Multimodal Large Language Models

Internet memes represent a popular form of multimodal online communication and often use figurative elements to convey layered meaning through the combination of text and images. However, it remains largely unclear how multimodal large language models (MLLMs) combine and interpret visual and textual information to identify figurative meaning in memes. To address this gap, we evaluate eight state-of-the-art generative MLLMs across three datasets on their ability to detect and explain six types of figurative meaning. In addition, we conduct a human evaluation of the explanations generated by these MLLMs, assessing whether the provided reasoning supports the predicted label and whether it remains faithful to the original meme content. Our findings indicate that all models exhibit a strong bias to associate a meme with figurative meaning, even when no such meaning is present. Qualitative analysis further shows that correct predictions are not always accompanied by faithful explanations.

Automated semantic annotation of broadcast television content presents distinctive challenges, combining structured audiovisual composition, domain-specific editorial patterns, and strict operational constraints. While multimodal large language models (MLLMs) have demonstrated strong general-purpose video understanding capabilities, their comparative effectiveness across pipeline architectures and input configurations in broadcast-specific settings remains empirically undercharacterized. This paper presents a systematic evaluation of multimodal annotation pipelines applied to broadcast television news in the Italian setting. We construct a domain-specific benchmark of clips labeled across four semantic dimensions: visual environment classification, topic classification, sensitive content detection, and named entity recognition. Two different pipeline architectures are evaluated across nine frontier models, including Gemini 3.0 Pro, LLaMA 4 Maverick, Qwen-VL variants, and Gemma 3, under progressively enriched input strategies combining visual signals, automatic speech recognition, speaker diarization, and metadata. Experimental results demonstrate that gains from video input are strongly model-dependent: larger models effectively leverage temporal continuity, while smaller models show performance degradation under extended multimodal context, likely due to token overload. Beyond benchmarking, the selected pipeline is deployed on 14 full broadcast episodes, with minute-level annotations integrated with normalized audience measurement data provided by an Italian media company. This integration enables correlational analysis of topic-level audience sensitivity and generational engagement divergence, demonstrating the operational viability of the proposed framework for content-based audience analytics.

Recent works have shown that multimodal large language models (MLLMs) are highly vulnerable to hidden-pattern visual illusions, where the hidden content is imperceptible to models but obvious to humans. This deficiency highlights a perceptual misalignment between current MLLMs and humans, and also introduces potential safety concerns. To systematically investigate this failure, we introduce IlluChar, a comprehensive and challenging illusion dataset, and uncover a key underlying mechanism for the models' failure: high-frequency attention bias, where the models are easily distracted by high-frequency background textures in illusion images, causing them to overlook hidden patterns. To address the issue, we propose the Strategy of Multi-Scale Perception (SMSP), a plug-and-play framework that aligns with human visual perceptual strategies. By suppressing distracting high-frequency background signals, SMSP generates images closer to human perception. Our experiments demonstrate that SMSP significantly improves the performance of all evaluated MLLMs on illusion images, for instance, increasing the accuracy of Qwen3-VL-8B-Instruct from 13.0% to 84.0%. Our work provides novel insights into MLLMs' visual perception, and offers a practical and robust solution to enhance it. Our code is publicly available at https://github.com/Tujz2023/SMSP.

We introduce SAGE Celer 2.6, the latest in our line of general-purpose Celer models from SAGEA. Celer 2.6 is available in 5B, 10B, and 27B parameter sizes and benefits from extensive architectural modifications and further pre-training on an undisclosed model. Using our Inverse Reasoning (IR) pipeline, SAGEA natively trains Celer 2.6 to validate its own logic paths, minimizing cascading error and hallucination in complex reasoning tasks. Celer 2.6 also boasts natively integrated multimodal functionality with an end-to-end vision encoder to avoid common pitfalls in adapter-based approaches. Celer 2.6 provides highly competitive results on mathematics, coding, and general intelligence benchmarks (ACUMEN), along with low latency. Most importantly, Celer 2.6 is specifically optimized for South Asian language support, with a custom tokenizer for the Devanagari script and strong performance in both Nepali and Hindi without sacrificing English reasoning ability.

