a novel training-free approach that introduces multi-spectral data within the inference pipeline of standard RGB-only LMMs, allowing large gains in performance. Our approach leverages the LMMs' understanding of the visual space by adapting non-RGB inputs to that space and injecting domain-specific information and Chain-of-Thought reasoning as instructions. We demonstrate this with the Gemini 2.5 model and observe strong Zero-Shot performance gains on popular Remote Sensing benchmarks. These results highlight the potential for geospatial professionals to leverage powerful generalist models for specialized sensor inputs, benefiting from rich reasoning capabilities grounded in specialized data.

Multimodal Large Language Models (MLLMs) have shown promising capabilities in generating Scalable Vector Graphics (SVG) via direct code synthesis. However, existing paradigms typically adopt an open-loop "blind drawing" approach, where models generate symbolic code sequences without perceiving intermediate visual outcomes. This methodology severely underutilizes the powerful visual priors embedded in MLLMs vision encoders, treating SVG generation as a disjointed textual sequence modeling task rather than an integrated visuo-spatial one. Consequently, models struggle to reason about partial canvas states and implicit occlusion relationships, which are visually explicit but textually ambiguous. To bridge this gap, we propose Render-in-the-Loop, a novel generation paradigm that reformulates SVG synthesis as a step-wise, visual-context-aware process. By rendering intermediate code states into a cumulative canvas, the model explicitly observes the evolving visual context at each step, leveraging on-the-fly feedback to guide subsequent generation. However, we demonstrate that applying this visual loop naively to off-the-shelf models is suboptimal due to their inability to leverage incremental visual-code mappings. To address this, we first utilize fine-grained path decomposition to construct dense multi-step visual trajectories, and then introduce a Visual Self-Feedback (VSF) training strategy to condition the next primitive generation on intermediate visual states. Furthermore, a Render-and-Verify (RaV) inference mechanism is proposed to effectively filter degenerate and redundant primitives. Our framework, instantiated on a multimodal foundation model, outperforms strong open-weight baselines on the standard MMSVGBench. This result highlights the remarkable data efficiency and generalization capability of our Render-in-the-Loop paradigm for both Text-to-SVG and Image-to-SVG tasks.

Reinforcement learning (RL) with verifiable rewards (RLVR) has demonstrated the great potential of enhancing the reasoning abilities in multimodal large language models (MLLMs). However, the reliance on language-centric priors and expensive manual annotations prevents MLLMs' intrinsic visual understanding and scalable reward designs. In this work, we introduce SSL-R1, a generic self-supervised RL framework that derives verifiable rewards directly from images. To this end, we revisit self-supervised learning (SSL) in visual domains and reformulate widely-used SSL tasks into a set of verifiable visual puzzles for RL post-training, requiring neither human nor external model supervision. Training MLLMs on these tasks substantially improves their performance on multimodal understanding and reasoning benchmarks, highlighting the potential of leveraging vision-centric self-supervised tasks for MLLM post-training. We think this work will provide useful experience in devising effective self-supervised verifiable rewards to enable RL at scale. Project page: https://github.com/Jiahao000/SSL-R1.

Accurate extraction of structured information from Safety Data Sheets (SDS) remains challenging in industrial safety due to heterogeneous document formats and the limitations of traditional rule-based methods. This study benchmarks state-of-the-art Large Language Models (LLMs) for automated SDS data extraction, comparing text-based and multimodal processing pipelines. We systematically evaluate four models: Gemini 1.5 Pro, GPT-4o, Claude 3.7 Sonnet, and Llama 3.1-70B, across three prompting strategies: zero-shot, few-shot, and chain-of-thought. The evaluation framework assessed accuracy, latency, and cost across more than 50,000 extracted data fields. Results show that text-based extraction consistently outperforms multimodal processing across all metrics. Gemini 1.5 Pro combined with a Chain-of-Thought prompt achieved the highest accuracy (84%), outperforming GPT-4o (81%) and Claude 3.7 Sonnet (79%). However, no model surpassed the 90% accuracy threshold commonly required for reliable real-world deployment. These findings indicate that general-purpose LLMs are not yet robust enough for unsupervised industrial use, though performance suggests strong potential with task-specific fine-tuning. Future research should focus on domain-adapted training, model calibration, and the integration of Human-in-the-Loop verification to ensure safety-critical reliability.

