Multimodal Large Language Models

Multimodal Large Language Models frequently suffer from inference hallucinations, partially stemming from language priors dominating visual evidence. Existing training-free mitigation methods either perturb the visual representation and deviate from the natural image distribution, or enforce intrusive manipulations that compromise the model's inherent generative fluency. We introduce a novel perspective that multimodal hallucination manifests as the hypersensitivity of visual grounding to textual phrasing during the decoding phase. Building on this insight, we propose Decoding by Perturbation (DeP), a training-free framework mitigating prior-induced hallucinations via controlled textual interventions. DeP employs a dynamic probe applying multi-level textual perturbations to elicit latent language priors. Leveraging attention variance, it enhances stable evidence regions while suppressing suspicious noise in the feature space. Furthermore, it constructs an interpretable prior drift direction using logits statistics to counteract probability biases from textual co-occurrences. Extensive experiments confirm DeP effectively reduces hallucinations and achieves superior performance across multiple benchmarks.

Spreadsheets are central to real-world applications such as enterprise reporting, auditing, and scientific data management. Despite their ubiquity, existing large language model based approaches typically treat tables as plain text, overlooking critical layout cues and visual semantics. Moreover, real-world spreadsheets are often massive in scale, exceeding the input length that LLMs can efficiently process. To address these challenges, we propose SpreadsheetAgent, a two-stage multi-agent framework for spreadsheet understanding that adopts a step-by-step reading and reasoning paradigm. Instead of loading the entire spreadsheet at once, SpreadsheetAgent incrementally interprets localized regions through multiple modalities, including code execution results, images, and LaTeX tables. The method first constructs a structural sketch and row/column summaries, and then performs task-driven reasoning over this intermediate representation in the Solving Stage. To further enhance reliability, we design a verification module that validates extracted structures via targeted inspections, reducing error propagation and ensuring trustworthy inputs for downstream reasoning. Extensive experiments on two spreadsheet datasets demonstrate the effectiveness of our approach. With GPT-OSS-120B, SpreadsheetAgent achieves 38.16% on Spreadsheet Bench, outperforming the ChatGPT Agent baseline (35.27%) by 2.89 absolute points. These results highlight the potential of SpreadsheetAgent to advance robust and scalable spreadsheet understanding in real-world applications. Code is available at https://github.com/renhouxing/SpreadsheetAgent.git.

Large Multimodal Models (LMMs) have achieved remarkable progress in general-purpose vision--language understanding, yet they remain limited in tasks requiring precise object-level grounding, fine-grained spatial reasoning, and controllable visual manipulation. In particular, existing systems often struggle to identify the correct instance, preserve object identity across interactions, and localize or modify designated regions with high precision. Object-centric vision provides a principled framework for addressing these challenges by promoting explicit representations and operations over visual entities, thereby extending multimodal systems from global scene understanding to object-level understanding, segmentation, editing, and generation. This paper presents a comprehensive review of recent advances at the convergence of LMMs and object-centric vision. We organize the literature into four major themes: object-centric visual understanding, object-centric referring segmentation, object-centric visual editing, and object-centric visual generation. We further summarize the key modeling paradigms, learning strategies, and evaluation protocols that support these capabilities. Finally, we discuss open challenges and future directions, including robust instance permanence, fine-grained spatial control, consistent multi-step interaction, unified cross-task modeling, and reliable benchmarking under distribution shift. We hope this paper provides a structured perspective on the development of scalable, precise, and trustworthy object-centric multimodal systems.

Multimodal Large Language Models (MLLMs) have recently demonstrated remarkable capabilities in cross-modal understanding and generation. However, the rapid growth of visual token sequences--especially in long-video and streaming scenarios--poses a major challenge to their scalability and real-world deployment. Thus, we introduce POINTS-Long, a native dual-mode MLLM featuring dynamic visual token scaling inspired by the human visual system. The model supports two complementary perception modes: focus mode and standby mode, enabling users to dynamically trade off efficiency and accuracy during inference. On fine-grained visual tasks, the focus mode retains the optimal performance, while on long-form general visual understanding, the standby mode retains 97.7-99.7% of the original accuracy using only 1/40-1/10th of the visual tokens. Moreover, POINTS-Long natively supports streaming visual understanding via a dynamically detachable KV-cache design, allowing efficient maintenance of ultra-long visual memory. Our work provides new insights into the design of future MLLMs and lays the foundation for adaptive and efficient long-form visual understanding.

