Search

The planar two-loop scalar Feynman integrals contributing to the massive NNLO QCD corrections for $W$-boson pair production via quark-antiquark annihilation can be classified into three family branches, each of which is reduced to a distinct set of master integrals (MIs), totaling $27$, $45$ and $15$, respectively. These MIs are analytically calculated using the method of differential equations, with solutions expanded as Taylor series in the dimensional regulator $\epsilon$. For the first two family branches, the differential systems can be successfully transformed into canonical form by adopting appropriate bases of MIs. This enables the MIs of these family branches to be expressed either as Goncharov polylogarithms (GPLs) or as one-fold integrals over GPLs, up to $\mathcal{O}(\epsilon^4)$. In contrast, the differential system for the third family branch can only be cast into a form linear in $\epsilon$ due to the presence of elliptic integrals. The solution to this linear-form differential system is expressed in an iterated form owing to the strictly lower-triangular structure of the coefficient matrices at $\epsilon = 0$. Our analytic expressions for these MIs are verified with high accuracy against the numerical results from the \texttt{AMFlow} package., Comment: 39 pages, 4 figures

While deep learning techniques have proven successful in image-related tasks, the exponentially increased data storage and computation costs become a significant challenge. Dataset distillation addresses these challenges by synthesizing only a few images for each class that encapsulate all essential information. Most current methods focus on matching. The problems lie in the synthetic images not being human-readable and the dataset performance being insufficient for downstream learning tasks. Moreover, the distillation time can quickly get out of bounds when the number of synthetic images per class increases even slightly. To address this, we train a class conditional latent diffusion model capable of generating realistic synthetic images with labels. The sampling time can be reduced to several tens of images per seconds. We demonstrate that models can be effectively trained using only a small set of synthetic images and evaluated on a large real test set. Our approach achieved rank \(1\) in The First Dataset Distillation Challenge at ECCV 2024 on the CIFAR100 and TinyImageNet datasets., Comment: 13 pages, 7 figures

Embodied AI is transforming how AI systems interact with the physical world, yet existing datasets are inadequate for developing versatile, general-purpose agents. These limitations include a lack of standardized formats, insufficient data diversity, and inadequate data volume. To address these issues, we introduce ARIO (All Robots In One), a new data standard that enhances existing datasets by offering a unified data format, comprehensive sensory modalities, and a combination of real-world and simulated data. ARIO aims to improve the training of embodied AI agents, increasing their robustness and adaptability across various tasks and environments. Building upon the proposed new standard, we present a large-scale unified ARIO dataset, comprising approximately 3 million episodes collected from 258 series and 321,064 tasks. The ARIO standard and dataset represent a significant step towards bridging the gaps of existing data resources. By providing a cohesive framework for data collection and representation, ARIO paves the way for the development of more powerful and versatile embodied AI agents, capable of navigating and interacting with the physical world in increasingly complex and diverse ways. The project is available on https://imaei.github.io/project_pages/ario/, Comment: Project website: https://imaei.github.io/project_pages/ario/

Significant wave height (SWH) is a vital metric in marine science, and accurate SWH estimation is crucial for various applications, e.g., marine energy development, fishery, early warning systems for potential risks, etc. Traditional SWH estimation methods that are based on numerical models and physical theories are hindered by computational inefficiencies. Recently, machine learning has emerged as an appealing alternative to improve accuracy and reduce computational time. However, due to limited observational technology and high costs, the scarcity of real-world data restricts the potential of machine learning models. To overcome these limitations, we propose an ocean SWH estimation framework, namely Orca. Specifically, Orca enhances the limited spatio-temporal reasoning abilities of classic LLMs with a novel spatiotemporal aware encoding module. By segmenting the limited buoy observational data temporally, encoding the buoys' locations spatially, and designing prompt templates, Orca capitalizes on the robust generalization ability of LLMs to estimate significant wave height effectively with limited data. Experimental results on the Gulf of Mexico demonstrate that Orca achieves state-of-the-art performance in SWH estimation.

