Search

A significant challenge in sound event detection (SED) is the effective utilization of unlabeled data, given the limited availability of labeled data due to high annotation costs. Semi-supervised algorithms rely on labeled data to learn from unlabeled data, and the performance is constrained by the quality and size of the former. In this paper, we introduce the Prototype based Masked Audio Model~(PMAM) algorithm for self-supervised representation learning in SED, to better exploit unlabeled data. Specifically, semantically rich frame-level pseudo labels are constructed from a Gaussian mixture model (GMM) based prototypical distribution modeling. These pseudo labels supervise the learning of a Transformer-based masked audio model, in which binary cross-entropy loss is employed instead of the widely used InfoNCE loss, to provide independent loss contributions from different prototypes, which is important in real scenarios in which multiple labels may apply to unsupervised data frames. A final stage of fine-tuning with just a small amount of labeled data yields a very high performing SED model. On like-for-like tests using the DESED task, our method achieves a PSDS1 score of 62.5\%, surpassing current state-of-the-art models and demonstrating the superiority of the proposed technique., Comment: Submitted to ICASSP2025; The code for this paper will be available at https://github.com/cai525/Transformer4SED after the paper is accepted

We construct entire curves in projective spaces, which are frequently hypercyclic simultaneously for countably many given translations, with optimal slow growth rates.

This paper describes the USTC-KXDIGIT system submitted to the ASVspoof5 Challenge for Track 1 (speech deepfake detection) and Track 2 (spoofing-robust automatic speaker verification, SASV). Track 1 showcases a diverse range of technical qualities from potential processing algorithms and includes both open and closed conditions. For these conditions, our system consists of a cascade of a frontend feature extractor and a back-end classifier. We focus on extensive embedding engineering and enhancing the generalization of the back-end classifier model. Specifically, the embedding engineering is based on hand-crafted features and speech representations from a self-supervised model, used for closed and open conditions, respectively. To detect spoof attacks under various adversarial conditions, we trained multiple systems on an augmented training set. Additionally, we used voice conversion technology to synthesize fake audio from genuine audio in the training set to enrich the synthesis algorithms. To leverage the complementary information learned by different model architectures, we employed activation ensemble and fused scores from different systems to obtain the final decision score for spoof detection. During the evaluation phase, the proposed methods achieved 0.3948 minDCF and 14.33% EER in the close condition, and 0.0750 minDCF and 2.59% EER in the open condition, demonstrating the robustness of our submitted systems under adversarial conditions. In Track 2, we continued using the CM system from Track 1 and fused it with a CNN-based ASV system. This approach achieved 0.2814 min-aDCF in the closed condition and 0.0756 min-aDCF in the open condition, showcasing superior performance in the SASV system., Comment: ASVspoof5 workshop paper

Sound event detection (SED) methods that leverage a large pre-trained Transformer encoder network have shown promising performance in recent DCASE challenges. However, they still rely on an RNN-based context network to model temporal dependencies, largely due to the scarcity of labeled data. In this work, we propose a pure Transformer-based SED model with masked-reconstruction based pre-training, termed MAT-SED. Specifically, a Transformer with relative positional encoding is first designed as the context network, pre-trained by the masked-reconstruction task on all available target data in a self-supervised way. Both the encoder and the context network are jointly fine-tuned in a semi-supervised manner. Furthermore, a global-local feature fusion strategy is proposed to enhance the localization capability. Evaluation of MAT-SED on DCASE2023 task4 surpasses state-of-the-art performance, achieving 0.587/0.896 PSDS1/PSDS2 respectively., Comment: Received by interspeech 2024

We present the design and scalable implementation of an exascale climate emulator for addressing the escalating computational and storage requirements of high-resolution Earth System Model simulations. We utilize the spherical harmonic transform to stochastically model spatio-temporal variations in climate data. This provides tunable spatio-temporal resolution and significantly improves the fidelity and granularity of climate emulation, achieving an ultra-high spatial resolution of 0.034 (approximately 3.5 km) in space. Our emulator, trained on 318 billion hourly temperature data points from a 35-year and 31 billion daily data points from an 83-year global simulation ensemble, generates statistically consistent climate emulations. We extend linear solver software to mixed-precision arithmetic GPUs, applying different precisions within a single solver to adapt to different correlation strengths. The PaRSEC runtime system supports efficient parallel matrix operations by optimizing the dynamic balance between computation, communication, and memory requirements. Our BLAS3-rich code is optimized for systems equipped with four different families and generations of GPUs, scaling well to achieve 0.976 EFlop/s on 9,025 nodes (36,100 AMD MI250X multichip module (MCM) GPUs) of Frontier (nearly full system), 0.739 EFlop/s on 1,936 nodes (7,744 Grace-Hopper Superchips (GH200)) of Alps, 0.243 EFlop/s on 1,024 nodes (4,096 A100 GPUs) of Leonardo, and 0.375 EFlop/s on 3,072 nodes (18,432 V100 GPUs) of Summit.

