The exponential growth of large language models (LLMs) has opened up numerous possibilities for multi-modal AGI systems. However, progress in vision and vision-language foundation models, critical for multi-modal AGI, lags behind LLMs. In this chapter, we discuss a large-scale vision-language foundation model (InternVL) , which scales up the vision foundation model to 6 billion parameters and progressively aligns it with the LLM, using web-scale image-text data from various sources. This model demonstrates state-of-the-art performance across 32 generic visual-linguistic benchmarks, including visual perception tasks such as image-level and pixel-level recognition, vision-language tasks like zero-shot image/video classification and zero-shot image/video-text retrieval, and integration with LLMs to develop powerful multi-modal dialog systems, which closes the performance gap from open-sourced MLLMs to commercial multimodal models like GPT-4V.

Despite the remarkable progress of large language models (LLMs), the capabilities of standalone LLMs have begun to plateau when tackling real-world, complex tasks that require interaction with external tools and dynamic environments. Although recent agent frameworks aim to enhance model autonomy through tool integration and external interaction, they still suffer from naive workflows, unstable performance, limited support across diverse benchmarks and tasks, and heavy reliance on costly commercial APIs. In this work, we propose a high-performance and robust open-source agent framework, termed MiroFlow, which incorporates an agent graph for flexible orchestration, an optional deep reasoning mode to enhance performance, and a robust workflow execution to ensure stable and reproducible performance. Extensive experiments demonstrate that MiroFlow consistently achieves state-of-the-art performance across multiple agent benchmarks, including GAIA, BrowseComp-EN/ZH, HLE, xBench-DeepSearch, and notably FutureX. We hope it could serve as an easily accessible, reproducible, and comparable baseline for the deep research community.

Multimodal sentiment analysis seeks to recognize and interpret emotional expressions from heterogeneous sources such as text, images, and speech. However, existing methods still face significant limitations in robustness and generalization due to strong modality heterogeneity, alignment challenges, and label sparsity. In this paper, we propose a cross-modal collaborative semantic enhancement method that leverages supplementary features and labels to improve the model’s perceptual sensitivity to multimodal sentiment information and structural adaptability. Specifically, we design three composite interaction structures based on Multi-Head Cross Attention to model high-order dependencies across modalities, thereby enabling explicit cross-modal feature fusion and complementarity. To further address the challenges posed by limited supervision, we introduce image captioning and speech recognition as auxiliary tasks, establishing external semantic generation pathways. The intermediate representations produced by these tasks are leveraged as supplementary features to help improve the primary sentiment analysis task, while their predicted labels are utilized as supplementary supervision signals to alleviate the problem of label sparsity. This collaborative framework not only facilitates semantic transfer and structural sharing between the main and auxiliary tasks, but also improves the model’s robustness to missing modalities and noise. Extensive comparative and ablation experiments conducted on the public CMU-MOSEI dataset demonstrate that our approach consistently outperforms existing state-of-the-art models.

Despite significant advancements in general AI, its effectiveness in the medical domain is limited by the lack of specialized medical knowledge. To address this, we formulate GMAI-VL-5.5M, a multimodal medical dataset created by converting hundreds of specialized medical datasets with various annotations into high-quality image-text pairs. This dataset offers comprehensive task coverage, diverse modalities, and rich image-text data. Building upon this dataset, we develop GMAI-VL, a 7B-parameter general medical vision-language model, with a three-stage training strategy that enhances the integration of visual and textual information. This approach significantly improves the model's ability to process multimodal data, supporting accurate diagnoses and clinical decision-making. Experiments show that GMAI-VL achieves state-of-the-art performance across various multimodal medical tasks, including visual question answering and medical image diagnosis.

Recent benchmarks and datasets have been proposed to improve spatial reasoning in vision-language models (VLMs), yet existing open resources remain limited in scale, visual diversity, and instruction expressiveness. In this work, we introduce InternSpatial, the largest open-source dataset for spatial reasoning in VLMs, along with InternSpatial-Bench, a corresponding evaluation benchmark designed to assess spatial understanding under diverse instruction formats. InternSpatial comprises 12 million QA pairs spanning both single-view and multi-view settings, drawn from diverse visual environments and supporting 19 instruction formats that reflect varied query styles. For evaluation, we propose InternSpatial-Bench for single-view tasks and expand multi-view reasoning by introducing a novel rotation angle prediction task that has not been explored in prior work. Experimental results show that models trained on InternSpatial achieve 12.1% improvement on InternSpatial-Bench and 10.7% on VSI-Bench, while maintaining strong performance on general-purpose benchmarks. We hope these resources will support the development of spatially capable VLMs in practical applications such as robotics and embodied AI.