Reconfigurable intelligent surfaces (RISs) have emerged as a promising auxiliary technology for radio frequency imaging. However, existing works face challenges of faint and intricate back-scattered waves and the restricted field-of-view (FoV), both resulting from complex target structures and a limited number of antennas. The synergistic benefits of multi-RIS-aided imaging hold promise for addressing these challenges. Here, we propose a dual-RIS-aided imaging system, Dreamer, which operates collaboratively in complementary modes (reflection-mode and transmission-mode). Dreamer significantly expands the FoV and enhances perception by deploying dual-RIS across various spatial and measurement patterns. Specifically, we perform a fine-grained analysis of how radio-frequency (RF) signals encode scene information in the scattered object modeling. Based on this modeling, we design illumination strategies to balance spatial resolution and observation scale, and implement a prototype system in a typical indoor environment. Moreover, we design a novel artificial neural network with a CNN-external-attention mechanism to translate RF signals into high-resolution images of human contours. Our approach achieves an impressive SSIM score exceeding 0.83, validating its effectiveness in broadening perception modes and enhancing imaging capabilities. The code to reproduce our results is available at https://github.com/fuhaiwang/Dreamer., Comment: 15 pages

We present a novel pipeline for learning high-quality triangular human avatars from multi-view videos. Recent methods for avatar learning are typically based on neural radiance fields (NeRF), which is not compatible with traditional graphics pipeline and poses great challenges for operations like editing or synthesizing under different environments. To overcome these limitations, our method represents the avatar with an explicit triangular mesh extracted from an implicit SDF field, complemented by an implicit material field conditioned on given poses. Leveraging this triangular avatar representation, we incorporate physics-based rendering to accurately decompose geometry and texture. To enhance both the geometric and appearance details, we further employ a 2D UNet as the network backbone and introduce pseudo normal ground-truth as additional supervision. Experiments show that our method can learn triangular avatars with high-quality geometry reconstruction and plausible material decomposition, inherently supporting editing, manipulation or relighting operations., Comment: Project Page: https://shad0wta9.github.io/meshavatar-page/

Deep learning has deeply changed the paradigms of many research fields. At the heart of chemical and physical sciences is the accurate ab initio calculation of many-body wavefunction, which has become one of the most notable examples to demonstrate the power of deep learning in science. In particular, the introduction of deep learning into quantum Monte Carlo (QMC) has significantly advanced the frontier of ab initio calculation, offering a universal tool to solve the electronic structure of materials and molecules. Deep learning QMC architectures were initial designed and tested on small molecules, focusing on comparisons with other state-of-the-art ab initio methods. Methodological developments, including extensions to real solids and periodic models, have been rapidly progressing and reported applications are fast expanding. This review covers the theoretical foundation of deep learning QMC for solids, the neural network wavefunction ansatz, and various of other methodological developments. Applications on computing energy, electron density, electric polarization, force and stress of real solids are also reviewed. The methods have also been extended to other periodic systems and finite temperature calculations. The review highlights the potentials and existing challenges of deep learning QMC in materials chemistry and condensed matter physics.

Video instance segmentation requires detecting, segmenting, and tracking objects in videos, typically relying on costly video annotations. This paper introduces a method that eliminates video annotations by utilizing image datasets. The PM-VIS algorithm is adapted to handle both bounding box and instance-level pixel annotations dynamically. We introduce ImageNet-bbox to supplement missing categories in video datasets and propose the PM-VIS+ algorithm to adjust supervision based on annotation types. To enhance accuracy, we use pseudo masks and semi-supervised optimization techniques on unannotated video data. This method achieves high video instance segmentation performance without manual video annotations, offering a cost-effective solution and new perspectives for video instance segmentation applications. The code will be available in https://github.com/ldknight/PM-VIS-plus, Comment: MIPR 2024

We present Subtractive Training, a simple and novel method for synthesizing individual musical instrument stems given other instruments as context. This method pairs a dataset of complete music mixes with 1) a variant of the dataset lacking a specific stem, and 2) LLM-generated instructions describing how the missing stem should be reintroduced. We then fine-tune a pretrained text-to-audio diffusion model to generate the missing instrument stem, guided by both the existing stems and the text instruction. Our results demonstrate Subtractive Training's efficacy in creating authentic drum stems that seamlessly blend with the existing tracks. We also show that we can use the text instruction to control the generation of the inserted stem in terms of rhythm, dynamics, and genre, allowing us to modify the style of a single instrument in a full song while keeping the remaining instruments the same. Lastly, we extend this technique to MIDI formats, successfully generating compatible bass, drum, and guitar parts for incomplete arrangements.

