Search

Human motion prediction is a cornerstone of human-robot collaboration (HRC), as robots need to infer the future movements of human workers based on past motion cues to proactively plan their motion, ensuring safety in close collaboration scenarios. The diffusion model has demonstrated remarkable performance in predicting high-quality motion samples with reasonable diversity, but suffers from a slow generative process which necessitates multiple model evaluations, hindering real-world applications. To enable real-time prediction, in this work, we propose training a one-step multi-layer perceptron-based (MLP-based) diffusion model for motion prediction using knowledge distillation and Bayesian optimization. Our method contains two steps. First, we distill a pretrained diffusion-based motion predictor, TransFusion, directly into a one-step diffusion model with the same denoiser architecture. Then, to further reduce the inference time, we remove the computationally expensive components from the original denoiser and use knowledge distillation once again to distill the obtained one-step diffusion model into an even smaller model based solely on MLPs. Bayesian optimization is used to tune the hyperparameters for training the smaller diffusion model. Extensive experimental studies are conducted on benchmark datasets, and our model can significantly improve the inference speed, achieving real-time prediction without noticeable degradation in performance.

A symmetry preserving treatment of a vector $\otimes$ vector contact interaction (SCI) is used as the basis for calculations of the two pion transverse momentum dependent parton distribution functions (TMDs); namely, that for unpolarised valence degrees-of-freedom and the analogous Boer-Mulders (BM) function. Amongst other things, the analysis enables the following themes to be addressed: the quark current mass dependence of pion TMDs; the impact of the gauge link model on the positivity constraint that bounds the BM function relative to the unpolarised TMD; the equivalence of direct diagrammatic and light-front wave function TMD calculations; and the size of the BM shift. Interpreted astutely, these SCI results enable one to draw insightful pictures of pion TMDs., Comment: 14 pages, 9 figures, 1 table

LLMs obtain remarkable performance but suffer from hallucinations. Most research on detecting hallucination focuses on the questions with short and concrete correct answers that are easy to check the faithfulness. Hallucination detections for text generation with open-ended answers are more challenging. Some researchers use external knowledge to detect hallucinations in generated texts, but external resources for specific scenarios are hard to access. Recent studies on detecting hallucinations in long text without external resources conduct consistency comparison among multiple sampled outputs. To handle long texts, researchers split long texts into multiple facts and individually compare the consistency of each pairs of facts. However, these methods (1) hardly achieve alignment among multiple facts; (2) overlook dependencies between multiple contextual facts. In this paper, we propose a graph-based context-aware (GCA) hallucination detection for text generations, which aligns knowledge facts and considers the dependencies between contextual knowledge triples in consistency comparison. Particularly, to align multiple facts, we conduct a triple-oriented response segmentation to extract multiple knowledge triples. To model dependencies among contextual knowledge triple (facts), we construct contextual triple into a graph and enhance triples' interactions via message passing and aggregating via RGCN. To avoid the omission of knowledge triples in long text, we conduct a LLM-based reverse verification via reconstructing the knowledge triples. Experiments show that our model enhances hallucination detection and excels all baselines.

Extreme-mass-ratio inspiral (EMRI) signals pose significant challenges in gravitational wave (GW) astronomy owing to their low-frequency nature and highly complex waveforms, which occupy a high-dimensional parameter space with numerous variables. Given their extended inspiral timescales and low signal-to-noise ratios, EMRI signals warrant prolonged observation periods. Parameter estimation becomes particularly challenging due to non-local parameter degeneracies, arising from multiple local maxima, as well as flat regions and ridges inherent in the likelihood function. These factors lead to exceptionally high time complexity for parameter analysis while employing traditional matched filtering and random sampling methods. To address these challenges, the present study applies machine learning to Bayesian posterior estimation of EMRI signals, leveraging the recently developed flow matching technique based on ODE neural networks. Our approach demonstrates computational efficiency several orders of magnitude faster than the traditional Markov Chain Monte Carlo (MCMC) methods, while preserving the unbiasedness of parameter estimation. We show that machine learning technology has the potential to efficiently handle the vast parameter space, involving up to seventeen parameters, associated with EMRI signals. Furthermore, to our knowledge, this is the first instance of applying machine learning, specifically the Continuous Normalizing Flows (CNFs), to EMRI signal analysis. Our findings highlight the promising potential of machine learning in EMRI waveform analysis, offering new perspectives for the advancement of space-based GW detection and GW astronomy.