Electronic Navigational Charts (ENCs) are the safety-critical backbone of modern maritime navigation, yet it remains unclear whether multimodal large language models (MLLMs) can reliably interpret them. Unlike natural images or conventional charts, ENCs encode regulations, bathymetry, and route constraints via standardized vector symbols, scale-dependent rendering, and precise geometric structure -- requiring specialized maritime expertise for interpretation. We introduce ENC-Bench, the first benchmark dedicated to professional ENC understanding. ENC-Bench contains 20,490 expert-validated samples from 840 authentic National Oceanic and Atmospheric Administration (NOAA) ENCs, organized into a three-level hierarchy: Perception (symbol and feature recognition), Spatial Reasoning (coordinate localization, bearing, distance), and Maritime Decision-Making (route legality, safety assessment, emergency planning under multiple constraints). All samples are generated from raw S-57 data through a calibrated vector-to-image pipeline with automated consistency checks and expert review. We evaluate 10 state-of-the-art MLLMs such as GPT-4o, Gemini 2.5, Qwen3-VL, InternVL-3, and GLM-4.5V, under a unified zero-shot protocol. The best model achieves only 47.88% accuracy, with systematic challenges in symbolic grounding, spatial computation, multi-constraint reasoning, and robustness to lighting and scale variations. By establishing the first rigorous ENC benchmark, we open a new research frontier at the intersection of specialized symbolic reasoning and safety-critical AI, providing essential infrastructure for advancing MLLMs toward professional maritime applications.

Multimodal Large Language Models (MLLMs) have recently demonstrated remarkable perceptual and reasoning abilities. However, they struggle to perceive fine-grained geometric structures, constraining their ability of geometric understanding and visual reasoning. To address this, we propose GeoTikzBridge, a framework that enhances local geometric perception and visual reasoning through tikz-based code generation. Within this framework, we build two models supported by two complementary datasets. The GeoTikzBridge-Base model is trained on GeoTikz-Base dataset, the largest image-to-tikz dataset to date with 2.5M pairs (16 $\times$ larger than existing open-sourced datasets). This process is achieved via iterative data expansion and a localized geometric transformation strategy. Subsequently, GeoTikzBridge-Instruct is fine-tuned on GeoTikz-Instruct dataset which is the first instruction-augmented tikz dataset supporting visual reasoning. Extensive experimental results demonstrate that our models achieve state-of-the-art performance among open-sourced MLLMs. Furthermore, GeoTikzBridge models can serve as plug-and-play reasoning modules for any MLLM(LLM), enhancing reasoning performance in geometric problem-solving. Datasets and codes are publicly available at: https://github.com/sjy-1995/GeoTikzBridge.

Recent advances in Multimodal Large Language Models (MLLMs) have enabled automated generation of structured layouts from natural language descriptions. Existing methods typically follow a code-only paradigm that generates code to represent layouts, which are then rendered by graphic engines to produce final images. However, they are blind to the rendered visual outcome, making it difficult to guarantee readability and aesthetics. In this paper, we identify visual feedback as a critical factor in layout generation and propose Visual Feedback Layout Model (VFLM), a self-improving framework that leverages visual feedback iterative refinement. VFLM is capable of performing adaptive reflective generation, which leverages visual information to reflect on previous issues and iteratively generates outputs until satisfactory quality is achieved. It is achieved through reinforcement learning with a visually grounded reward model that incorporates OCR accuracy. By rewarding only the final generated outcome, we can effectively stimulate the model's iterative and reflective generative capabilities. Experiments across multiple benchmarks show that VFLM consistently outperforms advanced MLLMs, existing layout models, and code-only baselines, establishing visual feedback as critical for design-oriented MLLMs. Our code and data are available at https://github.com/FolSpark/VFLM.

This work presents a collection of multi-modal domain adapted large language models built upon the instruction tuned variants of open weight models (Gemma 3, Qwen 3, Gemma 4) using a relatively small dataset of around 50 million tokens. The dataset consists of open-access additive manufacturing journal articles with data extracted for the domain adaptive pretraining and visual instruction tuning processes. Various stages of the developed model are evaluated with the Additive-Manufacturing-Benchmark which consists of additive manufacturing domain specific tasks compiled published resources. Domain adapted and instruction tuned models exhibit proficiency in both language and vision based tasks, achieving accuracies upwards of 90% in general additive manufacturing knowledge. This domain adaptive pretraining and instruction tuning strategy outline an accessible specialization method for large language models to a domain such as additive manufacturing.

