Extracting and Transferring Abilities For Building Multi-lingual Ability-enhanced Large Language Models

Multi-lingual ability transfer has become increasingly important for the broad application of large language models (LLMs). Existing work highly relies on training with the multi-lingual ability-related data, which may be not available for low-resource languages. To solve it, we propose a Multi-lingual Ability Extraction and Transfer approach, named as MAET. Our key idea is to decompose and extract language-agnostic ability-related weights from LLMs, and transfer them across different languages by simple addition and subtraction operations without training. Specially, our MAET consists of the extraction and transfer stages. In the extraction stage, we firstly locate key neurons that are highly related to specific abilities, and then employ them to extract the transferable ability-specific weights. In the transfer stage, we further select the ability-related parameter tensors, and design the merging strategy based on the linguistic and ability specific weights, to build the multi-lingual ability-enhanced LLM. To demonstrate the effectiveness of our proposed approach, we conduct extensive experiments on mathematical and scientific tasks in both high-resource lingual and low-resource lingual scenarios. Experiment results have shown that MAET can effectively and efficiently extract and transfer the advanced abilities, and outperform training-based baseline methods. Our code and data are available at \url{https://github.com/RUCAIBox/MAET}.

Explain EEG-based End-to-end Deep Learning Models in the Frequency Domain

The recent rise of EEG-based end-to-end deep learning models presents a significant challenge in elucidating how these models process raw EEG signals and generate predictions in the frequency domain. This challenge limits the transparency and credibility of EEG-based end-to-end models, hindering their application in security-sensitive areas. To address this issue, we propose a mask perturbation method to explain the behavior of end-to-end models in the frequency domain. Considering the characteristics of EEG data, we introduce a target alignment loss to mitigate the out-of-distribution problem associated with perturbation operations. Additionally, we develop a perturbation generator to define perturbation generation in the frequency domain. Our explanation method is validated through experiments on multiple representative end-to-end deep learning models in the EEG decoding field, using an established EEG benchmark dataset. The results demonstrate the effectiveness and superiority of our method, and highlight its potential to advance research in EEG-based end-to-end models.

MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic

The advent of large language models (LLMs) like GPT-4 has catalyzed the exploration of multi-task learning (MTL), in which a single model demonstrates proficiency across diverse tasks. Task arithmetic has emerged as a cost-effective approach for MTL. It enables performance enhancement across multiple tasks by adding their corresponding task vectors to a pre-trained model. However, the current lack of a method that can simultaneously achieve optimal performance, computational efficiency, and data privacy limits their application to LLMs. In this paper, we propose \textbf{M}odel \textbf{E}xclusive \textbf{T}ask \textbf{A}rithmetic for merging \textbf{GPT}-scale models, which formalizes the objective of model merging into a multi-task learning framework, aiming to minimize the average loss difference between the merged model and each individual task model. Since data privacy limits the use of multi-task training data, we leverage LLMs' local linearity and task vectors' orthogonality to separate the data term and scaling coefficients term and derive a model-exclusive task arithmetic method. Our proposed MetaGPT is data-agnostic and bypasses the heavy search process, making it cost-effective and easy to implement for LLMs.Extensive experiments demonstrate that MetaGPT leads to improvements in task arithmetic and achieves state-of-the-art performance on multiple tasks.

Networking Systems for Video Anomaly Detection: A Tutorial and Survey

The increasing prevalence of surveillance cameras in smart cities, coupled with the surge of online video applications, has heightened concerns regarding public security and privacy protection, which propelled automated Video Anomaly Detection (VAD) into a fundamental research task within the Artificial Intelligence (AI) community. With the advancements in deep learning and edge computing, VAD has made significant progress and advances synergized with emerging applications in smart cities and video internet, which has moved beyond the conventional research scope of algorithm engineering to deployable Networking Systems for VAD (NSVAD), a practical hotspot for intersection exploration in the AI, IoVT, and computing fields. In this article, we delineate the foundational assumptions, learning frameworks, and applicable scenarios of various deep learning-driven VAD routes, offering an exhaustive tutorial for novices in NSVAD. This article elucidates core concepts by reviewing recent advances and typical solutions, and aggregating available research resources (e.g., literatures, code, tools, and workshops) accessible at https://github.com/fdjingliu/NSVAD. Additionally, we showcase our latest NSVAD research in industrial IoT and smart cities, along with an end-cloud collaborative architecture for deployable NSVAD to further elucidate its potential scope of research and application. Lastly, this article projects future development trends and discusses how the integration of AI and computing technologies can address existing research challenges and promote open opportunities, serving as an insightful guide for prospective researchers and engineers.

Cascaded Self-supervised Learning for Subject-independent EEG-based Emotion Recognition

EEG-based Emotion recognition holds significant promise for applications in human-computer interaction, medicine, and neuroscience. While deep learning has shown potential in this field, current approaches usually rely on large-scale high-quality labeled datasets, limiting the performance of deep learning. Self-supervised learning offers a solution by automatically generating labels, but its inter-subject generalizability remains under-explored. For this reason, our interest lies in offering a self-supervised learning paradigm with better inter-subject generalizability. Inspired by recent efforts in combining low-level and high-level tasks in deep learning, we propose a cascaded self-supervised architecture for EEG emotion recognition. Then, we introduce a low-level task, time-to-frequency reconstruction (TFR). This task leverages the inherent time-frequency relationship in EEG signals. Our architecture integrates it with the high-level contrastive learning modules, performing self-supervised learning for EEG-based emotion recognition. Experiment on DEAP and DREAMER datasets demonstrates superior performance of our method over similar works. The outcome results also highlight the indispensability of the TFR task and the robustness of our method to label scarcity, validating the effectiveness of the proposed method.

