Wenqi Shao

Jiaming Han, Renrui Zhang, Wenqi Shao et al. · berkeley

We present ImageBind-LLM, a multi-modality instruction tuning method of large language models (LLMs) via ImageBind. Existing works mainly focus on language and image instruction tuning, different from which, our ImageBind-LLM can respond to multi-modality conditions, including audio, 3D point clouds, video, and their embedding-space arithmetic by only image-text alignment training. During training, we adopt a learnable bind network to align the embedding space between LLaMA and ImageBind's image encoder. Then, the image features transformed by the bind network are added to word tokens of all layers in LLaMA, which progressively injects visual instructions via an attention-free and zero-initialized gating mechanism. Aided by the joint embedding of ImageBind, the simple image-text training enables our model to exhibit superior multi-modality instruction-following capabilities. During inference, the multi-modality inputs are fed into the corresponding ImageBind encoders, and processed by a proposed visual cache model for further cross-modal embedding enhancement. The training-free cache model retrieves from three million image features extracted by ImageBind, which effectively mitigates the training-inference modality discrepancy. Notably, with our approach, ImageBind-LLM can respond to instructions of diverse modalities and demonstrate significant language generation quality. Code is released at https://github.com/OpenGVLab/LLaMA-Adapter.

Peng Xu, Wenqi Shao, Kaipeng Zhang et al. · pku

Large Vision-Language Models (LVLMs) have recently played a dominant role in multimodal vision-language learning. Despite the great success, it lacks a holistic evaluation of their efficacy. This paper presents a comprehensive evaluation of publicly available large multimodal models by building a LVLM evaluation Hub (LVLM-eHub). Our LVLM-eHub consists of $8$ representative LVLMs such as InstructBLIP and MiniGPT-4, which are thoroughly evaluated by a quantitative capability evaluation and an online arena platform. The former evaluates $6$ categories of multimodal capabilities of LVLMs such as visual question answering and embodied artificial intelligence on $47$ standard text-related visual benchmarks, while the latter provides the user-level evaluation of LVLMs in an open-world question-answering scenario. The study reveals several innovative findings. First, instruction-tuned LVLM with massive in-domain data such as InstructBLIP heavily overfits many existing tasks, generalizing poorly in the open-world scenario. Second, instruction-tuned LVLM with moderate instruction-following data may result in object hallucination issues (i.e., generate objects that are inconsistent with target images in the descriptions). It either makes the current evaluation metric such as CIDEr for image captioning ineffective or generates wrong answers. Third, employing a multi-turn reasoning evaluation framework can mitigate the issue of object hallucination, shedding light on developing an effective pipeline for LVLM evaluation. The findings provide a foundational framework for the conception and assessment of innovative strategies aimed at enhancing zero-shot multimodal techniques. Our LVLM-eHub will be available at https://github.com/OpenGVLab/Multi-Modality-Arena

Wenqi Shao, Xun Zhao, Yixiao Ge et al. · tencent-ai

This paper addresses an important problem of ranking the pre-trained deep neural networks and screening the most transferable ones for downstream tasks. It is challenging because the ground-truth model ranking for each task can only be generated by fine-tuning the pre-trained models on the target dataset, which is brute-force and computationally expensive. Recent advanced methods proposed several lightweight transferability metrics to predict the fine-tuning results. However, these approaches only capture static representations but neglect the fine-tuning dynamics. To this end, this paper proposes a new transferability metric, called \textbf{S}elf-challenging \textbf{F}isher \textbf{D}iscriminant \textbf{A}nalysis (\textbf{SFDA}), which has many appealing benefits that existing works do not have. First, SFDA can embed the static features into a Fisher space and refine them for better separability between classes. Second, SFDA uses a self-challenging mechanism to encourage different pre-trained models to differentiate on hard examples. Third, SFDA can easily select multiple pre-trained models for the model ensemble. Extensive experiments on $33$ pre-trained models of $11$ downstream tasks show that SFDA is efficient, effective, and robust when measuring the transferability of pre-trained models. For instance, compared with the state-of-the-art method NLEEP, SFDA demonstrates an average of $59.1$\% gain while bringing $22.5$x speedup in wall-clock time. The code will be available at \url{https://github.com/TencentARC/SFDA}.

Wenqi Shao, Mengzhao Chen, Zhaoyang Zhang et al.

Large language models (LLMs) have revolutionized natural language processing tasks. However, their practical deployment is hindered by their immense memory and computation requirements. Although recent post-training quantization (PTQ) methods are effective in reducing memory footprint and improving the computational efficiency of LLM, they hand-craft quantization parameters, leading to low performance, especially in extremely low-bit quantization. To tackle this issue, we introduce an Omnidirectionally calibrated Quantization (\textbf{OmniQuant}) technique for LLMs, which achieves good performance in diverse quantization settings while maintaining the computational efficiency of PTQ by efficiently optimizing various quantization parameters. OmniQuant comprises two innovative components including Learnable Weight Clipping (LWC) and Learnable Equivalent Transformation (LET). LWC modulates the extreme values of weights by optimizing the clipping threshold. Meanwhile, LET tackles activation outliers by shifting the challenge of quantization from activations to weights. Operating within a differentiable framework using block-wise error minimization, OmniQuant can optimize the quantization process efficiently for both weight-only and weight-activation quantization. For instance, the LLaMA-2 model family size 7-70B can be processed with OmniQuant on a single A100-40G GPU within 1-16 hours using 128 samples. Extensive experiments validate OmniQuant's superior performance across diverse quantization configurations such as W4A4 (4-bit weight, 4-bit activation), W6A6, W4A16, W3A16, and W2A16. Additionally, OmniQuant demonstrates effectiveness in instruction-tuned models and delivers notable improvements in inference speed and memory reduction on real devices. Codes are available at \url{https://github.com/OpenGVLab/OmniQuant}.

Ziyi Lin, Chris Liu, Renrui Zhang et al.

We present SPHINX, a versatile multi-modal large language model (MLLM) with a joint mixing of model weights, tuning tasks, and visual embeddings. First, for stronger vision-language alignment, we unfreeze the large language model (LLM) during pre-training, and introduce a weight mix strategy between LLMs trained by real-world and synthetic data. By directly integrating the weights from two domains, the mixed LLM can efficiently incorporate diverse semantics with favorable robustness. Then, to enable multi-purpose capabilities, we mix a variety of tasks for joint visual instruction tuning, and design task-specific instructions to avoid inter-task conflict. In addition to the basic visual question answering, we include more challenging tasks such as region-level understanding, caption grounding, document layout detection, and human pose estimation, contributing to mutual enhancement over different scenarios. Additionally, we propose to extract comprehensive visual embeddings from various network architectures, pre-training paradigms, and information granularity, providing language models with more robust image representations. Based on our proposed joint mixing, SPHINX exhibits superior multi-modal understanding capabilities on a wide range of applications. On top of this, we further propose an efficient strategy aiming to better capture fine-grained appearances of high-resolution images. With a mixing of different scales and high-resolution sub-images, SPHINX attains exceptional visual parsing and reasoning performance on existing evaluation benchmarks. We hope our work may cast a light on the exploration of joint mixing in future MLLM research. Code is released at https://github.com/Alpha-VLLM/LLaMA2-Accessory.

Shilong Zhang, Peize Sun, Shoufa Chen et al.