Chain-of-Thought (CoT) reasoning significantly elevates the complex problem-solving capabilities of multimodal large language models (MLLMs). However, adapting CoT to vision typically discretizes signals to fit LLM inputs, causing early semantic collapse and discarding fine-grained details. While external tools can mitigate this, they introduce a rigid bottleneck, confining reasoning to predefined operations. Although recent latent reasoning paradigms internalize visual states to overcome these limitations, optimizing the resulting hybrid discrete-continuous action space remains challenging. In this work, we propose HyLaR (Hybrid Latent Reasoning), a framework that seamlessly interleaves discrete text generation with continuous visual latent representations. Specifically, following an initial cold-start supervised fine-tuning (SFT), we introduce DePO (Decoupled Policy Optimization) to enable effective reinforcement learning within this hybrid space. DePO decomposes the policy gradient objective, applying independent trust-region constraints to the textual and latent components, alongside an exact closed-form von Mises-Fisher (vMF) KL regularizer. Extensive experiments demonstrate that HyLaR outperforms standard MLLMs and state-of-the-art latent reasoning approaches across fine-grained perception and general multimodal understanding benchmarks. Code is available at https://github.com/EthenCheng/HyLaR.

Audio carries richer information than text, including emotion, speaker traits, and environmental context, while also enabling lower-latency processing compared to speech-to-text pipelines. However, recent multimodal information retrieval research has predominantly focused on images, largely overlooking audio, especially in the setting of interleaved audio-text contextual retrieval. In this work, we introduce the Audio-Text Interleaved contextual Retrieval (ATIR) task, where queries can alternate between audio and text modalities. We construct an ATIR benchmark by integrating several Automatic Speech Recognition (ASR), QA, and retrieval datasets, ultimately unifying four types of contextual retrieval tasks. This benchmark substantially addresses the limitations of existing audio retrieval datasets in semantic retrieval. To study this task, we evaluate several off-the-shelf retrievers and train our ATIR model based on a Multimodal Large Language Model (MLLM). We further introduce a novel token compression mechanism that is orthogonal to existing compression methods, thereby alleviating the issue of excessive audio tokens in MLLM-based ATIR models. Experimental results demonstrate that our ATIR model achieves substantial improvements over strong baselines.

Grounded Multimodal Named Entity Recognition (GMNER) aims to extract named entities and localize their visual regions within image-text pairs, serving as a pivotal capability for various downstream applications. In open-world social media platforms, GMNER remains challenging due to the prevalence of long-tailed, rapidly evolving, and unseen entities. To tackle this, existing approaches typically rely on either external knowledge exploration through heuristic retrieval or internal knowledge exploitation via iterative refinement in Multimodal Large Language Models (MLLMs). However, heuristic retrieval often introduces noisy or conflicting evidence that degrades precision on known entities, while solely internal exploitation is constrained by the knowledge boundaries of MLLMs and prone to hallucinations. To address this, we propose SAKE, an end-to-end agentic framework that harmonizes internal knowledge exploitation and external knowledge exploration via self-aware reasoning and adaptive search tool invocation. We implement this via a two-stage training paradigm. First, we propose Difficulty-aware Search Tag Generation, which quantifies the model's entity-level uncertainty through multiple forward samplings to produce explicit knowledge-gap signals. Based on these signals, we construct SAKE-SeCoT, a high-quality Chain-of-Thought dataset that equips the model with basic self-awareness and tool-use capabilities through supervised fine-tuning. Second, we employ agentic reinforcement learning with a hybrid reward function that penalizes unnecessary retrieval, enabling the model to evolve from rigid search imitation to genuine self-aware decision-making about when retrieval is truly necessary. Extensive experiments on two widely used social media benchmarks demonstrate SAKE's effectiveness.

Multimodal representation is crucial for E-commerce tasks such as identical product retrieval. Large representation models (e.g., VLM2Vec) demonstrate strong multimodal understanding capabilities, yet they struggle with fine-grained semantic comprehension, which is essential for distinguishing highly similar items. To address this, we propose Attribute-Enhanced Fine-Grained Multi-Modal Representation Learning (AFMRL), which defines product fine-grained understanding as an attribute generation task. It leverages the generative power of Multimodal Large Language Models (MLLMs) to extract key attributes from product images and text, and enhances representation learning through a two-stage training framework: 1) Attribute-Guided Contrastive Learning (AGCL), where the key attributes generated by the MLLM are used in the image-text contrastive learning training process to identify hard samples and filter out noisy false negatives. 2) Retrieval-aware Attribute Reinforcement (RAR), where the improved retrieval performance of the representation model post-attribute integration serves as a reward signal to enhance MLLM's attribute generation during multimodal fine-tuning. Extensive experiments on large-scale E-commerce datasets demonstrate that our method achieves state-of-the-art performance on multiple downstream retrieval tasks, validating the effectiveness of harnessing generative models to advance fine-grained representation learning.

