Search

Class imbalance is a critical issue in image classification that significantly affects the performance of deep recognition models. In this work, we first identify a network degeneration dilemma that hinders the model learning by introducing a high linear dependence among the features inputted into the classifier. To overcome this challenge, we propose a novel framework called Whitening-Net to mitigate the degenerate solutions, in which ZCA whitening is integrated before the linear classifier to normalize and decorrelate the batch samples. However, in scenarios with extreme class imbalance, the batch covariance statistic exhibits significant fluctuations, impeding the convergence of the whitening operation. Therefore, we propose two covariance-corrected modules, the Group-based Relatively Balanced Batch Sampler (GRBS) and the Batch Embedded Training (BET), to get more accurate and stable batch covariance, thereby reinforcing the capability of whitening. Our modules can be trained end-to-end without incurring substantial computational costs. Comprehensive empirical evaluations conducted on benchmark datasets, including CIFAR-LT-10/100, ImageNet-LT, and iNaturalist-LT, validate the effectiveness of our proposed approaches., Comment: 20 pages, 10 figures, 10 tables. arXiv admin note: text overlap with arXiv:2112.05958

The cosmic variance on the star formation history may lead to bias to the merger rate density estimation of binary neutron star (BNS) mergers by the compact binary population synthesis. In this paper, we take the advantage of the large boxsize of the Millennium Simulation combined with the semi-analytic galaxy formation model GABE, and the parameterized population binary star evolution (BSE) model to examine how much effect will the cosmic variance introduce on the estimation of merger rate density of BNS mergers. We find that for sub-box size of $100\rm Mpc$ and $200\rm Mpc$, the variance of merger rate density $\sigma_{\rm R}/\rm R$ at different redshift is about $23\%-35\%$ and $13\%-20\%$ respectively. On one hand, as for the variance of the detection rate on BNS mergers with current LIGO-Virgo-KAGRA (LVK) detector network, this value is very small $\lesssim 10\%$, which indicates ignoring the cosmic variance is reasonable for estimating the merger rate density from current LVK observation. On the other hand, with next-generation gravitational wave detectors, it is possible to localize BNS mergers within sub-boxes possessing length of $\rm 40 Mpc$ for source redshift $z_{s}<0.2$. In such a small box, the cosmic variance of the merger rate density is significant, i.e., the value of $\sigma_{\rm R}/\rm R$ is about $\sim 55\%$. This hints that estimating the merger rate density of BNS in different sky areas may provide useful information on the cosmic variance., Comment: 7 pages, 5 figures, Accepted for Publication in ApJ

Recent advancements in large language model alignment leverage token-level supervisions to perform fine-grained preference optimization. However, existing token-level alignment methods either optimize on all available tokens, which can be noisy and inefficient, or perform selective training with complex and expensive key token selection strategies. In this work, we propose Selective Preference Optimization (SePO), a novel selective alignment strategy that centers on efficient key token selection. SePO proposes the first token selection method based on Direct Preference Optimization (DPO), which trains an oracle model to estimate a token-level reward function on the target data. This method applies to any existing alignment datasets with response-level annotations and enables cost-efficient token selection with small-scale oracle models and training data. The estimated reward function is then utilized to score all tokens within the target dataset, where only the key tokens are selected to supervise the target policy model with a reference model-free contrastive objective function. Extensive experiments on three public evaluation benchmarks show that SePO significantly outperforms competitive baseline methods by only optimizing 30% key tokens on the target dataset. SePO applications on weak-to-strong generalization show that weak oracle models effectively supervise strong policy models with up to 16.8x more parameters. SePO also effectively selects key tokens from out-of-distribution data to enhance strong policy models and alleviate the over-optimization problem., Comment: Work in progress

Large language models (LLMs) have advanced financial applications, yet they often lack sufficient financial knowledge and struggle with tasks involving multi-modal inputs like tables and time series data. To address these limitations, we introduce \textit{Open-FinLLMs}, a series of Financial LLMs. We begin with FinLLaMA, pre-trained on a 52 billion token financial corpus, incorporating text, tables, and time-series data to embed comprehensive financial knowledge. FinLLaMA is then instruction fine-tuned with 573K financial instructions, resulting in FinLLaMA-instruct, which enhances task performance. Finally, we present FinLLaVA, a multimodal LLM trained with 1.43M image-text instructions to handle complex financial data types. Extensive evaluations demonstrate FinLLaMA's superior performance over LLaMA3-8B, LLaMA3.1-8B, and BloombergGPT in both zero-shot and few-shot settings across 19 and 4 datasets, respectively. FinLLaMA-instruct outperforms GPT-4 and other Financial LLMs on 15 datasets. FinLLaVA excels in understanding tables and charts across 4 multimodal tasks. Additionally, FinLLaMA achieves impressive Sharpe Ratios in trading simulations, highlighting its robust financial application capabilities. We will continually maintain and improve our models and benchmarks to support ongoing innovation in academia and industry., Comment: 33 pages, 13 figures

In 1967, Katona and Szemer\'{e}di showed that no undirected graph with $n$ vertices and fewer than $\frac{n}{2}\log_2\frac{n}{2}$ edges admits an orientation of diameter two. In 1978, Chv\'atal and Thomassen revealed the complexity of determining whether an undirected graph can be oriented to achieve a diameter of two, proving it to be NP-complete. This breakthrough has sparked ongoing interest in identifying sufficient conditions for graphs to be oriented with the smallest possible diameter of two -- critical for optimizing communication and network flow in larger structures. In 2019, Czabarka, Dankelmann, and Sz\'ekely significantly advanced this field by establishing that the minimum degree threshold for achieving such an orientation in undirected graphs of order $n$ is $\frac{n}{2} + \Theta(\ln n)$. In this paper, we extend this foundational result by determining the minimum degree threshold necessary for realizing an orientation with diameter two in mixed graphs, which contain both undirected and directed edges. Mixed graphs offer a versatile framework, representing an intermediate stage in the orientation process, making our findings a substantial generalization of previous results.

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

In ferromagnetic materials, magnons - quanta of spin waves - typically resonate in the gigahertz range. Beyond conventional magnons, while theoretical studies have predicted magnons associated with orbital magnetic moments, their direct observation has remained challenging. Here, we present the discovery of two distinct terahertz orbitally-coupled magnon resonances in the topological kagome ferromagnet Co3Sn2S2. Using time-resolved Kerr rotation spectroscopy, we pinpoint two magnon resonances at 0.61 and 0.49 THz at 6 K, surpassing all previously reported magnon resonances in ferromagnets due to strong magnetocrystalline anisotropy. These dual modes originate from the strong coupling of localized spin and orbital magnetic moments. These findings unveil a novel category of magnons stemming from orbital magnetic moments, and position Co3Sn2S2 as a promising candidate for high-speed terahertz spintronic applications

Device-to-device (D2D) spectrum sharing in wireless communications is a challenging non-convex combinatorial optimization problem, involving entangled link scheduling and power control in a large-scale network. The state-of-the-art methods, either from a model-based or a data-driven perspective, exhibit certain limitations such as the critical need for channel state information (CSI) and/or a large number of (solved) instances (e.g., network layouts) as training samples. To advance this line of research, we propose a novel hybrid model/datadriven spectrum sharing mechanism with graph reinforcement learning for link scheduling (GRLinQ), injecting information theoretical insights into machine learning models, in such a way that link scheduling and power control can be solved in an intelligent yet explainable manner. Through an extensive set of experiments, GRLinQ demonstrates superior performance to the existing model-based and data-driven link scheduling and/or power control methods, with a relaxed requirement for CSI, a substantially reduced number of unsolved instances as training samples, a possible distributed deployment, reduced online/offline computational complexity, and more remarkably excellent scalability and generalizability over different network scenarios and system configurations.