Nonlinear optical (NLO) effects in materials with band crossings have attracted significant research interests due to the divergent band geometric quantities around these crossings. Most current research has focused on band crossings between the valence and conduction bands. However, such crossings are absent in insulators, which are more relevant for NLO applications. In this work, we demonstrate that NLO effects can be significantly enhanced by band crossings within the valence or conduction bands, which we designate as "deep band crossings" (DBCs). As an example, in two dimensions, we show that shift conductivity can be substantially enhanced or even divergent due to a mirror-protected "deep Dirac nodal point". In three dimensions, we propose GeTe as an ideal material where shift conductivity is enhanced by "deep Dirac nodal lines". The ubiquity of this enhancement is further confirmed by high-throughput calculations. Other types of DBCs and NLO effects are also discussed. By manipulating band crossings between arbitrary bands, our work offers a simple, practical, and universal way to greatly enhance NLO effects.

Language models have been effectively applied to modeling natural signals, such as images, video, speech, and audio. A crucial component of these models is the codec tokenizer, which compresses high-dimensional natural signals into lower-dimensional discrete tokens. In this paper, we introduce WavTokenizer, which offers several advantages over previous SOTA acoustic codec models in the audio domain: 1)extreme compression. By compressing the layers of quantizers and the temporal dimension of the discrete codec, one-second audio of 24kHz sampling rate requires only a single quantizer with 40 or 75 tokens. 2)improved subjective quality. Despite the reduced number of tokens, WavTokenizer achieves state-of-the-art reconstruction quality with outstanding UTMOS scores and inherently contains richer semantic information. Specifically, we achieve these results by designing a broader VQ space, extended contextual windows, and improved attention networks, as well as introducing a powerful multi-scale discriminator and an inverse Fourier transform structure. We conducted extensive reconstruction experiments in the domains of speech, audio, and music. WavTokenizer exhibited strong performance across various objective and subjective metrics compared to state-of-the-art models. We also tested semantic information, VQ utilization, and adaptability to generative models. Comprehensive ablation studies confirm the necessity of each module in WavTokenizer. The related code, demos, and pre-trained models are available at https://github.com/jishengpeng/WavTokenizer., Comment: Working in progress. arXiv admin note: text overlap with arXiv:2402.12208

The rapid progress in Deep Learning (DL) and Large Language Models (LLMs) has exponentially increased demands of computational power and bandwidth. This, combined with the high costs of faster computing chips and interconnects, has significantly inflated High Performance Computing (HPC) construction costs. To address these challenges, we introduce the Fire-Flyer AI-HPC architecture, a synergistic hardware-software co-design framework and its best practices. For DL training, we deployed the Fire-Flyer 2 with 10,000 PCIe A100 GPUs, achieved performance approximating the DGX-A100 while reducing costs by half and energy consumption by 40%. We specifically engineered HFReduce to accelerate allreduce communication and implemented numerous measures to keep our Computation-Storage Integrated Network congestion-free. Through our software stack, including HaiScale, 3FS, and HAI-Platform, we achieved substantial scalability by overlapping computation and communication. Our system-oriented experience from DL training provides valuable insights to drive future advancements in AI-HPC., Comment: This is the preprint version of the paper accepted for presentation at the 2024 International Conference for High Performance Computing, Networking, Storage, and Analysis (SC'24). \c{opyright} 2024 IEEE. Personal use of this material is permitted. For other uses, permission from IEEE must be obtained. Please refer to IEEE Xplore for the final published version