Histopathology can help clinicians make accurate diagnoses, determine disease prognosis, and plan appropriate treatment strategies. As deep learning techniques prove successful in the medical domain, the primary challenges become limited data availability and concerns about data sharing and privacy. Federated learning has addressed this challenge by training models locally and updating parameters on a server. However, issues, such as domain shift and bias, persist and impact overall performance. Dataset distillation presents an alternative approach to overcoming these challenges. It involves creating a small synthetic dataset that encapsulates essential information, which can be shared without constraints. At present, this paradigm is not practicable as current distillation approaches only generate non human readable representations and exhibit insufficient performance for downstream learning tasks. We train a latent diffusion model and construct a new distilled synthetic dataset with a small number of human readable synthetic images. Selection of maximally informative synthetic images is done via graph community analysis of the representation space. We compare downstream classification models trained on our synthetic distillation data to models trained on real data and reach performances suitable for practical application., Comment: accepted at MICCAI 2024

This paper proposes joint speaker feature learning methods for zero-shot adaptation of audio-visual multichannel speech separation and recognition systems. xVector and ECAPA-TDNN speaker encoders are connected using purpose-built fusion blocks and tightly integrated with the complete system training. Experiments conducted on LRS3-TED data simulated multichannel overlapped speech suggest that joint speaker feature learning consistently improves speech separation and recognition performance over the baselines without joint speaker feature estimation. Further analyses reveal performance improvements are strongly correlated with increased inter-speaker discrimination measured using cosine similarity. The best-performing joint speaker feature learning adapted system outperformed the baseline fine-tuned WavLM model by statistically significant WER reductions of 21.6% and 25.3% absolute (67.5% and 83.5% relative) on Dev and Test sets after incorporating WavLM features and video modality., Comment: Accepted by Interspeech 2024

In this work we try to search for signals generated by ultra-heavy dark matter at the Large High Altitude Air Shower Observatory (LHAASO) data. We look for possible gamma-ray by dark matter annihilation or decay from 16 dwarf spheroidal galaxies in the field of view of LHAASO. Dwarf spheroidal galaxies are among the most promising targets for indirect detection of dark matter which have low fluxes of astrophysical $\gamma$-ray background while large amount of dark matter. By analyzing more than 700 days observational data at LHAASO, no significant dark matter signal from 1 TeV to 1 EeV is detected. Accordingly we derive the most stringent constraints on the ultra-heavy dark matter annihilation cross-section up to EeV. The constraints on the lifetime of dark matter in decay mode are also derived., Comment: 17 pages, 12 figures, accepted by PRL

Large language models (LLMs) have achieved remarkable performance on Natural Language Processing (NLP) tasks, but they are hindered by high computational costs and memory requirements. Ternarization, an extreme form of quantization, offers a solution by reducing memory usage and enabling energy-efficient floating-point additions. However, applying ternarization to LLMs faces challenges stemming from outliers in both weights and activations. In this work, observing asymmetric outliers and non-zero means in weights, we introduce Dual Learnable Ternarization (DLT), which enables both scales and shifts to be learnable. We also propose Outlier-Friendly Feature Knowledge Distillation (OFF) to recover the information lost in extremely low-bit quantization. The proposed OFF can incorporate semantic information and is insensitive to outliers. At the core of OFF is maximizing the mutual information between features in ternarized and floating-point models using cosine similarity. Extensive experiments demonstrate that our TernaryLLM surpasses previous low-bit quantization methods on the standard text generation and zero-shot benchmarks for different LLM families. Specifically, for one of the most powerful open-source models, LLaMA-3, our approach (W1.58A16) outperforms the previous state-of-the-art method (W2A16) by 5.8 in terms of perplexity on C4 and by 8.2% in terms of average accuracy on zero-shot tasks.

The integration of deep neural networks with the Variational Monte Carlo (VMC) method has marked a significant advancement in solving the Schr\"odinger equation. In this work, we enforce spin symmetry in the neural network-based VMC calculation with modified optimization target. Our method is designed to solve for the ground state and multiple excited states with target spin symmetry at a low computational cost. It predicts accurate energies while maintaining the correct symmetry in strongly correlated systems, even in cases where different spin states are nearly degenerate. Our approach also excels at spin-gap calculations, including the singlet-triplet gap in biradical systems, which is of high interest in photochemistry. Overall, this work establishes a robust framework for efficiently calculating various quantum states with specific spin symmetry in correlated systems, paving the way for novel discoveries in quantum science.

