Haodong Duan

Yuan Liu, Haodong Duan, Yuanhan Zhang et al. · pku

Large vision-language models (VLMs) have recently achieved remarkable progress, exhibiting impressive multimodal perception and reasoning abilities. However, effectively evaluating these large VLMs remains a major challenge, hindering future development in this domain. Traditional benchmarks like VQAv2 or COCO Caption provide quantitative performance measurements but lack fine-grained ability assessment and robust evaluation metrics. Meanwhile, subjective benchmarks, such as OwlEval, offer comprehensive evaluations of a model's abilities by incorporating human labor, which is not scalable and may display significant bias. In response to these challenges, we propose MMBench, a bilingual benchmark for assessing the multi-modal capabilities of VLMs. MMBench methodically develops a comprehensive evaluation pipeline, primarily comprised of the following key features: 1. MMBench is meticulously curated with well-designed quality control schemes, surpassing existing similar benchmarks in terms of the number and variety of evaluation questions and abilities; 2. MMBench introduces a rigorous CircularEval strategy and incorporates large language models to convert free-form predictions into pre-defined choices, which helps to yield accurate evaluation results for models with limited instruction-following capabilities. 3. MMBench incorporates multiple-choice questions in both English and Chinese versions, enabling an apples-to-apples comparison of VLMs' performance under a bilingual context. To summarize, MMBench is a systematically designed objective benchmark for a robust and holistic evaluation of vision-language models. We hope MMBench will assist the research community in better evaluating their models and facilitate future progress in this area. The evalutation code of MMBench has been integrated into VLMEvalKit: https://github.com/open-compass/VLMEvalKit.

Haodong Duan, Jiaqi Wang, Kai Chen et al. · pku

We present PYSKL: an open-source toolbox for skeleton-based action recognition based on PyTorch. The toolbox supports a wide variety of skeleton action recognition algorithms, including approaches based on GCN and CNN. In contrast to existing open-source skeleton action recognition projects that include only one or two algorithms, PYSKL implements six different algorithms under a unified framework with both the latest and original good practices to ease the comparison of efficacy and efficiency. We also provide an original GCN-based skeleton action recognition model named ST-GCN++, which achieves competitive recognition performance without any complicated attention schemes, serving as a strong baseline. Meanwhile, PYSKL supports the training and testing of nine skeleton-based action recognition benchmarks and achieves state-of-the-art recognition performance on eight of them. To facilitate future research on skeleton action recognition, we also provide a large number of trained models and detailed benchmark results to give some insights. PYSKL is released at https://github.com/kennymckormick/pyskl and is actively maintained. We will update this report when we add new features or benchmarks. The current version corresponds to PYSKL v0.2.

Pan Zhang, Xiaoyi Dong, Bin Wang et al. · pku

We propose InternLM-XComposer, a vision-language large model that enables advanced image-text comprehension and composition. The innovative nature of our model is highlighted by three appealing properties: 1) Interleaved Text-Image Composition: InternLM-XComposer can effortlessly generate coherent and contextual articles that seamlessly integrate images, providing a more engaging and immersive reading experience. Simply provide a writing instruction, and our system will generate the corresponding manuscript. It can intelligently identify the areas in the text where images would enhance the content and automatically insert the most appropriate visual candidates. 2) Comprehension with Rich Multilingual Knowledge: The text-image comprehension is empowered by training on an extensive multi-modal multilingual database with carefully crafted strategies, resulting in a deep understanding of visual content. 3) State-of-the-art Performance: Our model consistently achieves state-of-the-art results across various mainstream benchmarks for vision-language foundational models, including MME Benchmark, MMBench, MMBench-CN, Seed-Bench, CCBench (Chinese Cultural Benchmark), QBench and Tiny LVLM. Owing to the absence of established metrics for quantitatively assessing text-image composition, we have devised a robust evaluation procedure that comprises both human and GPT4-Vision (GPT4-V) to ensure reliability. Notably, our InternLM-XComposer achieves competitive text-image composition scores compared to public solutions, including GPT4-V and GPT3.5. Collectively, InternLM-XComposer seamlessly blends advanced text-image comprehension and composition, revolutionizing vision-language interaction and offering new insights and opportunities. The InternLM-XComposer model series are publicly available at https://github.com/InternLM/InternLM-XComposer.

Haodong Duan, Xinyu Fang, Junming Yang et al. · pku

We present VLMEvalKit: an open-source toolkit for evaluating large multi-modality models based on PyTorch. The toolkit aims to provide a user-friendly and comprehensive framework for researchers and developers to evaluate existing multi-modality models and publish reproducible evaluation results. In VLMEvalKit, we implement over 200+ different large multi-modality models, including both proprietary APIs and open-source models, as well as more than 80 different multi-modal benchmarks. By implementing a single interface, new models can be easily added to the toolkit, while the toolkit automatically handles the remaining workloads, including data preparation, distributed inference, prediction post-processing, and metric calculation. Although the toolkit is currently mainly used for evaluating large vision-language models, its design is compatible with future updates that incorporate additional modalities, such as audio and video. Based on the evaluation results obtained with the toolkit, we host OpenVLM Leaderboard, a comprehensive leaderboard to track the progress of multi-modality learning research. The toolkit is released on https://github.com/open-compass/VLMEvalKit and is actively maintained.

Haodong Duan, Nanxuan Zhao, Kai Chen et al. · pku

Recognizing transformation types applied to a video clip (RecogTrans) is a long-established paradigm for self-supervised video representation learning, which achieves much inferior performance compared to instance discrimination approaches (InstDisc) in recent works. However, based on a thorough comparison of representative RecogTrans and InstDisc methods, we observe the great potential of RecogTrans on both semantic-related and temporal-related downstream tasks. Based on hard-label classification, existing RecogTrans approaches suffer from noisy supervision signals in pre-training. To mitigate this problem, we developed TransRank, a unified framework for recognizing Transformations in a Ranking formulation. TransRank provides accurate supervision signals by recognizing transformations relatively, consistently outperforming the classification-based formulation. Meanwhile, the unified framework can be instantiated with an arbitrary set of temporal or spatial transformations, demonstrating good generality. With a ranking-based formulation and several empirical practices, we achieve competitive performance on video retrieval and action recognition. Under the same setting, TransRank surpasses the previous state-of-the-art method by 6.4% on UCF101 and 8.3% on HMDB51 for action recognition (Top1 Acc); improves video retrieval on UCF101 by 20.4% (R@1). The promising results validate that RecogTrans is still a worth exploring paradigm for video self-supervised learning. Codes will be released at https://github.com/kennymckormick/TransRank.

Pan Zhang, Xiaoyi Dong, Yuhang Zang et al. · pku

We present InternLM-XComposer-2.5 (IXC-2.5), a versatile large-vision language model that supports long-contextual input and output. IXC-2.5 excels in various text-image comprehension and composition applications, achieving GPT-4V level capabilities with merely 7B LLM backend. Trained with 24K interleaved image-text contexts, it can seamlessly extend to 96K long contexts via RoPE extrapolation. This long-context capability allows IXC-2.5 to excel in tasks requiring extensive input and output contexts. Compared to its previous 2.0 version, InternLM-XComposer-2.5 features three major upgrades in vision-language comprehension: (1) Ultra-High Resolution Understanding, (2) Fine-Grained Video Understanding, and (3) Multi-Turn Multi-Image Dialogue. In addition to comprehension, IXC-2.5 extends to two compelling applications using extra LoRA parameters for text-image composition: (1) Crafting Webpages and (2) Composing High-Quality Text-Image Articles. IXC-2.5 has been evaluated on 28 benchmarks, outperforming existing open-source state-of-the-art models on 16 benchmarks. It also surpasses or competes closely with GPT-4V and Gemini Pro on 16 key tasks. The InternLM-XComposer-2.5 is publicly available at https://github.com/InternLM/InternLM-XComposer.

