Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in multimodal understanding, reasoning, and interaction. Given the extensive applications of MLLMs, the associated safety issues have become increasingly critical. Due to the effectiveness of preference optimization in aligning MLLMs with human preferences, there is an urgent need for safety-related preference data for MLLMs. To address this, we construct the MMSafe-PO preference dataset towards harmless multimodal assistants, featuring multimodal instructions, the conversational format, and ranked paired responses from human feedback. We also identify two insightful observations: modality co-defense and modality cheating, which illustrate that MLLMs possess a certain level of inherent defense while still presenting unique safety challenges. Based on these observations, we propose the Blind Preference Optimization (BPO) approach. Comprehensive experiments on three benchmarks show that BPO effectively enhances the safety capabilities of MLLMs. Notably, BPO significantly improves the safety rate of the base MLLM by 45.0%, outperforming the DPO approach. Additionally, applying BPO to the MMSafe-PO dataset greatly reduces the base MLLM's unsafe rate on other safety benchmarks (14.5% on MM-SafetyBench and 82.9% on HarmEval, demonstrating the effectiveness and robustness of both the dataset and the approach. We release code and data at https://lu-yang666.github.io/MMsafe-PO-Web/.

Universal Information Extraction (UIE) has garnered significant attention due to its ability to address model explosion problems effectively. Extractive UIE can achieve strong performance using a relatively small model, making it widely adopted. Extractive UIEs generally rely on task instructions for different tasks, including single-target instructions and multiple-target instructions. Single-target instruction UIE enables the extraction of only one type of relation at a time, limiting its ability to model correlations between relations and thus restricting its capability to extract complex relations. While multiple-target instruction UIE allows for the extraction of multiple relations simultaneously, the inclusion of irrelevant relations introduces decision complexity and impacts extraction accuracy. Therefore, for multi-relation extraction, we propose LDNet, which incorporates multi-aspect relation modeling and a label drop mechanism. By assigning different relations to different levels for understanding and decision-making, we reduce decision confusion. Additionally, the label drop mechanism effectively mitigates the impact of irrelevant relations. Experiments show that LDNet outperforms or achieves competitive performance with state-of-the-art systems on 9 tasks, 33 datasets, in both single-modal and multi-modal, few-shot and zero-shot settings.\footnote{https://github.com/Lu-Yang666/LDNet}

Symbolic music is represented in two distinct forms: two-dimensional, visually intuitive score images, and one-dimensional, standardized text annotation sequences. While large language models have shown extraordinary potential in music, current research has primarily focused on unimodal symbol sequence text. Existing general-domain visual language models still lack the ability of music notation understanding. Recognizing this gap, we propose NOTA, the first large-scale comprehensive multimodal music notation dataset. It consists of 1,019,237 records, from 3 regions of the world, and contains 3 tasks. Based on the dataset, we trained NotaGPT, a music notation visual large language model. Specifically, we involve a pre-alignment training phase for cross-modal alignment between the musical notes depicted in music score images and their textual representation in ABC notation. Subsequent training phases focus on foundational music information extraction, followed by training on music notation analysis. Experimental results demonstrate that our NotaGPT-7B achieves significant improvement on music understanding, showcasing the effectiveness of NOTA and the training pipeline. Our datasets are open-sourced at https://huggingface.co/datasets/MYTH-Lab/NOTA-dataset.

Ensuring compliance with international data protection standards for privacy and data security is a crucial but complex task, often requiring substantial legal expertise. This paper introduces LegiLM, a novel legal language model specifically tailored for consulting on data or information compliance. LegiLM leverages a pre-trained GDPR Fines dataset and has been fine-tuned to automatically assess whether particular actions or events breach data security and privacy regulations. By incorporating a specialized dataset that includes global data protection laws, meticulously annotated policy documents, and relevant privacy policies, LegiLM is optimized for addressing data compliance challenges. The model integrates advanced legal reasoning methods and information retrieval enhancements to enhance accuracy and reliability in practical legal consulting scenarios. Our evaluation using a custom benchmark dataset demonstrates that LegiLM excels in detecting data regulation breaches, offering sound legal justifications, and recommending necessary compliance modifications, setting a new benchmark for AI-driven legal compliance solutions. Our resources are publicly available at https://github.com/DAOLegalAI/LegiLM

