Search

Audio-driven talking head synthesis strives to generate lifelike video portraits from provided audio. The diffusion model, recognized for its superior quality and robust generalization, has been explored for this task. However, establishing a robust correspondence between temporal audio cues and corresponding spatial facial expressions with diffusion models remains a significant challenge in talking head generation. To bridge this gap, we present DreamHead, a hierarchical diffusion framework that learns spatial-temporal correspondences in talking head synthesis without compromising the model's intrinsic quality and adaptability.~DreamHead learns to predict dense facial landmarks from audios as intermediate signals to model the spatial and temporal correspondences.~Specifically, a first hierarchy of audio-to-landmark diffusion is first designed to predict temporally smooth and accurate landmark sequences given audio sequence signals. Then, a second hierarchy of landmark-to-image diffusion is further proposed to produce spatially consistent facial portrait videos, by modeling spatial correspondences between the dense facial landmark and appearance. Extensive experiments show that proposed DreamHead can effectively learn spatial-temporal consistency with the designed hierarchical diffusion and produce high-fidelity audio-driven talking head videos for multiple identities.

Booming time-critical services, such as automated manufacturing and remote operations, stipulate increasing demands for facilitating large-scale Industrial Internet of Things (IoT). Recently, a cycle specified queuing and forwarding (CSQF) scheme has been advocated to enhance the Ethernet. However, CSQF only outlines a foundational equipment-level primitive, while how to attain network-wide flow scheduling is not yet determined. Prior endeavors primarily focus on the range of a local area, rendering them unsuitable for long-distance factory interconnection. This paper devises the cycle tags planning (CTP) mechanism, the first integer programming model for the CSQF, which makes the CSQF practical for efficient global flow scheduling. In the CTP model, the per-hop cycle alignment problem is solved by decoupling the long-distance link delay from cyclic queuing time. To avoid queue overflows, we discretize the underlying network resources into cycle-related queue resource blocks and detail the core constraints within multiple periods. Then, two heuristic algorithms named flow offset and cycle shift (FO-CS) and Tabu FO-CS are designed to calculate the flows' cycle tags and maximize the number of schedulable flows, respectively. Evaluation results show that FO-CS increases the number of scheduled flows by 31.2%. The Tabu FO-CS algorithm can schedule 94.45% of flows at the level of 2000 flows.

Large Language Models (LLMs) have become indispensable in numerous real-world applications. Unfortunately, fine-tuning these models at scale, especially in federated settings where data privacy and communication efficiency are critical, presents significant challenges. Existing methods often resort to parameter-efficient fine-tuning (PEFT) to mitigate communication overhead, but this typically comes at the cost of model accuracy. To address these limitations, we propose federated full-parameter tuning at scale for LLMs (Ferret), the first first-order method with shared randomness to enable scalable full-parameter tuning of LLMs across decentralized data sources while maintaining competitive model accuracy. Ferret accomplishes this through three aspects: (1) it employs widely applied first-order methods for efficient local updates; (2) it projects these updates into a low-dimensional space to considerably reduce communication overhead; and (3) it reconstructs local updates from this low-dimensional space with shared randomness to facilitate effective full-parameter global aggregation, ensuring fast convergence and competitive final performance. Our rigorous theoretical analyses and insights along with extensive experiments, show that Ferret significantly enhances the scalability of existing federated full-parameter tuning approaches by achieving high computational efficiency, reduced communication overhead, and fast convergence, all while maintaining competitive model accuracy. Our implementation is available at https://github.com/allen4747/Ferret.

Dense colored point clouds enhance visual perception and are of significant value in various robotic applications. However, existing learning-based point cloud upsampling methods are constrained by computational resources and batch processing strategies, which often require subdividing point clouds into smaller patches, leading to distortions that degrade perceptual quality. To address this challenge, we propose a novel 2D-3D hybrid colored point cloud upsampling framework (GaussianPU) based on 3D Gaussian Splatting (3DGS) for robotic perception. This approach leverages 3DGS to bridge 3D point clouds with their 2D rendered images in robot vision systems. A dual scale rendered image restoration network transforms sparse point cloud renderings into dense representations, which are then input into 3DGS along with precise robot camera poses and interpolated sparse point clouds to reconstruct dense 3D point clouds. We have made a series of enhancements to the vanilla 3DGS, enabling precise control over the number of points and significantly boosting the quality of the upsampled point cloud for robotic scene understanding. Our framework supports processing entire point clouds on a single consumer-grade GPU, such as the NVIDIA GeForce RTX 3090, eliminating the need for segmentation and thus producing high-quality, dense colored point clouds with millions of points for robot navigation and manipulation tasks. Extensive experimental results on generating million-level point cloud data validate the effectiveness of our method, substantially improving the quality of colored point clouds and demonstrating significant potential for applications involving large-scale point clouds in autonomous robotics and human-robot interaction scenarios., Comment: 7 pages, 5 figures