Current robotic manipulators require fast and efficient motion-planning algorithms to operate in cluttered environments. State-of-the-art sampling-based motion planners struggle to scale to high-dimensional configuration spaces and are inefficient in complex environments. This inefficiency arises because these planners utilize either uniform or hand-crafted sampling heuristics within the configuration space. To address these challenges, we present the Spatial-informed Motion Planning Network (SIMPNet). SIMPNet consists of a stochastic graph neural network (GNN)-based sampling heuristic for informed sampling within the configuration space. The sampling heuristic of SIMPNet encodes the workspace embedding into the configuration space through a cross-attention mechanism. It encodes the manipulator's kinematic structure into a graph, which is used to generate informed samples within the framework of sampling-based motion planning algorithms. We have evaluated the performance of SIMPNet using a UR5e robotic manipulator operating within simple and complex workspaces, comparing it against baseline state-of-the-art motion planners. The evaluation results show the effectiveness and advantages of the proposed planner compared to the baseline planners.

Accurate assessment of lymph node size in 3D CT scans is crucial for cancer staging, therapeutic management, and monitoring treatment response. Existing state-of-the-art segmentation frameworks in medical imaging often rely on fully annotated datasets. However, for lymph node segmentation, these datasets are typically small due to the extensive time and expertise required to annotate the numerous lymph nodes in 3D CT scans. Weakly-supervised learning, which leverages incomplete or noisy annotations, has recently gained interest in the medical imaging community as a potential solution. Despite the variety of weakly-supervised techniques proposed, most have been validated only on private datasets or small publicly available datasets. To address this limitation, the Mediastinal Lymph Node Quantification (LNQ) challenge was organized in conjunction with the 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2023). This challenge aimed to advance weakly-supervised segmentation methods by providing a new, partially annotated dataset and a robust evaluation framework. A total of 16 teams from 5 countries submitted predictions to the validation leaderboard, and 6 teams from 3 countries participated in the evaluation phase. The results highlighted both the potential and the current limitations of weakly-supervised approaches. On one hand, weakly-supervised approaches obtained relatively good performance with a median Dice score of $61.0\%$. On the other hand, top-ranked teams, with a median Dice score exceeding $70\%$, boosted their performance by leveraging smaller but fully annotated datasets to combine weak supervision and full supervision. This highlights both the promise of weakly-supervised methods and the ongoing need for high-quality, fully annotated data to achieve higher segmentation performance., Comment: Submitted to MELBA

The thriving mobile app ecosystem encompasses a wide range of functionalities. However, within this ecosystem, a subset of apps provides illicit services such as gambling and pornography to pursue economic gains, collectively referred to as "underground economy apps". While previous studies have examined these apps' characteristics and identification methods, investigations into their distribution via platforms beyond app markets (like Telegram) remain scarce, which has emerged as a crucial channel for underground activities and cybercrime due to the robust encryption and user anonymity. This study provides the first comprehensive exploration of the underground mobile app ecosystem on Telegram. Overcoming the complexities of the Telegram environment, we build a novel dataset and analyze the prevalence, promotional strategies, and characteristics of these apps. Our findings reveal that these apps reach approximately 1% of Telegram's user base, primarily catering to gambling and pornography services. We uncover sophisticated promotional strategies involving complex networks of apps, websites, users, and channels, and identify significant gaps in Telegram's content moderation capabilities. Our analysis also exposes the misuse of iOS features for app distribution and the prevalence of malicious behaviors in these apps. This research not only enhances our understanding of the underground app ecosystem but also provides valuable insights for developing effective regulatory measures and protecting users from potential risks associated with these covert operations. Our findings provide implications for platform regulators, app market operators, law enforcement agencies, and cybersecurity professionals in combating the proliferation of underground apps on encrypted messaging platforms.