Despite significant advancements in Multimodal Large Language Models (MLLMs) for understanding complex human intentions through cross-modal interactions, capturing intricate image details remains challenging. Previous methods integrating multiple vision encoders to enhance visual detail introduce redundancy and computational overhead. We observe that most MLLMs utilize only the last-layer feature map of the vision encoder for visual representation, neglecting the rich fine-grained information in shallow feature maps. To address this issue, we propose MMFuser, a simple yet effective multi-layer feature fuser that efficiently integrates deep and shallow features from Vision Transformers (ViTs). Specifically, it leverages semantically aligned deep features as queries to dynamically extract missing details from shallow features, thus preserving semantic alignment while enriching the representation with fine-grained information. Applied to the LLaVA-1.5 model, MMFuser achieves significant improvements in visual representation and benchmark performance, providing a more flexible and lightweight solution than multi-encoder methods.

We construct VisualPRM400K, a dataset comprising about 400K multimodal process supervision data. Building upon this dataset, we develop VisualPRM, an advanced multimodal Process Reward Model (PRM) capable of estimating the value score of each step during the reasoning process. Under the Best-of-N evaluation setting, our model improves the reasoning performance of three types of MLLMs and four different model scales. Even when applied to the highly capable InternVL2.5-78B, it achieves a 5.9-point improvement across seven multimodal reasoning benchmarks. Experimental results show that the PRM model trained on our VisualPRM400K exhibits superior performance compared to Outcome Reward Models and Self-Consistency during BoN evaluation. To further facilitate the development of multimodal PRMs, we construct VisualProcessBench, a benchmark designed to measure the abilities of PRMs and MLLMs to detect incorrect steps in multimodal reasoning tasks. We hope that our work can inspire more future research and contribute to the development of MLLMs. Our model, data, and benchmark will be released.

Building a powerful vision-language model (VLM) necessitates a holistic system design encompassing model architecture, data curation, and training paradigms. In this paper, we present a longitudinal study of the InternVL series (v1.0-v3.0), distilling its technical evolution into a systematic framework for constructing large-scale, high-performance VLMs. This framework is characterized by three pivotal technical shifts: 1) Perceptual Scaling: We develop a 6-billion parameter vision encoder (InternViT-6B) and introduce a VLM-oriented alignment strategy, which bridges the representation gap between vision and language while enabling fine-grained, high-resolution perception. 2) Multimodal Alignment Scaling: We implement a multimodal dynamic high-resolution (mDHR) mechanism that provides a unified interface for single-image, multi-image, and video inputs. Combined with massive data curation and multi-scale model expansion, this shift pushes the performance frontier through systematic scaling. 3) Native Multimodal Pre-training: We transition from decoupled multi-stage tuning to a native multimodal continual pre-training paradigm. By jointly optimizing interleaved multimodal and text-only data, the model achieves a deep synergy that preserves linguistic proficiency while internalizing visual-world knowledge. Extensive evaluations across a broad range of benchmarks demonstrate that models built upon this framework achieve state-of-the-art performance among open-source VLMs and rival leading proprietary systems. By formalizing these design principles, we offer a reproducible roadmap for future multimodal research. Code and models are available at https://github.com/OpenGVLab/InternVL.

We introduce MMBench-GUI, a hierarchical benchmark for evaluating GUI automation agents across Windows, macOS, Linux, iOS, Android, and Web. The benchmark spans four levels: Content Understanding, Element Grounding, Task Automation, and Task Collaboration, covering essential skills for GUI agents. To assess both effectiveness and efficiency, we further propose the Efficiency–Quality-Aware (EQA) metric, which measures task success alongside action redundancy. Extensive evaluations reveal that precise visual grounding is the critical determinant of performance, underscoring the advantages of modular designs with specialized grounding modules. Moreover, all agents suffer from substantial inefficiencies, frequently completing tasks with excessive steps despite eventual success. Performance also degrades on complex or cross-application tasks, exposing weaknesses in memory, planning, and adaptive reasoning. By providing broad coverage, standardized protocols, and novel metrics, MMBench-GUI establishes the first comprehensive foundation for advancing GUI agent research.