Multimodal Large Language Models (MLLMs) have achieved remarkable progress but incur substantial computational overhead and energy consumption during inference, limiting deployment in resource-constrained environments. Spiking Neural Networks (SNNs), with their sparse event-driven computation, offer inherent energy efficiency advantages on neuromorphic hardware, yet extending them to MLLMs faces two key challenges: heterogeneous modalities make uniform spike encoding insufficient, and high-resolution image inputs amplify timestep unfolding overhead. We propose SpikeMLLM, the first spike-based framework for MLLMs, which unifies existing ANN quantization methods in the spiking representation space and incorporates Modality-Specific Temporal Scales (MSTS) guided by Modality Evolution Discrepancy (MED) and Temporally Compressed LIF (TC-LIF) for timestep compression from T=L-1 to T=log2(L)-1. Experiments on four representative MLLMs across diverse multimodal benchmarks show that SpikeMLLM maintains near-lossless performance under aggressive timestep compression (Tv/Tt=3/4), with average gaps of only 0.72% and 1.19% relative to the FP16 baseline on InternVL2-8B and Qwen2VL-72B. We further develop a dedicated RTL accelerator tailored to the spike-driven datapath, observing 9.06x higher throughput and 25.8x better power efficiency relative to an FP16 GPU baseline under a deployment-oriented co-design setting, suggesting the promise of algorithm-hardware co-design for efficient multimodal intelligence.

Multimodal Large Language Models (MLLMs) have achieved remarkable progress but continue to struggle with geometric reasoning, primarily due to the perception bottleneck regarding fine-grained visual elements. While formal languages have aided plane geometry understanding, solid geometry which requires spatial understanding remains largely unexplored. In this paper, we address this challenge by designing a unified formal language that integrates plane and solid geometry, comprehensively covering geometric structures and semantic relations. We construct GDP-29K, a large-scale dataset comprising 20k plane and 9k solid geometry samples collected from diverse real-world sources, each paired with its ground-truth formal description. To ensure syntactic correctness and geometric consistency, we propose a training paradigm that combines Supervised Fine-Tuning with Reinforcement Learning via Verifiable Rewards. Experiments show that our approach achieves state-of-the-art parsing performance. Furthermore, we demonstrate that our parsed formal descriptions serve as a critical cognitive scaffold, significantly boosting MLLMs' capabilities for downstream geometry reasoning tasks. Our data and code are available at Geoparsing.

Reinforcement learning (RL) post-training has proven effective at unlocking reasoning, self-reflection, and tool-use capabilities in large language models. As models extend to omni-modal inputs and agentic multi-turn workflows, RL training systems face three interdependent challenges: heterogeneous data flows, operational robustness at scale, and the staleness -- throughput tradeoff. We present Relax (Reinforcement Engine Leveraging Agentic X-modality), an open-source RL training engine that addresses these challenges through three co-designed architectural layers. First, an omni-native architecture builds multimodal support into the full stack -- from data preprocessing and modality-aware parallelism to inference generation -- rather than retrofitting it onto a text-centric pipeline. Second, each RL role runs as an independent, fault-isolated service that can be scaled, recovered, and upgraded without global coordination. Third, service-level decoupling enables asynchronous training via the TransferQueue data bus, where a single staleness parameter smoothly interpolates among on-policy, near-on-policy, and fully asynchronous execution. Relax achieves a 1.20$\times$ end-to-end speedup over veRL on Qwen3-4B on-policy training. Its fully async mode delivers a 1.76$\times$ speedup over colocate on Qwen3-4B and a 2.00$\times$ speedup on Qwen3-Omni-30B, while all modes converge to the same reward level. Relax supports R3 (Rollout Routing Replay)~\cite{ma2025r3} for MoE models with only 1.9% overhead, compared to 32% degradation in veRL under the same configuration. It further demonstrates stable omni-modal RL convergence on Qwen3-Omni across image, text, and audio, sustaining over 2{,}000 steps on video without degradation. Relax is available at https://github.com/rednote-ai/Relax.