Multimodal Large Language Models (MLLMs) effectively integrate text and audio to interpret context in complex interactive dialogues. However, the internal mechanisms by which heterogeneous modalities influence model behavior remain opaque. While Shapley Values (SV) provide a robust, model-agnostic framework for local explainability in text-based NLP, their extension to multimodal data is hindered by cross-channel dependencies, intricate dialogue structures, and the prohibitive computational complexity of dense audio representations. In this work, we formalize a multimodal extension of the Shapley Value framework, treating discrete text tokens and aligned audio segments as cooperative features. To ensure computational feasibility, we deploy a suite of efficient estimation strategies: exact SV computation for low-dimensional inputs and sampling-based approximations - including Monte Carlo permutations and stratified sampling with Neyman-optimal allocation - to minimize variance under constrained computational budgets. To resolve the granularity mismatch between modalities, we propose Spectrogram-Guided Phonetic Alignment (SGPA), a novel preprocessing method that maps high-frequency audio streams to interpretable, word-aligned segments. Our contribution is twofold: first, we provide an open-source, model-agnostic Python package and a companion GUI for the computation and interactive visualization of multimodal attributions. Second, we evaluate our framework using curated subsets of the VoiceBench and Infinity Instruct datasets across diverse multilingual scenarios. Our experimental results reveal that input modality is a primary driver of attribution volatility and demonstrate that standard syntactic importance proxies often fail to predict model attention in multimodal, cross-lingual contexts.

We introduce mllm-shap, an open-source Python framework designed to extend Shapley Value (SV) explainability from text-only Large Language Models to Multimodal LLMs (MLLMs) processing joint text and audio inputs. While text-based attribution is well-studied, mllm-shap addresses three critical challenges unique to the multimodal regime: (1) Modality-aware coalition masking, which manages the interleaved processing of discrete text tokens and dense audio encoder frames. (2) Multi-turn conversation tracking, utilizing per-token metadata to maintain role and modality context. (3) Phonetic alignment-based token grouping, a novel technique that reduces the coalition space by 10x to 50x, rendering SV estimation computationally feasible for long-form audio. The platform implements five SV estimation strategies, including a Complementary Contributions (CC) estimator with Neyman-optimal allocation that demonstrates superior convergence over standard Monte Carlo baselines. mllm-shap is provided as a pip-installable package featuring an interactive web-based GUI for granular attribution visualization. To our knowledge, this is the first publicly available framework providing a complete, reproducible pipeline for SV-based explainability in text-audio MLLMs.

Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the feasibility of backdoors in MLLMs via fine-tuning data poisoning to manipulate inference, the underlying mechanisms of backdoor attacks remain opaque, complicating the understanding and mitigation. To bridge this gap, we propose ProjLens, an interpretability framework designed to demystify MLLMs backdoors. We first establish that normal downstream task alignment--even when restricted to projector fine--tuning--introduces vulnerability to backdoor injection, whose activation mechanism is different from that observed in text-only LLMs. Through extensive experiments across four backdoor variants, we uncover:(1) Low-Rank Structure: Backdoor injection updates appear overall full-rank and lack dedicated ``trigger neurons'', but the backdoor-critical parameters are encoded within a low-rank subspace of the projector;(2) Activation Mechanism: Both clean and poisoned embedding undergoes a semantic shift toward a shared direction aligned with the backdoor target, but the shifting magnitude scales linearly with the input norm, resulting in the distinct backdoor activation on poisoned samples. Our code is available at: https://anonymous.4open.science/r/ProjLens-8FD7

Multimodal large language models (MLLMs) have achieved impressive performance on visual perception and reasoning tasks with RGB imagery, yet they remain fragile under common degradations, such as fog, blur, or low-light conditions. Infrared (IR) imaging, a well-established complement to RGB, offers inherent robustness in these conditions, but its integration into MLLMs remains underexplored. To bridge this gap, we propose DUALVISION, a lightweight fusion module that efficiently incorporates IR-RGB information into MLLMs via patch-level localized cross-attention. To support training and evaluation and to facilitate future research, we also introduce DV-204K, a dataset of ~25K publicly available aligned IR-RGB image pairs with 204K modality-specific QA annotations, and DV-500, a benchmark of 500 IR-RGB image pairs with 500 QA pairs designed for evaluating cross-modal reasoning. Leveraging these datasets, we benchmark both open- and closed-source MLLMs and demonstrate that DUALVISION delivers strong empirical performance under a wide range of visual degradations. Our code and dataset are available at https://abrarmajeedi.github.io/dualvision.