Visual instruction tuning large language model(LLM) on image-text pairs has achieved general-purpose vision-language abilities. However, the lack of region-text pairs limits their advancements to fine-grained multimodal understanding. In this paper, we propose spatial instruction tuning, which introduces the reference to the region-of-interest(RoI) in the instruction. Before sending to LLM, the reference is replaced by RoI features and interleaved with language embeddings as a sequence. Our model GPT4RoI, trained on 7 region-text pair datasets, brings an unprecedented interactive and conversational experience compared to previous image-level models. (1) Interaction beyond language: Users can interact with our model by both language and drawing bounding boxes to flexibly adjust the referring granularity. (2) Versatile multimodal abilities: A variety of attribute information within each RoI can be mined by GPT4RoI, e.g., color, shape, material, action, etc. Furthermore, it can reason about multiple RoIs based on common sense. On the Visual Commonsense Reasoning(VCR) dataset, GPT4RoI achieves a remarkable accuracy of 81.6%, surpassing all existing models by a significant margin (the second place is 75.6%) and almost reaching human-level performance of 85.0%. The code and model can be found at https://github.com/jshilong/GPT4RoI.

Yutao Hu, Qixiong Wang, Wenqi Shao et al.

Referring image segmentation aims to segment the target object referred by a natural language expression. However, previous methods rely on the strong assumption that one sentence must describe one target in the image, which is often not the case in real-world applications. As a result, such methods fail when the expressions refer to either no objects or multiple objects. In this paper, we address this issue from two perspectives. First, we propose a Dual Multi-Modal Interaction (DMMI) Network, which contains two decoder branches and enables information flow in two directions. In the text-to-image decoder, text embedding is utilized to query the visual feature and localize the corresponding target. Meanwhile, the image-to-text decoder is implemented to reconstruct the erased entity-phrase conditioned on the visual feature. In this way, visual features are encouraged to contain the critical semantic information about target entity, which supports the accurate segmentation in the text-to-image decoder in turn. Secondly, we collect a new challenging but realistic dataset called Ref-ZOM, which includes image-text pairs under different settings. Extensive experiments demonstrate our method achieves state-of-the-art performance on different datasets, and the Ref-ZOM-trained model performs well on various types of text inputs. Codes and datasets are available at https://github.com/toggle1995/RIS-DMMI.

Fanqing Meng, Jin Wang, Chuanhao Li et al.

The capability to process multiple images is crucial for Large Vision-Language Models (LVLMs) to develop a more thorough and nuanced understanding of a scene. Recent multi-image LVLMs have begun to address this need. However, their evaluation has not kept pace with their development. To fill this gap, we introduce the Multimodal Multi-image Understanding (MMIU) benchmark, a comprehensive evaluation suite designed to assess LVLMs across a wide range of multi-image tasks. MMIU encompasses 7 types of multi-image relationships, 52 tasks, 77K images, and 11K meticulously curated multiple-choice questions, making it the most extensive benchmark of its kind. Our evaluation of 24 popular LVLMs, including both open-source and proprietary models, reveals significant challenges in multi-image comprehension, particularly in tasks involving spatial understanding. Even the most advanced models, such as GPT-4o, achieve only 55.7% accuracy on MMIU. Through multi-faceted analytical experiments, we identify key performance gaps and limitations, providing valuable insights for future model and data improvements. We aim for MMIU to advance the frontier of LVLM research and development, moving us toward achieving sophisticated multimodal multi-image user interactions.

Fanqing Meng, Wenqi Shao, Zhanglin Peng et al.

This paper investigates an under-explored but important problem: given a collection of pre-trained neural networks, predicting their performance on each multi-modal task without fine-tuning them, such as image recognition, referring, captioning, visual question answering, and text question answering. A brute-force approach is to finetune all models on all target datasets, bringing high computational costs. Although recent-advanced approaches employed lightweight metrics to measure models' transferability,they often depend heavily on the prior knowledge of a single task, making them inapplicable in a multi-modal multi-task scenario. To tackle this issue, we propose an efficient multi-task model selector (EMMS), which employs large-scale foundation models to transform diverse label formats such as categories, texts, and bounding boxes of different downstream tasks into a unified noisy label embedding. EMMS can estimate a model's transferability through a simple weighted linear regression, which can be efficiently solved by an alternating minimization algorithm with a convergence guarantee. Extensive experiments on 5 downstream tasks with 24 datasets show that EMMS is fast, effective, and generic enough to assess the transferability of pre-trained models, making it the first model selection method in the multi-task scenario. For instance, compared with the state-of-the-art method LogME enhanced by our label embeddings, EMMS achieves 9.0\%, 26.3\%, 20.1\%, 54.8\%, 12.2\% performance gain on image recognition, referring, captioning, visual question answering, and text question answering, while bringing 5.13x, 6.29x, 3.59x, 6.19x, and 5.66x speedup in wall-clock time, respectively. The code is available at https://github.com/OpenGVLab/Multitask-Model-Selector.

Mengzhao Chen, Wenqi Shao, Peng Xu et al.

Large language models (LLMs) are crucial in modern natural language processing and artificial intelligence. However, they face challenges in managing their significant memory requirements. Although quantization-aware training (QAT) offers a solution by reducing memory consumption through low-bit representations with minimal accuracy loss, it is impractical due to substantial training resources. To address this, we propose Efficient Quantization-Aware Training (EfficientQAT), a more feasible QAT algorithm. EfficientQAT involves two consecutive phases: Block-wise training of all parameters (Block-AP) and end-to-end training of quantization parameters (E2E-QP). To the best of our knowledge, Block-AP is the first method to enable direct training of all parameters in a block-wise manner, reducing accuracy loss in low-bit scenarios by enhancing the solution space during optimization. E2E-QP then trains only the quantization parameters (step sizes) end-to-end, further improving the performance of quantized models by considering interactions among all sub-modules. Extensive experiments demonstrate that EfficientQAT outperforms previous quantization methods across a range of models, including base LLMs, instruction-tuned LLMs, and multimodal LLMs, with scales from 7B to 70B parameters at various quantization bits. For instance, EfficientQAT obtains a 2-bit Llama-2-70B model on a single A100-80GB GPU in 41 hours, with less than 3 points accuracy degradation compared to the full precision (69.48 vs. 72.41). Code is available at https://github.com/OpenGVLab/EfficientQAT.

Wenqi Shao, Meng Lei, Yutao Hu et al. · pku

Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated significant progress in tackling complex multimodal tasks. Among these cutting-edge developments, Google's Bard stands out for its remarkable multimodal capabilities, promoting comprehensive comprehension and reasoning across various domains. This work presents an early and holistic evaluation of LVLMs' multimodal abilities, with a particular focus on Bard, by proposing a lightweight variant of LVLM-eHub, named Tiny LVLM-eHub. In comparison to the vanilla version, Tiny LVLM-eHub possesses several appealing properties. Firstly, it provides a systematic assessment of six categories of multimodal capabilities, including visual perception, visual knowledge acquisition, visual reasoning, visual commonsense, object hallucination, and embodied intelligence, through quantitative evaluation of $42$ standard text-related visual benchmarks. Secondly, it conducts an in-depth analysis of LVLMs' predictions using the ChatGPT Ensemble Evaluation (CEE), which leads to a robust and accurate evaluation and exhibits improved alignment with human evaluation compared to the word matching approach. Thirdly, it comprises a mere $2.1$K image-text pairs, facilitating ease of use for practitioners to evaluate their own offline LVLMs. Through extensive experimental analysis, this study demonstrates that Bard outperforms previous LVLMs in most multimodal capabilities except object hallucination, to which Bard is still susceptible. Tiny LVLM-eHub serves as a baseline evaluation for various LVLMs and encourages innovative strategies aimed at advancing multimodal techniques. Our project is publicly available at \url{https://github.com/OpenGVLab/Multi-Modality-Arena}.

Zhaoyang Zhang, Yitong Jiang, Wenqi Shao et al.