In recent years, rapid advances in Multimodal Large Language Models (MLLMs) have increasingly stimulated research on ancient Chinese scripts. As the evolution of written characters constitutes a fundamental pathway for understanding cultural transformation and historical continuity, how MLLMs can be systematically leveraged to support and advance text evolution analysis remains an open and largely underexplored problem. To bridge this gap, we construct a comprehensive benchmark comprising 11 tasks and over 130,000 instances, specifically designed to evaluate the capability of MLLMs in analyzing the evolution of ancient Chinese scripts. We conduct extensive evaluations across multiple widely used MLLMs and observe that, while existing models demonstrate a limited ability in glyph-level comparison, their performance on core tasks-such as character recognition and evolutionary reasoning-remains substantially constrained. Motivated by these findings, we propose a glyph-driven fine-tuning framework (GEVO) that explicitly encourages models to capture evolutionary consistency in glyph transformations and enhances their understanding of text evolution. Experimental results show that even models at the 2B scale achieve consistent and comprehensive performance improvements across all evaluated tasks. To facilitate future research, we publicly release both the benchmark and the trained models\footnote{https://github.com/songruiecho/GEVO}.

Recent progress in multimodal large language models (MLLMs) is reshaping video translation from a cascaded pipeline of automatic speech recognition, machine translation, text-to-speech, and lip synchronization into a unified multimodal reasoning and generation problem. High-quality video translation requires not only semantic fidelity, but also temporal alignment, speaker consistency, and emotional expressiveness across visual, acoustic, and linguistic streams. This survey provides a focused review of MLLM-enabled video translation through a role-oriented taxonomy. We organize MLLM-enabled and MLLM-relevant studies into three functional roles: Semantic Reasoner, which grounds translation in video understanding, temporal reasoning, and multimodal fusion; Expressive Performer, which supports controllable and context-aware speech generation; and Visual Synthesizer, which enables lip synchronization and visually coherent speaker rendering. We further summarize representative datasets, benchmarks, and metrics for each role, and discuss how current evaluation protocols fall short of end-to-end video translation requirements. Finally, we identify open challenges in long-form video understanding, temporal modeling, multimodal alignment, multilingual robustness, and responsible deployment, outlining future directions for natural and trustworthy cross-lingual video communication.

Object-level spatial-temporal understanding is essential for video question answering, yet existing multimodal large language models (MLLMs) encode frames holistically and lack explicit mechanisms for fine-grained object grounding. Recent work addresses this by serializing bounding box coordinates as text tokens, but this text-coordinate paradigm suffers from a fundamental modality mismatch: object information is inherently visual, yet encoding it as text incurs a high token cost that forces aggressive temporal downsampling. We propose BoxTuning, which resolves this mismatch by injecting object spatial-temporal information directly into the visual modality. Colored bounding boxes and trajectory trails are rendered onto video frames as visual prompts, with only a concise color-to-object legend retained as text. This reduces the token cost significantly, achieving 87-93% text token reduction in practice. It also preserves full temporal resolution, where the trajectory trails further encode inter-frame motion direction and speed within each keyframe, recovering fine-grained dynamics that text-coordinate methods are forced to discard. Experimental results on five video QA benchmarks (CLEVRER, Perception Test, STAR, NExT-QA, IntentQA) show that BoxTuning surpasses text-coordinate baselines on spatially oriented tasks and nearly eliminates the accuracy degradation observed on reasoning-centric tasks, establishing visual prompting as a more natural and efficient paradigm for conveying object information to video MLLMs.

Current multimodal large language models (MLLMs) have demonstrated remarkable capabilities in short-form video understanding, yet translating long-form cinematic videos into detailed, temporally grounded scripts remains a significant challenge. This paper introduces the novel video-to-script (V2S) task, aiming to generate hierarchical, scene-by-scene scripts encompassing character actions, dialogues, expressions, and audio cues. To facilitate this, we construct a first-of-its-kind human-annotated benchmark and propose a temporally-aware hierarchical evaluation framework. Furthermore, we present OmniScript, an 8B-parameter omni-modal (audio-visual) language model tailored for long-form narrative comprehension. OmniScript is trained via a progressive pipeline that leverages chain-of-thought supervised fine-tuning for plot and character reasoning, followed by reinforcement learning using temporally segmented rewards. Extensive experiments demonstrate that despite its parameter efficiency, OmniScript significantly outperforms larger open-source models and achieves performance comparable to state-of-the-art proprietary models, including Gemini 3-Pro, in both temporal localization and multi-field semantic accuracy.