Facial Expression Analysis remains a challenging task due to unexpected task-irrelevant noise, such as identity, head pose, and background. To address this issue, this paper proposes a novel framework, called Norface, that is unified for both Action Unit (AU) analysis and Facial Emotion Recognition (FER) tasks. Norface consists of a normalization network and a classification network. First, the carefully designed normalization network struggles to directly remove the above task-irrelevant noise, by maintaining facial expression consistency but normalizing all original images to a common identity with consistent pose, and background. Then, these additional normalized images are fed into the classification network. Due to consistent identity and other factors (e.g. head pose, background, etc.), the normalized images enable the classification network to extract useful expression information more effectively. Additionally, the classification network incorporates a Mixture of Experts to refine the latent representation, including handling the input of facial representations and the output of multiple (AU or emotion) labels. Extensive experiments validate the carefully designed framework with the insight of identity normalization. The proposed method outperforms existing SOTA methods in multiple facial expression analysis tasks, including AU detection, AU intensity estimation, and FER tasks, as well as their cross-dataset tasks. For the normalized datasets and code please visit {https://norface-fea.github.io/}., Comment: Accepted by ECCV2024

Interrogation of biological pathways is an integral part of omics data analysis. Large language models (LLMs) enable the generation of custom pathways and gene sets tailored to specific scientific questions. These targeted sets are significantly smaller than traditional pathway enrichment analysis libraries, reducing multiple hypothesis testing and potentially enhancing statistical power. Lomics (Large Language Models for Omics Studies) v1.0 is a python-based bioinformatics toolkit that streamlines the generation of pathways and gene sets for transcriptomic analysis. It operates in three steps: 1) deriving relevant pathways based on the researcher's scientific question, 2) generating valid gene sets for each pathway, and 3) outputting the results as .GMX files. Lomics also provides explanations for pathway selections. Consistency and accuracy are ensured through iterative processes, JSON format validation, and HUGO Gene Nomenclature Committee (HGNC) gene symbol verification. Lomics serves as a foundation for integrating LLMs into omics research, potentially improving the specificity and efficiency of pathway analysis.

We establish a convergence speed estimate for hole probabilities of zeros of random holomorphic sections on compact Riemann surfaces.

Electronic Medical Records (EMRs), while integral to modern healthcare, present challenges for clinical reasoning and diagnosis due to their complexity and information redundancy. To address this, we proposed medIKAL (Integrating Knowledge Graphs as Assistants of LLMs), a framework that combines Large Language Models (LLMs) with knowledge graphs (KGs) to enhance diagnostic capabilities. medIKAL assigns weighted importance to entities in medical records based on their type, enabling precise localization of candidate diseases within KGs. It innovatively employs a residual network-like approach, allowing initial diagnosis by the LLM to be merged into KG search results. Through a path-based reranking algorithm and a fill-in-the-blank style prompt template, it further refined the diagnostic process. We validated medIKAL's effectiveness through extensive experiments on a newly introduced open-sourced Chinese EMR dataset, demonstrating its potential to improve clinical diagnosis in real-world settings.

Between 2021 and 2023, AI-Olympics, a series of online AI competitions was hosted by the online evaluation platform Jidi in collaboration with the IJCAI committee. In these competitions, an agent is required to accomplish diverse sports tasks in a two-dimensional continuous world, while competing against an opponent. This paper provides a brief overview of the competition series and highlights notable findings. We aim to contribute insights to the field of multi-agent decision-making and explore the generalization of agents through engineering efforts., Comment: IJCAI 2024 Demo Track Paper

Recently, Hadfield et al. proposed the Quantum Alternating Operator Ansatz (QAOA+) to tackle Constrained Combinatorial Optimization Problems (CCOPs). This paper proposes a Progressive Quantum Algorithm (PQA) to reduce the required qubits in solving the Maximum Independent Set (MIS) problem using QAOA+ ansatz. PQA constructs a subgraph that contains the MIS solution of the target graph $G$ and then solves the MIS problem on this subgraph to obtain the solution for $G$. To induce such a subgraph, PQA starts with a small-scale initial subgraph and progressively expands its graph size utilizing designed expansion rules. After each expansion, PQA solves the MIS problem on the current subgraph using QAOA+. In each run, PQA repeats the graph expansion and solving process until a predefined stopping condition is reached. Simulation results demonstrate that to achieve an optimal approximation ratio of 0.95, PQA requires only $5.5565\%$ ($15.4\%$) of the qubits and $10.695\%$ ($7.23\%$) of the runtime compared with QAOA+ on Erd\H{o}s-R\'enyi (regular) graphs, highlighting the efficiency of PQA.