Controllable image denoising aims to generate clean samples with human perceptual priors and balance sharpness and smoothness. In traditional filter-based denoising methods, this can be easily achieved by adjusting the filtering strength. However, for NN (Neural Network)-based models, adjusting the final denoising strength requires performing network inference each time, making it almost impossible for real-time user interaction. In this paper, we introduce Real-time Controllable Denoising (RCD), the first deep image and video denoising pipeline that provides a fully controllable user interface to edit arbitrary denoising levels in real-time with only one-time network inference. Unlike existing controllable denoising methods that require multiple denoisers and training stages, RCD replaces the last output layer (which usually outputs a single noise map) of an existing CNN-based model with a lightweight module that outputs multiple noise maps. We propose a novel Noise Decorrelation process to enforce the orthogonality of the noise feature maps, allowing arbitrary noise level control through noise map interpolation. This process is network-free and does not require network inference. Our experiments show that RCD can enable real-time editable image and video denoising for various existing heavy-weight models without sacrificing their original performance.

Runjian Chen, Yao Mu, Runsen Xu et al.

Unsupervised contrastive learning for indoor-scene point clouds has achieved great successes. However, unsupervised learning point clouds in outdoor scenes remains challenging because previous methods need to reconstruct the whole scene and capture partial views for the contrastive objective. This is infeasible in outdoor scenes with moving objects, obstacles, and sensors. In this paper, we propose CO^3, namely Cooperative Contrastive Learning and Contextual Shape Prediction, to learn 3D representation for outdoor-scene point clouds in an unsupervised manner. CO^3 has several merits compared to existing methods. (1) It utilizes LiDAR point clouds from vehicle-side and infrastructure-side to build views that differ enough but meanwhile maintain common semantic information for contrastive learning, which are more appropriate than views built by previous methods. (2) Alongside the contrastive objective, shape context prediction is proposed as pre-training goal and brings more task-relevant information for unsupervised 3D point cloud representation learning, which are beneficial when transferring the learned representation to downstream detection tasks. (3) As compared to previous methods, representation learned by CO^3 is able to be transferred to different outdoor scene dataset collected by different type of LiDAR sensors. (4) CO^3 improves current state-of-the-art methods on both Once and KITTI datasets by up to 2.58 mAP. We believe CO^3 will facilitate understanding LiDAR point clouds in outdoor scene.

Yue Yang, Kaipeng Zhang, Yuying Ge et al.

Text-guided image generation has witnessed unprecedented progress due to the development of diffusion models. Beyond text and image, sound is a vital element within the sphere of human perception, offering vivid representations and naturally coinciding with corresponding scenes. Taking advantage of sound therefore presents a promising avenue for exploration within image generation research. However, the relationship between audio and image supervision remains significantly underdeveloped, and the scarcity of related, high-quality datasets brings further obstacles. In this paper, we propose a unified framework 'Align, Adapt, and Inject' (AAI) for sound-guided image generation, editing, and stylization. In particular, our method adapts input sound into a sound token, like an ordinary word, which can plug and play with existing powerful diffusion-based Text-to-Image (T2I) models. Specifically, we first train a multi-modal encoder to align audio representation with the pre-trained textual manifold and visual manifold, respectively. Then, we propose the audio adapter to adapt audio representation into an audio token enriched with specific semantics, which can be injected into a frozen T2I model flexibly. In this way, we are able to extract the dynamic information of varied sounds, while utilizing the formidable capability of existing T2I models to facilitate sound-guided image generation, editing, and stylization in a convenient and cost-effective manner. The experiment results confirm that our proposed AAI outperforms other text and sound-guided state-of-the-art methods. And our aligned multi-modal encoder is also competitive with other approaches in the audio-visual retrieval and audio-text retrieval tasks.

Mengkang Hu, Yao Mu, Xinmiao Yu et al.

This paper studies close-loop task planning, which refers to the process of generating a sequence of skills (a plan) to accomplish a specific goal while adapting the plan based on real-time observations. Recently, prompting Large Language Models (LLMs) to generate actions iteratively has become a prevalent paradigm due to its superior performance and user-friendliness. However, this paradigm is plagued by two inefficiencies: high token consumption and redundant error correction, both of which hinder its scalability for large-scale testing and applications. To address these issues, we propose Tree-Planner, which reframes task planning with LLMs into three distinct phases: plan sampling, action tree construction, and grounded deciding. Tree-Planner starts by using an LLM to sample a set of potential plans before execution, followed by the aggregation of them to form an action tree. Finally, the LLM performs a top-down decision-making process on the tree, taking into account real-time environmental information. Experiments show that Tree-Planner achieves state-of-the-art performance while maintaining high efficiency. By decomposing LLM queries into a single plan-sampling call and multiple grounded-deciding calls, a considerable part of the prompt are less likely to be repeatedly consumed. As a result, token consumption is reduced by 92.2% compared to the previously best-performing model. Additionally, by enabling backtracking on the action tree as needed, the correction process becomes more flexible, leading to a 40.5% decrease in error corrections.

Yanqing Liu, Kai Wang, Wenqi Shao et al.

Visual-language pre-training has achieved remarkable success in many multi-modal tasks, largely attributed to the availability of large-scale image-text datasets. In this work, we demonstrate that Multi-modal Large Language Models (MLLMs) can enhance visual-language representation learning by establishing richer image-text associations for image-text datasets. Our approach is simple, utilizing MLLMs to extend multiple diverse captions for each image. To prevent the bias introduced by MLLMs' hallucinations and monotonous language styles, we propose "text shearing" to maintain the quality and availability of extended captions. In image-text retrieval, without introducing additional training cost, our method consistently obtains 5.6 ~ 35.0 and 16.8 ~ 46.1 improvement on Recall@1 under the fine-tuning and zero-shot settings, respectively. Notably, we obtain zero-shot results that are comparable to fine-tuning on target datasets, which encourages more exploration of the versatile use of MLLMs.

Hao Zhang, Lumin Xu, Shenqi Lai et al.

Current image-based keypoint detection methods for animal (including human) bodies and faces are generally divided into full-supervised and few-shot class-agnostic approaches. The former typically relies on laborious and time-consuming manual annotations, posing considerable challenges in expanding keypoint detection to a broader range of keypoint categories and animal species. The latter, though less dependent on extensive manual input, still requires necessary support images with annotation for reference during testing. To realize zero-shot keypoint detection without any prior annotation, we introduce the Open-Vocabulary Keypoint Detection (OVKD) task, which is innovatively designed to use text prompts for identifying arbitrary keypoints across any species. In pursuit of this goal, we have developed a novel framework named Open-Vocabulary Keypoint Detection with Semantic-feature Matching (KDSM). This framework synergistically combines vision and language models, creating an interplay between language features and local keypoint visual features. KDSM enhances its capabilities by integrating Domain Distribution Matrix Matching (DDMM) and other special modules, such as the Vision-Keypoint Relational Awareness (VKRA) module, improving the framework's generalizability and overall performance.Our comprehensive experiments demonstrate that KDSM significantly outperforms the baseline in terms of performance and achieves remarkable success in the OVKD task.Impressively, our method, operating in a zero-shot fashion, still yields results comparable to state-of-the-art few-shot species class-agnostic keypoint detection methods.We will make the source code publicly accessible.

Xiangchao Yan, Runjian Chen, Bo Zhang et al.