Yujie Zhou, Haodong Duan, Anyi Rao et al. · pku

Self-supervised learning has demonstrated remarkable capability in representation learning for skeleton-based action recognition. Existing methods mainly focus on applying global data augmentation to generate different views of the skeleton sequence for contrastive learning. However, due to the rich action clues in the skeleton sequences, existing methods may only take a global perspective to learn to discriminate different skeletons without thoroughly leveraging the local relationship between different skeleton joints and video frames, which is essential for real-world applications. In this work, we propose a Partial Spatio-Temporal Learning (PSTL) framework to exploit the local relationship from a partial skeleton sequences built by a unique spatio-temporal masking strategy. Specifically, we construct a negative-sample-free triplet steam structure that is composed of an anchor stream without any masking, a spatial masking stream with Central Spatial Masking (CSM), and a temporal masking stream with Motion Attention Temporal Masking (MATM). The feature cross-correlation matrix is measured between the anchor stream and the other two masking streams, respectively. (1) Central Spatial Masking discards selected joints from the feature calculation process, where the joints with a higher degree of centrality have a higher possibility of being selected. (2) Motion Attention Temporal Masking leverages the motion of action and remove frames that move faster with a higher possibility. Our method achieves SOTA performance on NTU-60, NTU-120 and PKU-MMD under various downstream tasks. A practical evaluation is performed where some skeleton joints are lost in downstream tasks. In contrast to previous methods that suffer from large performance drops, our PSTL can still achieve remarkable results, validating the robustness of our method. Code: https://github.com/YujieOuO/PSTL.git.

Haodong Duan, Jueqi Wei, Chonghua Wang et al. · pku

Interacting with human via high-quality multi-turn dialogues is a key feature of large language models (LLMs). However, human-based evaluation of such capability involves intensive manual labor. This report provides a preliminary evaluation of existing large language models for human-style multi-turn chatting, through an LLM-based approach. We start from real-world human dialogues and keep the very first utterances as the ChatSEED. Then we prompt LLMs to generate a full multi-turn dialogue (tens of utterances) based on the ChatSEED, utterance by utterance. Finally, we adopt state-of-the-art LLMs (GPT-4, \etc) as the judge to evaluate the generated dialogues. With different evaluation protocols, we come to substantially identical conclusions. We find that GPT-4 can generate human-style multi-turn dialogues with impressive quality, significantly outperforms its counterparts. It's difficult for a discriminator to distinguish between GPT-4 generated dialogues and human dialogues. In contrast, other LLMs struggle to generate multi-turn dialogues of satisfactory quality due to poor instruction-following capability, tendency to generate lengthy utterances, or limited general capability. All data and codes will be provided in https://github.com/open-compass/BotChat/ and we hope they can serve as a valuable resource for evaluating multi-turn chatting capabilities of LLMs.

Keqiang Sun, Junting Pan, Yuying Ge et al. · pku

While recent advancements in vision-language models have had a transformative impact on multi-modal comprehension, the extent to which these models possess the ability to comprehend generated images remains uncertain. Synthetic images, in comparison to real data, encompass a higher level of diversity in terms of both content and style, thereby presenting significant challenges for the models to fully grasp. In light of this challenge, we introduce a comprehensive dataset, referred to as JourneyDB, that caters to the domain of generative images within the context of multi-modal visual understanding. Our meticulously curated dataset comprises 4 million distinct and high-quality generated images, each paired with the corresponding text prompts that were employed in their creation. Furthermore, we additionally introduce an external subset with results of another 22 text-to-image generative models, which makes JourneyDB a comprehensive benchmark for evaluating the comprehension of generated images. On our dataset, we have devised four benchmarks to assess the performance of generated image comprehension in relation to both content and style interpretation. These benchmarks encompass prompt inversion, style retrieval, image captioning, and visual question answering. Lastly, we evaluate the performance of state-of-the-art multi-modal models when applied to the JourneyDB dataset, providing a comprehensive analysis of their strengths and limitations in comprehending generated content. We anticipate that the proposed dataset and benchmarks will facilitate further research in the field of generative content understanding. The dataset is publicly available at https://journeydb.github.io.

Mo Li, Songyang Zhang, Taolin Zhang et al. · pku

The capability of large language models to handle long-context information is crucial across various real-world applications. Existing evaluation methods often rely either on real-world long texts, making it difficult to exclude the influence of models' inherent knowledge, or introduce irrelevant filler content to artificially achieve target lengths, reducing assessment effectiveness. To address these limitations, we introduce NeedleBench, a synthetic framework for assessing retrieval and reasoning performance in bilingual long-context tasks with adaptive context lengths. NeedleBench systematically embeds key data points at varying depths to rigorously test model capabilities. Tasks are categorized into two scenarios: information-sparse, featuring minimal relevant details within extensive irrelevant text to simulate simple retrieval tasks; and information-dense (the Ancestral Trace Challenge), where relevant information is continuously distributed throughout the context to simulate complex reasoning tasks. Our experiments reveal that although recent reasoning models like Deepseek-R1 and OpenAI's o3 excel in mathematical reasoning, they struggle with continuous retrieval and reasoning in information-dense scenarios, even at shorter context lengths. We also characterize a phenomenon termed 'under-thinking', where models prematurely conclude reasoning despite available information. NeedleBench thus provides critical insights and targeted tools essential for evaluating and improving LLMs' long-context capabilities. All resources are available at OpenCompass: https://github.com/open-compass/opencompass.

Haodong Duan, Jiaqi Wang, Kai Chen et al. · pku

Graph convolution networks (GCN) have been widely used in skeleton-based action recognition. We note that existing GCN-based approaches primarily rely on prescribed graphical structures (ie., a manually defined topology of skeleton joints), which limits their flexibility to capture complicated correlations between joints. To move beyond this limitation, we propose a new framework for skeleton-based action recognition, namely Dynamic Group Spatio-Temporal GCN (DG-STGCN). It consists of two modules, DG-GCN and DG-TCN, respectively, for spatial and temporal modeling. In particular, DG-GCN uses learned affinity matrices to capture dynamic graphical structures instead of relying on a prescribed one, while DG-TCN performs group-wise temporal convolutions with varying receptive fields and incorporates a dynamic joint-skeleton fusion module for adaptive multi-level temporal modeling. On a wide range of benchmarks, including NTURGB+D, Kinetics-Skeleton, BABEL, and Toyota SmartHome, DG-STGCN consistently outperforms state-of-the-art methods, often by a notable margin.

Haodong Duan, Yue Zhao, Kai Chen et al. · pku

Deep learning models have achieved excellent recognition results on large-scale video benchmarks. However, they perform poorly when applied to videos with rare scenes or objects, primarily due to the bias of existing video datasets. We tackle this problem from two different angles: algorithm and dataset. From the perspective of algorithms, we propose Spatial-aware Multi-Aspect Debiasing (SMAD), which incorporates both explicit debiasing with multi-aspect adversarial training and implicit debiasing with the spatial actionness reweighting module, to learn a more generic representation invariant to non-action aspects. To neutralize the intrinsic dataset bias, we propose OmniDebias to leverage web data for joint training selectively, which can achieve higher performance with far fewer web data. To verify the effectiveness, we establish evaluation protocols and perform extensive experiments on both re-distributed splits of existing datasets and a new evaluation dataset focusing on the action with rare scenes. We also show that the debiased representation can generalize better when transferred to other datasets and tasks.