Federated Collaborative Filtering (FedCF) is an emerging field focused on developing a new recommendation framework with preserving privacy in a federated setting. Existing FedCF methods typically combine distributed Collaborative Filtering (CF) algorithms with privacy-preserving mechanisms, and then preserve personalized information into a user embedding vector. However, the user embedding is usually insufficient to preserve the rich information of the fine-grained personalization across heterogeneous clients. This paper proposes a novel personalized FedCF method by preserving users' personalized information into a latent variable and a neural model simultaneously. Specifically, we decompose the modeling of user knowledge into two encoders, each designed to capture shared knowledge and personalized knowledge separately. A personalized gating network is then applied to balance personalization and generalization between the global and local encoders. Moreover, to effectively train the proposed framework, we model the CF problem as a specialized Variational AutoEncoder (VAE) task by integrating user interaction vector reconstruction with missing value prediction. The decoder is trained to reconstruct the implicit feedback from items the user has interacted with, while also predicting items the user might be interested in but has not yet interacted with. Experimental results on benchmark datasets demonstrate that the proposed method outperforms other baseline methods, showcasing superior performance., Comment: 10 pages, 3 figures, 4 tables, conference

Multi-modal brain tumor segmentation typically involves four magnetic resonance imaging (MRI) modalities, while incomplete modalities significantly degrade performance. Existing solutions employ explicit or implicit modality adaptation, aligning features across modalities or learning a fused feature robust to modality incompleteness. They share a common goal of encouraging each modality to express both itself and the others. However, the two expression abilities are entangled as a whole in a seamless feature space, resulting in prohibitive learning burdens. In this paper, we propose DeMoSeg to enhance the modality adaptation by Decoupling the task of representing the ego and other Modalities for robust incomplete multi-modal Segmentation. The decoupling is super lightweight by simply using two convolutions to map each modality onto four feature sub-spaces. The first sub-space expresses itself (Self-feature), while the remaining sub-spaces substitute for other modalities (Mutual-features). The Self- and Mutual-features interactively guide each other through a carefully-designed Channel-wised Sparse Self-Attention (CSSA). After that, a Radiologist-mimic Cross-modality expression Relationships (RCR) is introduced to have available modalities provide Self-feature and also `lend' their Mutual-features to compensate for the absent ones by exploiting the clinical prior knowledge. The benchmark results on BraTS2020, BraTS2018 and BraTS2015 verify the DeMoSeg's superiority thanks to the alleviated modality adaptation difficulty. Concretely, for BraTS2020, DeMoSeg increases Dice by at least 0.92%, 2.95% and 4.95% on whole tumor, tumor core and enhanced tumor regions, respectively, compared to other state-of-the-arts. Codes are at https://github.com/kk42yy/DeMoSeg, Comment: 8 pages, 4 figures

Conventional frame camera is the mainstream sensor of the autonomous driving scene perception, while it is limited in adverse conditions, such as low light. Event camera with high dynamic range has been applied in assisting frame camera for the multimodal fusion, which relies heavily on the pixel-level spatial alignment between various modalities. Typically, existing multimodal datasets mainly place event and frame cameras in parallel and directly align them spatially via warping operation. However, this parallel strategy is less effective for multimodal fusion, since the large disparity exacerbates spatial misalignment due to the large event-frame baseline. We argue that baseline minimization can reduce alignment error between event and frame cameras. In this work, we introduce hybrid coaxial event-frame devices to build the multimodal system, and propose a coaxial stereo event camera (CoSEC) dataset for autonomous driving. As for the multimodal system, we first utilize the microcontroller to achieve time synchronization, and then spatially calibrate different sensors, where we perform intra- and inter-calibration of stereo coaxial devices. As for the multimodal dataset, we filter LiDAR point clouds to generate depth and optical flow labels using reference depth, which is further improved by fusing aligned event and frame data in nighttime conditions. With the help of the coaxial device, the proposed dataset can promote the all-day pixel-level multimodal fusion. Moreover, we also conduct experiments to demonstrate that the proposed dataset can improve the performance and generalization of the multimodal fusion., Comment: This work has been submitted to the IEEE for possible publication

Large language model (LLM) agents have shown great potential in solving real-world software engineering (SWE) problems. The most advanced open-source SWE agent can resolve over 27% of real GitHub issues in SWE-Bench Lite. However, these sophisticated agent frameworks exhibit varying strengths, excelling in certain tasks while underperforming in others. To fully harness the diversity of these agents, we propose DEI (Diversity Empowered Intelligence), a framework that leverages their unique expertise. DEI functions as a meta-module atop existing SWE agent frameworks, managing agent collectives for enhanced problem-solving. Experimental results show that a DEI-guided committee of agents is able to surpass the best individual agent's performance by a large margin. For instance, a group of open-source SWE agents, with a maximum individual resolve rate of 27.3% on SWE-Bench Lite, can achieve a 34.3% resolve rate with DEI, making a 25% improvement and beating most closed-source solutions. Our best-performing group excels with a 55% resolve rate, securing the highest ranking on SWE-Bench Lite. Our findings contribute to the growing body of research on collaborative AI systems and their potential to solve complex software engineering challenges.