Large Language Models (LLMs) have garnered widespread attention due to their remarkable performance across various tasks. However, to mitigate the issue of hallucinations, LLMs often incorporate retrieval-augmented pipeline to provide them with rich external knowledge and context. Nevertheless, challenges stem from inaccurate and coarse-grained context retrieved from the retriever. Supplying irrelevant context to the LLMs can result in poorer responses, increased inference latency, and higher costs. This paper introduces a method called Instruction-Aware Contextual Compression, which filters out less informative content, thereby accelerating and enhancing the use of LLMs. The experimental results demonstrate that Instruction-Aware Contextual Compression notably reduces memory consumption and minimizes generation latency while maintaining performance levels comparable to those achieved with the use of the full context. Specifically, we achieved a 50% reduction in context-related costs, resulting in a 5% reduction in inference memory usage and a 2.2-fold increase in inference speed, with only a minor drop of 0.047 in Rouge-1. These findings suggest that our method strikes an effective balance between efficiency and performance., Comment: 20 pages

In this work, we investigate the resonance production in $\Lambda^+_c \to \gamma \pi^+ \Lambda$ decay through the triangle singularity (TS) mechanism, within an effective Lagrangian approach. We find that the appropriate loop decay process could develop a triangle singularity in the invariant mass $M_{\pi\Lambda}$ around $1.35$ GeV, with the shape depending on the quantum numbers of $\Sigma^*$ states that couple to the final $\pi\Lambda$ system. Especially, the $\Sigma(1380)1/2^-$ state newly predicted in the pentaquark model, if exists, significantly enhances the TS contribution and sharpens the TS peak due to the $S$-wave $\Sigma^*\pi\Sigma$ vertex in the loop. Therefore, the existence of the $\Sigma(1380)1/2^-$ state can be examined by measuring the TS signal in $\Lambda^+_c \to \gamma \pi^+ \Lambda$. Considering also possible tree-level diagrams, we additionally obtain the branching ratio ${\rm Br}(\Lambda^+_c \to \gamma \pi^+ \Lambda)\simeq 1.5\times 10^{-5}$. We suggest the investigation of this reaction by future BESIII, LHCb, and Belle experiments., Comment: 8 pages, 6 figures

Large Language Models (LLMs) are driving advancements in artificial intelligence by increasing the scale of model parameters, which has significantly enhanced generalization ability and unlocked new capabilities in practice. However, their performance in specific downstream tasks is usually hindered by their knowledge boundaries on these tasks. Thus, fine-tuning techniques, especially the widely used Low-Rank Adaptation (LoRA) method, have been introduced to expand the boundaries on these tasks, whereas LoRA would underperform on certain tasks owing to its potential overfitting on these tasks. To overcome this overfitting and improve the performance of LoRA, we propose the flexible low rank adaptation (Flexora) method to automatically and flexibly select the most important layers needing to be fine-tuned to achieve the best performance on different downstream tasks. Specifically, Flexora firstly frames this layer selection problem as a well-defined hyperparameter optimization (HPO) problem, then addresses it using the unrolled differentiation (UD) method, and finally selects the most useful layers based on the optimized hyperparameters. Our extensive experiments on many pretrained models and natural language tasks show that Flexora is able to consistently improve over the existing baselines, indicating the effectiveness of our Flexora in practice. We additionally provide insightful theoretical results and many ablation studies to deliver a comprehensive understanding of our Flexora., Comment: 29 pages, 13 figures