Hate speech online targets individuals or groups based on identity attributes and spreads rapidly, posing serious social risks. Memes, which combine images and text, have emerged as a nuanced vehicle for disseminating hate speech, often relying on cultural knowledge for interpretation. However, existing multimodal hate speech datasets suffer from coarse-grained labeling and a lack of integration with surrounding discourse, leading to imprecise and incomplete assessments. To bridge this gap, we propose an agentic annotation framework that coordinates seven specialized agents to generate hierarchical labels and rationales. Based on this framework, we construct M^3 (Multi-platform, Multi-lingual, and Multimodal Meme), a dataset of 2,455 memes collected from X, 4chan, and Weibo, featuring fine-grained hate labels and human-verified rationales. Benchmarking state-of-the-art Multimodal Large Language Models reveals that these models struggle to effectively utilize surrounding post context, which often fails to improve or even degrades detection performance. Our finding highlights the challenges these models face in reasoning over memes embedded in real-world discourse and underscores the need for a context-aware multimodal architecture. Our dataset and code are available at https://github.com/mira-ai-lab/M3.

While Omni-modal Large Language Models have made strides in joint sensory processing, they fundamentally struggle with a cornerstone of human interaction: deciphering complex, multi-person conversational dynamics to accurately answer Who said what and when.'' Current models suffer from an illusion of competence'' -- they exploit visual biases in conventional benchmarks to bypass genuine cross-modal alignment, while relying on sparse, low-frame-rate visual sampling that destroys crucial high-frequency dynamics like lip movements. To shatter this illusion, we introduce Visual-Registered Speaker Diarization and Recognition (VR-SDR) and the HumanOmni-Speaker Benchmark. By strictly eliminating visual shortcuts, this rigorous paradigm demands true end-to-end spatio-temporal identity binding using only natural language queries. To overcome the underlying architectural perception gap, we propose HumanOmni-Speaker, powered by a Visual Delta Encoder. By sampling raw video at 25 fps and explicitly compressing inter-frame motion residuals into just 6 tokens per frame, it captures fine-grained visemes and speaker trajectories without triggering a catastrophic token explosion. Ultimately, HumanOmni-Speaker demonstrates strong multimodal synergy, natively enabling end-to-end lip-reading and high-precision spatial localization without intrusive cropping, and achieving superior performance across a wide spectrum of speaker-centric tasks.

Multimodal large language models (MLLMs) achieve strong performance by jointly processing inputs from multiple modalities, such as vision, audio, and language. However, building such models or extending them to new modalities often requires large paired datasets and substantial computational resources. Since many pretrained MLLMs (e.g., vision-language or audio-language) are publicly available, we ask whether we can merge them into a single MLLM that can handle multiple modalities? Merging MLLMs with different input modalities remains challenging, partly because of differences in the learned representations and interference between their parameter spaces. To address these challenges, we propose Singular Subspace Alignment and Merging (SSAM), a training-free model merging framework that unifies independently trained specialist MLLMs into a single model capable of handling any combination of input modalities. SSAM maintains modality-specific parameter updates separately and identifies a shared low-rank subspace for language-related parameter updates, aligns them within this subspace, and merges them to preserve complementary knowledge while minimizing parameter interference. Without using any multimodal training data, SSAM achieves state-of-the-art performance across four datasets, surpassing prior training-free merging methods and even jointly trained multimodal models. These results demonstrate that aligning models in parameter space provides a scalable and resource-efficient alternative to conventional joint multimodal training.