Pengcheng Chen, Jin Ye, Guoan Wang et al. · pku

Large Vision-Language Models (LVLMs) are capable of handling diverse data types such as imaging, text, and physiological signals, and can be applied in various fields. In the medical field, LVLMs have a high potential to offer substantial assistance for diagnosis and treatment. Before that, it is crucial to develop benchmarks to evaluate LVLMs' effectiveness in various medical applications. Current benchmarks are often built upon specific academic literature, mainly focusing on a single domain, and lacking varying perceptual granularities. Thus, they face specific challenges, including limited clinical relevance, incomplete evaluations, and insufficient guidance for interactive LVLMs. To address these limitations, we developed the GMAI-MMBench, the most comprehensive general medical AI benchmark with well-categorized data structure and multi-perceptual granularity to date. It is constructed from 284 datasets across 38 medical image modalities, 18 clinical-related tasks, 18 departments, and 4 perceptual granularities in a Visual Question Answering (VQA) format. Additionally, we implemented a lexical tree structure that allows users to customize evaluation tasks, accommodating various assessment needs and substantially supporting medical AI research and applications. We evaluated 50 LVLMs, and the results show that even the advanced GPT-4o only achieves an accuracy of 53.96%, indicating significant room for improvement. Moreover, we identified five key insufficiencies in current cutting-edge LVLMs that need to be addressed to advance the development of better medical applications. We believe that GMAI-MMBench will stimulate the community to build the next generation of LVLMs toward GMAI.

Zhongying Deng, Cheng Tang, Ziyan Huang et al. · pku

Foundation models have demonstrated remarkable success across diverse domains and tasks, primarily due to the thrive of large-scale, diverse, and high-quality datasets. However, in the field of medical imaging, the curation and assembling of such medical datasets are highly challenging due to the reliance on clinical expertise and strict ethical and privacy constraints, resulting in a scarcity of large-scale unified medical datasets and hindering the development of powerful medical foundation models. In this work, we present the largest survey to date of medical image datasets, covering over 1,000 open-access datasets with a systematic catalog of their modalities, tasks, anatomies, annotations, limitations, and potential for integration. Our analysis exposes a landscape that is modest in scale, fragmented across narrowly scoped tasks, and unevenly distributed across organs and modalities, which in turn limits the utility of existing medical image datasets for developing versatile and robust medical foundation models. To turn fragmentation into scale, we propose a metadata-driven fusion paradigm (MDFP) that integrates public datasets with shared modalities or tasks, thereby transforming multiple small data silos into larger, more coherent resources. Building on MDFP, we release an interactive discovery portal that enables end-to-end, automated medical image dataset integration, and compile all surveyed datasets into a unified, structured table that clearly summarizes their key characteristics and provides reference links, offering the community an accessible and comprehensive repository. By charting the current terrain and offering a principled path to dataset consolidation, our survey provides a practical roadmap for scaling medical imaging corpora, supporting faster data discovery, more principled dataset creation, and more capable medical foundation models.

Yu Miao, Zequn Yang, Yake Wei et al. · pku

In different multimodal scenarios, it needs to integrate and utilize information across modalities in a specific way based on the demands of the task. Different integration ways between modalities are referred to as "multimodal interaction". How well a model handles various multimodal interactions largely characterizes its multimodal ability. In this paper, we introduce MIBench, a comprehensive benchmark designed to evaluate the multimodal interaction capabilities of Large Multimodal Models (LMMs), which formulates each instance as a (con_v , con_t, task) triplet with contexts from vision and text, necessitating that LMMs employ correct forms of multimodal interaction to effectively complete the task. MIBench assesses models from three key aspects: the ability to source information from vision-centric or text-centric cues, and the ability to generate new information from their joint synergy. Each interaction capability is evaluated hierarchically across three cognitive levels: Recognition, Understanding, and Reasoning. MIBench comprises over 10,000 vision-text context pairs spanning 32 distinct tasks. Evaluation of state-of-the-art LMMs show that: (1) LMMs' ability on multimodal interaction remains constrained, despite the scaling of model parameters and training data; (2) they are easily distracted by textual modalities when processing vision information; (3) they mostly possess a basic capacity for multimodal synergy; and (4) natively trained multimodal models show noticeable deficits in fundamental interaction ability. We expect that these observations can serve as a reference for developing LMMs with more enhanced multimodal ability in the future.

Maosong Cao, Kai Chen, Haodong Duan et al.

In recent years, the field of artificial intelligence has undergone a paradigm shift from task-specific small-scale models to general-purpose large language models (LLMs). With the rapid iteration of LLMs, objective, quantitative, and comprehensive evaluation of their capabilities has become a critical link in advancing technological development. Currently, the mainstream static benchmark dataset-based evaluation methods face challenges such as the diversity of task types, inconsistent evaluation criteria, and fragmentation of data and processing workflows, making it difficult to efficiently conduct cross-domain and large-scale model evaluation. To address the aforementioned issues, this paper proposes and open-sources OpenCompass, a one-stop, scalable, and high-concurrency-supported general-purpose LLM evaluation platform. Adhering to the design philosophy of modularization and component decoupling, the platform boasts three core advantages: high compatibility, flexibility, and high concurrency. The core architecture of OpenCompass comprises five key components: the Configuration System, Task Partitioning Module, Execution and Scheduling Module, Task Execution Unit, and Result Visualization Module. Its workflow provides rule-based, LLM-as-a-Judge, and cascaded evaluators to adapt to the requirements of different task scenarios. Supporting mainstream benchmark datasets across multiple domains, including knowledge, reasoning, computation, science, language, code, etc., the platform offers a unified and efficient LLM evaluation tool for both academia and industry, facilitating the accurate identification of strengths and weaknesses of LLMs as well as their subsequent optimization.

Yiheng Wang, Yixin Chen, Shuo Li et al.

We introduce SciEvalKit, a unified benchmarking toolkit designed to evaluate AI models for science across a broad range of scientific disciplines and task capabilities. Unlike general-purpose evaluation platforms, SciEvalKit focuses on the core competencies of scientific intelligence, including Scientific Multimodal Perception, Scientific Multimodal Reasoning, Scientific Multimodal Understanding, Scientific Symbolic Reasoning, Scientific Code Generation, Science Hypothesis Generation and Scientific Knowledge Understanding. It supports six major scientific domains, spanning from physics and chemistry to astronomy and materials science. SciEvalKit builds a foundation of expert-grade scientific benchmarks, curated from real-world, domain-specific datasets, ensuring that tasks reflect authentic scientific challenges. The toolkit features a flexible, extensible evaluation pipeline that enables batch evaluation across models and datasets, supports custom model and dataset integration, and provides transparent, reproducible, and comparable results. By bridging capability-based evaluation and disciplinary diversity, SciEvalKit offers a standardized yet customizable infrastructure to benchmark the next generation of scientific foundation models and intelligent agents. The toolkit is open-sourced and actively maintained to foster community-driven development and progress in AI4Science.

Xiaoyi Dong, Pan Zhang, Yuhang Zang et al. · pku

We introduce InternLM-XComposer2, a cutting-edge vision-language model excelling in free-form text-image composition and comprehension. This model goes beyond conventional vision-language understanding, adeptly crafting interleaved text-image content from diverse inputs like outlines, detailed textual specifications, and reference images, enabling highly customizable content creation. InternLM-XComposer2 proposes a Partial LoRA (PLoRA) approach that applies additional LoRA parameters exclusively to image tokens to preserve the integrity of pre-trained language knowledge, striking a balance between precise vision understanding and text composition with literary talent. Experimental results demonstrate the superiority of InternLM-XComposer2 based on InternLM2-7B in producing high-quality long-text multi-modal content and its exceptional vision-language understanding performance across various benchmarks, where it not only significantly outperforms existing multimodal models but also matches or even surpasses GPT-4V and Gemini Pro in certain assessments. This highlights its remarkable proficiency in the realm of multimodal understanding. The InternLM-XComposer2 model series with 7B parameters are publicly available at https://github.com/InternLM/InternLM-XComposer.