The widespread use of large language models (LLMs) has sparked concerns about the potential misuse of AI-generated text, as these models can produce content that closely resembles human-generated text. Current detectors for AI-generated text (AIGT) lack robustness against adversarial perturbations, with even minor changes in characters or words causing a reversal in distinguishing between human-created and AI-generated text. This paper investigates the robustness of existing AIGT detection methods and introduces a novel detector, the Siamese Calibrated Reconstruction Network (SCRN). The SCRN employs a reconstruction network to add and remove noise from text, extracting a semantic representation that is robust to local perturbations. We also propose a siamese calibration technique to train the model to make equally confidence predictions under different noise, which improves the model's robustness against adversarial perturbations. Experiments on four publicly available datasets show that the SCRN outperforms all baseline methods, achieving 6.5\%-18.25\% absolute accuracy improvement over the best baseline method under adversarial attacks. Moreover, it exhibits superior generalizability in cross-domain, cross-genre, and mixed-source scenarios. The code is available at \url{https://github.com/CarlanLark/Robust-AIGC-Detector}., Comment: Accepted to ACL 2024 main conference

Large language models (LLMs) are increasingly being adopted in a wide range of real-world applications. Despite their impressive performance, recent studies have shown that LLMs are vulnerable to deliberately crafted adversarial prompts even when aligned via Reinforcement Learning from Human Feedback or supervised fine-tuning. While existing defense methods focus on either detecting harmful prompts or reducing the likelihood of harmful responses through various means, defending LLMs against jailbreak attacks based on the inner mechanisms of LLMs remains largely unexplored. In this work, we investigate how LLMs response to harmful prompts and propose a novel defense method termed \textbf{L}ayer-specific \textbf{Ed}iting (LED) to enhance the resilience of LLMs against jailbreak attacks. Through LED, we reveal that several critical \textit{safety layers} exist among the early layers of LLMs. We then show that realigning these safety layers (and some selected additional layers) with the decoded safe response from selected target layers can significantly improve the alignment of LLMs against jailbreak attacks. Extensive experiments across various LLMs (e.g., Llama2, Mistral) show the effectiveness of LED, which effectively defends against jailbreak attacks while maintaining performance on benign prompts. Our code is available at \url{https://github.com/ledllm/ledllm}.

Federated Learning (FL) offers a promising framework for collaborative and privacy-preserving machine learning across distributed data sources. However, the substantial communication costs associated with FL significantly challenge its efficiency. Specifically, in each communication round, the communication costs scale linearly with the model's dimension, which presents a formidable obstacle, especially in large model scenarios. Despite various communication-efficient strategies, the intrinsic dimension-dependent communication cost remains a major bottleneck for current FL implementations. This paper proposes a novel dimension-free communication algorithm -- DeComFL, which leverages the zeroth-order optimization techniques and reduces the communication cost from $\mathscr{O}(d)$ to $\mathscr{O}(1)$ by transmitting only a constant number of scalar values between clients and the server in each round, regardless of the dimension $d$ of the model parameters. Theoretically, in non-convex functions, we prove that our algorithm achieves state-of-the-art rates, which show a linear speedup of the number of clients and local steps under standard assumptions. With additional low effective rank assumption, we can further show the convergence rate is independent of the model dimension $d$ as well. Empirical evaluations, encompassing both classic deep learning training and large language model fine-tuning, demonstrate significant reductions in communication overhead. Notably, DeComFL achieves this by transmitting only around 1MB of data in total between the server and a client to fine-tune a model with billions of parameters.

The KM2A is the largest sub-array of the Large High Altitude Air Shower Observatory (LHAASO). It consists of 5216 electromagnetic particle detectors (EDs) and 1188 muon detectors (MDs). The data recorded by the EDs and MDs are used to reconstruct primary information of cosmic ray and gamma-ray showers. This information is used for physical analysis in gamma-ray astronomy and cosmic ray physics. To ensure the reliability of the LHAASO-KM2A data, a three-level quality control system has been established. It is used to monitor the status of detector units, stability of reconstructed parameters and the performance of the array based on observations of the Crab Nebula and Moon shadow. This paper will introduce the control system and its application on the LHAASO-KM2A data collected from August 2021 to July 2023. During this period, the pointing and angular resolution of the array were stable. From the observations of the Moon shadow and Crab Nebula, the results achieved using the two methods are consistent with each other. According to the observation of the Crab Nebula at energies from 25 TeV to 100 TeV, the time averaged pointing errors are estimated to be $-0.003^{\circ} \pm 0.005^{\circ}$ and $0.001^{\circ} \pm 0.006^{\circ}$ in the R.A. and Dec directions, respectively., Comment: 15 pages, 9 figures