The Lucas critique emphasizes the importance of considering the impact of policy changes on the expectations of micro-level agents in macroeconomic policymaking. However, the inherently self-interested nature of large-scale micro-agents, who pursue long-term benefits, complicates the formulation of optimal macroeconomic policies. This paper proposes a novel general framework named Dynamic Stackelberg Mean Field Games (Dynamic SMFG) to model such policymaking within sequential decision-making processes, with the government as the leader and households as dynamic followers. Dynamic SMFGs capture the dynamic interactions among large-scale households and their response to macroeconomic policy changes. To solve dynamic SMFGs, we propose the Stackelberg Mean Field Reinforcement Learning (SMFRL) algorithm, which leverages the population distribution of followers to represent high-dimensional joint state and action spaces. In experiments, our method surpasses macroeconomic policies in the real world, existing AI-based and economic methods. It allows the leader to approach the social optimum with the highest performance, while large-scale followers converge toward their best response to the leader's policy. Besides, we demonstrate that our approach retains effectiveness even when some households do not adopt the SMFG policy. In summary, this paper contributes to the field of AI for economics by offering an effective tool for modeling and solving macroeconomic policy-making issues., Comment: 19 pages, 7 figures, 4 tables

Neural network is a powerful learning paradigm for data feature learning in the era of big data. However, most neural network models are deterministic models that ignore the uncertainty of data. Fuzzy neural networks are proposed to address this problem. FDNN is a hierarchical deep neural network that derives information from both fuzzy and neural representations, the representations are then fused to form representation to be classified. FDNN perform well on uncertain data classification tasks. In this paper, we proposed a novel hierarchical fused quantum fuzzy neural network (HQFNN). Different from classical FDNN, HQFNN uses quantum neural networks to learn fuzzy membership functions in fuzzy neural network. We conducted simulated experiment on two types of datasets (Dirty-MNIST and 15-Scene), the results show that the proposed model can outperform several existing methods. In addition, we demonstrate the robustness of the proposed quantum circuit.

Recent advancements in text-to-image models have significantly enhanced image generation capabilities, yet a notable gap of open-source models persists in bilingual or Chinese language support. To address this need, we present Taiyi-Diffusion-XL, a new Chinese and English bilingual text-to-image model which is developed by extending the capabilities of CLIP and Stable-Diffusion-XL through a process of bilingual continuous pre-training. This approach includes the efficient expansion of vocabulary by integrating the most frequently used Chinese characters into CLIP's tokenizer and embedding layers, coupled with an absolute position encoding expansion. Additionally, we enrich text prompts by large vision-language model, leading to better images captions and possess higher visual quality. These enhancements are subsequently applied to downstream text-to-image models. Our empirical results indicate that the developed CLIP model excels in bilingual image-text retrieval.Furthermore, the bilingual image generation capabilities of Taiyi-Diffusion-XL surpass previous models. This research leads to the development and open-sourcing of the Taiyi-Diffusion-XL model, representing a notable advancement in the field of image generation, particularly for Chinese language applications. This contribution is a step forward in addressing the need for more diverse language support in multimodal research. The model and demonstration are made publicly available at \href{https://huggingface.co/IDEA-CCNL/Taiyi-Stable-Diffusion-XL-3.5B/}, fostering further research and collaboration in this domain., Comment: Taiyi-Diffusion-XL Tech Report

With the open-sourcing of text-to-image models (T2I) such as stable diffusion (SD) and stable diffusion XL (SD-XL), there is an influx of models fine-tuned in specific domains based on the open-source SD model, such as in anime, character portraits, etc. However, there are few specialized models in certain domains, such as interior design, which is attributed to the complex textual descriptions and detailed visual elements inherent in design, alongside the necessity for adaptable resolution. Therefore, text-to-image models for interior design are required to have outstanding prompt-following capabilities, as well as iterative collaboration with design professionals to achieve the desired outcome. In this paper, we collect and optimize text-image data in the design field and continue training in both English and Chinese on the basis of the open-source CLIP model. We also proposed a fine-tuning strategy with curriculum learning and reinforcement learning from CLIP feedback to enhance the prompt-following capabilities of our approach so as to improve the quality of image generation. The experimental results on the collected dataset demonstrate the effectiveness of the proposed approach, which achieves impressive results and outperforms strong baselines.

