Recent advancements in Large Multimodal Models (LMMs) have shown promising results in mathematical reasoning within visual contexts, with models exceeding human-level performance on existing benchmarks such as MathVista. However, we observe significant limitations in the diversity of questions and breadth of subjects covered by these benchmarks. To address this issue, we present the MATH-Vision (MATH-V) dataset, a meticulously curated collection of 3,040 high-quality mathematical problems with visual contexts sourced from real math competitions. Spanning 16 distinct mathematical disciplines and graded across 5 levels of difficulty, our dataset provides a comprehensive and diverse set of challenges for evaluating the mathematical reasoning abilities of LMMs. Through extensive experimentation, we unveil a notable performance gap between current LMMs and human performance on \datasetname, underscoring the imperative for further advancements in LMMs. Moreover, our detailed categorization allows for a thorough error analysis of LMMs, offering valuable insights to guide future research and development.

Large Multimodal Model (LMM) is a hot research topic in the computer vision area and has also demonstrated remarkable potential across multiple disciplinary fields. A recent trend is to further extend and enhance the perception capabilities of LMMs. The current methods follow the paradigm of adapting the visual task outputs to the format of the language model, which is the main component of a LMM. This adaptation leads to convenient development of such LMMs with minimal modifications, however, it overlooks the intrinsic characteristics of diverse visual tasks and hinders the learning of perception capabilities. To address this issue, we propose a novel LMM architecture named Lumen, a Large multimodal model with versatile vision-centric capability enhancement.

Large multimodal models (LMMs) are processing increasingly longer and richer inputs. Albeit the progress, few public benchmark is available to measure such development. To mitigate this gap, we introduce LongVideoBench, a question-answering benchmark that features video-language interleaved inputs up to an hour long. Our benchmark includes 3,763 varying-length web-collected videos with their subtitles across diverse themes, designed to comprehensively evaluate LMMs on long-term multimodal understanding. To achieve this, we interpret the primary challenge as to accurately retrieve and reason over detailed multimodal information from long inputs. As such, we formulate a novel video question-answering task termed referring reasoning. Specifically, as part of the question, it contains a referring query that references related video contexts, called referred context. The model is then required to reason over relevant video details from the referred context.

Most large multimodal models (LMMs) are implemented by feeding visual tokens as a sequence into the first layer of a large language model (LLM). The resulting architecture is simple but significantly increases computation and memory costs, as it has to handle a large number of additional tokens in its input layer. This paper presents a new architecture *DeepStack* for LMMs. Considering $N$ layers in the language and vision transformer of LMMs, we stack the visual tokens into $N$ groups and feed each group to its aligned transformer layer from bottom to top. Surprisingly, this simple method greatly enhances the power of LMMs to model interactions among visual tokens across layers but with minimal additional cost. We apply *DeepStack* to both language and vision transformer in LMMs, and validate the effectiveness of *DeepStack* LMMs with extensive empirical results. Using the same context length, our DeepStack 7B and 13B parameters surpass their counterparts by 2.7 and 2.9 on average across 9 benchmarks, respectively.

The application of Large Multimodal Models (LMMs) to long-form video understanding is constrained by limited context lengths and the computationally prohibitive cost of processing dense video tokens. Consequently, recent research has focused on query-aware frame selection, methods that often incur significant computational overhead. This paper challenges the assumption that such complex search mechanisms are universally necessary. W e first identify and validate a query typology distinguishing between global query and localized query. W e demonstrate that while uniform sampling is both effective and efficient for global queries, localized queries indeed necessitate query-aware selection for optimal performance. Building on this insight, we propose DIG, a training-free frame selection framework that adapts its strategy based on the query type. Specifically, DIG employs efficient uniform sampling for global queries while activating a specialized pipeline to extract query-relevant frames for localized queries. Experiments on three long-form video understanding benchmarks demonstrate that DIG consistently outperforms existing baselines and robustly improves LMM performance, even when scaling the input frame count to 256.