Recent advances in Large Language Models (LLMs) have revolutionized code generation, leading to widespread adoption of AI coding tools by developers. However, LLMs can generate license-protected code without providing the necessary license information, leading to potential intellectual property violations during software production. This paper addresses the critical, yet underexplored, issue of license compliance in LLM-generated code by establishing a benchmark to evaluate the ability of LLMs to provide accurate license information for their generated code. To establish this benchmark, we conduct an empirical study to identify a reasonable standard for "striking similarity" that excludes the possibility of independent creation, indicating a copy relationship between the LLM output and certain open-source code. Based on this standard, we propose an evaluation benchmark LiCoEval, to evaluate the license compliance capabilities of LLMs. Using LiCoEval, we evaluate 14 popular LLMs, finding that even top-performing LLMs produce a non-negligible proportion (0.88% to 2.01%) of code strikingly similar to existing open-source implementations. Notably, most LLMs fail to provide accurate license information, particularly for code under copyleft licenses. These findings underscore the urgent need to enhance LLM compliance capabilities in code generation tasks. Our study provides a foundation for future research and development to improve license compliance in AI-assisted software development, contributing to both the protection of open-source software copyrights and the mitigation of legal risks for LLM users.

Bismuth oxyselenide (Bi$_2$O$_2$Se), a novel quasi-2D charge-carrying semiconductor, is hailed as one of the best emerging platforms for the next generation semiconductor devices. Recent efforts on developing diverse Bi$_2$O$_2$Se heterojunctions have produced extensive potential applications in electronics and optoelectronics. In-depth understanding of the band alignment and especially interface dynamics is, however, still challenging. In this work, a comprehensive experimental investigation on the band alignment is performed by a high-resolution X-ray photoelectron spectrometer (HRXPS), and the properties of interface states are also fully discussed. The results show that the ultrathin film Bi$_2$O$_2$Se grown on SrTiO$_3$ (TiO$_2$ (001) termination) exhibits Type-I (straddling gap) band alignment with a valence band offset (VBO) of about 1.77\pm0.04 eV and conduction band offset (CBO) of about 0.68\pm0.04 eV. However, further considering the contribution of the interface states, the bands on the interface present a herringbone configuration due to sizable build-in electric fields, which is significantly different from the conventional band alignment. In this sense, our results provide an insightful guidance to the development of high-efficiency electronic and optoelectronic devices, specifically of the devices where the charge transfer is highly sensitive to interface states.

As a novel and promising 2D material, bismuth oxyselenide (Bi$_2$O$_2$Se) has demonstrated significant potential to overcome existing technical barriers in various electronic device applications, due to its unique physical properties like high symmetry, adjustable electronic structure, ultra-high electron mobility. However, the rapid growth of Bi$_2$O$_2$Se films down to a few atomic layers with precise control remains a significant challenge. In this work, the growth of two-dimensional (2D) Bi$_2$O$_2$Se thin films by the pulsed laser deposition (PLD) method is systematically investigated. By controlling temperature, oxygen pressure, laser energy density and laser emission frequency, we successfully prepare atomically thin and flat Bi$_2$O$_2$Se (001) thin films on the (001) surface of SrTiO3. Importantly, we provide a fundamental and unique perspective toward understanding the growth process of atomically thin and flat Bi$_2$O$_2$Se films, and the growth process can be primarily summarized into four steps: i) anisotropic non-spontaneous nucleation preferentially along the step roots; ii) monolayer Bi$_2$O$_2$Se nanosheets expanding across the surrounding area, and eventually covering the entire STO substrate step; iii) vertical growth of Bi$_2$O$_2$Se monolayer in a 2D Frank-van der Merwe (FM) epitaxial growth, and iv) with a layer-by-layer 2D FM growth mode, ultimately producing an atomically flat and epitaxially aligned thin film. Moreover, the combined results of the crystallinity quality, surface morphology and the chemical states manifest the successful PLD-growth of high-quality Bi$_2$O$_2$Se films in a controllable and fast mode.

This paper introduces a unique force control and adaptation algorithm for a lightweight and low-complexity five-fingered robotic hand, namely an Integrated-Finger Robotic Hand (IFRH). The force control and adaptation algorithm is intuitive to design, easy to implement, and improves the grasping functionality through feedforward adaptation automatically. Specifically, we have extended Youla-parameterization which is traditionally used in feedback controller design into a feedforward iterative learning control algorithm (ILC). The uniqueness of such an extension is that both the feedback and feedforward controllers are parameterized over one unified design parameter which can be easily customized based on the desired closed-loop performance. While Youla-parameterization and ILC have been explored in the past on various applications, our unique parameterization and computational methods make the design intuitive and easy to implement. This provides both robust and adaptive learning capabilities, and our application rivals the complexity of many robotic hand control systems. Extensive experimental tests have been conducted to validate the effectiveness of our method.