Radiology report generation (RRG) aims to automatically generate free-text descriptions from clinical radiographs, e.g., chest X-Ray images. RRG plays an essential role in promoting clinical automation and presents significant help to provide practical assistance for inexperienced doctors and alleviate radiologists' workloads. Therefore, consider these meaningful potentials, research on RRG is experiencing explosive growth in the past half-decade, especially with the rapid development of deep learning approaches. Existing studies perform RRG from the perspective of enhancing different modalities, provide insights on optimizing the report generation process with elaborated features from both visual and textual information, and further facilitate RRG with the cross-modal interactions among them. In this paper, we present a comprehensive review of deep learning-based RRG from various perspectives. Specifically, we firstly cover pivotal RRG approaches based on the task-specific features of radiographs, reports, and the cross-modal relations between them, and then illustrate the benchmark datasets conventionally used for this task with evaluation metrics, subsequently analyze the performance of different approaches and finally offer our summary on the challenges and the trends in future directions. Overall, the goal of this paper is to serve as a tool for understanding existing literature and inspiring potential valuable research in the field of RRG., Comment: 26 pages, 6 figures

First, we show that every complex torus $\mathbb{T}$ contains some entire curve $g: \mathbb{C}\rightarrow \mathbb{T}$ such that the concentric holomorphic discs $\{g\restriction_{\overline{\mathbb D}_{r}}\}_{r>0}$ can generate all the Nevanlinna/Ahlfors currents on $\mathbb T$ at cohomological level. This confirms an anticipation of Sibony. Developing further our new method, we can construct some twisted entire curve $f: \mathbb{C}\rightarrow \mathbb{CP}^1\times E$ in the product of the rational curve $\mathbb{CP}^1$ and an elliptic curve $E$, such that, concerning Siu's decomposition, demanding any cardinality $|J|\in \mathbb{Z}_{\geqslant 0}\cup \{\infty\}$ and that $\mathcal{T}_{\mathrm{diff}}$ is trivial ($|J|\geqslant 1$) or not ($|J|\geqslant 0$), we can always find a sequence of concentric holomorphic discs $\{f\restriction_{\overline{\mathbb D}_{r_j}}\}_{j \geqslant 1}$ to generate a Nevanlinna/Ahlfors current $\mathcal{T}=\mathcal{T}_{\mathrm{alg}}+\mathcal{T}_{\mathrm{diff}}$ with the singular part $\mathcal{T}_{\mathrm{alg}}=\sum_{j\in J} \,\lambda_j\cdot[\mathsf C_j]$ in the desired shape. This fulfills the missing case where $|J|=0$ in the previous work of Huynh-Xie. By a result of Duval, each $\mathsf C_j$ must be rational or elliptic. We will show that there is no a priori restriction on the numbers of rational and elliptic components in the support of $\mathcal{T}_{\mathrm{alg}}$, thus answering a question of Yau and Zhou. Moreover, we will show that the positive coefficients $\{\lambda_j\}_{j\in J}$ can be arbitrary as long as the total mass of $\mathcal{T}_{\mathrm{alg}}$ is less than or equal to $1$. Our results foreshadow striking holomorphic flexibility of entire curves in Oka geometry, which deserves further exploration.

Having the difficulty of solving the semantic gap between images and texts for the image captioning task, conventional studies in this area paid some attention to treating semantic concepts as a bridge between the two modalities and improved captioning performance accordingly. Although promising results on concept prediction were obtained, the aforementioned studies normally ignore the relationship among concepts, which relies on not only objects in the image, but also word dependencies in the text, so that offers a considerable potential for improving the process of generating good descriptions. In this paper, we propose a structured concept predictor (SCP) to predict concepts and their structures, then we integrate them into captioning, so as to enhance the contribution of visual signals in this task via concepts and further use their relations to distinguish cross-modal semantics for better description generation. Particularly, we design weighted graph convolutional networks (W-GCN) to depict concept relations driven by word dependencies, and then learns differentiated contributions from these concepts for following decoding process. Therefore, our approach captures potential relations among concepts and discriminatively learns different concepts, so that effectively facilitates image captioning with inherited information across modalities. Extensive experiments and their results demonstrate the effectiveness of our approach as well as each proposed module in this work., Comment: 13 pages, 4 figures. Published at EMNLP 2023 (Main Conference, Oral)