Despite the widespread adoption of MLLMs in embodied agents, their capabilities remain largely confined to reactive planning from immediate observations, consistently failing in spatial reasoning across extensive spatiotemporal scales. Cognitive science reveals that Biological Intelligence (BI) thrives on "mental navigation": the strategic construction of spatial representations from experience and the subsequent mental simulation of paths prior to action. To bridge the gap between AI and BI, we introduce Video2Mental, a pioneering benchmark for evaluating the mental navigation capabilities of MLLMs. The task requires constructing hierarchical cognitive maps from long egocentric videos and generating landmark-based path plans step by step, with planning accuracy verified through simulator-based physical interaction. Our benchmarking results reveal that mental navigation capability does not naturally emerge from standard pre-training. Frontier MLLMs struggle profoundly with zero-shot structured spatial representation, and their planning accuracy decays precipitously over extended horizons. To overcome this, we propose NavMind, a reasoning model that internalizes mental navigation using explicit, fine-grained cognitive maps as learnable intermediate representations. Through a difficulty-stratified progressive supervised fine-tuning paradigm, NavMind effectively bridges the gap between raw perception and structured planning. Experiments demonstrate that NavMind achieves superior mental navigation capabilities, significantly outperforming frontier commercial and spatial MLLMs.

The prosperity of Multimodal Large Language Models (MLLMs) has stimulated the demand for video reasoning segmentation, which aims to segment video objects based on human instructions. Previous studies rely on unidirectional and implicit text-trajectory alignment, which struggles with trajectory perception when faced with severe video dynamics. In this work, we propose TrajSeg, a simple and unified framework built upon MLLMs. Concretely, we introduce bidirectional text-trajectory alignment, where MLLMs accept grounding-intended (text-to-trajectory) and captioning-intended (trajectory-to-text) instructions. This way, MLLMs can benefit from enhanced correspondence and better perceive object trajectories in videos. The mask generation from trajectories is achieved via a frame-level content integration (FCI) module and a unified mask decoder. The former adapts the MLLM-parsed trajectory-level token to frame-specific information. The latter unifies segmentation for all frames into a single structure, enabling the proposed framework to be simplified and end-to-end trainable. Extensive experiments on referring and reasoning video segmentation datasets demonstrate the effectiveness of TrajSeg, which outperforms all video reasoning segmentation methods on all metrics. The code will be publicly available at https://github.com/haodi19/TrajSeg.

Knowledge distillation establishes a learning paradigm that leverages both data supervision and teacher guidance. However, determining the optimal balance between learning from data and learning from the teacher is challenging, as some samples may be noisy while others are subject to teacher uncertainty. This motivates the need for adaptively balancing data and teacher supervision. We propose Beta-weighted Knowledge Distillation (Beta-KD), an uncertainty-aware distillation framework that adaptively modulates how much the student relies on teacher guidance. Specifically, we formulate teacher--student learning from a unified Bayesian perspective and interpret teacher supervision as a Gibbs prior over student activations. This yields a closed-form, uncertainty-aware weighting mechanism and supports arbitrary distillation objectives and their combinations. Extensive experiments on multimodal VQA benchmarks demonstrate that distilling student Vision-Language Models from a large teacher VLM consistently improves performance. The results show that Beta-KD outperforms existing knowledge distillation methods. The code is available at https://github.com/Jingchensun/beta-kd.

Multimodal large language models (MLLMs) achieve remarkable progress in cross-modal perception and reasoning, yet a fundamental question remains unresolved: should the vision encoder be fine-tuned or frozen? Despite the success of models such as LLaVA and Qwen-VL, inconsistent design choices and heterogeneous training setups hinder a unified understanding of visual fine-tuning (VFT) in MLLMs. Through a configuration-aligned benchmark, we find that existing VFT methods fail to consistently outperform the frozen baseline across multimodal tasks. Our analysis suggests that this instability arises from visual preference conflicts, where the context-agnostic nature of vision encoders induces divergent parameter updates under diverse multimodal context. To address this issue, we propose the Context-aware Visual Fine-tuning (CoVFT) framework, which explicitly incorporates multimodal context into visual adaptation. By integrating a Context Vector Extraction (CVE) and a Contextual Mixture-of-Experts (CoMoE) module, CoVFT decomposes conflicting optimization signals and enables stable, context-sensitive visual updates. Extensive experiments on 12 multimodal benchmarks demonstrate that CoVFT achieves state-of-the-art performance with superior stability. Notably, fine-tuning a 7B MLLM with CoVFT surpasses the average performance of its 13B counterpart, revealing substantial untapped potential in visual encoder optimization within MLLMs.