Annotating 3D LiDAR point clouds for perception tasks is fundamental for many applications e.g., autonomous driving, yet it still remains notoriously labor-intensive. Pretraining-finetuning approach can alleviate the labeling burden by fine-tuning a pre-trained backbone across various downstream datasets as well as tasks. In this paper, we propose SPOT, namely Scalable Pre-training via Occupancy prediction for learning Transferable 3D representations under such a label-efficient fine-tuning paradigm. SPOT achieves effectiveness on various public datasets with different downstream tasks, showcasing its general representation power, cross-domain robustness and data scalability which are three key factors for real-world application. Specifically, we both theoretically and empirically show, for the first time, that general representations learning can be achieved through the task of occupancy prediction. Then, to address the domain gap caused by different LiDAR sensors and annotation methods, we develop a beam re-sampling technique for point cloud augmentation combined with class-balancing strategy. Furthermore, scalable pre-training is observed, that is, the downstream performance across all the experiments gets better with more pre-training data. Additionally, such pre-training strategy also remains compatible with unlabeled data. The hope is that our findings will facilitate the understanding of LiDAR points and pave the way for future advancements in LiDAR pre-training.

Kaining Ying, Fanqing Meng, Jin Wang et al.

Large Vision-Language Models (LVLMs) show significant strides in general-purpose multimodal applications such as visual dialogue and embodied navigation. However, existing multimodal evaluation benchmarks cover a limited number of multimodal tasks testing rudimentary capabilities, falling short in tracking LVLM development. In this study, we present MMT-Bench, a comprehensive benchmark designed to assess LVLMs across massive multimodal tasks requiring expert knowledge and deliberate visual recognition, localization, reasoning, and planning. MMT-Bench comprises $31,325$ meticulously curated multi-choice visual questions from various multimodal scenarios such as vehicle driving and embodied navigation, covering $32$ core meta-tasks and $162$ subtasks in multimodal understanding. Due to its extensive task coverage, MMT-Bench enables the evaluation of LVLMs using a task map, facilitating the discovery of in- and out-of-domain tasks. Evaluation results involving $30$ LVLMs such as the proprietary GPT-4V, GeminiProVision, and open-sourced InternVL-Chat, underscore the significant challenges posed by MMT-Bench. We anticipate that MMT-Bench will inspire the community to develop next-generation multimodal foundation models aimed at achieving general-purpose multimodal intelligence.

Dongyang Liu, Renrui Zhang, Longtian Qiu et al. · stanford, tsinghua

We propose SPHINX-X, an extensive Multimodality Large Language Model (MLLM) series developed upon SPHINX. To improve the architecture and training efficiency, we modify the SPHINX framework by removing redundant visual encoders, bypassing fully-padded sub-images with skip tokens, and simplifying multi-stage training into a one-stage all-in-one paradigm. To fully unleash the potential of MLLMs, we assemble a comprehensive multi-domain and multimodal dataset covering publicly available resources in language, vision, and vision-language tasks. We further enrich this collection with our curated OCR intensive and Set-of-Mark datasets, extending the diversity and generality. By training over different base LLMs including TinyLlama1.1B, InternLM2-7B, LLaMA2-13B, and Mixtral8x7B, we obtain a spectrum of MLLMs that vary in parameter size and multilingual capabilities. Comprehensive benchmarking reveals a strong correlation between the multi-modal performance with the data and parameter scales. Code and models are released at https://github.com/Alpha-VLLM/LLaMA2-Accessory

Yutao Hu, Tianbin Li, Quanfeng Lu et al.

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in various multimodal tasks. However, their potential in the medical domain remains largely unexplored. A significant challenge arises from the scarcity of diverse medical images spanning various modalities and anatomical regions, which is essential in real-world medical applications. To solve this problem, in this paper, we introduce OmniMedVQA, a novel comprehensive medical Visual Question Answering (VQA) benchmark. This benchmark is collected from 73 different medical datasets, including 12 different modalities and covering more than 20 distinct anatomical regions. Importantly, all images in this benchmark are sourced from authentic medical scenarios, ensuring alignment with the requirements of the medical field and suitability for evaluating LVLMs. Through our extensive experiments, we have found that existing LVLMs struggle to address these medical VQA problems effectively. Moreover, what surprises us is that medical-specialized LVLMs even exhibit inferior performance to those general-domain models, calling for a more versatile and robust LVLM in the biomedical field. The evaluation results not only reveal the current limitations of LVLM in understanding real medical images but also highlight our dataset's significance. Our code with dataset are available at https://github.com/OpenGVLab/Multi-Modality-Arena.

Fanqing Meng, Lingxiao Du, Zongkai Liu et al.

DeepSeek R1, and o1 have demonstrated powerful reasoning capabilities in the text domain through stable large-scale reinforcement learning. To enable broader applications, some works have attempted to transfer these capabilities to multimodal reasoning. However, these efforts have been limited by the limited difficulty of selected tasks and relatively small training scales, making it challenging to demonstrate strong multimodal reasoning abilities. To address this gap, we introduce the MMK12 dataset and MM-EUREKA with 7B and 32B parameters. The former is a high-quality multimodal mathematics reasoning dataset featuring diverse knowledge domains with human-verified answers and solution processes. The latter is a multimodal model employing rule-based reinforcement learning on MMK12, utilizing online filtering and two-stage training strategy to enhance training stability. MM-EUREKA demonstrates remarkable performance gains in multimodal mathematical reasoning, outperforming previous powerful models like InternVL2.5-78B or InternVL2.5-38B-MPO. In particular, MM-EUREKA achieves competitive or superior performance compared to both open-source and closed-source models, and trails slightly behind o1 in multidisciplinary reasoning tasks. We open-source our complete pipeline to foster further research in this area. We release all our codes, models, data, etc. at https://github.com/ModalMinds/MM-EUREKA

Fanqing Meng, Wenqi Shao, Quanfeng Lu et al.

Charts play a vital role in data visualization, understanding data patterns, and informed decision-making. However, their unique combination of graphical elements (e.g., bars, lines) and textual components (e.g., labels, legends) poses challenges for general-purpose multimodal models. While vision-language models trained on chart data excel in comprehension, they struggle with generalization. To address these challenges, we propose ChartAssistant, a chart-based vision-language model for universal chart comprehension and reasoning. ChartAssistant leverages ChartSFT, a comprehensive dataset covering diverse chart-related tasks with basic (e.g. bars and pies) and specialized (e.g. radars, and bubbles) chart types. It undergoes a two-stage training process, starting with pre-training on chart-to-table parsing to align chart and text, followed by multitask instruction-following fine-tuning. This approach enables ChartAssistant to achieve competitive performance across various chart tasks. Experimental results demonstrate significant performance gains over the state-of-the-art UniChart and Chartllama method, especially outperforming them on real-world chart data with zero-shot setting. The code and data are available at https://github.com/OpenGVLab/ChartAst.

Peng Xu, Wenqi Shao, Mengzhao Chen et al.

Large language models (LLMs) have demonstrated outstanding performance in various tasks, such as text summarization, text question-answering, and etc. While their performance is impressive, the computational footprint due to their vast number of parameters can be prohibitive. Existing solutions such as SparseGPT and Wanda attempt to alleviate this issue through weight pruning. However, their layer-wise approach results in significant perturbation to the model's output and requires meticulous hyperparameter tuning, such as the pruning rate, which can adversely affect overall model performance. To address this, this paper introduces a novel LLM pruning technique dubbed blockwise parameter-efficient sparsity allocation (BESA) by applying a blockwise reconstruction loss. In contrast to the typical layer-wise pruning techniques, BESA is characterized by two distinctive attributes: i) it targets the overall pruning error with respect to individual transformer blocks, and ii) it allocates layer-specific sparsity in a differentiable manner, both of which ensure reduced performance degradation after pruning. Our experiments show that BESA achieves state-of-the-art performance, efficiently pruning LLMs like LLaMA1, and LLaMA2 with 7B to 70B parameters on a single A100 GPU in just five hours. Code is available at https://github.com/OpenGVLab/LLMPrune-BESA.