Current weakly supervised video anomaly detection (WSVAD) task aims to achieve frame-level anomalous event detection with only coarse video-level annotations available. Existing works typically involve extracting global features from full-resolution video frames and training frame-level classifiers to detect anomalies in the temporal dimension. However, most anomalous events tend to occur in localized spatial regions rather than the entire video frames, which implies existing frame-level feature based works may be misled by the dominant background information and lack the interpretation of the detected anomalies. To address this dilemma, this paper introduces a novel method called STPrompt that learns spatio-temporal prompt embeddings for weakly supervised video anomaly detection and localization (WSVADL) based on pre-trained vision-language models (VLMs). Our proposed method employs a two-stream network structure, with one stream focusing on the temporal dimension and the other primarily on the spatial dimension. By leveraging the learned knowledge from pre-trained VLMs and incorporating natural motion priors from raw videos, our model learns prompt embeddings that are aligned with spatio-temporal regions of videos (e.g., patches of individual frames) for identify specific local regions of anomalies, enabling accurate video anomaly detection while mitigating the influence of background information. Without relying on detailed spatio-temporal annotations or auxiliary object detection/tracking, our method achieves state-of-the-art performance on three public benchmarks for the WSVADL task., Comment: Accepted by ACMMM2024

Federated Knowledge Graph Embedding (FKGE) aims to facilitate collaborative learning of entity and relation embeddings from distributed Knowledge Graphs (KGs) across multiple clients, while preserving data privacy. Training FKGE models with higher dimensions is typically favored due to their potential for achieving superior performance. However, high-dimensional embeddings present significant challenges in terms of storage resource and inference speed. Unlike traditional KG embedding methods, FKGE involves multiple client-server communication rounds, where communication efficiency is critical. Existing embedding compression methods for traditional KGs may not be directly applicable to FKGE as they often require multiple model trainings which potentially incur substantial communication costs. In this paper, we propose a light-weight component based on Knowledge Distillation (KD) which is titled FedKD and tailored specifically for FKGE methods. During client-side local training, FedKD facilitates the low-dimensional student model to mimic the score distribution of triples from the high-dimensional teacher model using KL divergence loss. Unlike traditional KD way, FedKD adaptively learns a temperature to scale the score of positive triples and separately adjusts the scores of corresponding negative triples using a predefined temperature, thereby mitigating teacher over-confidence issue. Furthermore, we dynamically adjust the weight of KD loss to optimize the training process. Extensive experiments on three datasets support the effectiveness of FedKD.

In this study, we present an innovative fusion of language models and query analysis techniques to unlock cognition in artificial intelligence. Our system seamlessly integrates a Chess engine with a language model, enabling it to predict moves and provide strategic explanations. Leveraging a vector database to achieve retrievable answer generation, our OpenSI AI system elucidates its decision-making process, bridging the gap between raw computation and human-like understanding. Our choice of Chess as the demonstration environment underscores the versatility of our approach. Beyond Chess, our system holds promise for diverse applications, from medical diagnostics to financial forecasting.

The popularity of tag clouds has sparked significant interest in the geographic research community, leading to the development of map-based adaptations known as intrinsic tag maps. However, existing methodologies for tag maps primarily focus on tag layout at specific scales, which may result in large empty areas or close proximity between tags when navigating across multiple scales. This issue arises because initial tag layouts may not ensure an even distribution of tags with varying sizes across the region. To address this problem, we incorporate the negative spatial auto-correlation index into tag maps to assess the uniformity of tag size distribution. Subsequently, we integrate this index into a TIN-based intrinsic tag map layout approach to enhance its ability to support multi-scale visualization. This enhancement involves iteratively filtering out candidate tags and selecting optimal tags that meet the defined index criteria. Experimental findings from two representative areas (the USA and Italy) demonstrate the efficacy of our approach in enhancing multi-scale visualization capabilities, albeit with trade-offs in compactness and time efficiency. Specifically, when retaining the same number of tags in the layout, our approach achieves higher compactness but requires more time. Conversely, when reducing the number of tags in the layout, our approach exhibits reduced time requirements but lower compactness. Furthermore, we discuss the effectiveness of various applied strategies aligned with existing approaches to generate diverse intrinsic tag maps tailored to user preferences. Additional details and resources can be found on our project website: https://github.com/TrentonWei/Multi-scale-TagMap.git., Comment: 39 pages,10 figures, an accepted version of Journal Cartography and Geographic Information Science

Multi-Label Text Classification (MLTC) is a practical yet challenging task that involves assigning multiple non-exclusive labels to each document. Previous studies primarily focus on capturing label correlations to assist label prediction by introducing special labeling schemes, designing specific model structures, or adding auxiliary tasks. Recently, the $k$ Nearest Neighbor ($k$NN) framework has shown promise by retrieving labeled samples as references to mine label co-occurrence information in the embedding space. However, two critical biases, namely embedding alignment bias and confidence estimation bias, are often overlooked, adversely affecting prediction performance. In this paper, we introduce a DEbiased Nearest Neighbors (DENN) framework for MLTC, specifically designed to mitigate these biases. To address embedding alignment bias, we propose a debiased contrastive learning strategy, enhancing neighbor consistency on label co-occurrence. For confidence estimation bias, we present a debiased confidence estimation strategy, improving the adaptive combination of predictions from $k$NN and inductive binary classifications. Extensive experiments conducted on four public benchmark datasets (i.e., AAPD, RCV1-V2, Amazon-531, and EUR-LEX57K) showcase the effectiveness of our proposed method. Besides, our method does not introduce any extra parameters.

Magnetic soft continuum robots (MSCRs) have emerged as powerful devices in endovascular interventions owing to their hyperelastic fibre matrix and enhanced magnetic manipulability. Effective closed-loop control of tethered magnetic devices contributes to the achievement of autonomous vascular robotic surgery. In this article, we employ a magnetic actuation system equipped with a single rotatable permanent magnet to achieve closed-loop deflection control of the MSCR. To this end, we establish a differential kinematic model of MSCRs exposed to non-uniform magnetic fields. The relationship between the existence and uniqueness of Jacobian and the geometric position between robots is deduced. The accurate control direction induced by Jacobian is demonstrated to be crucial in simulations. Then, the corresponding quasi-static control (QSC) framework integrates a linear extended state observer to estimate model uncertainties. Finally, the effectiveness of the proposed QSC framework is validated through comparative trajectory tracking experiments with the PD controller under external disturbances. The proposed control framework effectively prevents the actuator from reaching the joint limit and achieves fast and low error-tracking performance without overshooting.

Superconductivity and magnetism are antagonistic quantum matter, while their intertwining has long been considered in frustrated-lattice systems1-3. In this work, we utilize scanning tunneling microscopy and muon spin resonance to discover time-reversal symmetry-breaking superconductivity in kagome metal Cs(V,Ta)3Sb5, where the Cooper pairing exhibits magnetism and is modulated by it. In the magnetic channel, we observe spontaneous internal magnetism in a full-gap superconducting state. Under perturbations of inverse magnetic fields, we detect a time-reversal asymmetrical interference of Bogoliubov quasi-particles at a circular vector. At this vector, the pairing gap spontaneously modulates, which is distinct from pair density waves occurring at a point vector and consistent with the theoretical proposal of unusual interference effect under time-reversal symmetry-breaking. The correlation between internal magnetism, Bogoliubov quasi-particles, and pairing modulation provides a chain of experimental clues for time-reversal symmetry-breaking kagome superconductivity., Comment: To appear in Nature Materials (2024)