Meta-learning has been extensively applied in the domains of few-shot learning and fast adaptation, achieving remarkable performance. While Meta-learning methods like Model-Agnostic Meta-Learning (MAML) and its variants provide a good set of initial parameters for the model, the model still tends to learn shortcut features, which leads to poor generalization. In this paper, we propose the formal conception of "learn to learn more precisely", which aims to make the model learn precise target knowledge from data and reduce the effect of noisy knowledge, such as background and noise. To achieve this target, we proposed a simple and effective meta-learning framework named Meta Self-Distillation(MSD) to maximize the consistency of learned knowledge, enhancing the models' ability to learn precise target knowledge. In the inner loop, MSD uses different augmented views of the same support data to update the model respectively. Then in the outer loop, MSD utilizes the same query data to optimize the consistency of learned knowledge, enhancing the model's ability to learn more precisely. Our experiment demonstrates that MSD exhibits remarkable performance in few-shot classification tasks in both standard and augmented scenarios, effectively boosting the accuracy and consistency of knowledge learned by the model., Comment: 10pages,4 figures, meta learning

Personalized motion planning holds significant importance within urban automated driving, catering to the unique requirements of individual users. Nevertheless, prior endeavors have frequently encountered difficulties in simultaneously addressing two crucial aspects: personalized planning within intricate urban settings and enhancing planning performance through data utilization. The challenge arises from the expensive and limited nature of user data, coupled with the scene state space tending towards infinity. These factors contribute to overfitting and poor generalization problems during model training. Henceforth, we propose an instance-based transfer imitation learning approach. This method facilitates knowledge transfer from extensive expert domain data to the user domain, presenting a fundamental resolution to these issues. We initially train a pre-trained model using large-scale expert data. Subsequently, during the fine-tuning phase, we feed the batch data, which comprises expert and user data. Employing the inverse reinforcement learning technique, we extract the style feature distribution from user demonstrations, constructing the regularization term for the approximation of user style. In our experiments, we conducted extensive evaluations of the proposed method. Compared to the baseline methods, our approach mitigates the overfitting issue caused by sparse user data. Furthermore, we discovered that integrating the driving model with a differentiable nonlinear optimizer as a safety protection layer for end-to-end personalized fine-tuning results in superior planning performance., Comment: IROS 2024 Accepted

In domain-specific applications, GPT-4, augmented with precise prompts or Retrieval-Augmented Generation (RAG), shows notable potential but faces the critical tri-lemma of performance, cost, and data privacy. High performance requires sophisticated processing techniques, yet managing multiple agents within a complex workflow often proves costly and challenging. To address this, we introduce the PEER (Plan, Execute, Express, Review) multi-agent framework. This systematizes domain-specific tasks by integrating precise question decomposition, advanced information retrieval, comprehensive summarization, and rigorous self-assessment. Given the concerns of cost and data privacy, enterprises are shifting from proprietary models like GPT-4 to custom models, striking a balance between cost, security, and performance. We developed industrial practices leveraging online data and user feedback for efficient model tuning. This study provides best practice guidelines for applying multi-agent systems in domain-specific problem-solving and implementing effective agent tuning strategies. Our empirical studies, particularly in the financial question-answering domain, demonstrate that our approach achieves 95.0% of GPT-4's performance, while effectively managing costs and ensuring data privacy.

Affective computing stands at the forefront of artificial intelligence (AI), seeking to imbue machines with the ability to comprehend and respond to human emotions. Central to this field is emotion recognition, which endeavors to identify and interpret human emotional states from different modalities, such as speech, facial images, text, and physiological signals. In recent years, important progress has been made in generative models, including Autoencoder, Generative Adversarial Network, Diffusion Model, and Large Language Model. These models, with their powerful data generation capabilities, emerge as pivotal tools in advancing emotion recognition. However, up to now, there remains a paucity of systematic efforts that review generative technology for emotion recognition. This survey aims to bridge the gaps in the existing literature by conducting a comprehensive analysis of over 320 research papers until June 2024. Specifically, this survey will firstly introduce the mathematical principles of different generative models and the commonly used datasets. Subsequently, through a taxonomy, it will provide an in-depth analysis of how generative techniques address emotion recognition based on different modalities in several aspects, including data augmentation, feature extraction, semi-supervised learning, cross-domain, etc. Finally, the review will outline future research directions, emphasizing the potential of generative models to advance the field of emotion recognition and enhance the emotional intelligence of AI systems., Comment: Under Review

Despite the rapid development of Chinese vision-language models (VLMs), most existing Chinese vision-language (VL) datasets are constructed on Western-centric images from existing English VL datasets. The cultural bias in the images makes these datasets unsuitable for evaluating VLMs in Chinese culture. To remedy this issue, we present a new Chinese Vision- Language Understanding Evaluation (CVLUE) benchmark dataset, where the selection of object categories and images is entirely driven by Chinese native speakers, ensuring that the source images are representative of Chinese culture. The benchmark contains four distinct VL tasks ranging from image-text retrieval to visual question answering, visual grounding and visual dialogue. We present a detailed statistical analysis of CVLUE and provide a baseline performance analysis with several open-source multilingual VLMs on CVLUE and its English counterparts to reveal their performance gap between English and Chinese. Our in-depth category-level analysis reveals a lack of Chinese cultural knowledge in existing VLMs. We also find that fine-tuning on Chinese culture-related VL datasets effectively enhances VLMs' understanding of Chinese culture.