Zheng Cai, Maosong Cao, Haojiong Chen et al. · pku

The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI). However, replicating such advancements in open-source models has been challenging. This paper introduces InternLM2, an open-source LLM that outperforms its predecessors in comprehensive evaluations across 6 dimensions and 30 benchmarks, long-context modeling, and open-ended subjective evaluations through innovative pre-training and optimization techniques. The pre-training process of InternLM2 is meticulously detailed, highlighting the preparation of diverse data types including text, code, and long-context data. InternLM2 efficiently captures long-term dependencies, initially trained on 4k tokens before advancing to 32k tokens in pre-training and fine-tuning stages, exhibiting remarkable performance on the 200k ``Needle-in-a-Haystack" test. InternLM2 is further aligned using Supervised Fine-Tuning (SFT) and a novel Conditional Online Reinforcement Learning from Human Feedback (COOL RLHF) strategy that addresses conflicting human preferences and reward hacking. By releasing InternLM2 models in different training stages and model sizes, we provide the community with insights into the model's evolution.

Ziyu Liu, Zeyi Sun, Yuhang Zang et al. · pku

Reinforcement Fine-Tuning (RFT) in Large Reasoning Models like OpenAI o1 learns from feedback on its answers, which is especially useful in applications when fine-tuning data is scarce. Recent open-source work like DeepSeek-R1 demonstrates that reinforcement learning with verifiable reward is one key direction in reproducing o1. While the R1-style model has demonstrated success in language models, its application in multi-modal domains remains under-explored. This work introduces Visual Reinforcement Fine-Tuning (Visual-RFT), which further extends the application areas of RFT on visual tasks. Specifically, Visual-RFT first uses Large Vision-Language Models (LVLMs) to generate multiple responses containing reasoning tokens and final answers for each input, and then uses our proposed visual perception verifiable reward functions to update the model via the policy optimization algorithm such as Group Relative Policy Optimization (GRPO). We design different verifiable reward functions for different perception tasks, such as the Intersection over Union (IoU) reward for object detection. Experimental results on fine-grained image classification, few-shot object detection, reasoning grounding, as well as open-vocabulary object detection benchmarks show the competitive performance and advanced generalization ability of Visual-RFT compared with Supervised Fine-tuning (SFT). For example, Visual-RFT improves accuracy by $24.3\%$ over the baseline in one-shot fine-grained image classification with around 100 samples. In few-shot object detection, Visual-RFT also exceeds the baseline by $21.9$ on COCO's two-shot setting and $15.4$ on LVIS. Our Visual-RFT represents a paradigm shift in fine-tuning LVLMs, offering a data-efficient, reward-driven approach that enhances reasoning and adaptability for domain-specific tasks.

Yuhong Liu, Beichen Zhang, Yuhang Zang et al.

Spatial understanding remains a weakness of Large Vision-Language Models (LVLMs). Existing supervised fine-tuning (SFT) and recent reinforcement learning with verifiable rewards (RLVR) pipelines depend on costly supervision, specialized tools, or constrained environments that limit scale. We introduce Spatial-SSRL, a self-supervised RL paradigm that derives verifiable signals directly from ordinary RGB or RGB-D images. Spatial-SSRL automatically formulates five pretext tasks that capture 2D and 3D spatial structure: shuffled patch reordering, flipped patch recognition, cropped patch inpainting, regional depth ordering, and relative 3D position prediction. These tasks provide ground-truth answers that are easy to verify and require no human or LVLM annotation. Training on our tasks substantially improves spatial reasoning while preserving general visual capabilities. On seven spatial understanding benchmarks in both image and video settings, Spatial-SSRL delivers average accuracy gains of 4.63% (3B) and 3.89% (7B) over the Qwen2.5-VL baselines. Our results show that simple, intrinsic supervision enables RLVR at scale and provides a practical route to stronger spatial intelligence in LVLMs.

Aaron Branson Cigres Li, Zhaowei Wang, Yu Zhao et al.

Large vision-language models increasingly rely on long-context modeling to reason over documents, hour-level videos, and long-horizon agent trajectories, requiring them to locate relevant evidence across interleaved text and images. Prior work has studied this behavior using retrieval heads in large language models, but its copy-based criterion does not directly apply when evidence appears in images. We introduce a multimodal retrieval head detection method that scores attention from question tokens to textual or visual evidence. With this method, we show that multimodal retrieval heads are sparse, intrinsic, and causally important: only 4.4-10.2% of attention heads account for 50% of the positive retrieval-score mass, and masking the top-5% selected heads drops MMLongBench-Doc from 48.2% to 5.7% and SlideVQA from 71.2% to 8.9%, while random-head masking is far less damaging. Further analysis shows that these heads are partly shared across modalities yet remain dynamic within each modality, with image retrieval heads changing more than text retrieval heads as context length and haystack modality change. Without further training, we find that these heads can also be used directly to rank visually rich documents: on MMDocIR, Qwen3-VL-8B selected-head scoring improves Recall@1 by 7.7/7.4 macro/micro points for page retrieval and 6.3/6.8 points for layout retrieval over the strongest reported baseline.

Xiaoyi Dong, Pan Zhang, Yuhang Zang et al. · pku

The Large Vision-Language Model (LVLM) field has seen significant advancements, yet its progression has been hindered by challenges in comprehending fine-grained visual content due to limited resolution. Recent efforts have aimed to enhance the high-resolution understanding capabilities of LVLMs, yet they remain capped at approximately 1500 x 1500 pixels and constrained to a relatively narrow resolution range. This paper represents InternLM-XComposer2-4KHD, a groundbreaking exploration into elevating LVLM resolution capabilities up to 4K HD (3840 x 1600) and beyond. Concurrently, considering the ultra-high resolution may not be necessary in all scenarios, it supports a wide range of diverse resolutions from 336 pixels to 4K standard, significantly broadening its scope of applicability. Specifically, this research advances the patch division paradigm by introducing a novel extension: dynamic resolution with automatic patch configuration. It maintains the training image aspect ratios while automatically varying patch counts and configuring layouts based on a pre-trained Vision Transformer (ViT) (336 x 336), leading to dynamic training resolution from 336 pixels to 4K standard. Our research demonstrates that scaling training resolution up to 4K HD leads to consistent performance enhancements without hitting the ceiling of potential improvements. InternLM-XComposer2-4KHD shows superb capability that matches or even surpasses GPT-4V and Gemini Pro in 10 of the 16 benchmarks. The InternLM-XComposer2-4KHD model series with 7B parameters are publicly available at https://github.com/InternLM/InternLM-XComposer.

Weiyun Wang, Zhangwei Gao, Lixin Gu et al. · cmu, pku

We introduce InternVL 3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0\% gain in overall reasoning performance and a 4.05$\times$ inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks -- narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.

Hongwei Liu, Zilong Zheng, Yuxuan Qiao et al. · pku

Recent advancements in large language models (LLMs) have showcased significant improvements in mathematics. However, traditional math benchmarks like GSM8k offer a unidimensional perspective, falling short in providing a holistic assessment of the LLMs' math capabilities. To address this gap, we introduce MathBench, a new benchmark that rigorously assesses the mathematical capabilities of large language models. MathBench spans a wide range of mathematical disciplines, offering a detailed evaluation of both theoretical understanding and practical problem-solving skills. The benchmark progresses through five distinct stages, from basic arithmetic to college mathematics, and is structured to evaluate models at various depths of knowledge. Each stage includes theoretical questions and application problems, allowing us to measure a model's mathematical proficiency and its ability to apply concepts in practical scenarios. MathBench aims to enhance the evaluation of LLMs' mathematical abilities, providing a nuanced view of their knowledge understanding levels and problem solving skills in a bilingual context. The project is released at https://github.com/open-compass/MathBench .