Superconductivity involving finite momentum pairing can lead to spatial gap and pair density modulations, as well as Bogoliubov Fermi states within the superconducting gap. However, the experimental realization of their intertwined relations has been challenging. Here, we detect chiral kagome superconductivity modulations with residual Fermi arcs in KV3Sb5 and CsV3Sb5 by normal and Josephson scanning tunneling microscopy down to 30mK with resolved electronic energy difference at microelectronvolt level. We observe a U-shaped superconducting gap with flat residual in-gap states. This gap exhibits chiral 2 by 2 spatial modulations with magnetic field tunable chirality, which align with the chiral 2 by 2 pair density modulations observed through Josephson tunneling. These findings demonstrate a chiral pair density wave (PDW) that breaks time-reversal symmetry. Quasiparticle interference imaging of the in-gap zero-energy states reveals segmented arcs, with high-temperature data linking them to parts of the reconstructed V d-orbital states within the charge order. The detected residual Fermi arcs can be explained by the partial suppression of these d-orbital states through an interorbital 2 by 2 PDW and thus serve as candidate Bogoliubov Fermi states. Additionally, we differentiate the observed PDW order from impurity-induced gap modulations. Our observations not only uncover a chiral PDW order with orbital-selectivity, but also illuminate the fundamental space-momentum correspondence inherent in finite momentum paired superconductivity., Comment: To appear in Nature (2024)

Task inharmony problem commonly occurs in modern object detectors, leading to inconsistent qualities between classification and regression tasks. The predicted boxes with high classification scores but poor localization positions or low classification scores but accurate localization positions will worsen the performance of detectors after Non-Maximum Suppression. Furthermore, when object detectors collaborate with Quantization-Aware Training (QAT), we observe that the task inharmony problem will be further exacerbated, which is considered one of the main causes of the performance degradation of quantized detectors. To tackle this issue, we propose the Harmonious Quantization for Object Detection (HQOD) framework, which consists of two components. Firstly, we propose a task-correlated loss to encourage detectors to focus on improving samples with lower task harmony quality during QAT. Secondly, a harmonious Intersection over Union (IoU) loss is incorporated to balance the optimization of the regression branch across different IoU levels. The proposed HQOD can be easily integrated into different QAT algorithms and detectors. Remarkably, on the MS COCO dataset, our 4-bit ATSS with ResNet-50 backbone achieves a state-of-the-art mAP of 39.6%, even surpassing the full-precision one., Comment: 2024 IEEE International Conference on Multimedia and Expo (ICME), July 15 - July 19, 2024, Niagra Falls, Ontario, Canada

Current LiDAR point cloud-based 3D single object tracking (SOT) methods typically rely on point-based representation network. Despite demonstrated success, such networks suffer from some fundamental problems: 1) It contains pooling operation to cope with inherently disordered point clouds, hindering the capture of 3D spatial information that is useful for tracking, a regression task. 2) The adopted set abstraction operation hardly handles density-inconsistent point clouds, also preventing 3D spatial information from being modeled. To solve these problems, we introduce a novel tracking framework, termed VoxelTrack. By voxelizing inherently disordered point clouds into 3D voxels and extracting their features via sparse convolution blocks, VoxelTrack effectively models precise and robust 3D spatial information, thereby guiding accurate position prediction for tracked objects. Moreover, VoxelTrack incorporates a dual-stream encoder with cross-iterative feature fusion module to further explore fine-grained 3D spatial information for tracking. Benefiting from accurate 3D spatial information being modeled, our VoxelTrack simplifies tracking pipeline with a single regression loss. Extensive experiments are conducted on three widely-adopted datasets including KITTI, NuScenes and Waymo Open Dataset. The experimental results confirm that VoxelTrack achieves state-of-the-art performance (88.3%, 71.4% and 63.6% mean precision on the three datasets, respectively), and outperforms the existing trackers with a real-time speed of 36 Fps on a single TITAN RTX GPU. The source code and model will be released.

The unique diagnosis and treatment techniques and remarkable clinical efficacy of traditional Chinese medicine (TCM) make it play an important role in the field of elderly care and healthcare, especially in the rehabilitation of some common chronic diseases of the elderly. Therefore, building a TCM chatbot for healthcare application will help users obtain consultation services in a direct and natural way. However, concepts such as acupuncture points (acupoints) and meridians involved in TCM always appear in the consultation, which cannot be displayed intuitively. To this end, we develop a \textbf{h}ealthcare chat\textbf{bot} (HBot) based on a human body model in 3D and knowledge graph, which provides conversational services such as knowledge Q\&A, prescription recommendation, moxibustion therapy recommendation, and acupoint search. When specific acupoints are involved in the conversations between user and HBot, the 3D body will jump to the corresponding acupoints and highlight them. Moreover, Hbot can also be used in training scenarios to accelerate the teaching process of TCM by intuitively displaying acupuncture points and knowledge cards. The demonstration video is available at https://www.youtube.com/watch?v=UhQhutSKkTU . Our code and dataset are publicly available at Gitee: https://gitee.com/plabrolin/interactive-3d-acup.git, Comment: System Demonstration

We present the identification of changing-look active galactic nuclei (CL-AGNs) from the Dark Energy Spectroscopic Instrument First Data Release and Sloan Digital Sky Survey Data Release 16 at z \leq 0.9. To confirm the CL-AGNs, we utilize spectral flux calibration assessment via an [O\,{\sc iii}]-based calibration, pseudo-photometry examination, and visual inspection. This rigorous selection process allows us to compile a statistical catalog of 561 CL-AGNs, encompassing 527 $\rm H\beta$, 149$\rm H\alpha$, and 129 Mg II CL behaviors. In this sample, we find 1) a 283:278 ratio of turn-on to turn-off CL-AGNs. 2) the critical value for CL events is confirmed around Eddington ratio \sim 0.01. 3) a strong correlation between the change in the luminosity of the broad emission lines (BEL) and variation in the continuum luminosity, with Mg II and $\rm H\beta$ displaying similar responses during CL phases. 4) the Baldwin-Phillips-Terlevich diagram for CL-AGNs shows no statistically difference from the general AGN catalog. 5) five CL-AGNs are associated with asymmetrical mid-infrared flares, possibly linked to tidal disruption events. Given the large CL-AGNs and the stochastic sampling of spectra, we propose that some CL events are inherently due to typical AGN variability during low accretion rates, particularly for CL events of the singular BEL. Finally, we introduce a Peculiar CL phase, characterized by a gradual decline over decades in the light curve and the complete disappearance of entire BEL in faint spectra, indicative of a real transition in the accretion disk., Comment: Submitted to ApJS, comments welcome

In the vast landscape of internet information, recommender systems (RecSys) have become essential for guiding users through a sea of choices aligned with their preferences. These systems have applications in diverse domains, such as news feeds, game suggestions, and shopping recommendations. Personalization is a key technique in RecSys, where modern methods leverage representation learning to encode user/item interactions into embeddings, forming the foundation for personalized recommendations. However, integrating information from multiple sources to enhance recommendation performance remains challenging. This paper introduces a novel approach named PMTRec, the first personalized multi-task learning algorithm to obtain comprehensive user/item embeddings from various information sources. Addressing challenges specific to personalized RecSys, we develop modules to handle personalized task weights, diverse task orientations, and variations in gradient magnitudes across tasks. PMTRec dynamically adjusts task weights based on gradient norms for each user/item, employs a Task Focusing module to align gradient combinations with the main recommendation task, and uses a Gradient Magnitude Balancing module to ensure balanced training across tasks. Through extensive experiments on three real-world datasets with different scales, we demonstrate that PMTRec significantly outperforms existing multi-task learning methods, showcasing its effectiveness in achieving enhanced recommendation accuracy by leveraging multiple tasks simultaneously. Our contributions open new avenues for advancing personalized multi-task training in recommender systems., Comment: 11 pages

Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development.