While Multimodal Large Language Models (MLLMs) excel at vision-language tasks, the cost of their language-driven training on internal visual foundational competence remains unclear. In this paper, we conduct a detailed diagnostic analysis to unveil a pervasive issue: visual representation degradation in MLLMs. Specifically, we find that compared to the initial visual features, the visual representation in the middle layers of LLM exhibits both a degradation in global function and patch structure. We attribute this phenomenon to a visual sacrifice driven by the singular text-generation objective, where the model compromises its visual fidelity to optimize for answer generation. We argue that a robust MLLM requires both strong cross-modal reasoning and core visual competence, and propose Predictive Regularization (PRe) to force degraded intermediate features to predict initial visual features, thereby maintaining the inherent visual attributes of the MLLM's internal representations. Extensive experiments confirm that mitigating this visual degradation effectively boosts vision-language performance, underscoring the critical importance of fostering robust internal visual representations within MLLMs for comprehensive multimodal understanding.

An omni-modal language model can answer a question about a multimodal document, a recording, or a video, but it cannot show which part of the input the answer came from. Asking the model to cite its evidence yields what it says it used; measuring what it used has so far required rerunning it many times with parts of the input removed, a cost that grows with every second of audio and video. We show that the generation pass already holds most of this information. OmniTrace attributes each generated sentence to source units (text chunks, images, and seconds of audio or video) by reading late-layer attention as mass over units with no extra forward pass and no per-modality tuning; head weights can be trained where ablation data are available. With fixed causal test setting, the units OmniTrace selects are causally important for responses and for individual sentences in video, audio, and image-text question answering on Qwen3-Omni-30B, MiniCPM-o 4.5 and Qwen2.5-Omni-7B. With one generation pass, OmniTrace recovers 77-96% of the effect of leave-one-out attribution, which needs up to 41 extra passes. OmniTrace also agrees best with human-marked evidence: its response-level rankings reach an AUROC of 0.83 on documents and 0.64 on video, against 0.76 and 0.60 for the strongest baseline.

Multimodal large language models (MLLMs) excel at high-level reasoning yet fail on OCR tasks where fine-grained visual details are compromised or misaligned. We identify an overlooked optimization issue in multi-layer feature fusion. Skip pathways introduce direct back-propagation paths from high-level semantic objectives to early visual layers. This mechanism overwrites low-level signals and destabilizes training. To mitigate this gradient interference, we propose Detached Skip-Links, a minimal modification that reuses shallow features in the forward pass while stopping gradients through the skip branch during joint training. This asymmetric design reduces gradient interference, improving stability and convergence without adding learnable parameters. To diagnose whether fine-grained information is preserved and usable by an LLM, we introduce $R$-Probe, which measures pixel-level reconstructability of projected visual tokens using a shallow decoder initialized from the first quarter of the LLM layers. Across multiple ViT backbones and multimodal benchmarks, and at scales up to 7M training samples, our approach consistently improves OCR-centric benchmarks and delivers clear gains on general multimodal tasks.

The recent advancements introduced by Large Language Models (LLMs) have transformed how Artificial Intelligence (AI) can support complex, real world tasks, pushing research outside the text boundaries towards multi modal contexts and leading to Multimodal Large Language Models (MLMs). Given the current adoption of LLM based assistants in solving technical or domain specific problems, the natural continuation of this trend is to extend the input domains of these assistants exploiting MLMs. Ideally, these MLMs should be used as real time assistants in procedural tasks, hopefully integrating a view of the environment where the user being assisted is, or even better sharing the same point of view via Virtual Reality (VR) or Augmented Reality (AR) supports, to reason over the same scenario the user is experiencing. With this work, we aim at evaluating the quality of currently openly available MLMs to provide this kind of assistance on technical tasks. To this end, we annotated a data set of furniture assembly with step by step labels and manual references: the Manual to Action Dataset (M2AD). We used this dataset to assess (1) to which extent the reasoning abilities of MLMs can be used to reduce the need for detailed labelling, allowing for more efficient, cost effective annotation practices, (2) whether MLMs are able to track the progression of assembly steps (3) and whether MLMs can refer correctly to the instruction manual pages. Our results showed that while some models understand procedural sequences, their performance is limited by architectural and hardware constraints, highlighting the need for multi image and interleaved text image reasoning.