Jingming Zhuo, Songyang Zhang, Xinyu Fang et al. · pku

Large language models (LLMs) have demonstrated impressive capabilities across various tasks, but their performance is highly sensitive to the prompts utilized. This variability poses challenges for accurate assessment and user satisfaction. Current research frequently overlooks instance-level prompt variations and their implications on subjective evaluations. To address these shortcomings, we introduce ProSA, a framework designed to evaluate and comprehend prompt sensitivity in LLMs. ProSA incorporates a novel sensitivity metric, PromptSensiScore, and leverages decoding confidence to elucidate underlying mechanisms. Our extensive study, spanning multiple tasks, uncovers that prompt sensitivity fluctuates across datasets and models, with larger models exhibiting enhanced robustness. We observe that few-shot examples can alleviate this sensitivity issue, and subjective evaluations are also susceptible to prompt sensitivities, particularly in complex, reasoning-oriented tasks. Furthermore, our findings indicate that higher model confidence correlates with increased prompt robustness. We believe this work will serve as a helpful tool in studying prompt sensitivity of LLMs. The project is released at: https://github.com/open-compass/ProSA .

Shengyuan Ding, Xinyu Fang, Ziyu Liu et al.

Reward models are critical for aligning vision-language systems with human preferences, yet current approaches suffer from hallucination, weak visual grounding, and an inability to use tools for verification, limiting their reliability on complex multimodal reasoning tasks. We present ARM-Thinker, an A}gentic multimodal Reward Model that autonomously invokes external tools (e.g., image cropping, doc page retrieval) to ground judgments in verifiable evidence, replacing static, non-interactive reward scoring. This enables the model to verify fine-grained visual details, cross-reference multi-page evidence, and validate reasoning claims, which are capabilities absent in existing reward models. We train ARM-Thinker with multi-stage reinforcement learning, jointly optimizing tool-calling decisions and judgment accuracy. To evaluate agentic reward modeling, we introduce ARMBench-VL, comprising three benchmarks that assess fine-grained visual grounding (image-level tools), multi-page document understanding (retrieval tools), and instruction following (text-level verification). ARM-Thinker achieves +16.2% average improvement on reward modeling benchmarks, +9.6% on tool-use tasks, and outperforms baselines on multimodal math and logical reasoning benchmarks. Our results demonstrate that agentic capabilities significantly enhance both accuracy and interpretability of reward models.

Xiaozhe Li, Jixuan Chen, Xinyu Fang et al.

Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and tool use. However, the fundamental cognitive faculties essential for problem solving, including perception, reasoning, and memory, remain the stable core of intelligence. Unlike memorizing specific patterns, humans succeed in novel environments by applying these intrinsic faculties to adapt and optimize. Yet, whether LLMs possess this essential capacity, namely the ability to continuously refine solutions in response to dynamic environmental feedback, remains underexplored. To address this challenge, we introduce OPT-BENCH, a benchmark for evaluating self-improvement capabilities in large-scale search spaces. By combining 20 machine learning tasks with 10 classic NP-hard problems, OPT-BENCH provides a rigorous setting to assess whether agents can adapt through intrinsic self-reflection rather than rote tool application. We further propose OPT-Agent, a framework that emulates human-like cognitive adaptation. It operates through a general perception, memory, and reasoning loop, iteratively refining solutions based on environmental feedback. Through extensive experiments on 19 LLMs from 7 model families, including reasoning models, general models, and open-source models ranging from 3B to 235B parameters, we demonstrate that stronger models are more effective at leveraging feedback signals for self-improvement. However, this upper-bound adaptability remains fundamentally constrained by the models' base capacity, and even the most advanced LLMs still fall short of human expert performance.

Haodong Duan, Mingze Xu, Bing Shuai et al.

We present SkeleTR, a new framework for skeleton-based action recognition. In contrast to prior work, which focuses mainly on controlled environments, we target more general scenarios that typically involve a variable number of people and various forms of interaction between people. SkeleTR works with a two-stage paradigm. It first models the intra-person skeleton dynamics for each skeleton sequence with graph convolutions, and then uses stacked Transformer encoders to capture person interactions that are important for action recognition in general scenarios. To mitigate the negative impact of inaccurate skeleton associations, SkeleTR takes relative short skeleton sequences as input and increases the number of sequences. As a unified solution, SkeleTR can be directly applied to multiple skeleton-based action tasks, including video-level action classification, instance-level action detection, and group-level activity recognition. It also enables transfer learning and joint training across different action tasks and datasets, which result in performance improvement. When evaluated on various skeleton-based action recognition benchmarks, SkeleTR achieves the state-of-the-art performance.

Yuhang Zang, Xiaoyi Dong, Pan Zhang et al. · pku

Despite the promising performance of Large Vision Language Models (LVLMs) in visual understanding, they occasionally generate incorrect outputs. While reward models (RMs) with reinforcement learning or test-time scaling offer the potential for improving generation quality, a critical gap remains: publicly available multi-modal RMs for LVLMs are scarce, and the implementation details of proprietary models are often unclear. We bridge this gap with InternLM-XComposer2.5-Reward (IXC-2.5-Reward), a simple yet effective multi-modal reward model that aligns LVLMs with human preferences. To ensure the robustness and versatility of IXC-2.5-Reward, we set up a high-quality multi-modal preference corpus spanning text, image, and video inputs across diverse domains, such as instruction following, general understanding, text-rich documents, mathematical reasoning, and video understanding. IXC-2.5-Reward achieves excellent results on the latest multi-modal reward model benchmark and shows competitive performance on text-only reward model benchmarks. We further demonstrate three key applications of IXC-2.5-Reward: (1) Providing a supervisory signal for RL training. We integrate IXC-2.5-Reward with Proximal Policy Optimization (PPO) yields IXC-2.5-Chat, which shows consistent improvements in instruction following and multi-modal open-ended dialogue; (2) Selecting the best response from candidate responses for test-time scaling; and (3) Filtering outlier or noisy samples from existing image and video instruction tuning training data. To ensure reproducibility and facilitate further research, we have open-sourced all model weights and training recipes at https://github.com/InternLM/InternLM-XComposer/tree/main/InternLM-XComposer-2.5-Reward

Maosong Cao, Alexander Lam, Haodong Duan et al. · pku

Efficient and accurate evaluation is crucial for the continuous improvement of large language models (LLMs). Among various assessment methods, subjective evaluation has garnered significant attention due to its superior alignment with real-world usage scenarios and human preferences. However, human-based evaluations are costly and lack reproducibility, making precise automated evaluators (judgers) vital in this process. In this report, we introduce \textbf{CompassJudger-1}, the first open-source \textbf{all-in-one} judge LLM. CompassJudger-1 is a general-purpose LLM that demonstrates remarkable versatility. It is capable of: 1. Performing unitary scoring and two-model comparisons as a reward model; 2. Conducting evaluations according to specified formats; 3. Generating critiques; 4. Executing diverse tasks like a general LLM. To assess the evaluation capabilities of different judge models under a unified setting, we have also established \textbf{JudgerBench}, a new benchmark that encompasses various subjective evaluation tasks and covers a wide range of topics. CompassJudger-1 offers a comprehensive solution for various evaluation tasks while maintaining the flexibility to adapt to diverse requirements. Both CompassJudger and JudgerBench are released and available to the research community athttps://github.com/open-compass/CompassJudger. We believe that by open-sourcing these tools, we can foster collaboration and accelerate progress in LLM evaluation methodologies.