Monolayer WSe$_2$ (ML WSe$_2$) exhibits high second harmonic generation (SHG) efficiency under single 1-photon (1-p) or 2-photon (2-p) resonance conditions due to enhanced second-order susceptibility compared with the off-resonance state \cite{lin2021narrow,wang2015giant}. Here, we propose a novel strain engineering approach to dramatically boost the in-plane second-order susceptibility ($\chi_{yyy}$) by tuning the biaxial strain to shift two K-valley excitons (the A-exciton and a high-lying exciton (HX)) into double resonance. We first identify the A-exciton and HX from the 2D Mott-Wannier model and compare the enhanced $\chi_{yyy}$ at single 1-p and 2-p resonance states. The strongest enhancement arises from the 2-p resonance state of HX. By applying a small uniform biaxial strain (0.16%), we observe an excitonic double resonance state ($E_{\rm{HX}}$ = 2$E_{\rm{A}}$, $E_{\rm{HX}}$ and $E_{\rm{A}}$ are the exciton absorption energies). Strain-tuning can yield up to a $50$X enhancement in $\chi_{yyy}$ compared to the single 2-p resonance state of HX, resulting in a further three orders of magnitude enhancement in SHG efficiency. Further exploration of strain states near 0.16\% reveals double resonance also occurs at other wavevectors near the K valley, leading to a further increase in $\chi_{yyy}$, confirming that strain engineering is an effective methodology for enhancing $\chi_{yyy}$. Our findings suggest new avenues for strain engineering the optical properties of 2D materials for novel nonlinear optoelectronics applications.

Pixel-level fine-grained image editing remains an open challenge. Previous works fail to achieve an ideal trade-off between control granularity and inference speed. They either fail to achieve pixel-level fine-grained control, or their inference speed requires optimization. To address this, this paper for the first time employs a regression-based network to learn the variation patterns of StyleGAN latent codes during the image dragging process. This method enables pixel-level precision in dragging editing with little time cost. Users can specify handle points and their corresponding target points on any GAN-generated images, and our method will move each handle point to its corresponding target point. Through experimental analysis, we discover that a short movement distance from handle points to target points yields a high-fidelity edited image, as the model only needs to predict the movement of a small portion of pixels. To achieve this, we decompose the entire movement process into multiple sub-processes. Specifically, we develop a transformer encoder-decoder based network named 'Latent Predictor' to predict the latent code motion trajectories from handle points to target points in an autoregressive manner. Moreover, to enhance the prediction stability, we introduce a component named 'Latent Regularizer', aimed at constraining the latent code motion within the distribution of natural images. Extensive experiments demonstrate that our method achieves state-of-the-art (SOTA) inference speed and image editing performance at the pixel-level granularity., Comment: This paper has been accepted as a poster paper for ACM Multimedia 2024

Two-dimensional (2D) materials with remarkable second-harmonic generation (SHG) hold promise for future on-chip nonlinear optics. Relevant materials with both giant SHG response and environmental stability are long-sought targets. Here, we demonstrate the enormous SHG from the phase engineering of a high-performance semiconductor, Bi$_2$O$_2$Se (BOS), under uniaxial strain. SHG signals captured in strained 20 nm-BOS films exceed those of NbOI$_2$ and NbOCl$_2$ of similar thickness by a factor of 10, and are four orders of magnitude higher than monolayer-MoS$_2$, resulting in a significant second-order nonlinear susceptibility on the order of 1 nm V$^{-1}$. Intriguingly, the strain enables continuous adjustment of the ferroelectric phase transition across room temperature. Consequently, an exceptionally large tunability of SHG, approximately six orders of magnitude, is achieved through strain or thermal modulation. This colossal SHG, originating from the geometric phase of Bloch wave functions and coupled with sensitive tunability through multiple approaches in this air-stable 2D semiconductor, opens new possibilities for designing chip-scale, switchable nonlinear optical devices.

Off-policy evaluation (OPE) is widely applied in sectors such as pharmaceuticals and e-commerce to evaluate the efficacy of novel products or policies from offline datasets. This paper introduces a causal deepset framework that relaxes several key structural assumptions, primarily the mean-field assumption, prevalent in existing OPE methodologies that handle spatio-temporal interference. These traditional assumptions frequently prove inadequate in real-world settings, thereby restricting the capability of current OPE methods to effectively address complex interference effects. In response, we advocate for the implementation of the permutation invariance (PI) assumption. This innovative approach enables the data-driven, adaptive learning of the mean-field function, offering a more flexible estimation method beyond conventional averaging. Furthermore, we present novel algorithms that incorporate the PI assumption into OPE and thoroughly examine their theoretical foundations. Our numerical analyses demonstrate that this novel approach yields significantly more precise estimations than existing baseline algorithms, thereby substantially improving the practical applicability and effectiveness of OPE methodologies. A Python implementation of our proposed method is available at https://github.com/BIG-S2/Causal-Deepsets.

While large language models are rapidly moving towards consumer-facing applications, they are often still prone to factual errors and hallucinations. In order to reduce the potential harms that may come from these errors, it is important for users to know to what extent they can trust an LLM when it makes a factual claim. To this end, we study the problem of uncertainty quantification of factual correctness in long-form natural language generation. Given some output from a large language model, we study both uncertainty at the level of individual claims contained within the output (via calibration) and uncertainty across the entire output itself (via conformal prediction). Moreover, we invoke multicalibration and multivalid conformal prediction to ensure that such uncertainty guarantees are valid both marginally and across distinct groups of prompts. Using the task of biography generation, we demonstrate empirically that having access to and making use of additional group attributes for each prompt improves both overall and group-wise performance. As the problems of calibration, conformal prediction, and their multi-group counterparts have not been extensively explored previously in the context of long-form text generation, we consider these empirical results to form a benchmark for this setting.