Retrieval-Augmented Generation (RAG) has been widely adopted to enhance Large Language Models (LLMs) in knowledge-intensive tasks. Recently, Attributed Text Generation (ATG) has attracted growing attention, which provides citations to support the model's responses in RAG, so as to enhance the credibility of LLM-generated content and facilitate verification. Prior methods mainly adopt coarse-grained attributions, linking to passage-level references or providing paragraph-level citations. However, these methods still fall short in verifiability and require certain time costs for fact checking. This paper proposes a fine-grained ATG method called ReClaim(Refer & Claim), which alternates the generation of references and answers step by step. Unlike traditional coarse-grained attribution, ReClaim allows the model to add sentence-level fine-grained citations to each answer sentence in long-form question-answering tasks. Our experiments encompass various training and inference methods and multiple LLMs, verifying the effectiveness of our approach., Comment: 15 pages,2 figures

Efficient data transmission scheduling within vehicular environments poses a significant challenge due to the high mobility of such networks. Contemporary research predominantly centers on crafting cooperative scheduling algorithms tailored for vehicular networks. Notwithstanding, the intricacies of orchestrating scheduling in vehicular social networks both effectively and efficiently remain formidable. This paper introduces an innovative learning-based algorithm for scheduling data transmission that prioritizes efficiency and security within vehicular social networks. The algorithm first uses a specifically constructed neural network to enhance data processing capabilities. After this, it incorporates a Q-learning paradigm during the data transmission phase to optimize the information exchange, the privacy of which is safeguarded by differential privacy through the communication process. Comparative experiments demonstrate the superior performance of the proposed Q-learning enhanced scheduling algorithm relative to existing state-of-the-art scheduling algorithms in the context of vehicular social networks.

In a PN junction, the separation between positive and negative charges leads to diode transport. In the past few years, the intrinsic diode transport in noncentrosymmetric polar conductors has attracted great interest, because it suggests novel nonlinear applications and provides a symmetry-sensitive probe of Fermi surface. Recently, such studies have been extended to noncentrosymmetric superconductors, realizing the superconducting diode effect. Here, we show that, even in a centrosymmetric crystal without directional charge separation, the spins of an antiferromagnet (AFM) can generate a spatial directionality, leading to an AFM diode effect. We observe large second-harmonic transport in a nonlinear electronic device enabled by the compensated AFM state of even-layered MnBi2Te4. We also report a novel electrical sum-frequency generation (SFG), which has been rarely explored in contrast to the well-known optical SFG in wide-gap insulators. We demonstrate that the AFM enables an in-plane field-effect transistor and harvesting of wireless electromagnetic energy. The electrical SFG establishes a powerful method to study nonlinear electronics built by quantum materials. The AFM diode effect paves the way for potential device concepts including AFM logic circuits, self-powered AFM spintronics, and other applications that potentially bridge nonlinear electronics with AFM spintronics., Comment: 33+8 pages, 14+2 figures

Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this study, we introduce VisualRWKV, the first application of a linear RNN model to multimodal learning tasks, leveraging the pre-trained RWKV language model. We propose a data-dependent recurrence and sandwich prompts to enhance our modeling capabilities, along with a 2D image scanning mechanism to enrich the processing of visual sequences. Extensive experiments demonstrate that VisualRWKV achieves competitive performance compared to Transformer-based models like LLaVA-1.5 on various benchmarks. To facilitate further research and analysis, we have made the checkpoints and the associated code publicly accessible at the following GitHub repository: \href{https://github.com/howard-hou/VisualRWKV}{https://github.com/howard-hou/VisualRWKV}., Comment: 18 pages,14 tables,6 figures