Recently, the increasing demand for superior medical services has highlighted the discrepancies in the medical infrastructure. With big data, especially texts, forming the foundation of medical services, there is an exigent need for effective natural language processing (NLP) solutions tailored to the healthcare domain. Conventional approaches leveraging pre-trained models present promising results in this domain and current large language models (LLMs) offer advanced foundation for medical text processing. However, most medical LLMs are trained only with supervised fine-tuning (SFT), even though it efficiently empowers LLMs to understand and respond to medical instructions but is ineffective in learning domain knowledge and aligning with human preference. In this work, we propose ChiMed-GPT, a new benchmark LLM designed explicitly for Chinese medical domain, and undergoes a comprehensive training regime with pre-training, SFT, and RLHF. Evaluations on tasks including information extraction, question answering, and dialogue generation demonstrate ChiMed-GPT's superior performance over general domain LLMs. Furthermore, we analyze possible biases through prompting ChiMed-GPT to perform attitude scales regarding discrimination of patients, so as to contribute to further responsible development of LLMs in the medical domain. The code and model are released at https://github.com/synlp/ChiMed-GPT., Comment: 18 pages, 3 figures; Accepted by ACL-2024

Various large language models (LLMs) have been proposed in recent years, including closed- and open-source ones, continually setting new records on multiple benchmarks. However, the development of LLMs still faces several issues, such as high cost of training models from scratch, and continual pre-training leading to catastrophic forgetting, etc. Although many such issues are addressed along the line of research on LLMs, an important yet practical limitation is that many studies overly pursue enlarging model sizes without comprehensively analyzing and optimizing the use of pre-training data in their learning process, as well as appropriate organization and leveraging of such data in training LLMs under cost-effective settings. In this work, we propose Ziya2, a model with 13 billion parameters adopting LLaMA2 as the foundation model, and further pre-trained on 700 billion tokens, where we focus on pre-training techniques and use data-centric optimization to enhance the learning process of Ziya2 on different stages. We define three data attributes and firstly establish data-centric scaling laws to illustrate how different data impacts LLMs. Experiments show that Ziya2 significantly outperforms other models in multiple benchmarks especially with promising results compared to representative open-source ones. Ziya2 (Base) is released at https://huggingface.co/IDEA-CCNL/Ziya2-13B-Base and https://modelscope.cn/models/Fengshenbang/Ziya2-13B-Base/summary.

Large language models (LLMs) demonstrate their promise in tackling complicated practical challenges by combining action-based policies with chain of thought (CoT) reasoning. Having high-quality prompts on hand, however, is vital to the framework's effectiveness. Currently, these prompts are handcrafted utilising extensive human labor, resulting in CoT policies that frequently fail to generalise. Human intervention is also required to develop grounding functions that ensure low-level controllers appropriately process CoT reasoning. In this paper, we propose a comprehensive training framework for complex task-solving, incorporating human prior knowledge into the learning of action policies. To that purpose, we offer a new leader-follower bilevel framework that is capable of learning to ask relevant questions (prompts) and subsequently undertaking reasoning to guide the learning of actions. The prompt policy is employed to make introspective revisions based on historical findings, leading the CoT process to consider the anticipated goals and generate outputs that lead to decisive, high-performing actions. The action policy subsequently learns to comprehend and integrate the CoT outputs to take actions. Our empirical data reveal that our framework outperforms leading methods in $5$ decision-making tasks such as Overcooked and FourRoom.

Recent advancements enlarge the capabilities of large language models (LLMs) in zero-shot image-to-text generation and understanding by integrating multi-modal inputs. However, such success is typically limited to English scenarios due to the lack of large-scale and high-quality non-English multi-modal resources, making it extremely difficult to establish competitive counterparts in other languages. In this paper, we introduce the Ziya-Visual series, a set of bilingual large-scale vision-language models (LVLMs) designed to incorporate visual semantics into LLM for multi-modal dialogue. Composed of Ziya-Visual-Base and Ziya-Visual-Chat, our models adopt the Querying Transformer from BLIP-2, further exploring the assistance of optimization schemes such as instruction tuning, multi-stage training and low-rank adaptation module for visual-language alignment. In addition, we stimulate the understanding ability of GPT-4 in multi-modal scenarios, translating our gathered English image-text datasets into Chinese and generating instruction-response through the in-context learning method. The experiment results demonstrate that compared to the existing LVLMs, Ziya-Visual achieves competitive performance across a wide range of English-only tasks including zero-shot image-text retrieval, image captioning, and visual question answering. The evaluation leaderboard accessed by GPT-4 also indicates that our models possess satisfactory image-text understanding and generation capabilities in Chinese multi-modal scenario dialogues. Code, demo and models are available at ~\url{https://huggingface.co/IDEA-CCNL/Ziya-BLIP2-14B-Visual-v1}.