Despite large-scale diffusion models being highly capable of generating diverse open-world content, they still struggle to match the photorealism and fidelity of concept-specific generators. In this work, we present the task of customizing large-scale diffusion priors for specific concepts as concept-centric personalization. Our goal is to generate high-quality concept-centric images while maintaining the versatile controllability inherent to open-world models, enabling applications in diverse tasks such as concept-centric stylization and image translation. To tackle these challenges, we identify catastrophic forgetting of guidance prediction from diffusion priors as the fundamental issue. Consequently, we develop a guidance-decoupled personalization framework specifically designed to address this task. We propose Generalized Classifier-free Guidance (GCFG) as the foundational theory for our framework. This approach extends Classifier-free Guidance (CFG) to accommodate an arbitrary number of guidances, sourced from a variety of conditions and models. Employing GCFG enables us to separate conditional guidance into two distinct components: concept guidance for fidelity and control guidance for controllability. This division makes it feasible to train a specialized model for concept guidance, while ensuring both control and unconditional guidance remain intact. We then present a null-text Concept-centric Diffusion Model as a concept-specific generator to learn concept guidance without the need for text annotations. Code will be available at https://github.com/PRIV-Creation/Concept-centric-Personalization.

Accurate perception of objects in the environment is important for improving the scene understanding capability of SLAM systems. In robotic and augmented reality applications, object maps with semantic and metric information show attractive advantages. In this paper, we present RO-MAP, a novel multi-object mapping pipeline that does not rely on 3D priors. Given only monocular input, we use neural radiance fields to represent objects and couple them with a lightweight object SLAM based on multi-view geometry, to simultaneously localize objects and implicitly learn their dense geometry. We create separate implicit models for each detected object and train them dynamically and in parallel as new observations are added. Experiments on synthetic and real-world datasets demonstrate that our method can generate semantic object map with shape reconstruction, and be competitive with offline methods while achieving real-time performance (25Hz). The code and dataset will be available at: https://github.com/XiaoHan-Git/RO-MAP

Recently, inversion methods have been exploring the incorporation of additional high-rate information from pretrained generators (such as weights or intermediate features) to improve the refinement of inversion and editing results from embedded latent codes. While such techniques have shown reasonable improvements in reconstruction, they often lead to a decrease in editing capability, especially when dealing with complex images that contain occlusions, detailed backgrounds, and artifacts. To address this problem, we propose a novel refinement mechanism called Domain-Specific Hybrid Refinement (DHR), which draws on the advantages and disadvantages of two mainstream refinement techniques. We find that the weight modulation can gain favorable editing results but is vulnerable to these complex image areas and feature modulation is efficient at reconstructing. Hence, we divide the image into two domains and process them with these two methods separately. We first propose a Domain-Specific Segmentation module to automatically segment images into in-domain and out-of-domain parts according to their invertibility and editability without additional data annotation, where our hybrid refinement process aims to maintain the editing capability for in-domain areas and improve fidelity for both of them.

Traditional image stitching focuses on a single panorama frame without considering the spatial-temporal consistency in videos. The straightforward image stitching approach will cause temporal flicking and color inconstancy when it is applied to the video stitching task. Besides, inaccurate camera parameters will cause artifacts in the image warping. In this paper, we propose a real-time system to stitch multiple video sequences into a panoramic video, which is based on GPU accelerated color correction and frame warping without accurate camera parameters. We extend the traditional 2D-Matrix (2D-M) color correction approach and a present spatio-temporal 3D-Matrix (3D-M) color correction method for the overlap local regions with online color balancing using a piecewise function on global frames. Furthermore, we use pairwise homography matrices given by coarse camera calibration for global warping followed by accurate local warping based on the optical flow. Experimental results show that our system can generate highquality panorama videos in real time.

The virtual viewpoint is perceived as a new technique in virtual navigation, as yet not supported due to the lack of depth information and obscure camera parameters. In this paper, a method for achieving close-up virtual view is proposed and it only uses optical flow to build parallax effects to realize pseudo 3D projection without using depth sensor. We develop a bidirectional optical flow method to obtain any virtual viewpoint by proportional interpolation of optical flow. Moreover, with the ingenious application of the optical-flow-value, we achieve clear and visual-fidelity magnified results through lens stretching in any corner, which overcomes the visual distortion and image blur through viewpoint magnification and transition in Google Street View system.

Regressing the vector field of a dynamical system from a finite number of observed states is a natural way to learn surrogate models for such systems. A simple and interpretable way to learn a dynamical system from data is to interpolate its vector-field with a data-adapted kernel which can be learned by using Kernel Flows. The method of Kernel Flows is a trainable machine learning method that learns the optimal parameters of a kernel based on the premise that a kernel is good if there is no significant loss in accuracy if half of the data is used. The objective function could be a short-term prediction or some other objective for other variants of Kernel Flows). However, this method is limited by the choice of the base kernel. In this paper, we introduce the method of \emph{Sparse Kernel Flows } in order to learn the ``best'' kernel by starting from a large dictionary of kernels. It is based on sparsifying a kernel that is a linear combination of elemental kernels. We apply this approach to a library of 132 chaotic systems.