Search

A quantum network provides an infrastructure connecting quantum devices with revolutionary computing, sensing, and communication capabilities. As the best-known application of a quantum network, quantum key distribution (QKD) shares secure keys guaranteed by the laws of quantum mechanics. A quantum satellite constellation offers a solution to facilitate the quantum network on a global scale. The Micius satellite has verified the feasibility of satellite quantum communications, however, scaling up quantum satellite constellations is challenging, requiring small lightweight satellites, portable ground stations and real-time secure key exchange. Here we tackle these challenges and report the development of a quantum microsatellite capable of performing space-to-ground QKD using portable ground stations. The quantum microsatellite features a payload weighing approximately 23 kg, while the portable ground station weighs about 100 kg. These weights represent reductions by more than an order and two orders of magnitude, respectively, compared to the Micius satellite. Additionally, we multiplex bidirectional satellite-ground optical communication with quantum communication, enabling key distillation and secure communication in real-time. Using the microsatellite and the portable ground stations, we demonstrate satellite-based QKD with multiple ground stations and achieve the sharing of up to 0.59 million bits of secure keys during a single satellite pass. The compact quantum payload can be readily assembled on existing space stations or small satellites, paving the way for a satellite-constellation-based quantum and classical network for widespread real-life applications., Comment: 40 pages, 8 figures

Multi-agent systems must learn to communicate and understand interactions between agents to achieve cooperative goals in partially observed tasks. However, existing approaches lack a dynamic directed communication mechanism and rely on global states, thus diminishing the role of communication in centralized training. Thus, we propose the transformer-based graph coarsening network (TGCNet), a novel multi-agent reinforcement learning (MARL) algorithm. TGCNet learns the topological structure of a dynamic directed graph to represent the communication policy and integrates graph coarsening networks to approximate the representation of global state during training. It also utilizes the transformer decoder for feature extraction during execution. Experiments on multiple cooperative MARL benchmarks demonstrate state-of-the-art performance compared to popular MARL algorithms. Further ablation studies validate the effectiveness of our dynamic directed graph communication mechanism and graph coarsening networks., Comment: 9 pages, 7 figures

Implicit neural representations (INRs) have significantly advanced the field of arbitrary-scale super-resolution (ASSR) of images. Most existing INR-based ASSR networks first extract features from the given low-resolution image using an encoder, and then render the super-resolved result via a multi-layer perceptron decoder. Although these approaches have shown promising results, their performance is constrained by the limited representation ability of discrete latent codes in the encoded features. In this paper, we propose a novel ASSR method named GaussianSR that overcomes this limitation through 2D Gaussian Splatting (2DGS). Unlike traditional methods that treat pixels as discrete points, GaussianSR represents each pixel as a continuous Gaussian field. The encoded features are simultaneously refined and upsampled by rendering the mutually stacked Gaussian fields. As a result, long-range dependencies are established to enhance representation ability. In addition, a classifier is developed to dynamically assign Gaussian kernels to all pixels to further improve flexibility. All components of GaussianSR (i.e., encoder, classifier, Gaussian kernels, and decoder) are jointly learned end-to-end. Experiments demonstrate that GaussianSR achieves superior ASSR performance with fewer parameters than existing methods while enjoying interpretable and content-aware feature aggregations., Comment: 13 pages, 12 figures

This report introduces FunAudioLLM, a model family designed to enhance natural voice interactions between humans and large language models (LLMs). At its core are two innovative models: SenseVoice, which handles multilingual speech recognition, emotion recognition, and audio event detection; and CosyVoice, which facilitates natural speech generation with control over multiple languages, timbre, speaking style, and speaker identity. SenseVoice-Small delivers exceptionally low-latency ASR for 5 languages, and SenseVoice-Large supports high-precision ASR for over 50 languages, while CosyVoice excels in multi-lingual voice generation, zero-shot in-context learning, cross-lingual voice cloning, and instruction-following capabilities. The models related to SenseVoice and CosyVoice have been open-sourced on Modelscope and Huggingface, along with the corresponding training, inference, and fine-tuning codes released on GitHub. By integrating these models with LLMs, FunAudioLLM enables applications such as speech-to-speech translation, emotional voice chat, interactive podcasts, and expressive audiobook narration, thereby pushing the boundaries of voice interaction technology. Demos are available at https://fun-audio-llm.github.io, and the code can be accessed at https://github.com/FunAudioLLM., Comment: Work in progress. Authors are listed in alphabetical order by family name

Speech-driven 3D facial animation has recently garnered attention due to its cost-effective usability in multimedia production. However, most current advances overlook the intelligibility of lip movements, limiting the realism of facial expressions. In this paper, we introduce a method for speech-driven 3D facial animation to generate accurate lip movements, proposing an audio-visual multimodal perceptual loss. This loss provides guidance to train the speech-driven 3D facial animators to generate plausible lip motions aligned with the spoken transcripts. Furthermore, to incorporate the proposed audio-visual perceptual loss, we devise an audio-visual lip reading expert leveraging its prior knowledge about correlations between speech and lip motions. We validate the effectiveness of our approach through broad experiments, showing noticeable improvements in lip synchronization and lip readability performance. Codes are available at https://3d-talking-head-avguide.github.io/., Comment: INTERSPEECH 2024

A response to commenter Ke Lan's comment on our paper published in Nature Communications (2023)14:5782 by J. Yan et al