Chonghua Wang, Haodong Duan, Songyang Zhang et al. · pku

Recently, the large language model (LLM) community has shown increasing interest in enhancing LLMs' capability to handle extremely long documents. As various long-text techniques and model architectures emerge, the precise and detailed evaluation of models' long-text capabilities has become increasingly important. Existing long-text evaluation benchmarks, such as L-Eval and LongBench, construct long-text test sets based on open-source datasets, focusing mainly on QA and summarization tasks. These datasets include test samples of varying lengths (from 2k to 32k+) entangled together, making it challenging to assess model capabilities across different length ranges. Moreover, they do not cover the ultralong settings (100k+ tokens) that the latest LLMs claim to achieve. In this paper, we introduce Ada-LEval, a length-adaptable benchmark for evaluating the long-context understanding of LLMs. Ada-LEval includes two challenging subsets, TSort and BestAnswer, which enable a more reliable evaluation of LLMs' long context capabilities. These benchmarks support intricate manipulation of the length of test cases, and can easily produce text samples up to 128k tokens. We evaluate 4 state-of-the-art closed-source API models and 6 open-source models with Ada-LEval. The evaluation results demonstrate the limitations of current LLMs, especially in ultra-long-context settings. Our code is available at https://github.com/open-compass/Ada-LEval.

Xilin Wei, Xiaoran Liu, Yuhang Zang et al. · pku

While Rotary Position Embedding (RoPE) and its variants are widely adopted for their long-context capabilities, the extension of the 1D RoPE to video, with its complex spatio-temporal structure, remains an open challenge. This work first introduces a comprehensive analysis that identifies four key characteristics essential for the effective adaptation of RoPE to video, which have not been fully considered in prior work. As part of our analysis, we introduce a challenging V-NIAH-D (Visual Needle-In-A-Haystack with Distractors) task, which adds periodic distractors into V-NIAH. The V-NIAH-D task demonstrates that previous RoPE variants, lacking appropriate temporal dimension allocation, are easily misled by distractors. Based on our analysis, we introduce \textbf{VideoRoPE}, with a \textit{3D structure} designed to preserve spatio-temporal relationships. VideoRoPE features \textit{low-frequency temporal allocation} to mitigate periodic oscillations, a \textit{diagonal layout} to maintain spatial symmetry, and \textit{adjustable temporal spacing} to decouple temporal and spatial indexing. VideoRoPE consistently surpasses previous RoPE variants, across diverse downstream tasks such as long video retrieval, video understanding, and video hallucination. Our code will be available at \href{https://github.com/Wiselnn570/VideoRoPE}{https://github.com/Wiselnn570/VideoRoPE}.

Yifei Li, Junbo Niu, Ziyang Miao et al. · pku, tsinghua

Temporal Awareness, the ability to reason dynamically based on the timestamp when a question is raised, is the key distinction between offline and online video LLMs. Unlike offline models, which rely on complete videos for static, post hoc analysis, online models process video streams incrementally and dynamically adapt their responses based on the timestamp at which the question is posed. Despite its significance, temporal awareness has not been adequately evaluated in existing benchmarks. To fill this gap, we present OVO-Bench (Online-VideO-Benchmark), a novel video benchmark that emphasizes the importance of timestamps for advanced online video understanding capability benchmarking. OVO-Bench evaluates the ability of video LLMs to reason and respond to events occurring at specific timestamps under three distinct scenarios: (1) Backward tracing: trace back to past events to answer the question. (2) Real-time understanding: understand and respond to events as they unfold at the current timestamp. (3) Forward active responding: delay the response until sufficient future information becomes available to answer the question accurately. OVO-Bench comprises 12 tasks, featuring 644 unique videos and approximately human-curated 2,800 fine-grained meta-annotations with precise timestamps. We combine automated generation pipelines with human curation. With these high-quality samples, we further developed an evaluation pipeline to systematically query video LLMs along the video timeline. Evaluations of nine Video-LLMs reveal that, despite advancements on traditional benchmarks, current models struggle with online video understanding, showing a significant gap compared to human agents. We hope OVO-Bench will drive progress in video LLMs and inspire future research in online video reasoning. Our benchmark and code can be accessed at https://github.com/JoeLeelyf/OVO-Bench.

Sihan Yang, Runsen Xu, Yiman Xie et al. · pku

Spatial intelligence is essential for multimodal large language models (MLLMs) operating in the complex physical world. Existing benchmarks, however, probe only single-image relations and thus fail to assess the multi-image spatial reasoning that real-world deployments demand. We introduce MMSI-Bench, a VQA benchmark dedicated to multi-image spatial intelligence. Six 3D-vision researchers spent more than 300 hours meticulously crafting 1,000 challenging, unambiguous multiple-choice questions from over 120,000 images, each paired with carefully designed distractors and a step-by-step reasoning process. We conduct extensive experiments and thoroughly evaluate 34 open-source and proprietary MLLMs, observing a wide gap: the strongest open-source model attains roughly 30% accuracy and OpenAI's o3 reasoning model reaches 40%, while humans score 97%. These results underscore the challenging nature of MMSI-Bench and the substantial headroom for future research. Leveraging the annotated reasoning processes, we also provide an automated error analysis pipeline that diagnoses four dominant failure modes, including (1) grounding errors, (2) overlap-matching and scene-reconstruction errors, (3) situation-transformation reasoning errors, and (4) spatial-logic errors, offering valuable insights for advancing multi-image spatial intelligence. Project page: https://runsenxu.com/projects/MMSI_Bench .

Lei Bai, Zhongrui Cai, Yuhang Cao et al.

In recent years, a plethora of open-source foundation models have emerged, achieving remarkable progress in some widely attended fields, with performance being quite close to that of closed-source models. However, in high-value but more challenging scientific professional fields, either the fields still rely on expert models, or the progress of general foundation models lags significantly compared to those in popular areas, far from sufficient for transforming scientific research and leaving substantial gap between open-source models and closed-source models in these scientific domains. To mitigate this gap and explore a step further toward Artificial General Intelligence (AGI), we introduce Intern-S1, a specialized generalist equipped with general understanding and reasoning capabilities with expertise to analyze multiple science modal data. Intern-S1 is a multimodal Mixture-of-Experts (MoE) model with 28 billion activated parameters and 241 billion total parameters, continually pre-trained on 5T tokens, including over 2.5T tokens from scientific domains. In the post-training stage, Intern-S1 undergoes offline and then online reinforcement learning (RL) in InternBootCamp, where we propose Mixture-of-Rewards (MoR) to synergize the RL training on more than 1000 tasks simultaneously. Through integrated innovations in algorithms, data, and training systems, Intern-S1 achieved top-tier performance in online RL training. On comprehensive evaluation benchmarks, Intern-S1 demonstrates competitive performance on general reasoning tasks among open-source models and significantly outperforms open-source models in scientific domains, surpassing closed-source state-of-the-art models in professional tasks, such as molecular synthesis planning, reaction condition prediction, predicting thermodynamic stabilities for crystals. Our models are available at https://huggingface.co/internlm/Intern-S1.

Xiangyu Zhao, Peiyuan Zhang, Kexian Tang et al. · pku

Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but they still face challenges in General Visual Editing, particularly in following complex instructions, preserving appearance consistency, and supporting flexible input formats. To study this gap, we introduce RISEBench, the first benchmark for evaluating Reasoning-Informed viSual Editing (RISE). RISEBench focuses on four key reasoning categories: Temporal, Causal, Spatial, and Logical Reasoning. We curate high-quality test cases for each category and propose an robust evaluation framework that assesses Instruction Reasoning, Appearance Consistency, and Visual Plausibility with both human judges and the LMM-as-a-judge approach. We conducted experiments evaluating nine prominent visual editing models, comprising both open-source and proprietary models. The evaluation results demonstrate that current models face significant challenges in reasoning-based editing tasks. Even the most powerful model evaluated, GPT-4o-Image, achieves an accuracy of merely 28.8%. RISEBench effectively highlights the limitations of contemporary editing models, provides valuable insights, and indicates potential future directions for the field of reasoning-aware visual editing. Our code and data have been released at https://github.com/PhoenixZ810/RISEBench.