The first source catalog of Large High Altitude Air Shower Observatory reported the detection of a very-high-energy gamma ray source, 1LHAASO J1219+2915. In this paper a further detailed study of the spectral and temporal behavior of this point-like source have been carried. The best-fit position of the TeV source ($\rm{RA}=185.05^{\circ}\pm0.04^{\circ}$, $\rm{Dec}=29.25^{\circ}\pm0.03^{\circ}$) is compatible with NGC 4278 within $\sim0.03$ degree. Variation analysis shows an indication of the variability at a few months level in the TeV band, which is consistent with low frequency observations. Based on these observations, we report the detection of TeV $\gamma$-ray emissions from this low-luminosity AGN NGC 4278. The observations by LHAASO-WCDA during active period has a significance level of 8.8\,$\sigma$ with best-fit photon spectral index $\varGamma=2.56\pm0.14$ and a flux $f_{1-10\,\rm{TeV}}=(7.0\pm1.1_{\rm{sta}}\pm0.35_{\rm{syst}})\times10^{-13}\,\rm{photons\,cm^{-2}\,s^{-1}}$, or approximately $5\%$ of the Crab Nebula. The discovery of VHE from NGC 4278 indicates that the compact, weak radio jet can efficiently accelerate particles and emit TeV photons., Comment: 11 pages, 5 figures

Animatable clothing transfer, aiming at dressing and animating garments across characters, is a challenging problem. Most human avatar works entangle the representations of the human body and clothing together, which leads to difficulties for virtual try-on across identities. What's worse, the entangled representations usually fail to exactly track the sliding motion of garments. To overcome these limitations, we present Layered Gaussian Avatars (LayGA), a new representation that formulates body and clothing as two separate layers for photorealistic animatable clothing transfer from multi-view videos. Our representation is built upon the Gaussian map-based avatar for its excellent representation power of garment details. However, the Gaussian map produces unstructured 3D Gaussians distributed around the actual surface. The absence of a smooth explicit surface raises challenges in accurate garment tracking and collision handling between body and garments. Therefore, we propose two-stage training involving single-layer reconstruction and multi-layer fitting. In the single-layer reconstruction stage, we propose a series of geometric constraints to reconstruct smooth surfaces and simultaneously obtain the segmentation between body and clothing. Next, in the multi-layer fitting stage, we train two separate models to represent body and clothing and utilize the reconstructed clothing geometries as 3D supervision for more accurate garment tracking. Furthermore, we propose geometry and rendering layers for both high-quality geometric reconstruction and high-fidelity rendering. Overall, the proposed LayGA realizes photorealistic animations and virtual try-on, and outperforms other baseline methods. Our project page is https://jsnln.github.io/layga/index.html., Comment: SIGGRAPH 2024 conference track

JavaScript is prevalent in web and server apps, handling sensitive data. JS testing methods lag behind other languages. Insitu concolic testing for JS is effective but slow and complex. Our method enhances tracing with V8 Sparkplug baseline compiler and remill libraries for assembly to LLVM IR conversion. Evaluation on 160 Node.js libraries reveals comparable coverage and bug detection in significantly less time than the in-situ method.

In this paper, we explore the application of cognitive intelligence in legal knowledge, focusing on the development of judicial artificial intelligence. Utilizing natural language processing (NLP) as the core technology, we propose a method for the automatic construction of case knowledge graphs for judicial cases. Our approach centers on two fundamental NLP tasks: entity recognition and relationship extraction. We compare two pre-trained models for entity recognition to establish their efficacy. Additionally, we introduce a multi-task semantic relationship extraction model that incorporates translational embedding, leading to a nuanced contextualized case knowledge representation. Specifically, in a case study involving a "Motor Vehicle Traffic Accident Liability Dispute," our approach significantly outperforms the baseline model. The entity recognition F1 score improved by 0.36, while the relationship extraction F1 score increased by 2.37. Building on these results, we detail the automatic construction process of case knowledge graphs for judicial cases, enabling the assembly of knowledge graphs for hundreds of thousands of judgments. This framework provides robust semantic support for applications of judicial AI, including the precise categorization and recommendation of related cases.