In contemporary society, the issue of psychological health has become increasingly prominent, characterized by the diversification, complexity, and universality of mental disorders. Cognitive Behavioral Therapy (CBT), currently the most influential and clinically effective psychological treatment method with no side effects, has limited coverage and poor quality in most countries. In recent years, researches on the recognition and intervention of emotional disorders using large language models (LLMs) have been validated, providing new possibilities for psychological assistance therapy. However, are LLMs truly possible to conduct cognitive behavioral therapy? Many concerns have been raised by mental health experts regarding the use of LLMs for therapy. Seeking to answer this question, we collected real CBT corpus from online video websites, designed and conducted a targeted automatic evaluation framework involving the evaluation of emotion tendency of generated text, structured dialogue pattern and proactive inquiry ability. For emotion tendency, we calculate the emotion tendency score of the CBT dialogue text generated by each model. For structured dialogue pattern, we use a diverse range of automatic evaluation metrics to compare speaking style, the ability to maintain consistency of topic and the use of technology in CBT between different models . As for inquiring to guide the patient, we utilize PQA (Proactive Questioning Ability) metric. We also evaluated the CBT ability of the LLM after integrating a CBT knowledge base to explore the help of introducing additional knowledge to enhance the model's CBT counseling ability. Four LLM variants with excellent performance on natural language processing are evaluated, and the experimental result shows the great potential of LLMs in psychological counseling realm, especially after combining with other technological means.

This paper presents the development of a new collaborative road profile estimation and active suspension control framework in connected vehicles, where participating vehicles iteratively refine the road profile estimation and enhance suspension control performance through an iterative learning scheme. Specifically, we develop a robust iterative learning approach to tackle the heterogeneity and model uncertainties in participating vehicles, which are important for practical implementations. In addition, the framework can be adopted as an add-on system to augment existing suspension control schemes. Comprehensive numerical studies are performed to evaluate and validate the proposed framework.

This paper focuses on the cohomology of operator algebras associated with the free semigroup generated by the set $\{z_{\alpha}\}_{\alpha\in\Lambda}$, with the left regular free semigroup algebra $\mathfrak{L}_{\Lambda}$ and the non-commutative disc algebra $\mathfrak{A}_{\Lambda}$ serving as two typical examples. We establish that all derivations of these algebras are automatically continuous. By introducing a novel computational approach, we demonstrate that the first Hochschild cohomology group of $\mathfrak{A}_{\Lambda}$ with coefficients in $\mathfrak{L}_{\Lambda}$ is zero. Utilizing the Ces\`aro operators and conditional expectations, we show that the first normal cohomology group of $\mathfrak{L}_{\Lambda}$ is trivial. Finally, we prove that the higher cohomology groups of the non-commutative disc algebras with coefficients in the complex field vanish when $|\Lambda|<\infty$. These methods extend to compute the cohomology groups of a specific class of operator algebras generated by the left regular representations of cancellative semigroups, which notably include Thompson's semigroup., Comment: 19 pages

Deep learning electronic structures from ab initio calculations holds great potential to revolutionize computational materials studies. While existing methods proved success in deep-learning density functional theory (DFT) Hamiltonian matrices, they are limited to DFT programs using localized atomic-like bases and heavily depend on the form of the bases. Here, we propose the DeepH-r method for deep-learning DFT Hamiltonians in real space, facilitating the prediction of DFT Hamiltonian in a basis-independent manner. An equivariant neural network architecture for modeling the real-space DFT potential is developed, targeting a more fundamental quantity in DFT. The real-space potential exhibits simplified principles of equivariance and enhanced nearsightedness, further boosting the performance of deep learning. When applied to evaluate the Hamiltonian matrix, this method significantly improved in accuracy, as exemplified in multiple case studies. Given the abundance of data in the real-space potential, this work may pave a novel pathway for establishing a ``large materials model" with increased accuracy.