Recent studies in speech-driven 3D talking head generation have achieved convincing results in verbal articulations. However, generating accurate lip-syncs degrades when applied to input speech in other languages, possibly due to the lack of datasets covering a broad spectrum of facial movements across languages. In this work, we introduce a novel task to generate 3D talking heads from speeches of diverse languages. We collect a new multilingual 2D video dataset comprising over 420 hours of talking videos in 20 languages. With our proposed dataset, we present a multilingually enhanced model that incorporates language-specific style embeddings, enabling it to capture the unique mouth movements associated with each language. Additionally, we present a metric for assessing lip-sync accuracy in multilingual settings. We demonstrate that training a 3D talking head model with our proposed dataset significantly enhances its multilingual performance. Codes and datasets are available at https://multi-talk.github.io/., Comment: Interspeech 2024

Class imbalance significantly impacts the performance of multi-label classifiers. Oversampling is one of the most popular approaches, as it augments instances associated with less frequent labels to balance the class distribution. Existing oversampling methods generate feature vectors of synthetic samples through replication or linear interpolation and assign labels through neighborhood information. Linear interpolation typically generates new samples between existing data points, which may result in insufficient diversity of synthesized samples and further lead to the overfitting issue. Deep learning-based methods, such as AutoEncoders, have been proposed to generate more diverse and complex synthetic samples, achieving excellent performance on imbalanced binary or multi-class datasets. In this study, we introduce AEMLO, an AutoEncoder-guided Oversampling technique specifically designed for tackling imbalanced multi-label data. AEMLO is built upon two fundamental components. The first is an encoder-decoder architecture that enables the model to encode input data into a low-dimensional feature space, learn its latent representations, and then reconstruct it back to its original dimension, thus applying to the generation of new data. The second is an objective function tailored to optimize the sampling task for multi-label scenarios. We show that AEMLO outperforms the existing state-of-the-art methods with extensive empirical studies.

3D Object Affordance Grounding aims to predict the functional regions on a 3D object and has laid the foundation for a wide range of applications in robotics. Recent advances tackle this problem via learning a mapping between 3D regions and a single human-object interaction image. However, the geometric structure of the 3D object and the object in the human-object interaction image are not always consistent, leading to poor generalization. To address this issue, we propose to learn generalizable invariant affordance knowledge from multiple human-object interaction images within the same affordance category. Specifically, we introduce the \textbf{M}ulti-\textbf{I}mage Guided Invariant-\textbf{F}eature-Aware 3D \textbf{A}ffordance \textbf{G}rounding (\textbf{MIFAG}) framework. It grounds 3D object affordance regions by identifying common interaction patterns across multiple human-object interaction images. First, the Invariant Affordance Knowledge Extraction Module (\textbf{IAM}) utilizes an iterative updating strategy to gradually extract aligned affordance knowledge from multiple images and integrate it into an affordance dictionary. Then, the Affordance Dictionary Adaptive Fusion Module (\textbf{ADM}) learns comprehensive point cloud representations that consider all affordance candidates in multiple images. Besides, the Multi-Image and Point Affordance (\textbf{MIPA}) benchmark is constructed and our method outperforms existing state-of-the-art methods on various experimental comparisons. Project page: \url{https://goxq.github.io/mifag}

This work presents ParGo, a novel Partial-Global projector designed to connect the vision and language modalities for Multimodal Large Language Models (MLLMs). Unlike previous works that rely on global attention-based projectors, our ParGo bridges the representation gap between the separately pre-trained vision encoders and the LLMs by integrating global and partial views, which alleviates the overemphasis on prominent regions. To facilitate the effective training of ParGo, we collect a large-scale detail-captioned image-text dataset named ParGoCap-1M-PT, consisting of 1 million images paired with high-quality captions. Extensive experiments on several MLLM benchmarks demonstrate the effectiveness of our ParGo, highlighting its superiority in aligning vision and language modalities. Compared to conventional Q-Former projector, our ParGo achieves an improvement of 259.96 in MME benchmark. Furthermore, our experiments reveal that ParGo significantly outperforms other projectors, particularly in tasks that emphasize detail perception ability.

In the field of multimodal large language models (MLLMs), common methods typically involve unfreezing the language model during training to foster profound visual understanding. However, the fine-tuning of such models with vision-language data often leads to a diminution of their natural language processing (NLP) capabilities. To avoid this performance degradation, a straightforward solution is to freeze the language model while developing multimodal competencies. Unfortunately, previous works have not attained satisfactory outcomes. Building on the strategy of freezing the language model, we conduct thorough structural exploration and introduce the Inner-Adaptor Architecture (IAA). Specifically, the architecture incorporates multiple multimodal adaptors at varying depths within the large language model to facilitate direct interaction with the inherently text-oriented transformer layers, thereby enabling the frozen language model to acquire multimodal capabilities. Unlike previous approaches of freezing language models that require large-scale aligned data, our proposed architecture is able to achieve superior performance on small-scale datasets. We conduct extensive experiments to improve the general multimodal capabilities and visual grounding abilities of the MLLM. Our approach remarkably outperforms previous state-of-the-art methods across various vision-language benchmarks without sacrificing performance on NLP tasks. Code and models are available at https://github.com/360CVGroup/Inner-Adaptor-Architecture.