Multi-modality image fusion (MMIF) aims to integrate complementary information from different modalities into a single fused image to represent the imaging scene and facilitate downstream visual tasks comprehensively. In recent years, significant progress has been made in MMIF tasks due to advances in deep neural networks. However, existing methods cannot effectively and efficiently extract modality-specific and modality-fused features constrained by the inherent local reductive bias (CNN) or quadratic computational complexity (Transformers). To overcome this issue, we propose a Mamba-based Dual-phase Fusion (MambaDFuse) model. Firstly, a dual-level feature extractor is designed to capture long-range features from single-modality images by extracting low and high-level features from CNN and Mamba blocks. Then, a dual-phase feature fusion module is proposed to obtain fusion features that combine complementary information from different modalities. It uses the channel exchange method for shallow fusion and the enhanced Multi-modal Mamba (M3) blocks for deep fusion. Finally, the fused image reconstruction module utilizes the inverse transformation of the feature extraction to generate the fused result. Through extensive experiments, our approach achieves promising fusion results in infrared-visible image fusion and medical image fusion. Additionally, in a unified benchmark, MambaDFuse has also demonstrated improved performance in downstream tasks such as object detection. Code with checkpoints will be available after the peer-review process.

The digital innovation accompanied by explicit economic incentives have fundamentally changed the process of innovation diffusion. As a representative of digital innovation, NFTs provide a decentralized and secure way to authenticate and trade digital assets, offering the potential for new revenue streams in the digital space. However, current researches about NFTs mainly focus on their transaction networks and community culture, leaving the interplay among diffusion dynamics, economic dynamics, and social constraints on Twitter. By collecting and analyzing NFTs-related tweet dataset, the motivations of retweeters, the information mechanisms behind emojis, and the networked-based diffusion dynamics is systematically investigated. Results indicate that Retweeting is fueled by Freemint and trading information, with the higher economic incentives as a major motivation and some potential organizational tendencies. The diffusion of NFT is primarily driven by a 'Ringed-layered' information mechanism involving individual promoters and speculators. Both the frequency and presentation of content contribute positively to the growth of the retweet network. This study contributes to the innovation diffusion theory with economic incentives embedded.

KM2A is one of the main sub-arrays of LHAASO, working on gamma ray astronomy and cosmic ray physics at energies above 10 TeV. Detector simulation is the important foundation for estimating detector performance and data analysis. It is a big challenge to simulate the KM2A detector in the framework of Geant4 due to the need to track numerous photons from a large number of detector units (>6000) with large altitude difference (30 m) and huge coverage (1.3 km^2). In this paper, the design of the KM2A simulation code G4KM2A based on Geant4 is introduced. The process of G4KM2A is optimized mainly in memory consumption to avoid memory overffow. Some simpliffcations are used to signiffcantly speed up the execution of G4KM2A. The running time is reduced by at least 30 times compared to full detector simulation. The particle distributions and the core/angle resolution comparison between simulation and experimental data of the full KM2A array are also presented, which show good agreement.

Manipulating point defects for tailored macroscopic properties remains a formidable challenge in materials science. This study demonstrates a proof-of-principle for a universal law involving element Mn, significantly enhancing vacancy diffusion through an unprecedented anomalous Friedel Oscillations phenomenon, across most metals in the periodic table. The correlation between Mn-induced point-defect dynamic changes and intrinsic macro-properties is robustly validated through the first-principles theory and well-designed experiments. The physical origin stems from Mn's exceptionally large effective intra-elemental 3d electron interactions, surpassing the Coulomb attraction induced by vacancy and disrupting the electron screening effect. Given the ubiquitous nature of vacancies and their recognition as the most crucial defects influencing nearly all physical and mechanical properties of crystalline materials, this outcome may drive advances in a broad domain.