In recent years, notable progress has been made in the study of hole qubits in planar germanium, and circuit quantum electrodynamics (circuit QED) has emerged as a promising approach for achieving long-range coupling and scaling up of qubits. Here, we demonstrate the coupling between holes in a planar germanium double quantum dot (DQD) and photons in a microwave cavity. Specifically, a real-time calibrated virtual gate method is developed to characterize this hybrid system, which in turn allows us to determine the typical parameters sequentially through single-parameter fitting instead of conventional multi-parameter fitting with additional uncertainty, and gives the hole-photon coupling rate of $g_0/2\pi$ = 21.7 MHz. This work is a step toward further research on hole-photon interactions and long-range qubit coupling in planar germanium. The experimental method developed in this work contributes to the more accurate and efficient characterization of hybrid cavity-QED systems., Comment: 11 pages, 4 figures

By means of hypercyclic operator theory, we complement our previous results on hypercyclic holomorphic maps between complex Euclidean spaces having slow growth rates,by showing {\it abstract abundance} rather than {\it explicit existence}. Next, we establish that, in the space of holomorphic maps from $\mathbb{C}^n$ to any connected Oka manifold $Y$, equipped with the compact-open topology, there exists a {\em dense} subset consisting of common {\em frequently hypercyclic} elements for all nontrivial translation operators. To our knowledge, this is new even for $n=1$ and $Y=\mathbb{C}$.

The recursive intra-frame block partitioning decision process, a crucial component of the next-generation video coding standards, exerts significant influence over the encoding time. In this paper, we propose an encoder-decoder neural network (NN) to accelerate this process. Specifically, a CNN is utilized to compress the pixel data of the largest coding unit (LCU) into a fixed-length vector. Subsequently, a Transformer decoder is employed to transcribe the fixed-length vector into a variable-length vector, which represents the block partitioning outcomes of the encoding LCU. The vector transcription process adheres to the constraints imposed by the block partitioning algorithm. By fully parallelizing the NN prediction in the intra-mode decision, substantial time savings can be attained during the decision phase. The experimental results obtained from high-definition (HD) sequences coding demonstrate that this framework achieves a remarkable 87.84\% reduction in encoding time, with a relatively small loss (8.09\%) of coding performance compared to AVS3 HPM4.0.

Let $\{D_i\}_{i=1}^{n+1}$ be $n+1$ hypersurfaces in $\mathbb{P}^n(\mathbb{C})$ with total degrees $\sum_{i=1}^{n+1}\text{deg}D_i\geqslant n+2$, satisfying one precise geometric (generic) condition. Then, for every algebraically nondegenerate entire holomorphic curve $f\colon\mathbb{C}\rightarrow\mathbb{P}^n(\mathbb{C})$, we show a Second Main Theorem: $$ \sum_{i=1}^{n+1} \delta_f(D_i) < n+1 $$ in terms of defect inequality in Nevanlinna theory. This is the first result in the literature on Second Main Theorem for $n+1$ general hypersurfaces in $\mathbb{P}^n(\mathbb{C})$ with optimal total degrees., Comment: 19 pages, 5 figures, comments are welcome

Earth system models (ESMs) are fundamental for understanding Earth's complex climate system. However, the computational demands and storage requirements of ESM simulations limit their utility. For the newly published CESM2-LENS2 data, which suffer from this issue, we propose a novel stochastic generator (SG) as a practical complement to the CESM2, capable of rapidly producing emulations closely mirroring training simulations. Our SG leverages the spherical harmonic transformation (SHT) to shift from spatial to spectral domains, enabling efficient low-rank approximations that significantly reduce computational and storage costs. By accounting for axial symmetry and retaining distinct ranks for land and ocean regions, our SG captures intricate non-stationary spatial dependencies. Additionally, a modified Tukey g-and-h (TGH) transformation accommodates non-Gaussianity in high-temporal-resolution data. We apply the proposed SG to generate emulations for surface temperature simulations from the CESM2-LENS2 data across various scales, marking the first attempt of reproducing daily data. These emulations are then meticulously validated against training simulations. This work offers a promising complementary pathway for efficient climate modeling and analysis while overcoming computational and storage limitations.