With the burgeoning advancements in the field of natural language processing (NLP), the demand for training data has increased significantly. To save costs, it has become common for users and businesses to outsource the labor-intensive task of data collection to third-party entities. Unfortunately, recent research has unveiled the inherent risk associated with this practice, particularly in exposing NLP systems to potential backdoor attacks. Specifically, these attacks enable malicious control over the behavior of a trained model by poisoning a small portion of the training data. Unlike backdoor attacks in computer vision, textual backdoor attacks impose stringent requirements for attack stealthiness. However, existing attack methods meet significant trade-off between effectiveness and stealthiness, largely due to the high information entropy inherent in textual data. In this paper, we introduce the Efficient and Stealthy Textual backdoor attack method, EST-Bad, leveraging Large Language Models (LLMs). Our EST-Bad encompasses three core strategies: optimizing the inherent flaw of models as the trigger, stealthily injecting triggers with LLMs, and meticulously selecting the most impactful samples for backdoor injection. Through the integration of these techniques, EST-Bad demonstrates an efficient achievement of competitive attack performance while maintaining superior stealthiness compared to prior methods across various text classifier datasets., Comment: Under Review

Click-Through Rate (CTR) prediction is crucial for Recommendation System(RS), aiming to provide personalized recommendation services for users in many aspects such as food delivery, e-commerce and so on. However, traditional RS relies on collaborative signals, which lacks semantic understanding to real-time scenes. We also noticed that a major challenge in utilizing Large Language Models (LLMs) for practical recommendation purposes is their efficiency in dealing with long text input. To break through the problems above, we propose Large Language Model Aided Real-time Scene Recommendation(LARR), adopt LLMs for semantic understanding, utilizing real-time scene information in RS without requiring LLM to process the entire real-time scene text directly, thereby enhancing the efficiency of LLM-based CTR modeling. Specifically, recommendation domain-specific knowledge is injected into LLM and then RS employs an aggregation encoder to build real-time scene information from separate LLM's outputs. Firstly, a LLM is continual pretrained on corpus built from recommendation data with the aid of special tokens. Subsequently, the LLM is fine-tuned via contrastive learning on three kinds of sample construction strategies. Through this step, LLM is transformed into a text embedding model. Finally, LLM's separate outputs for different scene features are aggregated by an encoder, aligning to collaborative signals in RS, enhancing the performance of recommendation model.

The superiority of Multi-Robot Systems (MRS) in various complex environments is unquestionable. However, in complex situations such as search and rescue, environmental monitoring, and automated production, robots are often required to work collaboratively without a central control unit. This necessitates an efficient and robust decentralized control mechanism to process local information and guide the robots' behavior. In this work, we propose a new decentralized controller design method that utilizes the Deep Q-Network (DQN) algorithm from deep reinforcement learning, aimed at improving the integration of local information and robustness of multi-robot systems. The designed controller allows each robot to make decisions independently based on its local observations while enhancing the overall system's collaborative efficiency and adaptability to dynamic environments through a shared learning mechanism. Through testing in simulated environments, we have demonstrated the effectiveness of this controller in improving task execution efficiency, strengthening system fault tolerance, and enhancing adaptability to the environment. Furthermore, we explored the impact of DQN parameter tuning on system performance, providing insights for further optimization of the controller design. Our research not only showcases the potential application of the DQN algorithm in the decentralized control of multi-robot systems but also offers a new perspective on how to enhance the overall performance and robustness of the system through the integration of local information., Comment: Multi-robot system, Reinforcement learning, Information ingrated

Solving Algebra Problems with Geometry Diagrams (APGDs) is still a challenging problem because diagram processing is not studied as intensively as language processing. To work against this challenge, this paper proposes a hologram reasoning scheme and develops a high-performance method for solving APGDs by using this scheme. To reach this goal, it first defines a hologram, being a kind of graph, and proposes a hologram generator to convert a given APGD into a hologram, which represents the entire information of APGD and the relations for solving the problem can be acquired from it by a uniform way. Then HGR, a hologram reasoning method employs a pool of prepared graph models to derive algebraic equations, which is consistent with the geometric theorems. This method is able to be updated by adding new graph models into the pool. Lastly, it employs deep reinforcement learning to enhance the efficiency of model selection from the pool. The entire HGR not only ensures high solution accuracy with fewer reasoning steps but also significantly enhances the interpretability of the solution process by providing descriptions of all reasoning steps. Experimental results demonstrate the effectiveness of HGR in improving both accuracy and interpretability in solving APGDs.

Referring Video Object Segmentation is an emerging multi-modal task that aims to segment objects in the video given a natural language expression. In this work, we build two instance-centric models and fuse predicted results from frame-level and instance-level. First, we introduce instance mask into the DETR-based model for query initialization to achieve temporal enhancement and employ SAM for spatial refinement. Secondly, we build an instance retrieval model conducting binary instance mask classification whether the instance is referred. Finally, we fuse predicted results and our method achieved a score of 52.67 J&F in the validation phase and 60.36 J&F in the test phase, securing the final ranking of 3rd place in the 6-th LSVOS Challenge RVOS Track., Comment: arXiv admin note: substantial text overlap with arXiv:2406.13939

Large Language Models (LLMs) have become instrumental across various applications, with the customization of these models to specific scenarios becoming increasingly critical. System message, a fundamental component of LLMs, is consist of carefully crafted instructions that guide the behavior of model to meet intended goals. Despite the recognized potential of system messages to optimize AI-driven solutions, there is a notable absence of a comprehensive benchmark for evaluating how well different LLMs follow these system messages. To fill this gap, we introduce SysBench, a benchmark that systematically analyzes system message following ability in terms of three challenging aspects: constraint complexity, instruction misalignment and multi-turn stability. In order to enable effective evaluation, SysBench constructs multi-turn user conversations covering various interaction relationships, based on six common types of constraints from system messages in real-world scenarios. Our dataset contains 500 system messages from various domains, each paired with 5 turns of user conversations, which have been manually formulated and checked to guarantee high quality. SysBench provides extensive evaluation across various LLMs, measuring their ability to follow specified constraints given in system messages. The results highlight both the strengths and weaknesses of existing models, offering key insights and directions for future research. The open source library SysBench is available at https://github.com/PKU-Baichuan-MLSystemLab/SysBench.