Although recent large multimodal models (LMMs) demonstrate impressive progress on vision language tasks, their alignment with human centered (HC) principles, such as fairness, ethics, inclusivity, empathy, and robustness; remains poorly understood. We present HumaniBench, a unified evaluation framework designed to characterize HC alignment across realistic, socially grounded visual contexts. HumaniBench contains 32,000 expert-verified image question pairs derived from real world news imagery and spanning seven evaluation tasks: scene understanding, instance identity, multiple-choice visual question answering (VQA), multilinguality, visual grounding, empathetic captioning, and image resilience testing. Each task is mapped to one or more HC principles through a principled operationalization of metrics covering accuracy, harmful content detection, hallucination and faithfulness, coherence, cross lingual quality, empathy, and robustness.We evaluate 15 state-of-the-art LMMs under this framework and observe consistent cross model trade offs: proprietary systems achieve the strongest performance on ethics, reasoning, and empathy, while open-source models exhibit superior visual grounding and resilience. All models, however, show persistent gaps in fairness and multilingual inclusivity. We further analyze the effect of inference-time techniques, finding that chain of thought prompting and test-time scaling yield 8 to 12 % improvements on several HC dimensions. HumaniBench provides a reproducible, extensible foundation for systematic HC evaluation of LMMs and enables fine-grained analysis of alignment trade-offs that are not captured by conventional multimodal benchmarks. https://vectorinstitute.github.io/humanibench/

Recent advances in Large Multimodal Models (LMMs) have revolutionized their reasoning and Optical Character Recognition (OCR) capabilities. However, their complex logical reasoning performance on text-rich images remains underexplored. To bridge this gap, we introduce LogicOCR, a benchmark comprising 2780 questions with two subsets, i.e., LogicOCR-Gen with 1100 multi-choice questions on generated images, and LogicOCR-Real with 1680 meticulously designed free-form questions on real-world images. For constructing LogicOCR-Gen, we first curate a text corpus from the Chinese National Civil Servant Examination, and customize an automatic pipeline to steer GPT-Image-1 to generate images with varied layouts and fonts, ensuring contextual relevance and visual realism. Then, the generated images are manually verified. We evaluate a range of representative LMMs under Chain-of-Thought (CoT) and direct-answer settings. Our multi-dimensional analysis reveals key insights, such as the impact of test-time scaling, input modality differences, and sensitivity to visual-text orientation. Notably, LMMs still lag in multimodal reasoning compared to text-only inputs, indicating that they have not fully bridged visual reading with reasoning. Moreover, we propose TextCue, a training-free method that enhances LMMs' perception of image regions containing important text cues for solving questions. We leverage LMMs' attention maps and an off-the-shelf text segmentation specialist to determine the region, which is then cropped and enlarged to augment the original image. Experiments show its effectiveness, e.g., a 1.8% accuracy gain over LLaVA-OV-1.5-8B under the CoT setting. Our benchmark is available at https://github.com/MiliLab/LogicOCR.

Developing a robust visual quality assessment (VQualA) large multi-modal model (LMM) requires achieving versatility, powerfulness, and transferability. However, existing VQualA LMMs typically focus on a single task and rely on full-parameter fine-tuning, which makes them prone to overfitting on specific modalities or task types, thereby limiting their generalization capacity and transferability. To address this, we propose a vision-encoder-centered generative pre-training pipeline and develop the VITAL-Series LMMs. (1) We adopt a machine-executed annotation-scrutiny paradigm, constructing over 4.5M vision-language (VL) pairs-the largest VQualA training dataset to date. (2) We employ a multi-task training workflow that simultaneously enhances the model's quantitative scoring precision and strengthens its capability for quality interpretation across both image and video modalities. (3) Building upon the vision encoder, we realize an efficient model zoo extension: the model zoo exhibits strong zero-shot performance, and each paired decoder requires only a swift warm-up using less than 1/1000 of the pre-training data to achieve performance comparable to the fully trained counterpart. Overall, our work lays a cornerstone for advancing toward the foundation LMM for VQualA.

The recent success of interleaved Large Multimodal Models (LMMs) in few-shot learning suggests that in-context learning (ICL) with many examples can be promising for learning new tasks.

Large multimodal models (LMMs) combine unimodal encoders and large language models (LLMs) to perform multimodal tasks.