We extend our previous study of the interactions of $\bar{D}^{(*)} \Lambda_c - \bar{D}^{(*)}\Sigma_c^{(*)}$ within an analytic, unitary, coupled-channel approach by including the $J/\psi p$ channel and performing fits to the $J/\psi p$ invariant mass distributions in the $\Lambda_b^0 \to J/\psi p K^-$ decay by the LHCb Collaboration. We take into account the contributions of $t$-channel pseudoscalar and vector meson exchanges and $u$-channel baryon exchanges in this work, and a series of bound states and resonances with different spin-parities are dynamically generated. According to the results, four states have a significant impact on the physical observables, with two having a spin-parity of $1/2^-$ and the other two having $3/2^-$. These states can be associated with the LHCb hidden-charm pentaquarks. We further provide the coupling strength between each pole and different channels, which provides some insights on how to search for them in future experiments. Moreover, we also search for poles in higher partial waves up to $J=7/2$ and find indications for the existence of several states with larger widths., Comment: 9 pages

Despite the advancements and impressive performance of Multimodal Large Language Models (MLLMs) on benchmarks, their effectiveness in real-world, long-context, and multi-image tasks is unclear due to the benchmarks' limited scope. Existing benchmarks often focus on single-image and short-text samples, and when assessing multi-image tasks, they either limit the image count or focus on specific task (e.g time-series captioning), potentially obscuring the performance challenges of MLLMs. To address these limitations, we introduce MileBench, a pioneering benchmark designed to test the MultImodal Long-contExt capabilities of MLLMs. This benchmark comprises not only multimodal long contexts, but also multiple tasks requiring both comprehension and generation. We establish two distinct evaluation sets, diagnostic and realistic, to systematically assess MLLMs' long-context adaptation capacity and their ability to complete tasks in long-context scenarios. Our experimental results, obtained from testing 22 models, revealed that while the closed-source GPT-4o outperforms others, most open-source MLLMs struggle in long-context situations. Interestingly, the performance gap tends to widen with an increase in the number of images. We strongly encourage an intensification of research efforts towards enhancing MLLMs' long-context capabilities, especially in scenarios involving multiple images., Comment: 31 pages, 13 figures, 14 tables; We add results of GPT-4o in this version

Hadronic resonances emerge from strong interactions encoding the dynamics of quarks and gluons. The structure of these resonances can be probed by virtual photons parameterized in transition form factors. In this study, twelve $N^*$ and $\Delta$ transition form factors at the pole are extracted from data with the center-of-mass energy from $\pi N$ threshold to $1.8\,{\rm GeV}$, and the photon virtuality $0\leq Q^2/{\rm GeV}^2\leq 8$. For the first time, these results are determined from a simultaneous analysis of more than one state, i.e., $\sim 10^5$ $\pi N$, $\eta N$, and $K\Lambda$ electroproduction data. In addition, about $ 5\cdot 10^4$ data in the hadronic sector as well as photoproduction serve as boundary conditions. For the $\Delta(1232)$ and $N(1440)$ states our results are in qualitative agreement with previous studies, while the transition form factors at the poles of some higher excited states are estimated for the first time. Realistic uncertainties are determined by further exploring the parameter space., Comment: Text: 6 pages, 4 figures. Supplemental Material: 3 pages, 2 figures

Rendering photo-realistic novel-view images of complex scenes has been a long-standing challenge in computer graphics. In recent years, great research progress has been made on enhancing rendering quality and accelerating rendering speed in the realm of view synthesis. However, when rendering complex dynamic scenes with sparse views, the rendering quality remains limited due to occlusion problems. Besides, for rendering high-resolution images on dynamic scenes, the rendering speed is still far from real-time. In this work, we propose a generalizable view synthesis method that can render high-resolution novel-view images of complex static and dynamic scenes in real-time from sparse views. To address the occlusion problems arising from the sparsity of input views and the complexity of captured scenes, we introduce an explicit 3D visibility reasoning approach that can efficiently estimate the visibility of sampled 3D points to the input views. The proposed visibility reasoning approach is fully differentiable and can gracefully fit inside the volume rendering pipeline, allowing us to train our networks with only multi-view images as supervision while refining geometry and texture simultaneously. Besides, each module in our pipeline is carefully designed to bypass the time-consuming MLP querying process and enhance the rendering quality of high-resolution images, enabling us to render high-resolution novel-view images in real-time.Experimental results show that our method outperforms previous view synthesis methods in both rendering quality and speed, particularly when dealing with complex dynamic scenes with sparse views.