Purpose: Automated C-arm positioning ensures timely treatment in patients requiring emergent interventions. When a conventional Deep Learning (DL) approach for C-arm control fails, clinicians must revert to manual operation, resulting in additional delays. Consequently, an agentic C-arm control framework based on multimodal large language models (MLLMs) is highly desirable, as it can incorporate clinician feedback and use reasoning to make adjustments toward more accurate positioning. Skeletal landmark localization is essential for C-arm control, and we investigate adapting MLLMs for autonomous landmark localization. Methods: We used an annotated synthetic X-ray dataset and a real X-ray dataset. Each X-ray in both datasets is paired with several skeletal landmarks. We fine-tuned two MLLMs and tasked them with retrieving the closest landmarks from each X-ray. Quantitative evaluations of landmark localization were performed and compared against a leading DL approach. We further conducted qualitative experiments demonstrating: (1) how an MLLM can correct an initially incorrect prediction through reasoning, and (2) how the MLLM can sequentially navigate the C-arm toward a target location. Results: On both datasets, fine-tuned MLLMs demonstrate competitive performance across all localization tasks when compared with the DL approach. In the qualitative experiments, the MLLMs provide evidence of reasoning and spatial awareness. Conclusion: This study shows that fine-tuned MLLMs achieve accurate skeletal landmark localization and hold promise for agentic autonomous C-arm control. Our code is available athttps://github.com/marszzibros/C-arm-localization-LLMs.git

Change visual question answering (Change VQA) addresses the problem of answering natural-language questions about semantic changes between bi-temporal remote sensing (RS) images. Although vision-language models (VLMs) have recently been studied for temporal RS image understanding, Change VQA remains underexplored in the context of modern multimodal models. In this letter, we revisit the CDVQA benchmark using recent Qwen models under a unified low-rank adaptation (LoRA) setting. We compare Qwen3-VL, which follows a structured vision-language pipeline with multi-depth visual conditioning and a full-attention decoder, with Qwen3.5, a native multimodal model that combines a single-stage alignment with a hybrid decoder backbone. Experimental results on the official CDVQA test splits show that recent VLMs improve over earlier specialized baselines. They further show that performance does not scale monotonically with model size, and that native multimodal models are more effective than structured vision-language pipelines for this task. These findings indicate that tightly integrated multimodal backbones contribute more to performance than scale or explicit multi-depth visual conditioning for language-driven semantic change reasoning in RS imagery.

Self-evolution of multimodal large language models (MLLMs) remains a critical challenge: pseudo-label-based methods suffer from progressive quality degradation as model predictions drift, while template-based methods are confined to a static set of transformations that cannot adapt in difficulty or diversity. We contend that robust, continuous self-improvement requires not only deterministic external feedback independent of the model's internal certainty, but also a mechanism to perpetually diversify the training distribution. To this end, we introduce EVE (Executable Visual transformation-based self-Evolution), a novel framework that entirely bypasses pseudo-labels by harnessing executable visual transformations continuously enriched in both variety and complexity. EVE adopts a Challenger-Solver dual-policy architecture. The Challenger maintains and progressively expands a queue of visual transformation code examples, from which it synthesizes novel Python scripts to perform dynamic visual transformations. Executing these scripts yields VQA problems with absolute, execution-verified ground-truth answers, eliminating any reliance on model-generated supervision. A multi-dimensional reward system integrating semantic diversity and dynamic difficulty calibration steers the Challenger to enrich its code example queue while posing progressively more challenging tasks, preventing mode collapse and fostering reciprocal co-evolution between the two policies. Extensive experiments demonstrate that EVE consistently surpasses existing self-evolution methods, establishing a robust and scalable paradigm for verifiable MLLM self-evolution. The code is available at https://github.com/0001Henry/EVE .

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, audio), with paired instances from a reproducible generator. We also define arithmetic load, C, as the product of the total and non-zero digit count 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-squared often > 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. Beyond measuring when models fail, we ask which procedures they are predisposed to follow. We introduce a forced-completion loss probe that scores heuristic-specific reasoning prefixes--including columnar multiplication, distributive decomposition, and rounding/compensation. Here, 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.