Visual reasoning is a core component of human intelligence and a critical capability for advanced multimodal models. Yet current reasoning evaluations of multimodal large language models (MLLMs) often rely on text descriptions and allow language-based reasoning shortcuts, failing to measure genuine vision-centric reasoning. To address this, we introduce VisuLogic: a benchmark of 1,000 human-verified problems across six categories (e.g., quantitative shifts, spatial relations, attribute comparisons). These various types of questions can be evaluated to assess the visual reasoning capabilities of MLLMs from multiple perspectives. We evaluate leading MLLMs on this benchmark and analyze their results to identify common failure modes. Most models score below 30\% accuracy—only slightly above the 25\% random baseline and far below the 51.4\% achieved by humans—revealing significant gaps in visual reasoning.

We present MiroThinker v1.0, an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities. Unlike previous agents that only scale up model size or context length, MiroThinker explores interaction scaling at the model level, systematically training the model to handle deeper and more frequent agent-environment interactions as a third dimension of performance improvement. Unlike LLM test-time scaling, which operates in isolation and risks degradation with longer reasoning chains, interactive scaling leverages environment feedback and external information acquisition to correct errors and refine trajectories. Through reinforcement learning, the model achieves efficient interaction scaling: with a 256K context window, it can perform up to 600 tool calls per task, enabling sustained multi-turn reasoning and complex real-world research workflows. Across four representative benchmarks-GAIA, HLE, BrowseComp, and BrowseComp-ZH-the 72B variant achieves up to 81.9

Understanding videos is one of the fundamental directions in computer vision research, with extensive efforts dedicated to exploring various architectures such as RNN, 3D CNN, and Transformers. The newly proposed architecture of state space model, e.g., Mamba, shows promising traits to extend its success in long sequence modeling to video modeling. To assess whether Mamba can be a viable alternative to Transformers in the video understanding domain, in this work, we conduct a comprehensive set of studies, probing different roles Mamba can play in modeling videos, while investigating diverse tasks where Mamba could exhibit superiority. We categorize Mamba into four roles for modeling videos, deriving a Video Mamba Suite composed of 14 models/modules, and evaluating them on 12 video understanding tasks. Our extensive experiments reveal the strong potential of Mamba on both video-only and video-language tasks while showing promising efficiency-performance trade-offs. We hope this work could provide valuable data points and insights for future research on video understanding. Code is public: https://github.com/OpenGVLab/video-mamba-suite.

Identifying new cathode materials with excellent properties is crucial for improving the overall energy-storage performance of aqueous zinc-ion batteries (AZIBs). Vanadium-based materials with superior theoretical specific capacities are the main candidates for cathode materials in AZIBs; however, their slow kinetics and poor stability limit their application. Hence, we prepared K0.19V2O5 0.68H2O (KVOH) nanorods with mixed valence states by pre-inserting K+ into V2O5 to enhance the structural stability and electrical conductivity. The K+ in the interlayer altered the electronic structure and formed stable K-O bonds, constructing a 3D electron conduction network. Oxygen vacancies provided extra active sites for Zn2+, increased the surface reactivity to enhance Zn2+ storage capacity, and inhibited the dissolution of the electrode material in the electrolyte. The specific capacity of the KVOH cathode reached 479.4 mAh g-1 at 0.1 A g-1, with a 92.5% capacity retention after 10 000 cycles at 8 A g-1. Overall, this study provides a general strategy for designing and integrating cathode materials that achieve both high capacity and high-rate performance, paving the way for advancements in the field of AZIBs.

Vision-language models (VLMs) show remarkable performance in multimodal tasks. However, excessively long multimodal inputs lead to oversized Key-Value (KV) caches, resulting in significant memory consumption and I/O bottlenecks. Previous KV quantization methods for Large Language Models (LLMs) may alleviate these issues but overlook the attention saliency differences of multimodal tokens, resulting in suboptimal performance. In this paper, we investigate the attention-aware token saliency patterns in VLM and propose AKVQ-VL. AKVQ-VL leverages the proposed Text-Salient Attention (TSA) and Pivot-Token-Salient Attention (PSA) patterns to adaptively allocate bit budgets. Moreover, achieving extremely low-bit quantization requires effectively addressing outliers in KV tensors. AKVQ-VL utilizes the Walsh-Hadamard transform (WHT) to construct outlier-free KV caches, thereby reducing quantization difficulty. Evaluations of 2-bit quantization on 12 long-context and multimodal tasks demonstrate that AKVQ-VL maintains or even improves accuracy, outperforming LLM-oriented methods. AKVQ-VL can reduce peak memory usage by 2.13x, support up to 3.25x larger batch sizes and 2.46x throughput.