Shengyuan Ding, Shenxi Wu, Xiangyu Zhao et al. · pku

The Instruction Following (IF) ability measures how well Multi-modal Large Language Models (MLLMs) understand exactly what users are telling them and whether they are doing it right. Existing multimodal instruction following training data is scarce, the benchmarks are simple with atomic instructions, and the evaluation strategies are imprecise for tasks demanding exact output constraints. To address this, we present MM-IFEngine, an effective pipeline to generate high-quality image-instruction pairs. Our MM-IFEngine pipeline yields large-scale, diverse, and high-quality training data MM-IFInstruct-23k, which is suitable for Supervised Fine-Tuning (SFT) and extended as MM-IFDPO-23k for Direct Preference Optimization (DPO). We further introduce MM-IFEval, a challenging and diverse multi-modal instruction-following benchmark that includes (1) both compose-level constraints for output responses and perception-level constraints tied to the input images, and (2) a comprehensive evaluation pipeline incorporating both rule-based assessment and judge model. We conduct SFT and DPO experiments and demonstrate that fine-tuning MLLMs on MM-IFInstruct-23k and MM-IFDPO-23k achieves notable gains on various IF benchmarks, such as MM-IFEval (+10.2$\%$), MIA (+7.6$\%$), and IFEval (+12.3$\%$). We have fully open-sourced the datasets (both SFT and DPO), evaluation code and training scripts at https://github.com/SYuan03/MM-IFEngine.

Ziyu Liu, Yuhang Zang, Yushan Zou et al. · pku

A key trend in Large Reasoning Models (e.g., OpenAI's o3) is the native agentic ability to use external tools such as web browsers for searching and writing/executing code for image manipulation to think with images. In the open-source research community, while significant progress has been made in language-only agentic abilities such as function calling and tool integration, the development of multi-modal agentic capabilities that involve truly thinking with images, and their corresponding benchmarks, are still less explored. This work highlights the effectiveness of Visual Agentic Reinforcement Fine-Tuning (Visual-ARFT) for enabling flexible and adaptive reasoning abilities for Large Vision-Language Models (LVLMs). With Visual-ARFT, open-source LVLMs gain the ability to browse websites for real-time information updates and write code to manipulate and analyze input images through cropping, rotation, and other image processing techniques. We also present a Multi-modal Agentic Tool Bench (MAT) with two settings (MAT-Search and MAT-Coding) designed to evaluate LVLMs' agentic search and coding abilities. Our experimental results demonstrate that Visual-ARFT outperforms its baseline by +18.6% F1 / +13.0% EM on MAT-Coding and +10.3% F1 / +8.7% EM on MAT-Search, ultimately surpassing GPT-4o. Visual-ARFT also achieves +29.3 F1% / +25.9% EM gains on existing multi-hop QA benchmarks such as 2Wiki and HotpotQA, demonstrating strong generalization capabilities. Our findings suggest that Visual-ARFT offers a promising path toward building robust and generalizable multimodal agents.

Jiahao Meng, Tan Yue, Qi Xu et al.

Recent video multimodal large language models achieve impressive results across various benchmarks. However, current evaluations suffer from two critical limitations: (1) inflated scores can mask deficiencies in fine-grained visual understanding and reasoning, and (2) answer correctness is often measured without verifying whether models identify the precise spatio-temporal evidence supporting their predictions. To address this, we present VideoZeroBench, a hierarchical benchmark designed for challenging long-video question answering that rigorously verifies spatio-temporal evidence. It comprises 500 manually annotated questions across 13 domains, paired with temporal intervals and spatial bounding boxes as evidence. To disentangle answering generation, temporal grounding, and spatial grounding, we introduce a five-level evaluation protocol that progressively tightens evidence requirements. Experiments show that even Gemini-3-Pro correctly answers fewer than 17% of questions under the standard end-to-end QA setting (Level-3). When grounding constraints are imposed, performance drops sharply: No model exceeds 1% accuracy when both correct answering and accurate spatio-temporal localization are required (Level-5), with most failing to achieve any correct grounded predictions. These results expose a significant gap between surface-level answer correctness and genuine evidence-based reasoning, revealing that grounded video understanding remains a bottleneck for long-video QA. We further analyze performance across minimal evidence spans, atomic abilities, and inference paradigms, providing insights for future research in grounded video reasoning. The benchmark and code will be made publicly available.

Xuehui Wang, Zhenyu Wu, JingJing Xie et al. · pku

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.

Xiangyu Zhao, Shengyuan Ding, Zicheng Zhang et al. · pku

Recent advancements in open-source multi-modal large language models (MLLMs) have primarily focused on enhancing foundational capabilities, leaving a significant gap in human preference alignment. This paper introduces OmniAlign-V, a comprehensive dataset of 200K high-quality training samples featuring diverse images, complex questions, and varied response formats to improve MLLMs' alignment with human preferences. We also present MM-AlignBench, a human-annotated benchmark specifically designed to evaluate MLLMs' alignment with human values. Experimental results show that finetuning MLLMs with OmniAlign-V, using Supervised Fine-Tuning (SFT) or Direct Preference Optimization (DPO), significantly enhances human preference alignment while maintaining or enhancing performance on standard VQA benchmarks, preserving their fundamental capabilities. Our datasets, benchmark, code and checkpoints have been released at https://github.com/PhoenixZ810/OmniAlign-V.

Zicheng Zhang, Xiangyu Zhao, Xinyu Fang et al. · pku

With the rapid iteration of Multi-modality Large Language Models (MLLMs) and the evolving demands of the field, the number of benchmarks produced annually has surged into the hundreds. The rapid growth has inevitably led to significant redundancy among benchmarks. Therefore, it is crucial to take a step back and critically assess the current state of redundancy and propose targeted principles for constructing effective MLLM benchmarks. In this paper, we focus on redundancy from three key perspectives: 1) Redundancy of benchmark capability dimensions, 2) Redundancy in the number of test questions, and 3) Cross-benchmark redundancy within specific domains. Through the comprehensive analysis over hundreds of MLLMs' performance across more than 20 benchmarks, we aim to quantitatively measure the level of redundancy lies in existing MLLM evaluations, provide valuable insights to guide the future development of MLLM benchmarks, and offer strategies to refine and address redundancy issues effectively. The code is available at https://github.com/zzc-1998/Benchmark-Redundancy.

Xinyu Fang, Zhijian Chen, Kai Lan et al. · pku

Creativity is a fundamental aspect of intelligence, involving the ability to generate novel and appropriate solutions across diverse contexts. While Large Language Models (LLMs) have been extensively evaluated for their creative capabilities, the assessment of Multimodal Large Language Models (MLLMs) in this domain remains largely unexplored. To address this gap, we introduce Creation-MMBench, a multimodal benchmark specifically designed to evaluate the creative capabilities of MLLMs in real-world, image-based tasks. The benchmark comprises 765 test cases spanning 51 fine-grained tasks. To ensure rigorous evaluation, we define instance-specific evaluation criteria for each test case, guiding the assessment of both general response quality and factual consistency with visual inputs. Experimental results reveal that current open-source MLLMs significantly underperform compared to proprietary models in creative tasks. Furthermore, our analysis demonstrates that visual fine-tuning can negatively impact the base LLM's creative abilities. Creation-MMBench provides valuable insights for advancing MLLM creativity and establishes a foundation for future improvements in multimodal generative intelligence. Full data and evaluation code is released on https://github.com/open-compass/Creation-MMBench.