Medical image quality assessment (Med-IQA) is a prerequisite for clinical AI deployment, yet multimodal large language models (MLLMs) still fall substantially short of human experts, particularly when required to provide descriptive assessments with clinical reasoning beyond simple quality scores. However, improving them is hindered by the high cost of acquiring descriptive annotations and by the inability of one-time data collection to adapt to the model's evolving weaknesses. To address these challenges, we propose MedQ-Engine, a closed-loop data engine that iteratively evaluates the model to discover failure prototypes via data-driven clustering, explores a million-scale image pool using these prototypes as retrieval anchors with progressive human-in-the-loop annotation, and evolves through quality-assured fine-tuning, forming a self-improving cycle. Models are evaluated on complementary perception and description tasks. An entropy-guided routing mechanism triages annotations to minimize labeling cost. Experiments across five medical imaging modalities show that MedQ-Engine elevates an 8B-parameter model to surpass GPT-4o by over 13% and narrow the gap with human experts to only 4.34%, using only 10K annotations with more than 4x sample efficiency over random sampling.

Human Label Variation (HLV), i.e. systematic differences among annotators' judgments, remains underexplored in benchmarks despite rapid progress in large language model (LLM) development. We address this gap by introducing an evaluation protocol for multimodal large language model (MLLM) benchmarking that explicitly accounts for two conditions: (1) human label agreement and (2) disagreement. We apply this protocol to two state-of-the-art MLLM families (Gemma 3, Qwen 2.5 VL) using non-aggregated human annotations from a social media content classification dataset. Across tasks, we find that larger models tend to perform best on high-agreement subsets, yet often underperform medium-sized models when human disagreement is high, indicating that parameter count alone does not determine sensitivity to ambiguity and subjectivity. These results show that benchmarks based solely on consensus labels can overstate model capabilities in such domains and that incorporating human label variation yields more realistic and robust assessments of MLLMs in content moderation pipelines.

Conventional wisdom for selecting supervision data for multimodal large language models (MLLMs) is to prioritize datasets that appear similar to the target benchmark, such as text-intensive or vision-centric tasks. However, it remains unclear whether such intuitive similarity reliably predicts downstream performance gains. In this work, we take a first step toward answering a practical question: can we estimate the influence of a training dataset on a target benchmark before any training is performed? To investigate this question, we conduct an in-depth analysis of transfer across 14 vision-language datasets spanning 7 diverse tasks. Our results show that intuitive task similarity is an unreliable predictor of transferability, and that generalization depends more on the specific dataset than on its broad task category. Motivated by this finding, we propose DATAPROPHET, a simple and effective training-free metric that combines multimodal perplexity, similarity, and data diversity. Experiments show that DATAPROPHET produces supervision-data rankings that strongly correlate with rankings based on actual post-training performance gains, achieving a Kendall's tau of 86.0%. Moreover, DATAPROPHET enables better supervision-data selection, yielding up to 6.9% improvement over uniform selection, 1.4% over a state-of-the-art training-based baseline, and 0.2% above oracle selection based on experimental performance. Our code and data will be released.

Effective collaboration begins with knowing when to ask for help. For example, when trying to identify an occluded object, a human would ask someone to remove the obstruction. Can MLLMs exhibit a similar "proactive" behavior by requesting simple user interventions? To investigate this, we introduce ProactiveBench, a benchmark built from seven repurposed datasets that tests proactiveness across different tasks such as recognizing occluded objects, enhancing image quality, and interpreting coarse sketches. We evaluate 22 MLLMs on ProactiveBench, showing that (i) they generally lack proactiveness; (ii) proactiveness does not correlate with model capacity; (iii) "hinting" at proactiveness yields only marginal gains. Surprisingly, we found that conversation histories and in-context learning introduce negative biases, hindering performance. Finally, we explore a simple fine-tuning strategy based on reinforcement learning: its results suggest that proactiveness can be learned, even generalizing to unseen scenarios. We publicly release ProactiveBench as a first step toward building proactive multimodal models.