Adapting decoder-only multimodal large language models (MLLMs) for unified multimodal retrieval faces two structural gaps. First, existing methods rely on implicit pooling, which overloads the hidden state of a standard vocabulary token (e.g., <EOS>) as the sequence-level representation, a mechanism never designed for information aggregation. Second, contrastive fine-tuning specifies what the embedding should match but provides no token-level guidance on how information should be compressed into it. We address both gaps with two complementary components. Architecturally, we introduce Bottleneck Tokens (BToks), a small set of learnable tokens that serve as a fixed-capacity explicit pooling mechanism. For training, we propose Generative Information Condensation: a next-token prediction objective coupled with a Condensation Mask that severs the direct attention path from target tokens to query tokens. All predictive signals are thereby forced through the BToks, converting the generative loss into dense, token-level supervision for semantic compression. At inference time, only the input and BToks are processed in a single forward pass with negligible overhead over conventional last-token pooling. On MMEB-V2 (78 datasets, 3 modalities, 9 meta-tasks), our approach achieves state-of-the-art among 2B-scale methods under comparable data conditions, attaining an Overall score of 59.0 (+3.6 over VLM2Vec-V2) with substantial gains on semantically demanding tasks (e.g., +12.6 on Video-QA).

In the progress of industrial anomaly detection, general anomaly detection (GAD) is an emerging trend and also the ultimate goal. Unlike the conventional single- and multi-class AD, general AD aims to train a general AD model that can directly detect anomalies in diverse novel classes without any retraining or fine-tuning on the target data. Recently, Multimodal Large Language Models (MLLMs) have shown great promise in achieving general anomaly detection due to their revolutionary visual understanding and language reasoning capabilities. However, MLLM's general AD ability remains underexplored due to: (1) MLLMs are pretrained on amounts of data sourced from the Web, these data still have significant gaps with the data in AD scenarios. Moreover, the image-text pairs during pretraining are also not specifically for AD tasks. (2) The current mainstream AD datasets are image-based and not yet suitable for post-training MLLMs. To facilitate MLLM-based general AD research, we present MMR-AD, which is a comprehensive benchmark for both training and evaluating MLLM-based AD models. With MMR-AD, we reveal that the AD performance of current SOTA generalist MLLMs still falls far behind the industrial requirements. Based on MMR-AD, we also propose a baseline model, Anomaly-R1, which is a reasoning-based AD model that learns from the CoT data in MMR-AD and is further enhanced by reinforcement learning. Extensive experiments show that our Anomaly-R1 achieves remarkable improvements over generalist MLLMs in both anomaly detection and localization.

Tables contain rich structured information, yet when stored as images their contents remain "locked" within pixels. Converting table images into LaTeX code enables faithful digitization and reuse, but current multimodal large language models (MLLMs) often fail to preserve structural, style, or content fidelity. Conventional post-training with reinforcement learning (RL) typically relies on a single aggregated reward, leading to reward ambiguity that conflates multiple behavioral aspects and hinders effective optimization. We propose Component-Specific Policy Optimization (CSPO), an RL framework that disentangles optimization across LaTeX tables components-structure, style, and content. In particular, CSPO assigns component-specific rewards and backpropagates each signal only through the tokens relevant to its component, alleviating reward ambiguity and enabling targeted component-wise optimization. To comprehensively assess performance, we introduce a set of hierarchical evaluation metrics. Extensive experiments demonstrate the effectiveness of CSPO, underscoring the importance of component-specific optimization for reliable structured generation. Our code is available at https://github.com/microsoft/CSPO.

Multimodal large language models (MLLMs) have advanced clinical tasks for common conditions, but their performance on rare diseases remains largely untested. In rare-disease scenarios, clinicians often lack prior clinical knowledge, forcing them to rely strictly on case-level evidence for clinical judgments. Existing benchmarks predominantly evaluate common-condition, single-image settings, leaving multimodal and multi-image evidence integration under rare-disease data scarcity systematically unevaluated. We introduce MMRareBench, to our knowledge the first rare-disease benchmark jointly evaluating multimodal and multi-image clinical capability across four workflow-aligned tracks: diagnosis, treatment planning, cross-image evidence alignment, and examination suggestion. The benchmark comprises 1,756 question-answer pairs with 7,958 associated medical images curated from PMC case reports, with Orphanet-anchored ontology alignment, track-specific leakage control, evidence-grounded annotations, and a two-level evaluation protocol. A systematic evaluation of 23 MLLMs reveals fragmented capability profiles and universally low treatment-planning performance, with medical-domain models trailing general-purpose MLLMs substantially on multi-image tracks despite competitive diagnostic scores. These patterns are consistent with a capacity dilution effect: medical fine-tuning can narrow the diagnostic gap but may erode the compositional multi-image capability that rare-disease evidence integration demands.