Low-luminosity AGNs with low-mass black holes (BHs) in the early universe are fundamental to understanding the BH growth and their co-evolution with the host galaxies. Utilizing JWST NIRCam Wide Field Slitless Spectroscopy (WFSS), we perform a systematic search for broad-line ${\rm H\alpha}$ emitters (BHAEs) at $z\approx 4-5$ in 25 fields of the ASPIRE (A SPectroscopic survey of biased halos In the Reionization Era) project, covering a total area of 275 arcmin$^2$. We identify 16 BHAEs with FWHM of the broad components spanning from $\sim$ 1000 km s$^{-1}$ to 3000 km s$^{-1}$. Assuming the broad linewidths arise due to Doppler broadening around BHs, the implied BH masses range from $10^7$ to $10^{8}~M_\odot$, with broad ${\rm H\alpha}$-converted bolometric luminosity of $10^{44.5}-10^{45.5}$ erg s$^{-1}$ and Eddington ratios of $0.07-0.47$. The spatially extended structure of the F200W stacked image may trace the stellar light from the host galaxies. The ${\rm H\alpha}$ luminosity function indicates an increasing AGN fraction towards the higher ${\rm H\alpha}$ luminosities. We find possible evidence for clustering of BHAEs: two sources are at the same redshift with a projected separation of 519 kpc; one BHAE appears as a composite system residing in an overdense region with three close companion ${\rm H\alpha}$ emitters. Three BHAEs exhibit blueshifted absorption troughs indicative of the presence of high-column-density gas. We find the broad-line and photometrically selected BHAE samples exhibit different distributions in the optical continuum slopes, which can be attributed to their different selection methods. The ASPIRE broad-line ${\rm H\alpha}$ sample provides a good database for future studies of faint AGN populations at high redshift., Comment: 19 pages, 13 figures, 4 tables. Accepted by the ApJ

Social event detection refers to extracting relevant message clusters from social media data streams to represent specific events in the real world. Social event detection is important in numerous areas, such as opinion analysis, social safety, and decision-making. Most current methods are supervised and require access to large amounts of data. These methods need prior knowledge of the events and carry a high risk of leaking sensitive information in the messages, making them less applicable in open-world settings. Therefore, conducting unsupervised detection while fully utilizing the rich information in the messages and protecting data privacy remains a significant challenge. To this end, we propose a novel social event detection framework, ADP-SEMEvent, an unsupervised social event detection method that prioritizes privacy. Specifically, ADP-SEMEvent is divided into two stages, i.e., the construction stage of the private message graph and the clustering stage of the private message graph. In the first stage, an adaptive differential privacy approach is used to construct a private message graph. In this process, our method can adaptively apply differential privacy based on the events occurring each day in an open environment to maximize the use of the privacy budget. In the second stage, to address the reduction in data utility caused by noise, a novel 2-dimensional structural entropy minimization algorithm based on optimal subgraphs is used to detect events in the message graph. The highlight of this process is unsupervised and does not compromise differential privacy. Extensive experiments on two public datasets demonstrate that ADP-SEMEvent can achieve detection performance comparable to state-of-the-art methods while maintaining reasonable privacy budget parameters., Comment: Accepted to ACM CIKM 2024

We design and fabricate an 8-channel thin film lithium niobate (TFLN) arrayed-waveguide grating (AWG) and demonstrate the electro-optical tunability of the device. The monolithically integrated microelectrodes are designed for waveguides phase modulation and wavelength tunning. Experiments show that the fabricated electro-optically controlled TFLN AWG has a channel spacing of 200 GHz and a wavelength tuning efficiency of 10 pm/V.

As many Kagome metals, the topological superconductor AV$_3$Sb$_5$ with (A = K,Rb,Cs) hosts a charge density wave . A related chiral flux phase that breaks the time-reversal symmetry has been further theoretically predicted in these materials. The flux phase is associated with loop currents that produce ordered orbital magnetic moments, which would occur at the momentum points, $\bf M$, characterizing the charge-density wave state. Polarized neutron-diffraction experiments have been performed on an assembly of single crystals of ${\rm CsV_3Sb_5}$ to search for such orbital magnetic moments. No evidence for the existence of a three-dimensionally ordered moment is found at any temperature at the first ${\bf M_1}$=(1/2,0,0) point in the Brillouin zone within an excellent experimental uncertainty, ${\it i.e.}$ ${\bf m}=0 \pm 0.01\mu_B$ per vanadium atom. However, a hint to a magnetic orbital moment is found in the second Brillouin zone at {\bf M$_2$}=(1/2,1/2,0) at the detection limit of the experiment. Some loop currents patterns flowing ${\it only}$ on vanadium triangles are able to account for this finding suggesting an ordered orbital magnetic moment of, at most, $\sim 0.02 \pm 0.01\mu_B$ per vanadium triangle., Comment: 11 figures

Lane topology, which is usually modeled by a centerline graph, is essential for high-level autonomous driving. For a high-quality graph, both topology connectivity and spatial continuity of centerline segments are critical. However, most of existing approaches pay more attention to connectivity while neglect the continuity. Such kind of centerline graph usually cause problem to planning of autonomous driving. To overcome this problem, we present an end-to-end network, CGNet, with three key modules: 1)Junction Aware Query Enhancement module, which provides positional prior to accurately predict junction points; 2)B\'ezier Space Connection module, which enforces continuity constraints on any two topologically connected segments in a B\'ezier space; 3) Iterative Topology Refinement module, which is a graph-based network with memory to iteratively refine the predicted topological connectivity. CGNet achieves state-of-the-art performance on both nuScenes and Argoverse2 datasets., Comment: ECCV 2024

We study the gas inflows towards the Galactic Central Molecular Zone (CMZ) based on the gas morphological and kinematic features from the MWISP in the region of l=1.2 deg--19.0 deg and |b|<3.0 deg. We find that the near dust lane extends to l~15 deg, in which the end of the large-scale gas structure intersects with the 3 kpc-ring at a distance of ~5 kpc. Intriguingly, many filamentary MCs, together with the bow-like/ballistic-like clouds and continuous CO features with notable velocity gradient, are finely outlined along the long structure. These MCs also have relatively large velocity dispersions, indicating the shocked gas generated by local continuous accretion and thus the enhanced turbulence along the entire gas structure. We suggest that the ~3.1--3.6 kpc long CO structure originates from the accretion molecular gas driven by the Galactic bar. The gas near the bar end at the 3 kpc-ring becomes an important reservoir for the large-scale accreting flows inwards to the CMZ through the bar channel. The inclination angle of the bar is estimated to be 20--26 deg, while the pattern speed of the bar is 30--35 km/s. The total mass of the whole gas lane is about (0.9-1.7)x10^7 Msun according to the calculated X_CO=(0.6-1.4)x10^20 cm^-2 (Kkm/s)^-1 from the large-scale CO data and the complementary HI data. The mean gas inflow rate is about 0.8-1.4 Msun/yr, which seems to be comparable to the outflow's rate of the Galactic nuclear winds after applying the updated lower X-factor value above., Comment: 16 pages, 3 figures

Knowledge distillation plays a key role in compressing the Large Language Models (LLMs), which boosts a small-size student model under large teacher models' guidance. However, existing LLM distillation methods overly rely on student-generated outputs, which may introduce generation errors and misguide the distillation process. Moreover, the distillation loss functions introduced in previous art struggle to align the most informative part due to the complex distribution of LLMs' outputs. To address these problems, we propose a multi-granularity semantic revision method for LLM distillation. At the sequence level, we propose a sequence correction and re-generation (SCRG) strategy. SCRG first calculates the semantic cognitive difference between the teacher and student to detect the error token, then corrects it with the teacher-generated one, and re-generates the sequence to reduce generation errors and enhance generation diversity. At the token level, we design a distribution adaptive clipping Kullback-Leibler (DAC-KL) loss as the distillation objective function. DAC-KL loss exploits a learnable sub-network to adaptively extract semantically dense areas from the teacher's output, avoiding the interference of redundant information in the distillation process. Finally, at the span level, we leverage the span priors of a sequence to compute the probability correlations within spans, and constrain the teacher and student's probability correlations to be consistent, further enhancing the transfer of semantic information. Extensive experiments across different model families with parameters ranging from 0.1B to 13B demonstrate the superiority of our method compared to existing methods.