Junting Chen, Yao Mu, Qiaojun Yu et al.

Rapid progress in high-level task planning and code generation for open-world robot manipulation has been witnessed in Embodied AI. However, previous studies put much effort into general common sense reasoning and task planning capabilities of large-scale language or multi-modal models, relatively little effort on ensuring the deployability of generated code on real robots, and other fundamental components of autonomous robot systems including robot perception, motion planning, and control. To bridge this ``ideal-to-real'' gap, this paper presents \textbf{RobotScript}, a platform for 1) a deployable robot manipulation pipeline powered by code generation; and 2) a code generation benchmark for robot manipulation tasks in free-form natural language. The RobotScript platform addresses this gap by emphasizing the unified interface with both simulation and real robots, based on abstraction from the Robot Operating System (ROS), ensuring syntax compliance and simulation validation with Gazebo. We demonstrate the adaptability of our code generation framework across multiple robot embodiments, including the Franka and UR5 robot arms, and multiple grippers. Additionally, our benchmark assesses reasoning abilities for physical space and constraints, highlighting the differences between GPT-3.5, GPT-4, and Gemini in handling complex physical interactions. Finally, we present a thorough evaluation on the whole system, exploring how each module in the pipeline: code generation, perception, motion planning, and even object geometric properties, impact the overall performance of the system.

Tianle Zhang, Yuchen Zhang, Kun Wang et al. · pku

Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have raised growing concerns. As one of the most promising directions, graph condensation methods address these issues by employing gradient matching, aiming to condense the full graph into a more concise yet information-rich synthetic set. Though encouraging, these strategies primarily emphasize matching directions of the gradients, which leads to deviations in the training trajectories. Such deviations are further magnified by the differences between the condensation and evaluation phases, culminating in accumulated errors, which detrimentally affect the performance of the condensed graphs. In light of this, we propose a novel graph condensation method named \textbf{C}raf\textbf{T}ing \textbf{R}ationa\textbf{L} trajectory (\textbf{CTRL}), which offers an optimized starting point closer to the original dataset's feature distribution and a more refined strategy for gradient matching. Theoretically, CTRL can effectively neutralize the impact of accumulated errors on the performance of condensed graphs. We provide extensive experiments on various graph datasets and downstream tasks to support the effectiveness of CTRL. Code is released at https://github.com/NUS-HPC-AI-Lab/CTRL.

Lingxiao Du, Fanqing Meng, Zongkai Liu et al.

While Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision-language understanding, they still struggle with complex multi-step reasoning, often producing logically inconsistent or partially correct solutions. A key limitation lies in the lack of fine-grained supervision over intermediate reasoning steps. To address this, we propose MM-PRM, a process reward model trained within a fully automated, scalable framework. We first build MM-Policy, a strong multimodal model trained on diverse mathematical reasoning data. Then, we construct MM-K12, a curated dataset of 10,000 multimodal math problems with verifiable answers, which serves as seed data. Leveraging a Monte Carlo Tree Search (MCTS)-based pipeline, we generate over 700k step-level annotations without human labeling. The resulting PRM is used to score candidate reasoning paths in the Best-of-N inference setup and achieves significant improvements across both in-domain (MM-K12 test set) and out-of-domain (OlympiadBench, MathVista, etc.) benchmarks. Further analysis confirms the effectiveness of soft labels, smaller learning rates, and path diversity in optimizing PRM performance. MM-PRM demonstrates that process supervision is a powerful tool for enhancing the logical robustness of multimodal reasoning systems. We release all our codes and data at https://github.com/ModalMinds/MM-PRM.

Yuqi Lin, Hengjia Li, Wenqi Shao et al.

In this paper, we explore a principal way to enhance the quality of widely pre-existing coarse masks, enabling them to serve as reliable training data for segmentation models to reduce the annotation cost. In contrast to prior refinement techniques that are tailored to specific models or tasks in a close-world manner, we propose SAMRefiner, a universal and efficient approach by adapting SAM to the mask refinement task. The core technique of our model is the noise-tolerant prompting scheme. Specifically, we introduce a multi-prompt excavation strategy to mine diverse input prompts for SAM (i.e., distance-guided points, context-aware elastic bounding boxes, and Gaussian-style masks) from initial coarse masks. These prompts can collaborate with each other to mitigate the effect of defects in coarse masks. In particular, considering the difficulty of SAM to handle the multi-object case in semantic segmentation, we introduce a split-then-merge (STM) pipeline. Additionally, we extend our method to SAMRefiner++ by introducing an additional IoU adaption step to further boost the performance of the generic SAMRefiner on the target dataset. This step is self-boosted and requires no additional annotation. The proposed framework is versatile and can flexibly cooperate with existing segmentation methods. We evaluate our mask framework on a wide range of benchmarks under different settings, demonstrating better accuracy and efficiency. SAMRefiner holds significant potential to expedite the evolution of refinement tools. Our code is available at https://github.com/linyq2117/SAMRefiner.

Pengfei Zhou, Fanrui Zhang, Xiaopeng Peng et al.

Multimodal reasoning, which integrates language and visual cues into problem solving and decision making, is a fundamental aspect of human intelligence and a crucial step toward artificial general intelligence. However, the evaluation of multimodal reasoning capabilities in Multimodal Large Language Models (MLLMs) remains inadequate. Most existing reasoning benchmarks are constrained by limited data size, narrow domain coverage, and unstructured knowledge distribution. To close these gaps, we introduce MDK12-Bench, a multi-disciplinary benchmark assessing the reasoning capabilities of MLLMs via real-world K-12 examinations. Spanning six disciplines (math, physics, chemistry, biology, geography, and information science), our benchmark comprises 140K reasoning instances across diverse difficulty levels from primary school to 12th grade. It features 6,827 instance-level knowledge point annotations based on a well-organized knowledge structure, detailed answer explanations, difficulty labels and cross-year partitions, providing a robust platform for comprehensive evaluation. Additionally, we present a novel dynamic evaluation framework to mitigate data contamination issues by bootstrapping question forms, question types, and image styles during evaluation. Extensive experiment on MDK12-Bench reveals the significant limitation of current MLLMs in multimodal reasoning. The findings on our benchmark provide insights into the development of the next-generation models. Our data and codes are available at https://github.com/LanceZPF/MDK12.

Lirui Zhao, Yue Yang, Kaipeng Zhang et al.

Text-to-image (T2I) generative models have attracted significant attention and found extensive applications within and beyond academic research. For example, the Civitai community, a platform for T2I innovation, currently hosts an impressive array of 74,492 distinct models. However, this diversity presents a formidable challenge in selecting the most appropriate model and parameters, a process that typically requires numerous trials. Drawing inspiration from the tool usage research of large language models (LLMs), we introduce DiffAgent, an LLM agent designed to screen the accurate selection in seconds via API calls. DiffAgent leverages a novel two-stage training framework, SFTA, enabling it to accurately align T2I API responses with user input in accordance with human preferences. To train and evaluate DiffAgent's capabilities, we present DABench, a comprehensive dataset encompassing an extensive range of T2I APIs from the community. Our evaluations reveal that DiffAgent not only excels in identifying the appropriate T2I API but also underscores the effectiveness of the SFTA training framework. Codes are available at https://github.com/OpenGVLab/DiffAgent.

Jiahao Wang, Wenqi Shao, Mengzhao Chen et al.