Although recent advancements in text-to-3D generation have significantly improved generation quality, issues like limited level of detail and low fidelity still persist, which requires further improvement. To understand the essence of those issues, we thoroughly analyze current score distillation methods by connecting theories of consistency distillation to score distillation. Based on the insights acquired through analysis, we propose an optimization framework, Guided Consistency Sampling (GCS), integrated with 3D Gaussian Splatting (3DGS) to alleviate those issues. Additionally, we have observed the persistent oversaturation in the rendered views of generated 3D assets. From experiments, we find that it is caused by unwanted accumulated brightness in 3DGS during optimization. To mitigate this issue, we introduce a Brightness-Equalized Generation (BEG) scheme in 3DGS rendering. Experimental results demonstrate that our approach generates 3D assets with more details and higher fidelity than state-of-the-art methods. The codes are released at https://github.com/LMozart/ECCV2024-GCS-BEG., Comment: Paper accepted by ECCV2024

The geodetic and astrometric VLBI community is in the process of upgrading its existing infrastructure with VGOS. The primary objective of VGOS is to substantially boost the number of scans per hour for enhanced parameter estimation. However, the current observing strategy results in fewer scans than anticipated. During 2022, six 24-hour VGOS R&D sessions were conducted to demonstrate a proof-of-concept aimed at addressing this shortcoming. The new observation strategy centers around a signal-to-noise (SNR)-based scheduling approach combined with eliminating existing overhead times in existing VGOS sessions. Two SNR-based scheduling approaches were tested during these sessions: one utilizing inter-/extrapolation of existing S/X source flux density models and another based on a newly derived source flux density catalog at VGOS frequencies. Both approaches proved effective, leading to a 2.3-fold increase in the number of scheduled scans per station and a 2.6-fold increase in the number of observations per station, while maintaining a high observation success rate of approximately 90-95%. Consequently, both strategies succeeded in the main objective of these sessions by successfully increasing the number of scans per hour. The strategies described in this work can be easily applied to operational VGOS observations. Besides outlining and discussing the observation strategy, we further provide insight into the resulting signal-to-noise ratios, and discuss the impact on the precision of the estimated geodetic parameters. Monte Carlo simulations predicted a roughly 50% increase in geodetic precision compared to operational VGOS sessions. The analysis confirmed that the formal errors in estimated station coordinates were reduced by 40-50%. Additionally, Earth orientation parameters showed significant improvement, with a 40-50% reduction in formal errors.

The success of deep face recognition (FR) systems has raised serious privacy concerns due to their ability to enable unauthorized tracking of users in the digital world. Previous studies proposed introducing imperceptible adversarial noises into face images to deceive those face recognition models, thus achieving the goal of enhancing facial privacy protection. Nevertheless, they heavily rely on user-chosen references to guide the generation of adversarial noises, and cannot simultaneously construct natural and highly transferable adversarial face images in black-box scenarios. In light of this, we present a novel face privacy protection scheme with improved transferability while maintain high visual quality. We propose shaping the entire face space directly instead of exploiting one kind of facial characteristic like makeup information to integrate adversarial noises. To achieve this goal, we first exploit global adversarial latent search to traverse the latent space of the generative model, thereby creating natural adversarial face images with high transferability. We then introduce a key landmark regularization module to preserve the visual identity information. Finally, we investigate the impacts of various kinds of latent spaces and find that $\mathcal{F}$ latent space benefits the trade-off between visual naturalness and adversarial transferability. Extensive experiments over two datasets demonstrate that our approach significantly enhances attack transferability while maintaining high visual quality, outperforming state-of-the-art methods by an average 25% improvement in deep FR models and 10% improvement on commercial FR APIs, including Face++, Aliyun, and Tencent., Comment: Accepted by ACM MM 2024