Natural-language Guided Cross-view Geo-localization (NGCG) aims to retrieve geo-tagged satellite imagery using textual descriptions of ground scenes. While recent NGCG methods commonly rely on CLIP-style dual-encoder architectures, they often suffer from weak cross-modal generalization and require complex architectural designs. In contrast, Multimodal Large Language Models (MLLMs) offer powerful semantic reasoning capabilities but are not directly optimized for retrieval tasks. In this work, we present a simple yet effective framework to adapt MLLMs for NGCG via parameter-efficient finetuning. Our approach optimizes latent representations within the MLLM while preserving its pretrained multimodal knowledge, enabling strong cross-modal alignment without redesigning model architectures. Through systematic analysis of diverse variables, from model backbone to feature aggregation, we provide practical and generalizable insights for leveraging MLLMs in NGCG. Our method achieves SOTA on GeoText-1652 with a 12.2% improvement in Text-to-Image Recall@1 and secures top performance in 5 out of 12 subtasks on CVG-Text, all while surpassing baselines with far fewer trainable parameters. These results position MLLMs as a robust foundation for semantic cross-view retrieval and pave the way for MLLM-based NGCG to be adopted as a scalable, powerful alternative to traditional dual-encoder designs. Project page and code are available at https://yuqichen888.github.io/NGCG-MLLMs-web/.

We present the progress of the GPT family from GPT-3 through GPT-3.5, GPT-4, GPT-4 Turbo, GPT-4o, GPT-4.1, and the GPT-5 family. Our work is comparative rather than merely historical. We investigates how the family evolved in technical framing, user interaction, modality, deployment architecture, and governance viewpoint. The work focuses on five recurring themes: technical progression, capability changes, deployment shifts, persistent limitations, and downstream consequences. In term of research design, we consider official technical reports, system cards, API and model documentation, product announcements, release notes, and peer-reviewed secondary studies. A primary assertion is that later GPT generations should not be interpreted only as larger or more accurate language models. Instead, the family evolves from a scaled few-shot text predictor into a set of aligned, multimodal, tool-oriented, long-context, and increasingly workflow-integrated systems. This development complicates simple model-to-model comparison because product routing, tool access, safety tuning, and interface design become part of the effective system. Across generations, several limitations remain unchanged: hallucination, prompt sensitivity, benchmark fragility, uneven behavior across domains and populations, and incomplete public transparency about architecture and training. However, the family has evolved software development, educational practice, information work, interface design, and discussions of frontier-model governance. We infer that the transition from GPT-3 to GPT-5 is best understood not only as an improvement in model capability, but also as a broader reformulation of what a deployable AI system is, how it is evaluated, and where responsibility should be located when such systems are used at scale.

Composed Image Retrieval (CIR) retrieves target images using a reference image paired with modification text. Despite rapid advances, all existing methods and datasets operate at the image level -- a single reference image plus modification text in, a single target image out -- while real e-commerce users reason about products shown from multiple viewpoints. We term this mismatch View Incompleteness and formally define a new Multi-View CIR task that generalizes standard CIR from image-level to product-level retrieval. To support this task, we construct FashionMV, the first large-scale multi-view fashion dataset for product-level CIR, comprising 127K products, 472K multi-view images, and over 220K CIR triplets, built through a fully automated pipeline leveraging large multimodal models. We further propose ProCIR (Product-level Composed Image Retrieval), a modeling framework built upon a multimodal large language model that employs three complementary mechanisms -- two-stage dialogue, caption-based alignment, and chain-of-thought guidance -- together with an optional supervised fine-tuning (SFT) stage that injects structured product knowledge prior to contrastive training. Systematic ablation across 16 configurations on three fashion benchmarks reveals that: (1) alignment is the single most critical mechanism; (2) the two-stage dialogue architecture is a prerequisite for effective alignment; and (3) SFT and chain-of-thought serve as partially redundant knowledge injection paths. Our best 0.8B-parameter model outperforms all baselines, including general-purpose embedding models 10x its size. The dataset, model, and code are publicly available at https://github.com/yuandaxia2001/FashionMV.