This work examines whether decoder-only Transformers such as LLaMA, which were originally designed for large language models (LLMs), can be adapted to the computer vision field. We first "LLaMAfy" a standard ViT step-by-step to align with LLaMA's architecture, and find that directly applying a causal mask to the self-attention brings an attention collapse issue, resulting in the failure to the network training. We suggest to reposition the class token behind the image tokens with a post-sequence class token technique to overcome this challenge, enabling causal self-attention to efficiently capture the entire image's information. Additionally, we develop a soft mask strategy that gradually introduces a causal mask to the self-attention at the onset of training to facilitate the optimization behavior. The tailored model, dubbed as image LLaMA (iLLaMA), is akin to LLaMA in architecture and enables direct supervised learning. Its causal self-attention boosts computational efficiency and learns complex representation by elevating attention map ranks. iLLaMA rivals the performance with its encoder-only counterparts, achieving 75.1% ImageNet top-1 accuracy with only 5.7M parameters. Scaling the model to $\sim$310M and pre-training on ImageNet-21K further enhances the accuracy to 86.0%. Extensive experiments demonstrate iLLaMA's reliable properties: shape-texture bias, calibration, quantization compatibility, ADE20K segmentation and CIFAR transfer learning. We hope our study can kindle fresh views to visual architectures in the wave of LLMs and inspire the development of unified multimodal models. Pre-trained models and codes are available https://github.com/techmonsterwang/iLLaMA.

Zongkai Liu, Fanqing Meng, Lingxiao Du et al.

Recent advances in rule-based reinforcement learning (RL) have significantly improved the reasoning capability of language models (LMs) with rule-based rewards. However, existing RL methods -- such as GRPO, REINFORCE++, and RLOO -- often suffer from training instability, where large policy updates and improper clipping can lead to training collapse. To address this issue, we propose Clipped Policy Gradient Optimization with Policy Drift (CPGD), a novel algorithm designed to stabilize policy learning in LMs. CPGD introduces a policy drift constraint based on KL divergence to dynamically regularize policy updates, and leverages a clip mechanism on the logarithm of the ratio to prevent excessive policy updates. We provide theoretical justification for CPGD and demonstrate through empirical analysis that it mitigates the instability observed in prior approaches. Furthermore, we show that CPGD significantly improves performance while maintaining training stability. Our implementation balances theoretical rigor with practical usability, offering a robust alternative for RL in the post-training of LMs. We release our code at https://github.com/ModalMinds/MM-EUREKA.

Yizhuo Ding, Wanying Qu, Jiawei Geng et al.

Large Language Models (LLMs) achieve strong performance across diverse tasks but face prohibitive computational and memory costs. Pruning offers a promising path by inducing sparsity while preserving architectural flexibility. However, existing methods struggle to balance efficiency and robustness: local metric approaches prune layer by layer but often collapse under high sparsity, whereas global feedback methods enforce consistency at the cost of expensive weight updates or restrictive semi-structured formats. We present UniPruning, a unified post-training pruning framework that combines the speed of local saliency metrics with the stability of global coordination, enabled by a mirror descent based optimization, all without updating model weights. UniPruning leverages fast layer-wise scoring and a lightweight global controller to allocate a single sparsity budget, supporting both unstructured and semi-structured N :M pruning within one framework. After a brief calibration, it can generate pruning masks for arbitrary sparsity levels in one shot, and adapts seamlessly to hardware-aware constraints. Extensive experiments on multiple pretrained LLM families and standard benchmarks show that UniPruning consistently delivers competitive or superior perplexity and zero-shot accuracy. Ablation studies further highlight the importance of mirror descent and local saliency anchoring. Overall, UniPruning provides an efficient, principled, and scalable solution for sparsifying large-scale LLMs. Our code is available at: https://github.com/RainbowQTT/UniPruning.

Tianle Zhang, Langtian Ma, Yuchen Yan et al.

Recent text-to-video (T2V) technology advancements, as demonstrated by models such as Gen2, Pika, and Sora, have significantly broadened its applicability and popularity. Despite these strides, evaluating these models poses substantial challenges. Primarily, due to the limitations inherent in automatic metrics, manual evaluation is often considered a superior method for assessing T2V generation. However, existing manual evaluation protocols face reproducibility, reliability, and practicality issues. To address these challenges, this paper introduces the Text-to-Video Human Evaluation (T2VHE) protocol, a comprehensive and standardized protocol for T2V models. The T2VHE protocol includes well-defined metrics, thorough annotator training, and an effective dynamic evaluation module. Experimental results demonstrate that this protocol not only ensures high-quality annotations but can also reduce evaluation costs by nearly 50\%. We will open-source the entire setup of the T2VHE protocol, including the complete protocol workflow, the dynamic evaluation component details, and the annotation interface code. This will help communities establish more sophisticated human assessment protocols.

Weiyun Wang, Shuibo Zhang, Yiming Ren et al.

With the rapid advancement of multimodal large language models (MLLMs), their evaluation has become increasingly comprehensive. However, understanding long multimodal content, as a foundational ability for real-world applications, remains underexplored. In this work, we present Needle In A Multimodal Haystack (MM-NIAH), the first benchmark specifically designed to systematically evaluate the capability of existing MLLMs to comprehend long multimodal documents. Our benchmark includes three types of evaluation tasks: multimodal retrieval, counting, and reasoning. In each task, the model is required to answer the questions according to different key information scattered throughout the given multimodal document. Evaluating the leading MLLMs on MM-NIAH, we observe that existing models still have significant room for improvement on these tasks, especially on vision-centric evaluation. We hope this work can provide a platform for further research on long multimodal document comprehension and contribute to the advancement of MLLMs. Code and benchmark are released at https://github.com/OpenGVLab/MM-NIAH.

Hao Zhang, Wenqi Shao, Hong Liu et al.

Large Vision-Language Models (LVLMs) have shown significant progress in responding well to visual-instructions from users. However, these instructions, encompassing images and text, are susceptible to both intentional and inadvertent attacks. Despite the critical importance of LVLMs' robustness against such threats, current research in this area remains limited. To bridge this gap, we introduce B-AVIBench, a framework designed to analyze the robustness of LVLMs when facing various Black-box Adversarial Visual-Instructions (B-AVIs), including four types of image-based B-AVIs, ten types of text-based B-AVIs, and nine types of content bias B-AVIs (such as gender, violence, cultural, and racial biases, among others). We generate 316K B-AVIs encompassing five categories of multimodal capabilities (ten tasks) and content bias. We then conduct a comprehensive evaluation involving 14 open-source LVLMs to assess their performance. B-AVIBench also serves as a convenient tool for practitioners to evaluate the robustness of LVLMs against B-AVIs. Our findings and extensive experimental results shed light on the vulnerabilities of LVLMs, and highlight that inherent biases exist even in advanced closed-source LVLMs like GeminiProVision and GPT-4V. This underscores the importance of enhancing the robustness, security, and fairness of LVLMs. The source code and benchmark are available at https://github.com/zhanghao5201/B-AVIBench.

Mengzhao Chen, Wenqi Shao, Peng Xu et al.

Token compression aims to speed up large-scale vision transformers (e.g. ViTs) by pruning (dropping) or merging tokens. It is an important but challenging task. Although recent advanced approaches achieved great success, they need to carefully handcraft a compression rate (i.e. number of tokens to remove), which is tedious and leads to sub-optimal performance. To tackle this problem, we propose Differentiable Compression Rate (DiffRate), a novel token compression method that has several appealing properties prior arts do not have. First, DiffRate enables propagating the loss function's gradient onto the compression ratio, which is considered as a non-differentiable hyperparameter in previous work. In this case, different layers can automatically learn different compression rates layer-wisely without extra overhead. Second, token pruning and merging can be naturally performed simultaneously in DiffRate, while they were isolated in previous works. Third, extensive experiments demonstrate that DiffRate achieves state-of-the-art performance. For example, by applying the learned layer-wise compression rates to an off-the-shelf ViT-H (MAE) model, we achieve a 40% FLOPs reduction and a 1.5x throughput improvement, with a minor accuracy drop of 0.16% on ImageNet without fine-tuning, even outperforming previous methods with fine-tuning. Codes and models are available at https://github.com/OpenGVLab/DiffRate.

