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 title, 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 extensive multi-modal multilingual concepts 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, and CCBench (Chinese Cultural Benchmark). 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 with 7B parameters are publicly available at https://github.com/InternLM/InternLM-XComposer.
Reconfigurable intelligent surface (RIS) is a promising candidate technology for the upcoming Sixth Generation (6G) communication system for its ability to manipulate the wireless communication environment by controlling the coefficients of reflection elements (REs). However, since the RIS usually consists of a large number of passive REs, the pilot overhead for channel estimation in the RIS-aided system is prohibitively high. In this paper, the channel estimation problem for a RIS-aided multi-user multiple-input-single-output (MISO) communication system with clustered users is investigated. First, to describe the correlated feature for RIS-user channels, a beam domain channel model is developed for RIS-user channels. Then, a pilot reuse strategy is put forward to reduce the pilot overhead and decompose the channel estimation problem into several subproblems. Finally, by leveraging the correlated nature of RIS-user channels, an eigenspace projection (EP) algorithm is proposed to solve each subproblem respectively. Simulation results show that the proposed EP channel estimation scheme can achieve accurate channel estimation with lower pilot overhead than existing schemes.
Reconfigurable intelligent surface (RIS) is a promising candidate technology of the upcoming Sixth Generation (6G) communication system for its ability to provide unprecedented spectral and energy efficiency increment through passive beamforming. However, it is challenging to obtain instantaneous channel state information (I-CSI) for RIS, which obliges us to use statistical channel state information (S-CSI) to achieve passive beamforming. In this paper, RIS-aided multiple-input single-output (MISO) multi-user downlink communication system with correlated channels is investigated. Then, we formulate the problem of joint beamforming design at the AP and RIS to maximize the sum ergodic spectral efficiency (ESE) of all users to improve the network capacity. Since it is too hard to compute sum ESE, an ESE approximation is adopted to reformulate the problem into a more tractable form. Then, we present two joint beamforming algorithms, namely the singular value decomposition-gradient descent (SVD-GD) algorithm and the fractional programming-gradient descent (FP-GD) algorithm. Simulation results show the effectiveness of our proposed algorithms and validate that 2-bits quantizer is enough for RIS phase shifts implementation.
Domain generalization aims to train models on multiple source domains so that they can generalize well to unseen target domains. Among many domain generalization methods, Fourier-transform-based domain generalization methods have gained popularity primarily because they exploit the power of Fourier transformation to capture essential patterns and regularities in the data, making the model more robust to domain shifts. The mainstream Fourier-transform-based domain generalization swaps the Fourier amplitude spectrum while preserving the phase spectrum between the source and the target images. However, it neglects background interference in the amplitude spectrum. To overcome this limitation, we introduce a soft-thresholding function in the Fourier domain. We apply this newly designed algorithm to retinal fundus image segmentation, which is important for diagnosing ocular diseases but the neural network's performance can degrade across different sources due to domain shifts. The proposed technique basically enhances fundus image augmentation by eliminating small values in the Fourier domain and providing better generalization. The innovative nature of the soft thresholding fused with Fourier-transform-based domain generalization improves neural network models' performance by reducing the target images' background interference significantly. Experiments on public data validate our approach's effectiveness over conventional and state-of-the-art methods with superior segmentation metrics.
Many mathematical models have been leveraged to design embeddings for representing Knowledge Graph (KG) entities and relations for link prediction and many downstream tasks. These mathematically-inspired models are not only highly scalable for inference in large KGs, but also have many explainable advantages in modeling different relation patterns that can be validated through both formal proofs and empirical results. In this paper, we make a comprehensive overview of the current state of research in KG completion. In particular, we focus on two main branches of KG embedding (KGE) design: 1) distance-based methods and 2) semantic matching-based methods. We discover the connections between recently proposed models and present an underlying trend that might help researchers invent novel and more effective models. Next, we delve into CompoundE and CompoundE3D, which draw inspiration from 2D and 3D affine operations, respectively. They encompass a broad spectrum of techniques including distance-based and semantic-based methods. We will also discuss an emerging approach for KG completion which leverages pre-trained language models (PLMs) and textual descriptions of entities and relations and offer insights into the integration of KGE embedding methods with PLMs for KG completion.