SNI-SLAM: Semantic Neural Implicit SLAM

We propose SNI-SLAM, a semantic SLAM system utilizing neural implicit representation, that simultaneously performs accurate semantic mapping, high-quality surface reconstruction, and robust camera tracking. In this system, we introduce hierarchical semantic representation to allow multi-level semantic comprehension for top-down structured semantic mapping of the scene. In addition, to fully utilize the correlation between multiple attributes of the environment, we integrate appearance, geometry and semantic features through cross-attention for feature collaboration. This strategy enables a more multifaceted understanding of the environment, thereby allowing SNI-SLAM to remain robust even when single attribute is defective. Then, we design an internal fusion-based decoder to obtain semantic, RGB, Truncated Signed Distance Field (TSDF) values from multi-level features for accurate decoding. Furthermore, we propose a feature loss to update the scene representation at the feature level. Compared with low-level losses such as RGB loss and depth loss, our feature loss is capable of guiding the network optimization on a higher-level. Our SNI-SLAM method demonstrates superior performance over all recent NeRF-based SLAM methods in terms of mapping and tracking accuracy on Replica and ScanNet datasets, while also showing excellent capabilities in accurate semantic segmentation and real-time semantic mapping.

Baichuan 2: Open Large-scale Language Models

Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing the need for extensive feature engineering. However, most powerful LLMs are closed-source or limited in their capability for languages other than English. In this technical report, we present Baichuan 2, a series of large-scale multilingual language models containing 7 billion and 13 billion parameters, trained from scratch, on 2.6 trillion tokens. Baichuan 2 matches or outperforms other open-source models of similar size on public benchmarks like MMLU, CMMLU, GSM8K, and HumanEval. Furthermore, Baichuan 2 excels in vertical domains such as medicine and law. We will release all pre-training model checkpoints to benefit the research community in better understanding the training dynamics of Baichuan 2.

SC-NeRF: Self-Correcting Neural Radiance Field with Sparse Views

In recent studies, the generalization of neural radiance fields for novel view synthesis task has been widely explored. However, existing methods are limited to objects and indoor scenes. In this work, we extend the generalization task to outdoor scenes, trained only on object-level datasets. This approach presents two challenges. Firstly, the significant distributional shift between training and testing scenes leads to black artifacts in rendering results. Secondly, viewpoint changes in outdoor scenes cause ghosting or missing regions in rendered images. To address these challenges, we propose a geometric correction module and an appearance correction module based on multi-head attention mechanisms. We normalize rendered depth and combine it with light direction as query in the attention mechanism. Our network effectively corrects varying scene structures and geometric features in outdoor scenes, generalizing well from object-level to unseen outdoor scenes. Additionally, we use appearance correction module to correct appearance features, preventing rendering artifacts like blank borders and ghosting due to viewpoint changes. By combining these modules, our approach successfully tackles the challenges of outdoor scene generalization, producing high-quality rendering results. When evaluated on four datasets (Blender, DTU, LLFF, Spaces), our network outperforms previous methods. Notably, compared to MVSNeRF, our network improves average PSNR from 19.369 to 25.989, SSIM from 0.838 to 0.889, and reduces LPIPS from 0.265 to 0.224 on Spaces outdoor scenes.

Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception

Multi-agent collaborative perception as a potential application for vehicle-to-everything communication could significantly improve the perception performance of autonomous vehicles over single-agent perception. However, several challenges remain in achieving pragmatic information sharing in this emerging research. In this paper, we propose SCOPE, a novel collaborative perception framework that aggregates the spatio-temporal awareness characteristics across on-road agents in an end-to-end manner. Specifically, SCOPE has three distinct strengths: i) it considers effective semantic cues of the temporal context to enhance current representations of the target agent; ii) it aggregates perceptually critical spatial information from heterogeneous agents and overcomes localization errors via multi-scale feature interactions; iii) it integrates multi-source representations of the target agent based on their complementary contributions by an adaptive fusion paradigm. To thoroughly evaluate SCOPE, we consider both real-world and simulated scenarios of collaborative 3D object detection tasks on three datasets. Extensive experiments demonstrate the superiority of our approach and the necessity of the proposed components.

Multi-scale Spatial-temporal Interaction Network for Video Anomaly Detection

Video anomaly detection (VAD) is an essential yet challenge task in signal processing. Since certain anomalies cannot be detected by analyzing temporal or spatial information alone, the interaction between two types of information is considered crucial for VAD. However, current dual-stream architectures either limit interaction between the two types of information to the bottleneck of autoencoder or incorporate background pixels irrelevant to anomalies into the interaction. To this end, we propose a multi-scale spatial-temporal interaction network (MSTI-Net) for VAD. First, to pay particular attention to objects and reconcile the significant semantic differences between the two information, we propose an attention-based spatial-temporal fusion module (ASTM) as a substitute for the conventional direct fusion. Furthermore, we inject multi ASTM-based connections between the appearance and motion pathways of a dual stream network to facilitate spatial-temporal interaction at all possible scales. Finally, the regular information learned from multiple scales is recorded in memory to enhance the differentiation between anomalies and normal events during the testing phase. Solid experimental results on three standard datasets validate the effectiveness of our approach, which achieve AUCs of 96.8% for UCSD Ped2, 87.6% for CUHK Avenue, and 73.9% for the ShanghaiTech dataset.