Multimodal Large Language Models (MLLMs) have been increasingly used as automatic evaluators-a paradigm known as MLLM-as-a-Judge. However, their reliability and vulnerabilities to biases remain underexplored. We find that many MLLM judges fail to reliably integrate key visual or textual cues, yielding unreliable evaluations when evidence is missing or mismatched, and exhibiting instability under semantically irrelevant perturbations. To address this, we systematically define Compositional Bias in MLLM-as-a-Judge systems and introduce MM-JudgeBias, a benchmark for evaluating it. MM-JudgeBias introduces controlled perturbations across Query, Image, and Response, and evaluates model behavior via two complementary metrics: Bias-Deviation (BD) for sensitivity and Bias-Conformity (BC) for stability. Our dataset of over 1,800 curated and refined multimodal samples, drawn from 29 source benchmarks, enables a fine-grained diagnosis of nine bias types across diverse tasks and domains. Experiments on 26 state-of-the-art MLLMs reveal systematic modality neglect and asymmetric evaluation tendencies, underscoring the need for more reliable judges.

Although Knowledge Editing provides an efficient mechanism for updating the knowledge of Multimodal Large Language Models (MLLMs), we find that current paradigms still suffer from an important yet remain underexplored issue : editing decoupling failure, where entity-related knowledge can be updated when the model is triggered by multimodal inputs (text--image query pairs), however, it often reverts to outdated pre-edit facts when the paired inputs are split into unimodal ones. Our in-depth empirical analysis reveals that the entity knowledge in MLLMs is not stored as a unified representation, but is instead distributed across disentangled modality-specific pathways. As a result, updates biased toward multimodal queries fail to propagate effectively to unimodal circuits. To bridge this gap, we propose DECODE, which explicitly disentangles and localizes modality-specific neuron groups for targeted knowledge. Extensive experiments demonstrate that DECODE consistently achieves effective knowledge updates under different modality triggers, thereby mitigating editing decoupling failures.

Long video understanding remains a formidable challenge for Multimodal Large Language Models (MLLMs) due to the prohibitive computational cost of processing dense frame sequences. Prevailing solutions, which select a keyframe subset, typically rely on either a single visual-centric metric (e.g., CLIP similarity) or a static fusion of heuristic scores. This one-size-fits-all'' paradigm frequently fails: visual-only metrics are ineffective for plot-driven narrative queries, while indiscriminately incorporating textual scores introduces severe modal noise'' for purely visual tasks. To break this bottleneck, we propose Q-Gate, a plug-and-play and training-free framework that treats keyframe selection as a dynamic modality routing problem. We decouple the retrieval process into three lightweight expert streams: Visual Grounding for local details, Global Matching for scene semantics, and Contextual Alignment for subtitle-driven narratives. Crucially, Q-Gate introduces a Query-Modulated Gating Mechanism that leverages the in-context reasoning of an LLM to assess the query's intent and dynamically allocate attention weights across the experts. This mechanism intelligently activates necessary modalities while ``muting'' irrelevant ones, thereby maximizing the signal-to-noise ratio. Extensive experiments on LongVideoBench and Video-MME across multiple MLLM backbones demonstrate that Q-Gate substantially outperforms state-of-the-art baselines. By effectively suppressing modality-specific noise, it provides a robust, highly interpretable solution for scalable video reasoning.

Grounded Multimodal Named Entity Recognition (GMNER) aims to jointly identify named entity mentions in text, predict their semantic types, and ground each entity to a corresponding visual region in an associated image. Existing approaches predominantly adopt pipeline-based architectures that decouple textual entity recognition and visual grounding, leading to error accumulation and suboptimal joint optimization. In this paper, we propose E2E-GMNER, a fully end-to-end generative framework that unifies entity recognition, semantic typing, visual grounding, and implicit knowledge reasoning within a single multimodal large language model. We formulate GMNER as an instruction-tuned conditional generation task and incorporate chain-of-thought reasoning to enable the model to adaptively determine when visual evidence or background knowledge is informative, reducing reliance on noisy cues. To further address the instability of generative bounding box prediction, we introduce Gaussian Risk-Aware Box Perturbation (GRBP), which replaces hard box supervision with probabilistically perturbed soft targets to improve robustness against annotation noise and discretization errors. Extensive experiments on the Twitter-GMNER and Twitter-FMNERG benchmarks demonstrate that E2E-GMNER achieves highly competitive performance compared with state of the art methods, validating the effectiveness of unified end-to-end optimization and noise-aware grounding supervision. Code is available at:https://github.com/Finch-coder/E2E-GMNER