To adequately utilize the available image evidence in multi-view video-based avatar modeling, we propose TexVocab, a novel avatar representation that constructs a texture vocabulary and associates body poses with texture maps for animation. Given multi-view RGB videos, our method initially back-projects all the available images in the training videos to the posed SMPL surface, producing texture maps in the SMPL UV domain. Then we construct pairs of human poses and texture maps to establish a texture vocabulary for encoding dynamic human appearances under various poses. Unlike the commonly used joint-wise manner, we further design a body-part-wise encoding strategy to learn the structural effects of the kinematic chain. Given a driving pose, we query the pose feature hierarchically by decomposing the pose vector into several body parts and interpolating the texture features for synthesizing fine-grained human dynamics. Overall, our method is able to create animatable human avatars with detailed and dynamic appearances from RGB videos, and the experiments show that our method outperforms state-of-the-art approaches. The project page can be found at https://texvocab.github.io/.

We present the measurements of all-particle energy spectrum and mean logarithmic mass of cosmic rays in the energy range of 0.3-30 PeV using data collected from LHAASO-KM2A between September 2021 and December 2022, which is based on a nearly composition-independent energy reconstruction method, achieving unprecedented accuracy. Our analysis reveals the position of the knee at $3.67 \pm 0.05 \pm 0.15$ PeV. Below the knee, the spectral index is found to be -$2.7413 \pm 0.0004 \pm 0.0050$, while above the knee, it is -$3.128 \pm 0.005 \pm 0.027$, with the sharpness of the transition measured with a statistical error of 2%. The mean logarithmic mass of cosmic rays is almost heavier than helium in the whole measured energy range. It decreases from 1.7 at 0.3 PeV to 1.3 at 3 PeV, representing a 24% decline following a power law with an index of -$0.1200 \pm 0.0003 \pm 0.0341$. This is equivalent to an increase in abundance of light components. Above the knee, the mean logarithmic mass exhibits a power law trend towards heavier components, which is reversal to the behavior observed in the all-particle energy spectrum. Additionally, the knee position and the change in power-law index are approximately the same. These findings suggest that the knee observed in the all-particle spectrum corresponds to the knee of the light component, rather than the medium-heavy components., Comment: 8 pages, 3 figures

Recent advancements have underscored the impact of deep learning techniques on multivariate time series forecasting (MTSF). Generally, these techniques are bifurcated into two categories: Channel-independence and Channel-mixing approaches. Although Channel-independence methods typically yield better results, Channel-mixing could theoretically offer improvements by leveraging inter-variable correlations. Nonetheless, we argue that the integration of uncorrelated information in channel-mixing methods could curtail the potential enhancement in MTSF model performance. To substantiate this claim, we introduce the Cross-variable Decorrelation Aware feature Modeling (CDAM) for Channel-mixing approaches, aiming to refine Channel-mixing by minimizing redundant information between channels while enhancing relevant mutual information. Furthermore, we introduce the Temporal correlation Aware Modeling (TAM) to exploit temporal correlations, a step beyond conventional single-step forecasting methods. This strategy maximizes the mutual information between adjacent sub-sequences of both the forecasted and target series. Combining CDAM and TAM, our novel framework significantly surpasses existing models, including those previously considered state-of-the-art, in comprehensive tests.

Human activity recognition (HAR) holds significant importance in smart homes, security, and healthcare. Existing systems face limitations because of the insufficient spatial diversity provided by a limited number of antennas. Furthermore, inefficiencies in noise reduction and feature extraction from sensing data pose challenges to recognition performance. This study presents a reconfigurable intelligent surface (RIS)-assisted passive human activity recognition (RISAR) method, compatible with commercial Wi-Fi devices. RISAR leverages a RIS to enhance the spatial diversity of Wi-Fi signals, effectively capturing a wider range of information distributed across the spatial domain. A novel high-dimensional factor model based on random matrix theory is proposed to address noise reduction and feature extraction in the temporal domain. A dual-stream spatial-temporal attention network model is developed to assign variable weights to different characteristics and sequences, mimicking human cognitive processes in prioritizing essential information. Experimental analysis shows that RISAR significantly outperforms existing HAR methods in accuracy and efficiency, achieving an average accuracy of 97.26%. These findings underscore RISAR's adaptability and potential as a robust activity recognition solution in real environments.