3D medical image analysis is of great importance in disease diagnosis and treatment. Recently, multimodal large language models (MLLMs) have exhibited robust perceptual capacity, strong cross-modal alignment, and promising generalizability. Therefore, they have great potential to improve the performance of medical report generation (MRG) and medical visual question answering (MVQA), which serve as two important tasks in clinical scenarios. However, due to the scarcity of 3D medical images, existing 3D medical MLLMs suffer from insufficiently pretrained vision encoder and inability to extract customized image features for different kinds of tasks. In this paper, we propose to first transfer a 2D MLLM, which is well trained with 2D natural images, to support 3D medical volumetric inputs while reusing all of its pre-trained parameters. To enable the vision encoder to extract tailored image features for various tasks, we then design a Text-Guided Hierarchical MoE (TGH-MoE) framework, which can distinguish tasks under the guidance of the text prompt. Furthermore, we propose a two-stage training strategy to learn both task-shared and task-specific image features. As demonstrated empirically, our method outperforms existing 3D medical MLLMs in both MRG and MVQA tasks. Our code will be released once this paper is accepted.

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in Traffic Accident Detection (TAD) and Traffic Accident Understanding (TAU). However, existing studies mainly focus on describing and interpreting accident videos, leaving room for deeper causal reasoning and integration of legal knowledge. Traffic Accident Responsibility Allocation (TARA) is a more challenging task that requires multi-step reasoning grounded in traffic regulations. To address this, we introduce AITP (Artificial Intelligence Traffic Police), a multimodal large language model for responsibility reasoning and allocation. AITP enhances reasoning via a Multimodal Chain-of-Thought (MCoT) mechanism and integrates legal knowledge through Retrieval-Augmented Generation (RAG). We further present DecaTARA, a decathlon-style benchmark unifying ten interrelated traffic accident reasoning tasks with 67,941 annotated videos and 195,821 question-answer pairs. Extensive experiments show that AITP achieves state-of-the-art performance across responsibility allocation, TAD, and TAU tasks, establishing a new paradigm for reasoning-driven multimodal traffic analysis.

Multimodal Large Language Models (MLLMs) have demonstrated remarkable reasoning capabilities yet continue to suffer from hallucination, where generated text contradicts visual content. In this paper, we introduce Dual-Anchor Introspective Decoding (DaID), a novel contrastive decoding framework that dynamically calibrates each token generation by mining the model's internal perceptual discrepancies. Specifically, DaID identifies a Spotlight layer to amplify visual factual signals and a Shadow layer to suppress textual inertia. By leveraging visual attention distributions to guide this dual-anchor selection process, our method ensures precise, token-specific adaptation. Experimental results across multiple benchmarks and MLLMs demonstrate that DaID significantly mitigates hallucination while enhancing general reasoning capabilities.

Long video summarization presents significant challenges for multimodal large language models (MLLMs), particularly in maintaining temporal fidelity over extended durations and producing summaries that are both semantically and temporally grounded. We introduce LVSum, a human-annotated benchmark for evaluating long-form video summarization with fine-grained temporal alignment. LVSum comprises 72 diverse videos spanning 13 domains with an average duration of 16 minutes, each annotated with up to 10 human-generated summaries containing temporal references. We conduct a comprehensive evaluation of leading proprietary and open-source MLLMs using newly introduced LLM-based metrics for content relevance and modality coherence, alongside standard automatic metrics. Our experiments reveal three key findings: (1) transcripts contribute substantially more to summarization quality than visual frames alone, (2) a significant performance gap persists between model-generated and human-written summaries, and (3) current MLLMs exhibit systematic weaknesses in temporal grounding, instruction adherence, and cross-modal coherence. We release the dataset and code.