Recent advancements in omnimodal large language models (OmniLLMs) have significantly improved the comprehension of audio and video inputs. However, current evaluations primarily focus on short audio and video clips ranging from 10 seconds to 5 minutes, failing to reflect the demands of real-world applications, where videos typically run for tens of minutes. To address this critical gap, we introduce LVOmniBench, a new benchmark designed specifically for the cross-modal comprehension of long-form audio and video. This dataset comprises high-quality videos sourced from open platforms that feature rich audio-visual dynamics. Through rigorous manual selection and annotation, LVOmniBench comprises 275 videos, ranging in duration from 10 to 90 minutes, and 1,014 question-answer (QA) pairs. LVOmniBench aims to rigorously evaluate the capabilities of OmniLLMs across domains, including long-term memory, temporal localization, fine-grained understanding, and multimodal perception. Our extensive evaluation reveals that current OmniLLMs encounter significant challenges when processing extended audio-visual inputs. Open-source models generally achieve accuracies below 35%, whereas the Gemini 3 Pro reaches a peak accuracy of approximately 65%. We anticipate that this dataset, along with our empirical findings, will stimulate further research and the development of advanced models capable of resolving complex cross-modal understanding problems within long-form audio-visual contexts.

Recent segmentation methods leveraging Multi-modal Large Language Models (MLLMs) have shown reliable object-level segmentation and enhanced spatial perception. However, almost all previous methods predominantly rely on specialist mask decoders to interpret masks from generated segmentation-related embeddings and visual features, or incorporate multiple additional tokens to assist. This paper aims to investigate whether and how we can unlock segmentation from MLLM itSELF with 1 segmentation Embedding (SELF1E) while achieving competitive results, which eliminates the need for external decoders. To this end, our approach targets the fundamental limitation of resolution reduction in pixel-shuffled image features from MLLMs. First, we retain image features at their original uncompressed resolution, and refill them with residual features extracted from MLLM-processed compressed features, thereby improving feature precision. Subsequently, we integrate pixel-unshuffle operations on image features with and without LLM processing, respectively, to unleash the details of compressed features and amplify the residual features under uncompressed resolution, which further enhances the resolution of refilled features. Moreover, we redesign the attention mask with dual perception pathways, i.e., image-to-image and image-to-segmentation, enabling rich feature interaction between pixels and the segmentation token. Comprehensive experiments across multiple segmentation tasks validate that SELF1E achieves performance competitive with specialist mask decoder-based methods, demonstrating the feasibility of decoder-free segmentation in MLLMs. Project page: https://github.com/ANDYZAQ/SELF1E.

Long-form video question answering requires reasoning over extended temporal contexts, making frame selection a critical bottleneck for multi-modal large language models (MLLMs) bound by finite context windows. Within the controlled frame-budget regime that governs practical deployment, prior selectors score frames against a single global query embedding; as a result, compositional multimodal questions that involve temporal ordering or cross-modal cues such as "what happens on screen right after the narrator mentions the reaction?" are flattened into a representation that loses sub-event ordering and modality bindings. We introduce HiMu, a training-free framework for compositional multimodal frame selection. A single text-only LLM call decomposes the query into a hierarchical logic tree whose leaves are atomic predicates, each routed to a lightweight expert spanning vision (CLIP, open-vocabulary detection, OCR) and audio (speech recognition and non-speech sound matching). Expert signals are normalized, smoothed to align across modalities, and composed bottom-up through fuzzy-logic operators that enforce temporal sequencing and adjacency, yielding a continuous per-frame satisfaction curve. Under the standard 16-frame budget on Video-MME, LongVideoBench, and HERBench-Lite, HiMu achieves state-of-the-art accuracy among frame selection methods and improves over uniform sampling across seven diverse MLLMs as a drop-in module, matching the accuracy of uniform sampling at 4x its frame budget, without retraining and without multiple iterative MLLM calls during selection.