Image resampling is a basic technique that is widely employed in daily applications, such as camera photo editing. Recent deep neural networks (DNNs) have made impressive progress in performance by introducing learned data priors. Still, these methods are not the perfect substitute for interpolation, due to the drawbacks in efficiency and versatility. In this work, we propose a novel method of Learning Resampling Function (termed LeRF), which takes advantage of both the structural priors learned by DNNs and the locally continuous assumption of interpolation. Specifically, LeRF assigns spatially varying resampling functions to input image pixels and learns to predict the hyper-parameters that determine the shapes of these resampling functions with a neural network. Based on the formulation of LeRF, we develop a family of models, including both efficiency-orientated and performance-orientated ones. To achieve interpolation-level efficiency, we adopt look-up tables (LUTs) to accelerate the inference of the learned neural network. Furthermore, we design a directional ensemble strategy and edge-sensitive indexing patterns to better capture local structures. On the other hand, to obtain DNN-level performance, we propose an extension of LeRF to enable it in cooperation with pre-trained upsampling models for cascaded resampling. Extensive experiments show that the efficiency-orientated version of LeRF runs as fast as interpolation, generalizes well to arbitrary transformations, and outperforms interpolation significantly, e.g., up to 3dB PSNR gain over Bicubic for x2 upsampling on Manga109. Besides, the performance-orientated version of LeRF reaches comparable performance with existing DNNs at much higher efficiency, e.g., less than 25% running time on a desktop GPU., Comment: Code: https://github.com/ddlee-cn/LeRF-PyTorch

Understanding how biological visual systems process information is challenging because of the nonlinear relationship between visual input and neuronal responses. Artificial neural networks allow computational neuroscientists to create predictive models that connect biological and machine vision. Machine learning has benefited tremendously from benchmarks that compare different model on the same task under standardized conditions. However, there was no standardized benchmark to identify state-of-the-art dynamic models of the mouse visual system. To address this gap, we established the Sensorium 2023 Benchmark Competition with dynamic input, featuring a new large-scale dataset from the primary visual cortex of ten mice. This dataset includes responses from 78,853 neurons to 2 hours of dynamic stimuli per neuron, together with the behavioral measurements such as running speed, pupil dilation, and eye movements. The competition ranked models in two tracks based on predictive performance for neuronal responses on a held-out test set: one focusing on predicting in-domain natural stimuli and another on out-of-distribution (OOD) stimuli to assess model generalization. As part of the NeurIPS 2023 competition track, we received more than 160 model submissions from 22 teams. Several new architectures for predictive models were proposed, and the winning teams improved the previous state-of-the-art model by 50%. Access to the dataset as well as the benchmarking infrastructure will remain online at www.sensorium-competition.net.

High-temperature superconductivity (HTSC) remains one of the most challenging and fascinating mysteries in condensed matter physics. Recently, superconductivity with transition temperature exceeding liquid-nitrogen temperature is discovered in La3Ni2O7 at high pressure, which provides a new platform to explore the unconventional HTSC. In this work, using high-resolution angle-resolved photoemission spectroscopy and ab-initio calculation, we systematically investigate the electronic structures of La3Ni2O7 at ambient pressure. Our experiments are in nice agreement with ab-initio calculations after considering an orbital-dependent band renormalization effect. The strong electron correlation effect pushes a flat band of d_(z^2 ) orbital component below the Fermi level (EF), which is predicted to locate right at EF under high pressure. Moreover, the d_(x^2-y^2 ) band shows a pseudogap-like behavior with suppressed spectral weight and diminished quasiparticle peak near EF. Our findings provide important insights into the electronic structure of La3Ni2O7, which will shed light on the understanding of the unconventional superconductivity in nickelates.

While polar metals are a metallic analogue of ferroelectrics, magnetic polar metals can be considered as a metallic analogue of multiferroics. There have been a number of attempts to integrate magnetism into a polar metal by synthesizing new materials or heterostructures. Here we use a simple yet widely used approach--epitaxial strain in the search for intrinsic magnetic polar metals. Via first-principles calculations, we study strain engineering of a ferromagnetic metallic oxide SrCoO$_3$, whose bulk form crystallizes in a cubic structure. We find that under an experimentally feasible biaxial strain on the $ab$ plane, collective Co polar displacements are stabilized in SrCoO$_3$. Specifically, a compressive strain stabilizes Co polar displacements along the $c$ axis, while a tensile strain stabilizes Co polar displacements along the diagonal line in the $ab$ plane. In both cases, we find an intrinsic ferromagnetic polar metallic state in SrCoO$_3$. In addition, we also find that a sufficiently large biaxial strain ($> 4\%$) can yield a ferromagnetic-to-antiferromagnetic transition in SrCoO$_3$. Our work demonstrates that in addition to yielding emergent multiferroics, epitaxial strain is also a viable approach to inducing magnetic polar metallic states in quantum materials., Comment: 19 pages, 6 figures

A 16-dimensional Voronoi constellation concatenated with multilevel coding is experimentally demonstrated over a 50km four-core fiber transmission system. The proposed scheme reduces the required launch power by 6dB and provides a 17dB larger operating range than 16QAM with BICM at the outer HD-FEC BER threshold., Comment: 4 pages, 4 figures, accepted by 2024 European Conference on Optical Communication (ECOC)

We present CEIA, an effective framework for open-world event-based understanding. Currently training a large event-text model still poses a huge challenge due to the shortage of paired event-text data. In response to this challenge, CEIA learns to align event and image data as an alternative instead of directly aligning event and text data. Specifically, we leverage the rich event-image datasets to learn an event embedding space aligned with the image space of CLIP through contrastive learning. In this way, event and text data are naturally aligned via using image data as a bridge. Particularly, CEIA offers two distinct advantages. First, it allows us to take full advantage of the existing event-image datasets to make up the shortage of large-scale event-text datasets. Second, leveraging more training data, it also exhibits the flexibility to boost performance, ensuring scalable capability. In highlighting the versatility of our framework, we make extensive evaluations through a diverse range of event-based multi-modal applications, such as object recognition, event-image retrieval, event-text retrieval, and domain adaptation. The outcomes demonstrate CEIA's distinct zero-shot superiority over existing methods on these applications.