Multimodal Large Language Models (MLLMs) have achieved strong performance on RGB image understanding, yet their ability to use spectral evidence beyond the visible range remains largely unexplored. Hyperspectral imagery (HSI) provides dense spectral measurements that reveal material and environmental cues unavailable in RGB, but current MLLMs cannot directly ingest high-dimensional HSI. To study this gap, we introduce HM-Bench, an evidence-grounded benchmark for hyperspectral image understanding with MLLMs. HM-Bench contains 19,337 question--answer pairs from 2,178 hyperspectral samples across 13 task categories, covering general perception, spectral reasoning, and spatial--spectral reasoning. To make HSI accessible to the native image--text interfaces of existing MLLMs, we further propose VSR$^{2}, a training-free Visual--Spectral--Report Reasoning framework. VSR^{2} represents each HSI sample with three aligned views: an RGB image for visual semantics and spatial context, a PCA-based image for dominant spectral variation, and a structured report for quantitative spectral--spatial evidence. Under a controlled RGB-only versus VSR^{2} evaluation protocol, experiments on 17 representative MLLMs show that HSI information improves average accuracy from 38.26% to 40.35%, with gains varying substantially across models and task categories. These results indicate that HSI information (beyond RGB) is useful for current MLLMs, while robust hyperspectral reasoning remains an open challenge.

Multimodal Large Language Models (MLLMs) have been shown to be vulnerable to malicious queries that can elicit unsafe responses. Recent work uses prompt engineering, response classification, or finetuning to improve MLLM safety. Nevertheless, such approaches are often ineffective against evolving malicious patterns, may require rerunning the query, or demand heavy computational resources. Steering the activations of a frozen model at inference time has recently emerged as a flexible and effective solution. However, existing steering methods for MLLMs typically handle only a narrow set of safety-related concepts or struggle to adjust specific concepts without affecting others. To address these challenges, we introduce Dictionary-Aligned Concept Control (DACO), a framework that utilizes a curated concept dictionary and a Sparse Autoencoder (SAE) to provide granular control over MLLM activations. First, we curate a dictionary of 15,000 multimodal concepts by retrieving over 400,000 caption-image stimuli and summarizing their activations into concept directions. We name the dataset DACO-400K. Second, we show that the curated dictionary can be used to intervene activations via sparse coding. Third, we propose a new steering approach that uses our dictionary to initialize the training of an SAE and automatically annotate the semantics of the SAE atoms for safeguarding MLLMs. Experiments on multiple MLLMs (e.g., QwenVL, LLaVA, InternVL) across safety benchmarks (e.g., MM-SafetyBench, JailBreakV) show that DACO significantly improves MLLM safety while maintaining general-purpose capabilities.

Group Relative Policy Optimization (GRPO) has emerged as the de facto Reinforcement Learning (RL) objective driving recent advancements in Multimodal Large Language Models. However, extending this success to open-source multimodal generalist models remains heavily constrained by two primary challenges: the extreme variance in reward topologies across diverse visual tasks, and the inherent difficulty of balancing fine-grained perception with multi-step reasoning capabilities. To address these issues, we introduce Gaussian GRPO (G$^2$RPO), a novel RL training objective that replaces standard linear scaling with non-linear distributional matching. By mathematically forcing the advantage distribution of any given task to strictly converge to a standard normal distribution, $\mathcal{N}(0,1)$, G$^2$RPO theoretically ensures inter-task gradient equity, mitigates vulnerabilities to heavy-tail outliers, and offers symmetric update for positive and negative rewards. Leveraging the enhanced training stability provided by G$^2$RPO, we introduce two task-level shaping mechanisms to seamlessly balance perception and reasoning. First, response length shaping dynamically elicits extended reasoning chains for complex queries while enforce direct outputs to bolster visual grounding. Second, entropy shaping tightly bounds the model's exploration zone, effectively preventing both entropy collapse and entropy explosion. Integrating these methodologies, we present OpenVLThinkerV2, a highly robust, general-purpose multimodal model. Extensive evaluations across 18 diverse benchmarks demonstrate its superior performance over strong open-source and leading proprietary frontier models.

The rise of multimodal large language models (MLLMs) has sparked an unprecedented wave of applications in the field of medical imaging analysis. However, as one of the earliest and most fundamental tasks integrated into this paradigm, medical image classification reveals a sobering reality: state-of-the-art medical MLLMs consistently underperform compared to traditional deep learning models, despite their overwhelming advantages in pre-training data and model parameters. This paradox prompts a critical rethinking: where exactly does the performance degradation originate? In this paper, we conduct extensive experiments on 14 open-source medical MLLMs across three representative image classification datasets. Moving beyond superficial performance benchmarking, we employ feature probing to track the information flow of visual features module-by-module and layer-by-layer throughout the entire MLLM pipeline, enabling explicit visualization of where and how classification signals are distorted, diluted, or overridden. As the first attempt to dissect classification performance degradation in medical MLLMs, our findings reveal four failure modes: 1) quality limitation in visual representation, 2) fidelity loss in connector projection, 3) comprehension deficit in LLM reasoning, and 4) misalignment of semantic mapping. Meanwhile, we introduce quantitative scores that characterize the healthiness of feature evolution, enabling principled comparisons across diverse MLLMs and datasets. Furthermore, we provide insightful discussions centered on the critical barriers that prevent current medical MLLMs from fulfilling their promised clinical potential. We hope that our work provokes rethinking within the community-highlighting that the road from high expectations to clinically deployable MLLMs remains long and winding.