Multimodal large language models (MLLMs) perform strongly on natural images, yet their ability to understand discrete visual symbols remains unclear. We present a multi-domain benchmark spanning language, culture, mathematics, physics and chemistry, organized into three cognitive levels: perception and recognition, combination and reasoning, and association and critical thinking. Across leading MLLMs, we observe a consistent cognitive mismatch. Models frequently underperform on elementary symbol recognition while appearing relatively competent on more complex reasoning tasks. This recognition-reasoning inversion indicates that current systems often compensate with linguistic priors, template retrieval or procedural reasoning instead of robust visual grounding. The pattern is especially clear for sparse, low-redundancy symbols such as handwritten characters, formula graphs, circuit diagrams and chemical structures. These results show that symbolic understanding remains a major bottleneck for multimodal intelligence and motivate training and evaluation schemes that prioritize grounded perception in discrete semantic spaces.

Task interference, the performance degradation caused by task switches within a single conversation, has been studied exclusively in text-only settings despite the growing prevalence of multimodal dialogue systems. We introduce a benchmark for evaluating this phenomenon in multimodal LLMs, covering six tasks across text and vision with systematic variation of history-target along three axes: modality mismatch, reasoning mismatch, and answer format mismatch. Experiments on both open-weights and proprietary models reveal that task interference is highly directional: switching from text-only to image-based targets causes severe performance drops, while the reverse transition yields minimal degradation. Interference is further amplified when mismatches co-occur across multiple dimensions, and is driven most strongly by modality differences, followed by answer format, while reasoning requirement shifts cause minimal degradation.

Multimodal large language models (MLLMs) exhibit strong visual-language reasoning, yet cannot process structured, non-visual data such as human skeletons. Existing methods either compress skeleton dynamics into lossy feature vectors for text alignment, or quantize motion into discrete tokens that generalize poorly across heterogeneous skeleton formats. We present SkeletonLLM, which achieves universal skeleton understanding by translating arbitrary skeleton sequences into the MLLM's native visual modality. At its core is DrAction, a differentiable, format-agnostic renderer that converts skeletal kinematics into compact image sequences. Because the pipeline is end-to-end differentiable, MLLM gradients can directly guide the rendering to produce task-informative visual tokens. To further enhance reasoning capabilities, we introduce a cooperative training strategy: Causal Reasoning Distillation transfers structured, step-by-step reasoning from a teacher model, while Discriminative Finetuning sharpens decision boundaries between confusable actions. SkeletonLLM demonstrates strong generalization \revise{in open-vocabulary action recognition, while its learned reasoning capabilities naturally extend to motion captioning and question answering across heterogeneous skeleton formats} -- suggesting a viable path for applying MLLMs to non-native modalities. Code: https://github.com/wangzy01/SkeletonLLM.

Large Language Models (LLMs) have achieved remarkable reliability and advanced capabilities through extended test-time reasoning. However, extending these capabilities to Multi-modal Large Language Models (MLLMs) remains a significant challenge due to a critical scarcity of high-quality, long-chain reasoning data and optimized training pipelines. To bridge this gap, we present a unified multi-agent visual reasoning framework that systematically evolves from our foundational image-centric model, Insight-V, into a generalized spatial-temporal architecture, Insight-V++. We first propose a scalable data generation pipeline equipped with multi-granularity assessment that autonomously synthesizes structured, complex reasoning trajectories across image and video domains without human intervention. Recognizing that directly supervising MLLMs with such intricate data yields sub-optimal results, we design a dual-agent architecture comprising a reasoning agent to execute extensive analytical chains, and a summary agent to critically evaluate and distill final outcomes. While our initial framework utilized Direct Preference Optimization (DPO), its off-policy nature fundamentally constrained reinforcement learning potential. To overcome these limitations, particularly for long-horizon video understanding, Insight-V++ introduces two novel algorithms, ST-GRPO and J-GRPO, which enhance spatial-temporal reasoning and improve evaluative robustness. Crucially, by leveraging reliable feedback from the summary agent, we guide an iterative reasoning path generation process, retraining the entire multi-agent system in a continuous, self-improving loop. Extensive experiments on base models like LLaVA-NeXT and Qwen2.5-VL demonstrate significant performance gains across challenging image and video reasoning benchmarks while preserving strong capabilities on traditional perception-focused tasks.