3D Gaussian Splatting (3DGS) has become the de facto method of 3D representation in many vision tasks. This calls for the 3D understanding directly in this representation space. To facilitate the research in this direction, we first build a large-scale dataset of 3DGS using the commonly used ShapeNet and ModelNet datasets. Our dataset ShapeSplat consists of 65K objects from 87 unique categories, whose labels are in accordance with the respective datasets. The creation of this dataset utilized the compute equivalent of 2 GPU years on a TITAN XP GPU. We utilize our dataset for unsupervised pretraining and supervised finetuning for classification and segmentation tasks. To this end, we introduce \textbf{\textit{Gaussian-MAE}}, which highlights the unique benefits of representation learning from Gaussian parameters. Through exhaustive experiments, we provide several valuable insights. In particular, we show that (1) the distribution of the optimized GS centroids significantly differs from the uniformly sampled point cloud (used for initialization) counterpart; (2) this change in distribution results in degradation in classification but improvement in segmentation tasks when using only the centroids; (3) to leverage additional Gaussian parameters, we propose Gaussian feature grouping in a normalized feature space, along with splats pooling layer, offering a tailored solution to effectively group and embed similar Gaussians, which leads to notable improvement in finetuning tasks.

Recently, large-scale pre-trained vision-language models (e.g., CLIP), have garnered significant attention thanks to their powerful representative capabilities. This inspires researchers in transferring the knowledge from these large pre-trained models to other task-specific models, e.g., Video Action Recognition (VAR) models, via particularly leveraging side networks to enhance the efficiency of parameter-efficient fine-tuning (PEFT). However, current transferring approaches in VAR tend to directly transfer the frozen knowledge from large pre-trained models to action recognition networks with minimal cost, instead of exploiting the temporal modeling capabilities of the action recognition models themselves. Therefore, in this paper, we propose a memory-efficient Temporal Difference Side Network (TDS-CLIP) to balance knowledge transferring and temporal modeling, avoiding backpropagation in frozen parameter models. Specifically, we introduce a Temporal Difference Adapter (TD-Adapter), which can effectively capture local temporal differences in motion features to strengthen the model's global temporal modeling capabilities. Furthermore, we designed a Side Motion Enhancement Adapter (SME-Adapter) to guide the proposed side network in efficiently learning the rich motion information in videos, thereby improving the side network's ability to capture and learn motion information. Extensive experiments are conducted on three benchmark datasets, including Something-Something V1\&V2, and Kinetics-400. Experimental results demonstrate that our approach achieves competitive performance.

Prompt engineering has demonstrated remarkable success in enhancing the performance of large language models (LLMs) across diverse tasks. However, most existing prompt optimization methods only focus on the task-level performance, overlooking the importance of query-preferred prompts, which leads to suboptimal performances. Additionally, these methods rely heavily on frequent interactions with LLMs to obtain feedback for guiding the optimization process, incurring substantial redundant interaction costs. In this paper, we introduce Query-dependent Prompt Optimization (QPO), which leverages multi-loop offline reinforcement learning to iteratively fine-tune a small pretrained language model to generate optimal prompts tailored to the input queries, thus significantly improving the prompting effect on the large target LLM. We derive insights from offline prompting demonstration data, which already exists in large quantities as a by-product of benchmarking diverse prompts on open-sourced tasks, thereby circumventing the expenses of online interactions. Furthermore, we continuously augment the offline dataset with the generated prompts in each loop, as the prompts from the fine-tuned model are supposed to outperform the source prompts in the original dataset. These iterative loops bootstrap the model towards generating optimal prompts. Experiments on various LLM scales and diverse NLP and math tasks demonstrate the efficacy and cost-efficiency of our method in both zero-shot and few-shot scenarios.

Parameters in an effective field theory can be subject to certain positivity bounds if one requires a UV completion that obeys the fundamental principles of quantum field theory. These bounds are relatively straight forward at the tree level, but would become more obscure when loop effects are important. Using scalar theories as examples, we carefully exam the positivity bounds in a case where the leading contribution to a forward elastic amplitude arises at the one-loop level, and point out certain subtleties in terms of the implications of positivity bounds on the theory parameter space. In particular, the one-loop generated dimension-8 operator coefficients (that would be positive if generated at the tree level), as well as their $\beta$-functions are generally not subject to positivity bounds as they might correspond to interference terms of the cross sections under the optical theorem, which could have either sign. A strict positivity bound can only be implied when all contributions at the same loop order are considered, including the ones from dim-4 and dim-6 operator coefficients, which have important effects at the one-loop level. Our results may have important implications on the robustness of experimental tests of positivity bounds., Comment: 22 pages, 4 figures

The rapid advancement of deepfake technologies has sparked widespread public concern, particularly as face forgery poses a serious threat to public information security. However, the unknown and diverse forgery techniques, varied facial features and complex environmental factors pose significant challenges for face forgery analysis. Existing datasets lack descriptions of these aspects, making it difficult for models to distinguish between real and forged faces using only visual information amid various confounding factors. In addition, existing methods do not yield user-friendly and explainable results, complicating the understanding of the model's decision-making process. To address these challenges, we introduce a novel Open-World Face Forgery Analysis VQA (OW-FFA-VQA) task and the corresponding benchmark. To tackle this task, we first establish a dataset featuring a diverse collection of real and forged face images with essential descriptions and reliable forgery reasoning. Base on this dataset, we introduce FFAA: Face Forgery Analysis Assistant, consisting of a fine-tuned Multimodal Large Language Model (MLLM) and Multi-answer Intelligent Decision System (MIDS). By integrating hypothetical prompts with MIDS, the impact of fuzzy classification boundaries is effectively mitigated, enhancing the model's robustness. Extensive experiments demonstrate that our method not only provides user-friendly explainable results but also significantly boosts accuracy and robustness compared to previous methods., Comment: 17 pages, 18 figures; project page: https://ffaa-vl.github.io