Recommender systems usually leverage multi-task learning methods to simultaneously optimize several objectives because of the multi-faceted user behavior data. The typical way of conducting multi-task learning is to establish appropriate parameter sharing across multiple tasks at lower layers while reserving a separate task tower for each task at upper layers. Since the task towers exert direct impact on the prediction results, we argue that the architecture of standalone task towers is sub-optimal for promoting positive knowledge sharing. Accordingly, we propose the framework of Deep Mutual Learning across task towers, which is compatible with various backbone multi-task networks. Extensive offline experiments and online AB tests are conducted to evaluate and verify the proposed approach's effectiveness.
Deep learning models are widely deployed in many applications, such as object detection in various security fields. However, these models are vulnerable to backdoor attacks. Most backdoor attacks were intensively studied on classified models, but little on object detection. Previous works mainly focused on the backdoor attack in the digital world, but neglect the real world. Especially, the backdoor attack's effect in the real world will be easily influenced by physical factors like distance and illumination. In this paper, we proposed a variable-size backdoor trigger to adapt to the different sizes of attacked objects, overcoming the disturbance caused by the distance between the viewing point and attacked object. In addition, we proposed a backdoor training named malicious adversarial training, enabling the backdoor object detector to learn the feature of the trigger with physical noise. The experiment results show this robust backdoor attack (RBA) could enhance the attack success rate in the real world.
The integration of visual encoders and large language models (LLMs) has driven recent progress in multimodal large language models (MLLMs). However, the scarcity of high-quality instruction-tuning data for vision-language tasks remains a challenge. The current leading paradigm, such as LLaVA, relies on language-only GPT-4 to generate data, which requires pre-annotated image captions and detection bounding boxes, suffering from understanding image details. A practical solution to this problem would be to utilize the available multimodal large language models (MLLMs) to generate instruction data for vision-language tasks. However, it's worth noting that the currently accessible MLLMs are not as powerful as their LLM counterparts, as they tend to produce inadequate responses and generate false information. As a solution for addressing the current issue, this paper proposes the Visual Instruction Generation and Correction (VIGC) framework that enables multimodal large language models to generate instruction-tuning data and progressively enhance its quality on-the-fly. Specifically, Visual Instruction Generation (VIG) guides the vision-language model to generate diverse instruction-tuning data. To ensure generation quality, Visual Instruction Correction (VIC) adopts an iterative update mechanism to correct any inaccuracies in data produced by VIG, effectively reducing the risk of hallucination. Leveraging the diverse, high-quality data generated by VIGC, we finetune mainstream models and validate data quality based on various evaluations. Experimental results demonstrate that VIGC not only compensates for the shortcomings of language-only data generation methods, but also effectively enhances the benchmark performance. The models, datasets, and code are available at https://opendatalab.github.io/VIGC.
Despite the great advance of Multimodal Large Language Models (MLLMs) in both instruction dataset building and benchmarking, the independence of training and evaluation makes current MLLMs hard to further improve their capability under the guidance of evaluation results with a relatively low human cost. In this paper, we propose MLLM-DataEngine, a novel closed-loop system that bridges data generation, model training, and evaluation. Within each loop iteration, the MLLM-DataEngine first analyze the weakness of the model based on the evaluation results, then generate a proper incremental dataset for the next training iteration and enhance the model capability iteratively. Compared with previous data collection methods which are separate from the benchmarking, the data generated by MLLM-DataEngine shows better targeting, quality, and correctness. For targeting, we propose an Adaptive Bad-case Sampling module, which adjusts the ratio of different types of data within each incremental dataset based on the benchmarking results. For quality, we resort to GPT-4 to generate high-quality data with each given data type. For correctness, prompt design is critical for the data generation results. Rather than previous hand-crafted prompt, we propose an Interactive Prompt Optimization strategy, which optimizes the prompt with the multi-round interaction between human and GPT, and improve the correctness of generated data greatly. Through extensive experiments, we find our MLLM-DataEngine could boost the MLLM capability in a targeted and automatic manner, with only a few human participation. We hope it could be a general solution for the following MLLMs building. The MLLM-DataEngine has been open-sourced and is now available at https://github.com/opendatalab/MLLM-DataEngine.