We present the design, implementation and engineering experience in building and deploying MegaScale, a production system for training large language models (LLMs) at the scale of more than 10,000 GPUs. Training LLMs at this scale brings unprecedented challenges to training efficiency and stability. We take a full-stack approach that co-designs the algorithmic and system components across model block and optimizer design, computation and communication overlapping, operator optimization, data pipeline, and network performance tuning. Maintaining high efficiency throughout the training process (i.e., stability) is an important consideration in production given the long extent of LLM training jobs. Many hard stability issues only emerge at large scale, and in-depth observability is the key to address them. We develop a set of diagnosis tools to monitor system components and events deep in the stack, identify root causes, and derive effective techniques to achieve fault tolerance and mitigate stragglers. MegaScale achieves 55.2% Model FLOPs Utilization (MFU) when training a 175B LLM model on 12,288 GPUs, improving the MFU by 1.34x compared to Megatron-LM. We share our operational experience in identifying and fixing failures and stragglers. We hope by articulating the problems and sharing our experience from a systems perspective, this work can inspire future LLM systems research.

This research paper addresses the challenge of modality mismatch in multimodal learning, where the modalities available during inference differ from those available at training. We propose the Text-centric Alignment for Multi-Modality Learning (TAMML) approach, an innovative method that utilizes Large Language Models (LLMs) with in-context learning and foundation models to enhance the generalizability of multimodal systems under these conditions. By leveraging the unique properties of text as a unified semantic space, TAMML demonstrates significant improvements in handling unseen, diverse, and unpredictable modality combinations. TAMML not only adapts to varying modalities but also maintains robust performance, showcasing the potential of foundation models in overcoming the limitations of traditional fixed-modality frameworks in embedding representations. This study contributes to the field by offering a flexible, effective solution for real-world applications where modality availability is dynamic and uncertain.

This paper considers a class of noncooperative games in which the feasible decision sets of all players are coupled together by a coupled inequality constraint. Adopting the variational inequality formulation of the game, we first introduce a new local edge-based equilibrium condition and develop a distributed primal-dual proximal algorithm with full information. Considering challenges when communication delays occur, we devise an asynchronous distributed algorithm to seek a generalized Nash equilibrium. This asynchronous scheme arbitrarily activates one player to start new computations independently at different iteration instants, which means that the picked player can use the involved out-dated information from itself and its neighbors to perform new updates. A distinctive attribute is that the proposed algorithms enable the derivation of new distributed forward-backward-like extensions. In theoretical aspect, we provide explicit conditions on algorithm parameters, for instance, the step-sizes to establish a sublinear convergence rate for the proposed synchronous algorithm. Moreover, the asynchronous algorithm guarantees almost sure convergence in expectation under the same step-size conditions and some standard assumptions. An interesting observation is that our analysis approach improves the convergence rate of prior synchronous distributed forward-backward-based algorithms. Finally, the viability and performance of the proposed algorithms are demonstrated by numerical studies on the networked Cournot competition., Comment: 13 pages, 2 figures

Masked autoencoding and generative pretraining have achieved remarkable success in computer vision and natural language processing, and more recently, they have been extended to the point cloud domain. Nevertheless, existing point cloud models suffer from the issue of information leakage due to the pre-sampling of center points, which leads to trivial proxy tasks for the models. These approaches primarily focus on local feature reconstruction, limiting their ability to capture global patterns within point clouds. In this paper, we argue that the reduced difficulty of pretext tasks hampers the model's capacity to learn expressive representations. To address these limitations, we introduce a novel solution called the Differentiable Center Sampling Network (DCS-Net). It tackles the information leakage problem by incorporating both global feature reconstruction and local feature reconstruction as non-trivial proxy tasks, enabling simultaneous learning of both the global and local patterns within point cloud. Experimental results demonstrate that our method enhances the expressive capacity of existing point cloud models and effectively addresses the issue of information leakage.

The scarcity of annotated data has sparked significant interest in unsupervised pre-training methods that leverage medical reports as auxiliary signals for medical visual representation learning. However, existing research overlooks the multi-granularity nature of medical visual representation and lacks suitable contrastive learning techniques to improve the models' generalizability across different granularities, leading to the underutilization of image-text information. To address this, we propose MLIP, a novel framework leveraging domain-specific medical knowledge as guiding signals to integrate language information into the visual domain through image-text contrastive learning. Our model includes global contrastive learning with our designed divergence encoder, local token-knowledge-patch alignment contrastive learning, and knowledge-guided category-level contrastive learning with expert knowledge. Experimental evaluations reveal the efficacy of our model in enhancing transfer performance for tasks such as image classification, object detection, and semantic segmentation. Notably, MLIP surpasses state-of-the-art methods even with limited annotated data, highlighting the potential of multimodal pre-training in advancing medical representation learning.