Chunyi Li, Yuan Tian, Xiaoyue Ling et al.

Image Quality Assessment (IQA) based on human subjective preferences has undergone extensive research in the past decades. However, with the development of communication protocols, the visual data consumption volume of machines has gradually surpassed that of humans. For machines, the preference depends on downstream tasks such as segmentation and detection, rather than visual appeal. Considering the huge gap between human and machine visual systems, this paper proposes the topic: Image Quality Assessment for Machine Vision for the first time. Specifically, we (1) defined the subjective preferences of machines, including downstream tasks, test models, and evaluation metrics; (2) established the Machine Preference Database (MPD), which contains 2.25M fine-grained annotations and 30k reference/distorted image pair instances; (3) verified the performance of mainstream IQA algorithms on MPD. Experiments show that current IQA metrics are human-centric and cannot accurately characterize machine preferences. We sincerely hope that MPD can promote the evolution of IQA from human to machine preferences. Project page is on: https://github.com/lcysyzxdxc/MPD.

Xiaozhe Li, Jixuan Chen, Xinyu Fang et al. · pku

Large Language Models (LLMs) have shown remarkable capabilities in solving diverse tasks. However, their proficiency in iteratively optimizing complex solutions through learning from previous feedback remains insufficiently explored. To bridge this gap, we present OPT-BENCH, a comprehensive benchmark designed to evaluate LLM agents on large-scale search space optimization problems. OPT-BENCH includes 20 real-world machine learning tasks sourced from Kaggle and 10 classical NP problems, offering a diverse and challenging environment for assessing LLM agents on iterative reasoning and solution refinement. To enable rigorous evaluation, we introduce OPT-Agent, an end-to-end optimization framework that emulates human reasoning when tackling complex problems by generating, validating, and iteratively improving solutions through leveraging historical feedback. Through extensive experiments on 9 state-of-the-art LLMs from 6 model families, we analyze the effects of optimization iterations, temperature settings, and model architectures on solution quality and convergence. Our results demonstrate that incorporating historical context significantly enhances optimization performance across both ML and NP tasks. All datasets, code, and evaluation tools are open-sourced to promote further research in advancing LLM-driven optimization and iterative reasoning. Project page: \href{https://github.com/OliverLeeXZ/OPT-BENCH}{https://github.com/OliverLeeXZ/OPT-BENCH}.

Chunyi Li, Xiaozhe Li, Zicheng Zhang et al.

With the emergence of Multimodal Large Language Models (MLLMs), hundreds of benchmarks have been developed to ensure the reliability of MLLMs in downstream tasks. However, the evaluation mechanism itself may not be reliable. For developers of MLLMs, questions remain about which benchmark to use and whether the test results meet their requirements. Therefore, we propose a critical principle of Information Density, which examines how much insight a benchmark can provide for the development of MLLMs. We characterize it from four key dimensions: (1) Fallacy, (2) Difficulty, (3) Redundancy, (4) Diversity. Through a comprehensive analysis of more than 10,000 samples, we measured the information density of 19 MLLM benchmarks. Experiments show that using the latest benchmarks in testing can provide more insight compared to previous ones, but there is still room for improvement in their information density. We hope this principle can promote the development and application of future MLLM benchmarks. Project page: https://github.com/lcysyzxdxc/bench4bench

Lin Chen, Jinsong Li, Xiaoyi Dong et al. · pku

Large vision-language models (LVLMs) have recently achieved rapid progress, sparking numerous studies to evaluate their multi-modal capabilities. However, we dig into current evaluation works and identify two primary issues: 1) Visual content is unnecessary for many samples. The answers can be directly inferred from the questions and options, or the world knowledge embedded in LLMs. This phenomenon is prevalent across current benchmarks. For instance, GeminiPro achieves 42.9% on the MMMU benchmark without any visual input, and outperforms the random choice baseline across six benchmarks over 24% on average. 2) Unintentional data leakage exists in LLM and LVLM training. LLM and LVLM could still answer some visual-necessary questions without visual content, indicating the memorizing of these samples within large-scale training data. For example, Sphinx-X-MoE gets 43.6% on MMMU without accessing images, surpassing its LLM backbone with 17.9%. Both problems lead to misjudgments of actual multi-modal gains and potentially misguide the study of LVLM. To this end, we present MMStar, an elite vision-indispensable multi-modal benchmark comprising 1,500 samples meticulously selected by humans. MMStar benchmarks 6 core capabilities and 18 detailed axes, aiming to evaluate LVLMs' multi-modal capacities with carefully balanced and purified samples. These samples are first roughly selected from current benchmarks with an automated pipeline, human review is then involved to ensure each curated sample exhibits visual dependency, minimal data leakage, and requires advanced multi-modal capabilities. Moreover, two metrics are developed to measure data leakage and actual performance gain in multi-modal training. We evaluate 16 leading LVLMs on MMStar to assess their multi-modal capabilities, and on 7 benchmarks with the proposed metrics to investigate their data leakage and actual multi-modal gain.

Junying Wang, Wenzhe Li, Yalun Wu et al.

Affordance theory suggests that environments inherently provide action possibilities shaping perception and behavior. While Multimodal Large Language Models (MLLMs) achieve strong performance in vision-language tasks, their ability to perceive affordance, which is crucial for intuitive and safe interactions, remains underexplored. To address this, we introduce **A4Bench**, a novel benchmark designed to evaluate the affordance perception abilities of MLLMs across two dimensions: 1) Constitutive Affordance, assessing understanding of inherent object properties through 1,282 questionanswer pairs spanning nine sub-disciplines, and 2) Transformative Affordance, probing dynamic and contextual nuances (e.g., misleading, time-dependent, cultural, or individual-specific affordance) with 718 challenging question-answer pairs. We evaluate 17 MLLMs (nine proprietary and eight open-source) and compare them to human performance. Results show that proprietary models generally outperform open-source ones, yet all models perform far below humans, especially in transformative affordance. Furthermore, even top-performing models, such as Gemini-2.0-Pro (18.05% overall exact match accuracy), significantly lag behind human performance (best: 85.34%, worst: 81.25%). These findings highlight critical gaps in environmental understanding of MLLMs and provide a foundation for advancing AI systems toward more robust, context-aware interactions.

Siqi Li, Yufan Shen, Xiangnan Chen et al. · pku

The rapid advancement of multimodal large language models (MLLMs) has profoundly impacted the document domain, creating a wide array of application scenarios. This progress highlights the need for a comprehensive benchmark to evaluate these models' capabilities across various document-specific tasks. However, existing benchmarks often fail to locate specific model weaknesses or guide systematic improvements. To bridge this gap, we introduce a General Document Intelligence Benchmark (GDI-Bench), featuring 2.3k images across 9 key scenarios and 19 document-specific tasks. By decoupling visual complexity and reasoning complexity, the GDI-Bench structures graded tasks that allow performance assessment by difficulty, aiding in model weakness identification and optimization guidance. We evaluate various open-source and closed-source models on GDI-Bench, conducting decoupled analyses in the visual and reasoning domains, revealing their strengths and weaknesses. To address the diverse tasks and domains in the GDI-Bench, we propose a GDI-Model that mitigates catastrophic forgetting during the supervised fine-tuning (SFT) process through an intelligence-preserving training strategy, thereby reinforcing the inherent weaknesses of the base model. Our model achieves state-of-the-art performance on previous benchmarks and the GDI-Bench. Both our benchmark and models are or will be open-sourced on https://huggingface.co/GDIBench.