Wenqi Shao, Yixiao Ge, Zhaoyang Zhang et al.

Vision Transformer (ViT) and its variants (e.g., Swin, PVT) have achieved great success in various computer vision tasks, owing to their capability to learn long-range contextual information. Layer Normalization (LN) is an essential ingredient in these models. However, we found that the ordinary LN makes tokens at different positions similar in magnitude because it normalizes embeddings within each token. It is difficult for Transformers to capture inductive bias such as the positional context in an image with LN. We tackle this problem by proposing a new normalizer, termed Dynamic Token Normalization (DTN), where normalization is performed both within each token (intra-token) and across different tokens (inter-token). DTN has several merits. Firstly, it is built on a unified formulation and thus can represent various existing normalization methods. Secondly, DTN learns to normalize tokens in both intra-token and inter-token manners, enabling Transformers to capture both the global contextual information and the local positional context. {Thirdly, by simply replacing LN layers, DTN can be readily plugged into various vision transformers, such as ViT, Swin, PVT, LeViT, T2T-ViT, BigBird and Reformer. Extensive experiments show that the transformer equipped with DTN consistently outperforms baseline model with minimal extra parameters and computational overhead. For example, DTN outperforms LN by $0.5\%$ - $1.2\%$ top-1 accuracy on ImageNet, by $1.2$ - $1.4$ box AP in object detection on COCO benchmark, by $2.3\%$ - $3.9\%$ mCE in robustness experiments on ImageNet-C, and by $0.5\%$ - $0.8\%$ accuracy in Long ListOps on Long-Range Arena.} Codes will be made public at \url{https://github.com/wqshao126/DTN}

Peize Sun, Yi Jiang, Enze Xie et al.

Object detection has recently achieved a breakthrough for removing the last one non-differentiable component in the pipeline, Non-Maximum Suppression (NMS), and building up an end-to-end system. However, what makes for its one-to-one prediction has not been well understood. In this paper, we first point out that one-to-one positive sample assignment is the key factor, while, one-to-many assignment in previous detectors causes redundant predictions in inference. Second, we surprisingly find that even training with one-to-one assignment, previous detectors still produce redundant predictions. We identify that classification cost in matching cost is the main ingredient: (1) previous detectors only consider location cost, (2) by additionally introducing classification cost, previous detectors immediately produce one-to-one prediction during inference. We introduce the concept of score gap to explore the effect of matching cost. Classification cost enlarges the score gap by choosing positive samples as those of highest score in the training iteration and reducing noisy positive samples brought by only location cost. Finally, we demonstrate the advantages of end-to-end object detection on crowded scenes. The code is available at: \url{https://github.com/PeizeSun/OneNet}.

Shitao Tang, Litong Feng, Wenqi Shao et al.

Knowledge Distillation (KD) has been used in image classification for model compression. However, rare studies apply this technology on single-stage object detectors. Focal loss shows that the accumulated errors of easily-classified samples dominate the overall loss in the training process. This problem is also encountered when applying KD in the detection task. For KD, the teacher-defined hard samples are far more important than any others. We propose ADL to address this issue by adaptively mimicking the teacher's logits, with more attention paid on two types of hard samples: hard-to-learn samples predicted by teacher with low certainty and hard-to-mimic samples with a large gap between the teacher's and the student's prediction. ADL enlarges the distillation loss for hard-to-learn and hard-to-mimic samples and reduces distillation loss for the dominant easy samples, enabling distillation to work on the single-stage detector first time, even if the student and the teacher are identical. Besides, ADL is effective in both the supervised setting and the semi-supervised setting, even when the labeled data and unlabeled data are from different distributions. For distillation on unlabeled data, ADL achieves better performance than existing data distillation which simply utilizes hard targets, making the student detector surpass its teacher. On the COCO database, semi-supervised adaptive distillation (SAD) makes a student detector with a backbone of ResNet-50 surpasses its teacher with a backbone of ResNet-101, while the student has half of the teacher's computation complexity. The code is avaiable at https://github.com/Tangshitao/Semi-supervised-Adaptive-Distillation

Yao Mu, Junting Chen, Qinglong Zhang et al.

Robotic behavior synthesis, the problem of understanding multimodal inputs and generating precise physical control for robots, is an important part of Embodied AI. Despite successes in applying multimodal large language models for high-level understanding, it remains challenging to translate these conceptual understandings into detailed robotic actions while achieving generalization across various scenarios. In this paper, we propose a tree-structured multimodal code generation framework for generalized robotic behavior synthesis, termed RoboCodeX. RoboCodeX decomposes high-level human instructions into multiple object-centric manipulation units consisting of physical preferences such as affordance and safety constraints, and applies code generation to introduce generalization ability across various robotics platforms. To further enhance the capability to map conceptual and perceptual understanding into control commands, a specialized multimodal reasoning dataset is collected for pre-training and an iterative self-updating methodology is introduced for supervised fine-tuning. Extensive experiments demonstrate that RoboCodeX achieves state-of-the-art performance in both simulators and real robots on four different kinds of manipulation tasks and one navigation task.

Yefei He, Feng Chen, Jing Liu et al.

The efficiency of large vision-language models (LVLMs) is constrained by the computational bottleneck of the attention mechanism during the prefill phase and the memory bottleneck of fetching the key-value (KV) cache in the decoding phase, particularly in scenarios involving high-resolution images or videos. Visual content often exhibits substantial redundancy, resulting in highly sparse attention maps within LVLMs. This sparsity can be leveraged to accelerate attention computation or compress the KV cache through various approaches. However, most studies focus on addressing only one of these bottlenecks and do not adequately support dynamic adjustment of sparsity concerning distinct layers or tasks. In this paper, we present ZipVL, an efficient inference framework designed for LVLMs through a dynamic ratio allocation strategy of important tokens. This ratio is adaptively determined based on the layer-specific distribution of attention scores, rather than fixed hyper-parameters, thereby improving efficiency for less complex tasks while maintaining high performance for more challenging ones. Then we select important tokens based on their normalized attention scores and perform sparse attention mechanism solely on those important tokens, reducing the latency in the prefill phase. Tokens deemed less important will be discarded to reduce KV cache size, alleviating the memory bottleneck in the decoding phase. Our experiments demonstrate that ZipVL can accelerate the prefill phase by 2.3$\times$ and improve decoding throughput by 2.8$\times$, with a minimal accuracy reduction of only 0.5\% on VQAv2 benchmark over LLaVA-Next-13B model, effectively enhancing the generation efficiency of LVLMs.

Yue Yang, Shuibai Zhang, Wenqi Shao et al.

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across multimodal tasks such as visual perception and reasoning, leading to good performance on various multimodal evaluation benchmarks. However, these benchmarks keep a static nature and overlap with the pre-training data, resulting in fixed complexity constraints and data contamination issues. This raises the concern regarding the validity of the evaluation. To address these two challenges, we introduce a dynamic multimodal evaluation protocol called Vision-Language Bootstrapping (VLB). VLB provides a robust and comprehensive assessment for LVLMs with reduced data contamination and flexible complexity. To this end, VLB dynamically generates new visual question-answering samples through a multimodal bootstrapping module that modifies both images and language, while ensuring that newly generated samples remain consistent with the original ones by a judge module. By composing various bootstrapping strategies, VLB offers dynamic variants of existing benchmarks with diverse complexities, enabling the evaluation to co-evolve with the ever-evolving capabilities of LVLMs. Extensive experimental results across multiple benchmarks, including SEEDBench, MMBench, and MME, show that VLB significantly reduces data contamination and exposes performance limitations of LVLMs.