In this study, we focus on video captioning by fully open multimodal large language models (MLLMs). The comprehension of visual sequences is challenging because of their intricate temporal dependencies and substantial sequence length. The core attention mechanisms of existing Transformer-based approaches scale quadratically with the sequence length, making them computationally prohibitive. To address these limitations, we propose Aligned Hierarchical Bidirectional Scan Mamba (ABMamba), a fully open MLLM with linear computational complexity that enables the scalable processing of video sequences. ABMamba extends Deep State Space Models as its language backbone, replacing the costly quadratic attention mechanisms, and employs a novel Aligned Hierarchical Bidirectional Scan module that processes videos across multiple temporal resolutions. On standard video captioning benchmarks such as VATEX and MSR-VTT, ABMamba demonstrates competitive performance compared to typical MLLMs while achieving approximately three times higher throughput.

Large multimodal models (LMMs) show strong visual-linguistic reasoning but their capacity for spatial decision-making and action remains unclear. In this work, we investigate whether LMMs can achieve embodied spatial action like human through a challenging scenario: goal-oriented navigation in urban 3D spaces. We first spend over 500 hours constructing a dataset comprising 5,037 high-quality goal-oriented navigation samples, with an emphasis on 3D vertical actions and rich urban semantic information. Then, we comprehensively assess 17 representative models, including non-reasoning LMMs, reasoning LMMs, agent-based methods, and vision-language-action models. Experiments show that current LMMs exhibit emerging action capabilities, yet remain far from human-level performance. Furthermore, we reveal an intriguing phenomenon: navigation errors do not accumulate linearly but instead diverge rapidly from the destination after a critical decision bifurcation. The limitations of LMMs are investigated by analyzing their behavior at these critical decision bifurcations. Finally, we experimentally explore four promising directions for improvement: geometric perception, cross-view understanding, spatial imagination, and long-term memory. The project is available at: https://github.com/serenditipy-AC/Embodied-Navigation-Bench.

Industry classification schemes are integral parts of public and corporate databases as they classify businesses based on economic activity. Due to the size of the company registers, manual annotation is costly, and fine-tuning models with every update in industry classification schemes requires significant data collection. We replicate the manual expert verification by using existing or easily retrievable multimodal resources for industry classification. We present MONETA, the first multimodal industry classification benchmark with text (Website, Wikipedia, Wikidata) and geospatial sources (OpenStreetMap and satellite imagery). Our dataset enlists 1,000 businesses in Europe with 20 economic activity labels according to EU guidelines (NACE). Our training-free baseline reaches 62.10% and 74.10% with open and closed-source Multimodal Large Language Models (MLLM). We observe an increase of up to 22.80% with the combination of multi-turn design, context enrichment, and classification explanations. We will release our dataset and the enhanced guidelines.

Recent advances in text-to-image (T2I) generation have enabled visually coherent image synthesis from descriptions, but generating images containing multiple given subjects remains challenging. As the number of reference identities increases, existing methods often suffer from subject missing and semantic drift. To address this problem, we propose MUSIC, the first MLLM specifically designed for MUlti-Subject In-Context image generation. To overcome the data scarcity, we introduce an automatic and scalable data generation pipeline that eliminates the need for manual annotation. Furthermore, we enhance the model's understanding of multi-subject semantic relationships through a vision chain-of-thought (CoT) mechanism, guiding step-by-step reasoning from subject images to semantics and generation. To mitigate identity entanglement and manage visual complexity, we develop a novel semantics-driven spatial layout planning method and demonstrate its test-time scalability. By incorporating complex subject images during training, we improve the model's capacity for chained reasoning. In addition, we curate MSIC, a new benchmark tailored for multi-subject in-context generation. Experimental results demonstrate that MUSIC significantly surpasses other methods in both multi- and single-subject scenarios.