This paper presents the SZU-AFS anti-spoofing system, designed for Track 1 of the ASVspoof 5 Challenge under open conditions. The system is built with four stages: selecting a baseline model, exploring effective data augmentation (DA) methods for fine-tuning, applying a co-enhancement strategy based on gradient norm aware minimization (GAM) for secondary fine-tuning, and fusing logits scores from the two best-performing fine-tuned models. The system utilizes the Wav2Vec2 front-end feature extractor and the AASIST back-end classifier as the baseline model. During model fine-tuning, three distinct DA policies have been investigated: single-DA, random-DA, and cascade-DA. Moreover, the employed GAM-based co-enhancement strategy, designed to fine-tune the augmented model at both data and optimizer levels, helps the Adam optimizer find flatter minima, thereby boosting model generalization. Overall, the final fusion system achieves a minDCF of 0.115 and an EER of 4.04% on the evaluation set., Comment: 8 pages, 2 figures, ASVspoof 5 Workshop (Interspeech2024 Satellite)

In partially observable multi-agent systems, agents typically only have access to local observations. This severely hinders their ability to make precise decisions, particularly during decentralized execution. To alleviate this problem and inspired by image outpainting, we propose State Inference with Diffusion Models (SIDIFF), which uses diffusion models to reconstruct the original global state based solely on local observations. SIDIFF consists of a state generator and a state extractor, which allow agents to choose suitable actions by considering both the reconstructed global state and local observations. In addition, SIDIFF can be effortlessly incorporated into current multi-agent reinforcement learning algorithms to improve their performance. Finally, we evaluated SIDIFF on different experimental platforms, including Multi-Agent Battle City (MABC), a novel and flexible multi-agent reinforcement learning environment we developed. SIDIFF achieved desirable results and outperformed other popular algorithms., Comment: 15 pages, 12 figures

Event extraction (EE) is a critical direction in the field of information extraction, laying an important foundation for the construction of structured knowledge bases. EE from text has received ample research and attention for years, yet there can be numerous real-world applications that require direct information acquisition from speech signals, online meeting minutes, interview summaries, press releases, etc. While EE from speech has remained under-explored, this paper fills the gap by pioneering a SpeechEE, defined as detecting the event predicates and arguments from a given audio speech. To benchmark the SpeechEE task, we first construct a large-scale high-quality dataset. Based on textual EE datasets under the sentence, document, and dialogue scenarios, we convert texts into speeches through both manual real-person narration and automatic synthesis, empowering the data with diverse scenarios, languages, domains, ambiences, and speaker styles. Further, to effectively address the key challenges in the task, we tailor an E2E SpeechEE system based on the encoder-decoder architecture, where a novel Shrinking Unit module and a retrieval-aided decoding mechanism are devised. Extensive experimental results on all SpeechEE subsets demonstrate the efficacy of the proposed model, offering a strong baseline for the task. At last, being the first work on this topic, we shed light on key directions for future research.

The temperature jump problem in polyatomic gas flow with translational/internal non-equilibrium is investigated, where the internal temperature is excited by volumetric heating, while the translational temperature is heated via the inelastic translational-internal energy relaxation. In the near-continuum flow regime, analytical temperature profiles are derived, based on which the first and second temperature jump coefficients are extracted from the numerical solution of the Boltzmann equation. Analytical expressions for temperature jump coefficients are fitted over a wide range of inelastic collision number and accommodation coefficient.

Advancements in autonomous driving have increasingly focused on end-to-end (E2E) systems that manage the full spectrum of driving tasks, from environmental perception to vehicle navigation and control. This paper introduces V2X-VLM, an innovative E2E vehicle-infrastructure cooperative autonomous driving (VICAD) framework with large vision-language models (VLMs). V2X-VLM is designed to enhance situational awareness, decision-making, and ultimate trajectory planning by integrating data from vehicle-mounted cameras, infrastructure sensors, and textual information. The strength of the comprehensive multimodel data fusion of the VLM enables precise and safe E2E trajectory planning in complex and dynamic driving scenarios. Validation on the DAIR-V2X dataset demonstrates that V2X-VLM outperforms existing state-of-the-art methods in cooperative autonomous driving.

Existing RGBT tracking methods often design various interaction models to perform cross-modal fusion of each layer, but can not execute the feature interactions among all layers, which plays a critical role in robust multimodal representation, due to large computational burden. To address this issue, this paper presents a novel All-layer multimodal Interaction Network, named AINet, which performs efficient and effective feature interactions of all modalities and layers in a progressive fusion Mamba, for robust RGBT tracking. Even though modality features in different layers are known to contain different cues, it is always challenging to build multimodal interactions in each layer due to struggling in balancing interaction capabilities and efficiency. Meanwhile, considering that the feature discrepancy between RGB and thermal modalities reflects their complementary information to some extent, we design a Difference-based Fusion Mamba (DFM) to achieve enhanced fusion of different modalities with linear complexity. When interacting with features from all layers, a huge number of token sequences (3840 tokens in this work) are involved and the computational burden is thus large. To handle this problem, we design an Order-dynamic Fusion Mamba (OFM) to execute efficient and effective feature interactions of all layers by dynamically adjusting the scan order of different layers in Mamba. Extensive experiments on four public RGBT tracking datasets show that AINet achieves leading performance against existing state-of-the-art methods.

The dynamics of relativistic electrons interacting with a laser pulse in a plasma wave has been investigated theoretically and numerically based on the classical Landau-Lifshitz equation. There exists a convergent trajectory of electrons when the energy gain of electrons via direct laser acceleration can compensate the energy loss via radiation. An electron beam initially around the convergent trajectory evolves into the trajectory, making its occupied phase space volume decrease exponentially while mean energy remain the same. This mechanism can be used for cooling relativistic electron beams especially those produced in plasma-based acceleration.