Pengfei Zhou, Xiaopeng Peng, Jiajun Song et al.

Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding and generation tasks. However, generating interleaved image-text content remains a challenge, which requires integrated multimodal understanding and generation abilities. While the progress in unified models offers new solutions, existing benchmarks are insufficient for evaluating these methods due to limitations in data size and diversity. To bridge this gap, we introduce OpenING, a comprehensive benchmark comprising 5,400 high-quality human-annotated instances across 56 real-world tasks. OpenING covers diverse daily scenarios such as travel guide, design, and brainstorming, offering a robust platform for challenging interleaved generation methods. In addition, we present IntJudge, a judge model for evaluating open-ended multimodal generation methods. Trained with a novel data pipeline, our IntJudge achieves an agreement rate of 82.42% with human judgments, outperforming GPT-based evaluators by 11.34%. Extensive experiments on OpenING reveal that current interleaved generation methods still have substantial room for improvement. Key findings on interleaved image-text generation are further presented to guide the development of next-generation models.

Chuanhao Li, Zhen Li, Chenchen Jing et al.

Large vision-language models (LVLMs) are ignorant of the up-to-date knowledge, such as LLaVA series, because they cannot be updated frequently due to the large amount of resources required, and therefore fail in many cases. For example, if a LVLM was released on January 2024, and it wouldn't know the singer of the theme song for the new Detective Conan movie, which wasn't released until April 2024. To solve the problem, a promising solution motivated by retrieval-augmented generation (RAG) is to provide LVLMs with up-to-date knowledge via internet search during inference, i.e., internet-augmented generation (IAG), which is already integrated in some closed-source commercial LVLMs such as GPT-4V. However, the specific mechanics underpinning them remain a mystery. In this paper, we propose a plug-and-play framework, for augmenting existing LVLMs in handling visual question answering (VQA) about up-to-date knowledge, dubbed SearchLVLMs. A hierarchical filtering model is trained to effectively and efficiently find the most helpful content from the websites returned by a search engine to prompt LVLMs with up-to-date knowledge. To train the model and evaluate our framework's performance, we propose a pipeline to automatically generate news-related VQA samples to construct a dataset, dubbed UDK-VQA. A multi-model voting mechanism is introduced to label the usefulness of website/content for VQA samples to construct the training set. Experimental results demonstrate the effectiveness of our framework, outperforming GPT-4V by about 25% in accuracy.

Mengkang Hu, Tianxing Chen, Yude Zou et al.

Recently, there has been growing interest in leveraging large language models (LLMs) to generate symbolic world models from textual descriptions. Although LLMs have been extensively explored in the context of world modeling, prior studies encountered several challenges, including evaluation randomness, dependence on indirect metrics, and a limited domain scope. To address these limitations, we introduce a novel benchmark, Text2World, based on planning domain definition language (PDDL), featuring hundreds of diverse domains and employing multi-criteria, execution-based metrics for a more robust evaluation. We benchmark current LLMs using Text2World and find that reasoning models trained with large-scale reinforcement learning outperform others. However, even the best-performing model still demonstrates limited capabilities in world modeling. Building on these insights, we examine several promising strategies to enhance the world modeling capabilities of LLMs, including test-time scaling, agent training, and more. We hope that Text2World can serve as a crucial resource, laying the groundwork for future research in leveraging LLMs as world models. The project page is available at https://text-to-world.github.io/.

Zhaoyang Zhang, Wenqi Shao, Yixiao Ge et al. · tencent-ai

This work introduces a new Transformer model called Cached Transformer, which uses Gated Recurrent Cached (GRC) attention to extend the self-attention mechanism with a differentiable memory cache of tokens. GRC attention enables attending to both past and current tokens, increasing the receptive field of attention and allowing for exploring long-range dependencies. By utilizing a recurrent gating unit to continuously update the cache, our model achieves significant advancements in \textbf{six} language and vision tasks, including language modeling, machine translation, ListOPs, image classification, object detection, and instance segmentation. Furthermore, our approach surpasses previous memory-based techniques in tasks such as language modeling and displays the ability to be applied to a broader range of situations.

Yang Luo, Xuanlei Zhao, Mengzhao Chen et al.

DiT-based video generation has achieved remarkable results, but research into enhancing existing models remains relatively unexplored. In this work, we introduce a training-free approach to enhance the coherence and quality of DiT-based generated videos, named Enhance-A-Video. The core idea is enhancing the cross-frame correlations based on non-diagonal temporal attention distributions. Thanks to its simple design, our approach can be easily applied to most DiT-based video generation frameworks without any retraining or fine-tuning. Across various DiT-based video generation models, our approach demonstrates promising improvements in both temporal consistency and visual quality. We hope this research can inspire future explorations in video generation enhancement.

Jiahao Wang, Ning Kang, Lewei Yao et al.

In this paper, we investigate how to convert a pre-trained Diffusion Transformer (DiT) into a linear DiT, as its simplicity, parallelism, and efficiency for image generation. Through detailed exploration, we offer a suite of ready-to-use solutions, ranging from linear attention design to optimization strategies. Our core contributions include 5 practical guidelines: 1) Applying depth-wise convolution within simple linear attention is sufficient for image generation. 2) Using fewer heads in linear attention provides a free-lunch performance boost without increasing latency. 3) Inheriting weights from a fully converged, pre-trained DiT. 4) Loading all parameters except those related to linear attention. 5) Hybrid knowledge distillation: using a pre-trained teacher DiT to help the training of the student linear DiT, supervising not only the predicted noise but also the variance of the reverse diffusion process. These guidelines lead to our proposed \underline{L}inear D\underline{i}ffusion \underline{T}ransformer (LiT), which serves as a safe and efficient alternative baseline for DiT with pure linear attention. In class-conditional 256$\times$256 and 512$\times$512 ImageNet generation, LiT can be quickly adapted from DiT using only $20\%$ and $33\%$ of DiT's training steps, respectively, while achieving comparable performance. LiT also rivals methods based on Mamba or Gated Linear Attention. Moreover, the same guidelines generalize to text-to-image generation: LiT can be swiftly converted from PixArt-$Σ$ to generate high-quality images, maintaining comparable GenEval scores.

Pengfei Zhou, Xiaopeng Peng, Fanrui Zhang et al.

Multimodal large language models (MLLMs), which integrate language and visual cues for problem-solving, are crucial for advancing artificial general intelligence (AGI). However, current benchmarks for measuring the intelligence of MLLMs suffer from limited scale, narrow coverage, and unstructured knowledge, offering only static and undifferentiated evaluations. To bridge this gap, we introduce MDK12-Bench, a large-scale multidisciplinary benchmark built from real-world K-12 exams spanning six disciplines with 141K instances and 6,225 knowledge points organized in a six-layer taxonomy. Covering five question formats with difficulty and year annotations, it enables comprehensive evaluation to capture the extent to which MLLMs perform over four dimensions: 1) difficulty levels, 2) temporal (cross-year) shifts, 3) contextual shifts, and 4) knowledge-driven reasoning. We propose a novel dynamic evaluation framework that introduces unfamiliar visual, textual, and question form shifts to challenge model generalization while improving benchmark objectivity and longevity by mitigating data contamination. We further evaluate knowledge-point reference-augmented generation (KP-RAG) to examine the role of knowledge in problem-solving. Key findings reveal limitations in current MLLMs in multiple aspects and provide guidance for enhancing model robustness, interpretability, and AI-assisted education.