We introduce InternVL3, a significant advancement in the InternVL series featuring a native multimodal pre-training paradigm. Rather than adapting a text-only large language model (LLM) into a multimodal large language model (MLLM) that supports visual inputs, InternVL3 jointly acquires multimodal and linguistic capabilities from both diverse multimodal data and pure-text corpora during a single pre-training stage. This unified training paradigm effectively addresses the complexities and alignment challenges commonly encountered in conventional post-hoc training pipelines for MLLMs. To further improve performance and scalability, InternVL3 incorporates variable visual position encoding (V2PE) to support extended multimodal contexts, employs advanced post-training techniques such as supervised fine-tuning (SFT) and mixed preference optimization (MPO), and adopts test-time scaling strategies alongside an optimized training infrastructure. Extensive empirical evaluations demonstrate that InternVL3 delivers superior performance across a wide range of multi-modal tasks. In particular, InternVL3-78B achieves a score of 72.2 on the MMMU benchmark, setting a new state-of-the-art among open-source MLLMs. Its capabilities remain highly competitive with leading proprietary models, including ChatGPT-4o, Claude 3.5 Sonnet, and Gemini 2.5 Pro, while also maintaining strong pure-language proficiency. In pursuit of open-science principles, we will publicly release both the training data and model weights to foster further research and development in next-generation MLLMs.

We introduce MMBench-GUI, a hierarchical benchmark for evaluating GUI automation agents across Windows, macOS, Linux, iOS, Android, and Web platforms. It comprises four levels: GUI Content Understanding, Element Grounding, Task Automation, and Task Collaboration, covering essential skills for GUI agents. In addition, we propose a novel Efficiency-Quality Area (EQA) metric to assess GUI agent execution efficiency in online automation scenarios. Through MMBench-GUI, we identify accurate visual grounding as a critical determinant of overall task success, emphasizing the substantial benefits of modular frameworks that integrate specialized grounding modules. Furthermore, to achieve reliable GUI automation, an agent requires strong task planning and cross-platform generalization abilities, with long-context memory, a broad action space, and long-term reasoning playing a critical role. More important, task efficiency remains a critically underexplored dimension, and all models suffer from substantial inefficiencies, with excessive redundant steps even when tasks are ultimately completed. The integration of precise localization, effective planning, and early stopping strategies is indispensable to enable truly efficient and scalable GUI automation. Our benchmark code, evaluation data, and running environment will be publicly available at https://github.com/open-compass/MMBench-GUI.

The rapid advance of Large Language Models (LLMs) has catalyzed the development of Vision-Language Models (VLMs). Monolithic VLMs, which avoid modality-specific encoders, offer a promising alternative to the compositional ones but face the challenge of inferior performance. Most existing monolithic VLMs require tuning pre-trained LLMs to acquire vision abilities, which may degrade their language capabilities. To address this dilemma, this paper presents a novel high-performance monolithic VLM named HoVLE. We note that LLMs have been shown to be capable of interpreting images when image embeddings are aligned with text embeddings. The challenge for current monolithic VLMs actually lies in the lack of a holistic embedding module for both vision and language inputs. Therefore, HoVLE introduces a holistic embedding module that converts visual and textual inputs into a shared space, allowing LLMs to process images in the same way as texts. Furthermore, a multi-stage training strategy is carefully designed to empower the holistic embedding module. It is first trained to distill visual features from a pre-trained vision encoder and text embeddings from the LLM, enabling large-scale training with unpaired random images and text tokens. The whole model further undergoes next-token prediction on multi-modal data to align the embeddings. Finally, an instruction-tuning stage is incorporated. Our experiments show that HoVLE achieves performance close to leading compositional models on various benchmarks, outperforming previous monolithic models by a large margin.