First-order optimization (FOO) algorithms are pivotal in numerous computational domains such as machine learning and signal denoising. However, their application to complex tasks like neural network training often entails significant inefficiencies due to the need for many sequential iterations for convergence. In response, we introduce first-order optimization expedited with approximately parallelized iterations (OptEx), the first framework that enhances the efficiency of FOO by leveraging parallel computing to mitigate its iterative bottleneck. OptEx employs kernelized gradient estimation to make use of gradient history for future gradient prediction, enabling parallelization of iterations -- a strategy once considered impractical because of the inherent iterative dependency in FOO. We provide theoretical guarantees for the reliability of our kernelized gradient estimation and the iteration complexity of SGD-based OptEx, confirming that estimation errors diminish to zero as historical gradients accumulate and that SGD-based OptEx enjoys an effective acceleration rate of $\Omega(\sqrt{N})$ over standard SGD given parallelism of N. We also use extensive empirical studies, including synthetic functions, reinforcement learning tasks, and neural network training across various datasets, to underscore the substantial efficiency improvements achieved by OptEx.

We study the charmed meson and baryon production and elliptic flow in ultra-relativistic nucleus-nucleus collisions at the LHC energies. The space-time evolution of quark-gluon plasma (QGP) produced in these energetic collisions is obtained via the (3+1)-dimensional CLVisc hydrodynamics model, the heavy quark dynamics inside the QGP is simulated using an improved Langevin model that incorporates both elastic and inelastic parton energy loss processes, and the heavy quark hadronization is simulated utilizing a comprehensive coalescence-fragmentation model. Using our combined approach, we first calculate charmed hadron ratios, $\Lambda_c/D^0$ and $D_s/D^0$, as well as their elliptic flow ($v_2$) as a function of transverse momentum ($p_T$) for different centralities in Pb+Pb collisions at $\sqrt{s_{NN}}=5.02$~TeV. Due to strangeness enhancement and parton coalescence effects, $D_s/D^0$ and $\Lambda_c/D^0$ ratios increase from peripheral to central collisions, and such centrality dependence for $\Lambda_c/D^0$ is stronger than $D_s/D^0$. We further predict the $p_T$ and centrality dependences of charmed hadron chemistry and $v_2$ in smaller Xe+Xe, Ar+Ar and O+O collisions at the LHC energies. Strong centrality and system size dependences for $\Lambda_c/D^0$ and $D_s/D^0$ ratios are observed across four collision systems. As for charmed hadron flow, both system size and collision geometry are important to understand the centrality dependence of $v_2$ in different collision systems. Our study provides a significant reference for studying heavy quark evolution and hadronizaiton in large and small systems in relativistic nuclear collisions., Comment: 12 pages, 10 figures

The stock market is a crucial component of the financial system, but predicting the movement of stock prices is challenging due to the dynamic and intricate relations arising from various aspects such as economic indicators, financial reports, global news, and investor sentiment. Traditional sequential methods and graph-based models have been applied in stock movement prediction, but they have limitations in capturing the multifaceted and temporal influences in stock price movements. To address these challenges, the Multi-relational Dynamic Graph Neural Network (MDGNN) framework is proposed, which utilizes a discrete dynamic graph to comprehensively capture multifaceted relations among stocks and their evolution over time. The representation generated from the graph offers a complete perspective on the interrelationships among stocks and associated entities. Additionally, the power of the Transformer structure is leveraged to encode the temporal evolution of multiplex relations, providing a dynamic and effective approach to predicting stock investment. Further, our proposed MDGNN framework achieves the best performance in public datasets compared with state-of-the-art (SOTA) stock investment methods., Comment: 9 pages, 3 figures, accepted by AAAI 2024

In this article, we present a novel framework, named distributed task-oriented communication networks (DTCN), based on recent advances in multimodal semantic transmission and edge intelligence. In DTCN, the multimodal knowledge of semantic relays and the adaptive adjustment capability of edge intelligence can be integrated to improve task performance. Specifically, we propose the key techniques in the framework, such as semantic alignment and complement, a semantic relay scheme for deep joint source-channel relay coding, and collaborative device-server optimization and inference. Furthermore, a multimodal classification task is used as an example to demonstrate the benefits of the proposed DTCN over existing methods. Numerical results validate that DTCN can significantly improve the accuracy of classification tasks, even in harsh communication scenarios (e.g., low signal-to-noise regime), thanks to multimodal semantic relay and edge intelligence., Comment: 7 pages, 5 figures, 1 table, accepted by IEEE Communications Magazine