In recent years, radar systems have advanced significantly, offering environmental adaptation and multi-task capabilities. These developments pose new challenges for electronic intelligence (Elint) and electronic support measures (ESM), which need to identify and interpret sophisticated radar behaviors. This paper introduces a Deep Multi-Intentional Inverse Reinforcement Learning (DMIIRL) method for the identification and inverse cognition of cognitive multi-function radars (CMFR). Traditional Inverse Reinforcement Learning (IRL) methods primarily target single reward functions, but the complexity of CMFRs necessitates multiple reward functions to fully encapsulate their behavior. To this end, we develop a method that integrates IRL with Expectation-Maximization (EM) to concurrently handle multiple reward functions, offering better trajectory clustering and reward function estimation. Simulation results demonstrate the superiority of the proposed method over baseline approaches.

Pre-training & fine-tuning can enhance the transferring efficiency and performance in visual tasks. Recent delta-tuning methods provide more options for visual classification tasks. Despite their success, existing visual delta-tuning art fails to exceed the upper limit of full fine-tuning on challenging tasks like object detection and segmentation. To find a competitive alternative to full fine-tuning, we propose the Multi-cognitive Visual Adapter (Mona) tuning, a novel adapter-based tuning method. First, we introduce multiple vision-friendly filters into the adapter to enhance its ability to process visual signals, while previous methods mainly rely on language-friendly linear filters. Second, we add the scaled normalization layer in the adapter to regulate the distribution of input features for visual filters. To fully demonstrate the practicality and generality of Mona, we conduct experiments on multiple representative visual tasks, including instance segmentation on COCO, semantic segmentation on ADE20K, object detection on Pascal VOC, oriented object detection on DOTA/STAR, and image classification on three common datasets. Exciting results illustrate that Mona surpasses full fine-tuning on all these tasks, and is the only delta-tuning method outperforming full fine-tuning on the above various tasks. For example, Mona achieves 1% performance gain on the COCO dataset compared to full fine-tuning. Comprehensive results suggest that Mona-tuning is more suitable for retaining and utilizing the capabilities of pre-trained models than full fine-tuning. We will make the code publicly available., Comment: arXiv admin note: substantial text overlap with arXiv:2311.15010

In this paper, we explore the capabilities of state-of-the-art large language models (LLMs) such as GPT-4, GPT-4o, Claude 3.5 Sonnet, Claude 3 Opus, Gemini 1.5 Pro, Llama 3, and Llama 3.1 in solving some selected undergraduate-level transportation engineering problems. We introduce TransportBench, a benchmark dataset that includes a sample of transportation engineering problems on a wide range of subjects in the context of planning, design, management, and control of transportation systems. This dataset is used by human experts to evaluate the capabilities of various commercial and open-sourced LLMs, especially their accuracy, consistency, and reasoning behaviors, in solving transportation engineering problems. Our comprehensive analysis uncovers the unique strengths and limitations of each LLM, e.g. our analysis shows the impressive accuracy and some unexpected inconsistent behaviors of Claude 3.5 Sonnet in solving TransportBench problems. Our study marks a thrilling first step toward harnessing artificial general intelligence for complex transportation challenges.

In general class-incremental learning, researchers typically use sample sets as a tool to avoid catastrophic forgetting during continuous learning. At the same time, researchers have also noted the differences between class-incremental learning and Oracle training and have attempted to make corrections. In recent years, researchers have begun to develop class-incremental learning algorithms utilizing pre-trained models, achieving significant results. This paper observes that in class-incremental learning, the steady state among the weight guided by each class center is disrupted, which is significantly correlated with catastrophic forgetting. Based on this, we propose a new method to overcoming forgetting . In some cases, by retaining only a single sample unit of each class in memory for replay and applying simple gradient constraints, very good results can be achieved. Experimental results indicate that under the condition of pre-trained models, our method can achieve competitive performance with very low computational cost and by simply using the cross-entropy loss.

Recent breakthroughs have ushered the quantum network into a new era, where quantum information can be stored, transferred, and processed across multiple nodes on a metropolitan scale. A key challenge in this new era is enhancing the capabilities of individual nodes, providing precise and robust control over multiple qubits and advanced functionality for scalable quantum networks. Here, we report on precise and complex control in a hybrid quantum node based on a diamond color center. We demonstrate hybrid coherent control by entangling three types of qubits: an electron spin as an interface qubit, a nuclear spin with long memory time, and a flying photonic qubit, with their qubit frequencies spanning three distinct regimes from the optical domain to the rf domain. By incorporating two additional memory qubits, we encode three memory qubits into a logical state using the three-qubit repetition code and entangle this logical qubit with a photonic qubit. Leveraging hybrid qubits and precise control, we repeatedly read out the error syndromes of memory qubits through the electron spin, serving as an auxiliary qubit, then apply a real-time feedback operation to correct bit-flip errors. We execute and verify active error correction for up to twelve rounds and demonstrate the improvement over the uncorrected counterpart. Our results demonstrate the feasibility of several key functionalities for next-generation quantum repeaters, paving the way towards full-fledged metropolitan-scale quantum networks for a wide range of practical applications., Comment: 8 pages, 3 figures