Fundamental studies of the interaction of chiral light with chiral matter are important for the development of techniques that allow handedness-selective optical detection of chiral organic molecules. One approach to achieve this goal is the creation of a Fabry-P\'erot cavity that supports eigenmodes with a desired electromagnetic handedness, which interacts differently with left and right molecular enantiomers. In this paper, we theoretically study chiral Fabry-P\'erot cavities with mirrors comprising one-dimensional photonic crystal slabs made of van der Waals As$_2$S$_3$, a material with one of the highest known in-plane anisotropy. By utilizing the anisotropy degree of freedom provided by As$_2$S$_3$, we design Fabry-P\'erot cavities with constitutional and configurational geometrical chiralities. We demonstrate that in cavities with constitutional chirality, electromagnetic modes of left or right handedness exist due to the chirality of both mirrors, often referred to as handedness preserving mirrors in the literature. At the same time, cavities with configurational chirality support modes of both handednesses due to chiral morphology of the entire structure, set by the twist angle between the optical axes of the upper and lower non-chiral anisotropic mirrors. The developed chiral Fabry-P\'erot cavities can be tuned to the technologically available distance between the mirrors by properly twisting them, making such systems a prospective platform for the coupling of chiral light with chiral matter., Comment: 33 pages, 9 figures

Taxation and government spending are crucial tools for governments to promote economic growth and maintain social equity. However, the difficulty in accurately predicting the dynamic strategies of diverse self-interested households presents a challenge for governments to implement effective tax policies. Given its proficiency in modeling other agents in partially observable environments and adaptively learning to find optimal policies, Multi-Agent Reinforcement Learning (MARL) is highly suitable for solving dynamic games between the government and numerous households. Although MARL shows more potential than traditional methods such as the genetic algorithm and dynamic programming, there is a lack of large-scale multi-agent reinforcement learning economic simulators. Therefore, we propose a MARL environment, named \textbf{TaxAI}, for dynamic games involving $N$ households, government, firms, and financial intermediaries based on the Bewley-Aiyagari economic model. Our study benchmarks 2 traditional economic methods with 7 MARL methods on TaxAI, demonstrating the effectiveness and superiority of MARL algorithms. Moreover, TaxAI's scalability in simulating dynamic interactions between the government and 10,000 households, coupled with real-data calibration, grants it a substantial improvement in scale and reality over existing simulators. Therefore, TaxAI is the most realistic economic simulator for optimal tax policy, which aims to generate feasible recommendations for governments and individuals., Comment: 18 pages, 8 figures, 13 tables

Even though Google Research Football (GRF) was initially benchmarked and studied as a single-agent environment in its original paper, recent years have witnessed an increasing focus on its multi-agent nature by researchers utilizing it as a testbed for Multi-Agent Reinforcement Learning (MARL). However, the absence of standardized environment settings and unified evaluation metrics for multi-agent scenarios hampers the consistent understanding of various studies. Furthermore, the challenging 5-vs-5 and 11-vs-11 full-game scenarios have received limited thorough examination due to their substantial training complexities. To address these gaps, this paper extends the original environment by not only standardizing the environment settings and benchmarking cooperative learning algorithms across different scenarios, including the most challenging full-game scenarios, but also by discussing approaches to enhance football AI from diverse perspectives and introducing related research tools. Specifically, we provide a distributed and asynchronous population-based self-play framework with diverse pre-trained policies for faster training, two football-specific analytical tools for deeper investigation, and an online leaderboard for broader evaluation. The overall expectation of this work is to advance the study of Multi-Agent Reinforcement Learning on Google Research Football environment, with the ultimate goal of benefiting real-world sports beyond virtual games.