This talk focuses on a recent work aiming at determining the composition of certain $N^*$ and $\Delta$ resonances, i.e. whether they are compact states formed directly by quarks and gluons, or composite generated from the meson-baryon interaction. The information of the resonance poles is provided by a comprehensive coupled-channel approach, the J\"ulich-Bonn model. Thirteen states that are significant in this approach are studied. Two criteria for each state are adopted in this paper, the comparison thereof roughly indicates the model uncertainties. It is found that the conclusions for eight resonances are relatively certain: $N(1535) \frac{1}{2}^-$, $N(1440) \frac{1}{2}^+$, $N(1710) \frac{1}{2}^+$, and $N(1520) \frac{3}{2}^-$ tend to be composite; whereas $N(1650) \frac{1}{2}^-$, $N(1900) \frac{3}{2}^+$, $N(1680) \frac{5}{2}^+$, and $\Delta(1600) \frac{3}{2}^+$ tend to be compact., Comment: 6 pages, 2 figures, 16th International Conference on Meson-Nucleon Physics and the Structure of the Nucleon (MENU 2023), text overlaps with arXiv:2307.06799 [nucl-th]

This talk is on a refined investigation on light flavor meson-baryon scatterings, using a dynamical coupled-channel approach, i.e. the J\"ulich-Bonn model. The previous channel space of $\pi N$, $\pi \Delta$, $\sigma N$, $\rho N$, $\eta N$, $K \Lambda$ and $K \Sigma$ is extended by adding the $\omega N$ final state. The spectra of $N^*$ and $\Delta$ resonances are extracted, based on the result of a global fit to a worldwide collection of data, in the energy region from the $\pi N$ threshold to center-of-mass energy $z=2.3$ GeV (approximately $300$ parameters against $9000$ data points). A negative value of the $\omega N$ elastic spin-averaged scattering length has been extracted., Comment: 4 pages, 2 figures, 17th International Workshop on Meson Physics (MESON2023), text overlaps with arXiv:2208.03061 [nucl-th]

In this paper we explore the application of low-loss multimode anti-resonant hollow-core fiber (MM-AR-HCF) in the delivery of nanosecond laser pulses at 1 um wavelength. MM-AR-HCF of large core offers a rich content of low-loss higher-order modes which plays a key role in the efficient coupling and transmission of high-power laser of degraded beam quality. In the experiment, laser pulses of an average pulse energy of 21.8 mJ with 14.6 ns pulse width (corresponding a peak power of 1.49 MW) are transmitted through MM-AR-HCF of 9.8 m length without damaging. Up to 94 % coupling efficiency is achieved where the incident laser beam suffers a degraded beam quality with and of 2.18 and 1.99 respectively. Laser-induced damage threshold (LIDT) of MM-AR-HCF measures 22.6 mJ for 94 % coupling efficiency, which is 7 times higher than that for multimode silica optical fiber with a core diameter of 200 um., Comment: 8 pages, 9 figures

Large language models (LLMs) often struggle with maintaining accuracy throughout multiple multiple reasoning steps, especially in mathematical reasoning where an error in earlier steps can propagate to subsequent ones and it ultimately leading to an incorrect answer. To reduce error propagation, guided decoding is employed to direct the LM decoding on a step-by-step basis. We argue that in guided decoding, assessing the potential of an incomplete reasoning path can be more advantageous than simply ensuring per-step correctness, as the former approach leads towards a correct final answer. This transforms the task into a $\textit{value estimation}$ problem in planning. Inspired by the findings that $\textit{outcome supervision for guided decoding essentially acts as a value model}$, we propose Outcome-supervised Value Model (OVM) that employs outcome supervision for training a value model, which prioritizes steps that lead to accurate conclusions. Furthermore, the OVM eliminates the need for labor-intensive annotations of step-level correctness, thereby significantly enhancing its scalability. Our experiments on two multi-step mathematical reasoning datasets, GSM8K and Game of 24, demonstrate the superior performance of the OVM model. Notably, in GSM8K, our $\textbf{OVM-7B model achieves state-of-the-art results among LLMs up to 13B parameters}$; especially it does not utilize GPT-4 or code execution. These findings offer a novel perspective on the role of outcome supervision in training value models for multi-step reasoning tasks and provide theoretical justification for its advantage in value estimation for guided decoding., Comment: Accepted to NAACL findings. https://github.com/FreedomIntelligence/OVM