In this note, we study the asymptotic Plateau problem in hyperbolic space, and we prove the existence of a smooth complete hypersurface of constant scalar curvature in hyperbolic space with a prescribed asymptotic boundary at infinity. Following a pioneering work of Bo Guan and Joel Spruck, we seek the solution as a vertical graph over a bounded domain and solve the corresponding Dirichlet problem for a fully nonlinear partial differential equation by establishing the crucial second order estimates for admissible solutions. Our proof consists of three main ingredients: (1) a non-standard, special choice for the parameter in the auxiliary function, (2) a so-called almost-Jacobi inequality for the equation operator, and (3) a set of arguments which reduce the situation to semi-convex case and which keep the coefficient of the troublesome negative term within a suitable magnitude., Comment: fixed minor typos

With the development of Multimodal Large Language Models (MLLMs), the evaluation of multimodal models in the context of mathematical problems has become a valuable research field. Multimodal visual-textual mathematical reasoning serves as a critical indicator for evaluating the comprehension and complex multi-step quantitative reasoning abilities of MLLMs. However, previous multimodal math benchmarks have not sufficiently integrated visual and textual information. To address this gap, we proposed MathScape, a new benchmark that emphasizes the understanding and application of combined visual and textual information. MathScape is designed to evaluate photo-based math problem scenarios, assessing the theoretical understanding and application ability of MLLMs through a categorical hierarchical approach. We conduct a multi-dimensional evaluation on 11 advanced MLLMs, revealing that our benchmark is challenging even for the most sophisticated models. By analyzing the evaluation results, we identify the limitations of MLLMs, offering valuable insights for enhancing model performance.

In the binary black hole coalescence, the gravitational wave emitted at the ringdown stage can be well described within the black hole perturbation theory, where the quasinormal modes (QNMs) become the important ingredient in modeling the pattern wave form. In general ralativity (GR), the QNMs can be obtained from solving the Regge-Wheeler equation in static black hole, while in Horndeski gravity, the metric perturbation equation can be simplified into a modified Regge-Wheeler equation from the perturbed action. In this paper, we calculate the QNMs frequencies of the gravitational odd-parity perturbation of a specific hairy black hole in Horndeski gravity with the use of the matrix method and pseudo spectral method. Our results indicate that such a Horndeski hairy black hole is stable under the odd perturbation, which is also verified by the time evolution of the perturbation. In particular, we find that for a certain range of the Horndeski hair, the $\ell>2$ modes become the long-lived mode instead of $\ell=2$ mode in GR. Then, we use the ringdown QNMs to preliminarily investigate the signal-to-noise-ratio (SNR) rescaled measurement error of the Horndeski hair. We obtained significant effects of the angular momentum and overtone on the error bound of the hairy parameter. We hope that our findings could inspire more theoretical and phenomenal work on the test of no-hair theorem of black hole from gravitational wave physics.

The rapid evolution of deep learning and its integration with autonomous driving systems have led to substantial advancements in 3D perception using multimodal sensors. Notably, radar sensors show greater robustness compared to cameras and lidar under adverse weather and varying illumination conditions. This study delves into the often-overlooked yet crucial issue of domain shift in 4D radar-based object detection, examining how varying environmental conditions, such as different weather patterns and road types, impact 3D object detection performance. Our findings highlight distinct domain shifts across various weather scenarios, revealing unique dataset sensitivities that underscore the critical role of radar point cloud generation. Additionally, we demonstrate that transitioning between different road types, especially from highways to urban settings, introduces notable domain shifts, emphasizing the necessity for diverse data collection across varied road environments. To the best of our knowledge, this is the first comprehensive analysis of domain shift effects on 4D radar-based object detection. We believe this empirical study contributes to understanding the complex nature of domain shifts in radar data and suggests paths forward for data collection strategy in the face of environmental variability., Comment: 6 pages, 5 figures, 3 tables, accepted in IEEE International Conference on Intelligent Transportation Systems (ITSC) 2024

Diffusion generative models, famous for their performance in image generation, are popular in various cross-domain applications. However, their use in the communication community has been mostly limited to auxiliary tasks like data modeling and feature extraction. These models hold greater promise for fundamental problems in network optimization compared to traditional machine learning methods. Discriminative deep learning often falls short due to its single-step input-output mapping and lack of global awareness of the solution space, especially given the complexity of network optimization's objective functions. In contrast, diffusion generative models can consider a broader range of solutions and exhibit stronger generalization by learning parameters that describe the distribution of the underlying solution space, with higher probabilities assigned to better solutions. We propose a new framework Diffusion Model-based Solution Generation (DiffSG), which leverages the intrinsic distribution learning capabilities of diffusion generative models to learn high-quality solution distributions based on given inputs. The optimal solution within this distribution is highly probable, allowing it to be effectively reached through repeated sampling. We validate the performance of DiffSG on several typical network optimization problems, including mixed-integer non-linear programming, convex optimization, and hierarchical non-convex optimization. Our results show that DiffSG outperforms existing baselines. In summary, we demonstrate the potential of diffusion generative models in tackling complex network optimization problems and outline a promising path for their broader application in the communication community., Comment: 8 pages, 5 figures

Scale-aware monocular depth estimation poses a significant challenge in computer-aided endoscopic navigation. However, existing depth estimation methods that do not consider the geometric priors struggle to learn the absolute scale from training with monocular endoscopic sequences. Additionally, conventional methods face difficulties in accurately estimating details on tissue and instruments boundaries. In this paper, we tackle these problems by proposing a novel enhanced scale-aware framework that only uses monocular images with geometric modeling for depth estimation. Specifically, we first propose a multi-resolution depth fusion strategy to enhance the quality of monocular depth estimation. To recover the precise scale between relative depth and real-world values, we further calculate the 3D poses of instruments in the endoscopic scenes by algebraic geometry based on the image-only geometric primitives (i.e., boundaries and tip of instruments). Afterwards, the 3D poses of surgical instruments enable the scale recovery of relative depth maps. By coupling scale factors and relative depth estimation, the scale-aware depth of the monocular endoscopic scenes can be estimated. We evaluate the pipeline on in-house endoscopic surgery videos and simulated data. The results demonstrate that our method can learn the absolute scale with geometric modeling and accurately estimate scale-aware depth for monocular scenes.