In this paper, we propose a novel framework for recognizing both discrete and dimensional emotions. In our framework, deep features extracted from foundation models are used as robust acoustic and visual representations of raw video. Three different structures based on attention-guided feature gathering (AFG) are designed for deep feature fusion. Then, we introduce a joint decoding structure for emotion classification and valence regression in the decoding stage. A multi-task loss based on uncertainty is also designed to optimize the whole process. Finally, by combining three different structures on the posterior probability level, we obtain the final predictions of discrete and dimensional emotions. When tested on the dataset of multimodal emotion recognition challenge (MER 2023), the proposed framework yields consistent improvements in both emotion classification and valence regression. Our final system achieves state-of-the-art performance and ranks third on the leaderboard on MER-MULTI sub-challenge., Comment: 5 pages, 4 figures

First, inspired by a question of Sibony, we show that in every compact complex manifold $Y$ with certain Oka property, there exists some entire curve $f: \mathbb{C}\rightarrow Y$ generating all Nevanlinna/Ahlfors currents on $Y$, by holomorphic discs $\{f\restriction_{\mathbb{D}(c, r)}\}_{c\in \mathbb{C}, r>0}$. Next, we answer positively a question of Yau, by constructing some entire curve $g: \mathbb{C}\rightarrow X$ in the product $X:=E_1\times E_2$ of two elliptic curves $E_1$ and $E_2$, such that by using concentric holomorphic discs $\{g\restriction_{\mathbb{D}_{ r}}\}_{r>0}$ we can obtain infinitely many distinct Nevanlinna/Ahlfors currents proportional to the extremal currents of integration along curves $[\{e_1\}\times E_2]$, $[E_1\times \{e_2\}]$ for all $e_1\in E_1, e_2\in E_2$ simultaneously. This phenomenon is new, and it shows tremendous holomorphic flexibility of entire curves in large scale geometry., Comment: final version

We design an Algorithm to fabricate universal holomorphic maps between any two complex Euclidean spaces, within preassigned transcendental growth rate. As by-products, universal holomorphic maps from $\mathbb{C}^n$ to $\mathbb{CP}^m$ ($n\leqslant m$) and to complex tori having slow growth are obtained. We take inspiration from Oka manifolds theory, Nevanlinna theory, and hypercyclic operators theory., Comment: final version

In this paper, we propose a joint generative and contrastive representation learning method (GeCo) for anomalous sound detection (ASD). GeCo exploits a Predictive AutoEncoder (PAE) equipped with self-attention as a generative model to perform frame-level prediction. The output of the PAE together with original normal samples, are used for supervised contrastive representative learning in a multi-task framework. Besides cross-entropy loss between classes, contrastive loss is used to separate PAE output and original samples within each class. GeCo aims to better capture context information among frames, thanks to the self-attention mechanism for PAE model. Furthermore, GeCo combines generative and contrastive learning from which we aim to yield more effective and informative representations, compared to existing methods. Extensive experiments have been conducted on the DCASE2020 Task2 development dataset, showing that GeCo outperforms state-of-the-art generative and discriminative methods., Comment: Accepted by ICASSP2023

Few multi-agent reinforcement learning (MARL) research on Google Research Football (GRF) focus on the 11v11 multi-agent full-game scenario and to the best of our knowledge, no open benchmark on this scenario has been released to the public. In this work, we fill the gap by providing a population-based MARL training pipeline and hyperparameter settings on multi-agent football scenario that outperforms the bot with difficulty 1.0 from scratch within 2 million steps. Our experiments serve as a reference for the expected performance of Independent Proximal Policy Optimization (IPPO), a state-of-the-art multi-agent reinforcement learning algorithm where each agent tries to maximize its own policy independently across various training configurations. Meanwhile, we open-source our training framework Light-MALib which extends the MALib codebase by distributed and asynchronized implementation with additional analytical tools for football games. Finally, we provide guidance for building strong football AI with population-based training and release diverse pretrained policies for benchmarking. The goal is to provide the community with a head start for whoever experiment their works on GRF and a simple-to-use population-based training framework for further improving their agents through self-play. The implementation is available at https://github.com/Shanghai-Digital-Brain-Laboratory/DB-Football.

The minimum covariance determinant (MCD) estimator is ubiquitous in multivariate analysis, the critical step of which is to select a subset of a given size with the lowest sample covariance determinant. The concentration step (C-step) is a common tool for subset-seeking; however, it becomes computationally demanding for high-dimensional data. To alleviate the challenge, we propose a depth-based algorithm, termed as \texttt{FDB}, which replaces the optimal subset with the trimmed region induced by statistical depth. We show that the depth-based region is consistent with the MCD-based subset under a specific class of depth notions, for instance, the projection depth. With the two suggested depths, the \texttt{FDB} estimator is not only computationally more efficient but also reaches the same level of robustness as the MCD estimator. Extensive simulation studies are conducted to assess the empirical performance of our estimators. We also validate the computational efficiency and robustness of our estimators under several typical tasks such as principal component analysis, linear discriminant analysis, image denoise and outlier detection on real-life datasets. A R package \textit{FDB} and potential extensions are available in the Supplementary Materials.