3D single object tracking (SOT) methods based on appearance matching has long suffered from insufficient appearance information incurred by incomplete, textureless and semantically deficient LiDAR point clouds. While motion paradigm exploits motion cues instead of appearance matching for tracking, it incurs complex multi-stage processing and segmentation module. In this paper, we first provide in-depth explorations on motion paradigm, which proves that (\textbf{i}) it is feasible to directly infer target relative motion from point clouds across consecutive frames; (\textbf{ii}) fine-grained information comparison between consecutive point clouds facilitates target motion modeling. We thereby propose to perform part-to-part motion modeling for consecutive point clouds and introduce a novel tracking framework, termed \textbf{P2P}. The novel framework fuses each corresponding part information between consecutive point clouds, effectively exploring detailed information changes and thus modeling accurate target-related motion cues. Following this framework, we present P2P-point and P2P-voxel models, incorporating implicit and explicit part-to-part motion modeling by point- and voxel-based representation, respectively. Without bells and whistles, P2P-voxel sets a new state-of-the-art performance ($\sim$\textbf{89\%}, \textbf{72\%} and \textbf{63\%} precision on KITTI, NuScenes and Waymo Open Dataset, respectively). Moreover, under the same point-based representation, P2P-point outperforms the previous motion tracker M$^2$Track by \textbf{3.3\%} and \textbf{6.7\%} on the KITTI and NuScenes, while running at a considerably high speed of \textbf{107 Fps} on a single RTX3090 GPU. The source code and pre-trained models are available at \url{https://github.com/haooozi/P2P}., Comment: The source code and pre-trained models are available at https://github.com/haooozi/P2P

As the U.S. Census Bureau implements its controversial new disclosure avoidance system, researchers and policymakers debate the necessity of new privacy protections for public statistics. With experiments on both published statistics and synthetic data, we explore a particular privacy concern: respondents in subsidized housing may deliberately not mention unauthorized children and other household members for fear of being evicted. By combining public statistics from the Decennial Census and the Department of Housing and Urban Development, we demonstrate a simple, inexpensive reconstruction attack that could identify subsidized households living in violation of occupancy guidelines in 2010. Experiments on synthetic data suggest that a random swapping mechanism similar to the Census Bureau's 2010 disclosure avoidance measures does not significantly reduce the precision of this attack, while a differentially private mechanism similar to the 2020 disclosure avoidance system does. Our results provide a valuable example for policymakers seeking a trustworthy, accurate census.

Natural Language Counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class. The generated counterfactuals provide insight into the reasoning behind a model's predictions by highlighting which words significantly influence the outcomes. Additionally, they can be used to detect model fairness issues or augment the training data to enhance the model's robustness. A substantial amount of research has been conducted to generate counterfactuals for various NLP tasks, employing different models and methodologies. With the rapid growth of studies in this field, a systematic review is crucial to guide future researchers and developers. To bridge this gap, this survey comprehensively overview textual counterfactual generation methods, particularly including those based on Large Language Models. We propose a new taxonomy that categorizes the generation methods into four groups and systematically summarize the metrics for evaluating the generation quality. Finally, we discuss ongoing research challenges and outline promising directions for future work., Comment: A survey paper

Kagome superconductors AV3Sb5 (A = K, Rb, Cs) exhibit a characteristic superconducting and charge-density wave (CDW) phase diagram upon carrier doping and chemical substitution. However, the key electronic states responsible for such a phase diagram have yet to be clarified. Here we report a systematic micro-focused angle-resolved photoemission spectroscopy (ARPES) study of Cs(V1-xCrx)3Sb5 as a function of Cr content x, where Cr substitution causes monotonic reduction of superconducting and CDW transition temperatures. We found that the V-derived bands forming saddle points at the M point and Dirac nodes along high-symmetry cuts show an energy shift due to electron doping by Cr substitution, whereas the Sb-derived electron band at the Gamma point remains almost unchanged, signifying an orbital-selective band shift. We also found that band doubling associated with the emergence of three-dimensional CDW identified at x = 0 vanishes at x = 0.25, in line with the disappearance of CDW. A comparison of band diagrams among Ti-, Nb-, and Cr-substituted Cs(V1-xCrx)3Sb5 suggests the importance to simultaneously take into account the two saddle points at the M point and their proximity to the Fermi energy, to understand the complex phase diagram against carrier doping and chemical pressure., Comment: 7 pages, 4 figures

We present a comprehensive analysis of young stellar object (YSO) variability within the M17 Southwest Extension (M17 SWex), using 3.5 years of monitoring data from the JCMT Transient Survey at sub-millimeter (sub-mm) and 9 years from the NEOWISE mission at mid-infrared (mid-IR). Our study encompasses observations of 147 bright sub-mm peaks identified within our deep JCMT co-added map as well as 156 YSOs in NEOWISE W1 and 179 in W2 that were previously identified in Spitzer surveys. We find three robust sub-mm variables: two are candidate YSOs and one is a likely extragalactic source. At mid-IR wavelengths, our analysis reveals secular and stochastic variability in 47 YSOs, with the highest fraction of secular variability occurring at the earliest evolutionary stage. This is similar to what has previously been observed for low-mass YSO variability within the Gould Belt. However, we observe less overall variability in M17SWex at both the sub-mm and mid-IR. We suspect that this lower fraction is due to the greater distance to M17 SWex. Our findings showcase the utility of multi-wavelength observations to better capture the complex variability phenomena inherent to star formation processes and demonstrate the importance of years-long monitoring of a diverse selection of star-forming environments., Comment: Accepted for Publication in The Astronomical Journal

Transformer models have emerged as potent solutions to a wide array of multidisciplinary challenges. The deployment of Transformer architectures is significantly hindered by their extensive computational and memory requirements, necessitating the reliance on advanced efficient distributed training methodologies. Prior research has delved into the performance bottlenecks associated with distributed training, aiming to unravel these bottlenecks and suggest optimization directions. However, such analyses often overlook three aspects unique to Transformer models: the specialized architecture, the dependency on various distributed strategies, and the requirement to balance computational and memory overhead. This paper aims to bridge this gap by offering a comprehensive examination of the performance bottlenecks inherent in distributed training of Transformer models, leveraging both theoretical analysis and empirical investigation. We propose an analytical framework tailored to these unique aspects of Transformers, facilitating a holistic evaluation of model architectures, distributed strategies, and resource consumption. Based on this analytical framework, we conduct a comparative analysis of theoretical performances and further systematically explore how various distributed training strategies fare in real-world scenarios. Most of the experimental results can be well explained by the analytical outcomes derived from the analytical framework. Notably, our findings suggest an advantage of pipeline parallelism over data parallelism for Transformer models. Moreover, we shed light on some unexpected outcomes, such as the potential for increased total memory overhead due to suboptimal model partitioning within pipeline parallelism. Additionally, we underscore the significance of communication block size and waiting time to further enhance performance.