We propose a novel method to probe light-quark dipole moments by examining the azimuthal asymmetries between a collinear pair of hadrons in semi-inclusive deep inelastic lepton scattering off an unpolarized proton target at the Electron-Ion Collider. These asymmetries provide a means to observe transversely polarized quarks, which arise exclusively from the interference between the dipole and the Standard Model interactions, thereby depending linearly on the dipole couplings. We demonstrate that this novel approach can enhance current constraints on light-quark dipole operators by an order of magnitude, free from contamination of other new physics effects. Furthermore, it allows for a simultaneous determination of both the real and imaginary parts of the dipole couplings, offering a new avenue for investigating potential $CP$-violating effects at high energies., Comment: 6 pages, 2 figures

The roton-triggered charge-density-wave (CDW)is widely studied in fractional quantum Hall (FQH) and fractional Chern insulator (FCI) systems, and there also exist field theoretical and numerical realizations of continuous transition from FCI to superfluid (SF). However, the theory and numerical explorations of the transition between FCI and supersolid (SS) are still lacking. In this work, we study the topological flat-band lattice models with $\nu$ = 1/2 hard-core bosons, where the previous studies have discovered the existence of FCI states and possible direct FCI-SS transitions. While the FCI is robust, we find the direct FCI-SS transition is absent, and there exist more intriguing scenarios. In the case of checkerboard lattice, we find an intermediate gapless CDW state without SF, sandwiched between FCI and SS. This novel state is triggered by the roton instability in FCI and it further continuously brings about the intertwined finite-momentum SF fluctuation when the CDW order is strong enough, eventually transiting into an unconventional finite-momentum SS state. The intermediate gapless CDW state is a vestige from the SS state, since the increasing quantum fluctuation melts only the Larkin-Ovchinnikov-type SF order in SS but its (secondary) product -- the CDW order -- survives. On honeycomb lattice, we find no evidence of SS, but discover an interesting sequence of FCI-Solid I-Solid II transitions, with both solids incompressible. Moreover, in contrast to previous single-roton condensation, this sequence of FCI-Solid I-Solid II transitions is triggered by the softening of multi-roton modes in FCI. Considering the intertwined wave vectors of the CDW orders, Solid I is a vestige of Solid II. Our work provides new horizon not only for the quantum phase transitions in FCI but also for the intertwined orders and gapless states in bosonic systems, which will inspire future studies.

Epsilon Eridani ($\epsilon$ Eri) is one of the first debris disk systems detected by the Infrared Astronomical Satellite (IRAS). However, the system has thus far eluded detection in scattered light with no components having been directly imaged. Its similarity to a relatively young Solar System combined with its proximity makes it an excellent candidate to further our understanding of planetary system evolution. We present a set of coronagraphic images taken using the Space Telescope Imaging Spectrograph (STIS) coronagraph on the Hubble space telescope at a small inner working angle to detect a predicted warm inner debris disk inside 1". We used three different post-processing approaches; Non-negative Matrix Factorization (NMF), Karhunen-Lo`eve Image Processing (KLIP), and Classical reference differential imaging (RDI), to best optimize reference star subtraction, and find that NMF performed the best overall while KLIP produced the absolute best contrast inside 1". We present limits on scattered light from warm dust, with constraints on surface brightness at 6 mJy/as$^2$ at our inner working angle of 0.6". We also place a constraint of 0.5 mJy/as$^2$ outside 1", which gives us an upper limit on the brightness for outer disks and substellar companions. Finally, we calculated an upper limit on the dust albedo at $\omega <$ 0.487., Comment: 13+2 pages, 7+2 figures; Accepted for publication in the Astronomical Journal

We introduce CogVideoX, a large-scale diffusion transformer model designed for generating videos based on text prompts. To efficently model video data, we propose to levearge a 3D Variational Autoencoder (VAE) to compress videos along both spatial and temporal dimensions. To improve the text-video alignment, we propose an expert transformer with the expert adaptive LayerNorm to facilitate the deep fusion between the two modalities. By employing a progressive training technique, CogVideoX is adept at producing coherent, long-duration videos characterized by significant motions. In addition, we develop an effective text-video data processing pipeline that includes various data preprocessing strategies and a video captioning method. It significantly helps enhance the performance of CogVideoX, improving both generation quality and semantic alignment. Results show that CogVideoX demonstrates state-of-the-art performance across both multiple machine metrics and human evaluations. The model weights of both the 3D Causal VAE and CogVideoX are publicly available at https://github.com/THUDM/CogVideo.

In this letter, we propose a new movable antenna (MA) enabled symbiotic radio (SR) system that leverages the movement of MAs to maximize both the primary and secondary rates, thereby promoting their mutualism. Specifically, the primary transmitter (PT) equipped with MAs utilizes a maximum ratio transmission (MRT) beamforming scheme to ensure the highest primary rate at the primary user (PU). Concurrently, the backscatter device (BD) establishes the secondary transmission by overlaying onto the primary signal. The utilization of MAs aims to enhance the secondary rate by optimizing the positions of MAs to improve the beam gain at the BD. Accordingly, the beam gains for both MA and fixed-position antenna (FPA) scenarios are analyzed, confirming the effectiveness of the MA scheme in achieving the highest primary and secondary rates. Numerical results verity the superiority of our proposed MA enabled scheme., Comment: 5 pages, 5 figures. Accepted to IEEE Wireless Communications Letters