Multimodal large language models (MLLMs) have shown promising advancements in general visual and language understanding. However, the representation of multimodal information using MLLMs remains largely unexplored. In this work, we introduce a new framework, E5-V, designed to adapt MLLMs for achieving universal multimodal embeddings. Our findings highlight the significant potential of MLLMs in representing multimodal inputs compared to previous approaches. By leveraging MLLMs with prompts, E5-V effectively bridges the modality gap between different types of inputs, demonstrating strong performance in multimodal embeddings even without fine-tuning. We propose a single modality training approach for E5-V, where the model is trained exclusively on text pairs. This method demonstrates significant improvements over traditional multimodal training on image-text pairs, while reducing training costs by approximately 95%. Additionally, this approach eliminates the need for costly multimodal training data collection. Extensive experiments across four types of tasks demonstrate the effectiveness of E5-V. As a universal multimodal model, E5-V not only achieves but often surpasses state-of-the-art performance in each task, despite being trained on a single modality., Comment: Code and models are available at https://github.com/kongds/E5-V

Embodied artificial intelligence (AI) represents an artificial intelligence system that interacts with the physical world through sensors and actuators, seamlessly integrating perception and action. This design enables AI to learn from and operate within complex, real-world environments. Large Language Models (LLMs) deeply explore language instructions, playing a crucial role in devising plans for complex tasks. Consequently, they have progressively shown immense potential in empowering embodied AI, with LLM-based embodied AI emerging as a focal point of research within the community. It is foreseeable that, over the next decade, LLM-based embodied AI robots are expected to proliferate widely, becoming commonplace in homes and industries. However, a critical safety issue that has long been hiding in plain sight is: could LLM-based embodied AI perpetrate harmful behaviors? Our research investigates for the first time how to induce threatening actions in embodied AI, confirming the severe risks posed by these soon-to-be-marketed robots, which starkly contravene Asimov's Three Laws of Robotics and threaten human safety. Specifically, we formulate the concept of embodied AI jailbreaking and expose three critical security vulnerabilities: first, jailbreaking robotics through compromised LLM; second, safety misalignment between action and language spaces; and third, deceptive prompts leading to unaware hazardous behaviors. We also analyze potential mitigation measures and advocate for community awareness regarding the safety of embodied AI applications in the physical world., Comment: Preliminary version (17 pages, 4 figures). Work in progress, revisions ongoing. Appreciate understanding and welcome any feedback

Automatic and precise multi-class vertebrae segmentation from CT images is crucial for various clinical applications. However, due to a lack of explicit consistency constraints, existing methods especially for single-stage methods, still suffer from the challenge of intra-vertebrae segmentation inconsistency, which refers to multiple label predictions inside a singular vertebra. For multi-stage methods, vertebrae detection serving as the first step, tends to be affected by the pathology and metal implants. Thus, imprecise detections cause biased patches before segmentation, which then leads to inaccurate contour delineation and inconsistent segmentation. In our work, we intend to label individual and complete binary masks to address that challenge. Specifically, a contour generation network is proposed based on Structural Low-Rank Descriptors for shape consistency, termed SLoRD. For a structural representation of vertebral contours, we adopt the spherical coordinate system and devise the spherical centroid to calculate contour descriptors. Due to vertebrae's similar appearances, basic contour descriptors can be acquired to restore original contours. Therefore, SLoRD leverages these contour priors and explicit shape constraints to facilitate regressed contour points close to vertebral surfaces. Quantitative and qualitative evaluations on VerSe 2019 and 2020 demonstrate the superior performance of our framework over other single-stage and multi-stage state-of-the-art (SOTA) methods. Further, SLoRD is a plug-and-play framework to refine the segmentation inconsistency existing in coarse predictions from other approaches., Comment: Under review

Understanding of video creativity and content often varies among individuals, with differences in focal points and cognitive levels across different ages, experiences, and genders. There is currently a lack of research in this area, and most existing benchmarks suffer from several drawbacks: 1) a limited number of modalities and answers with restrictive length; 2) the content and scenarios within the videos are excessively monotonous, transmitting allegories and emotions that are overly simplistic. To bridge the gap to real-world applications, we introduce a large-scale Subjective Response Indicators for Advertisement Videos dataset, namely SRI-ADV. Specifically, we collected real changes in Electroencephalographic (EEG) and eye-tracking regions from different demographics while they viewed identical video content. Utilizing this multi-modal dataset, we developed tasks and protocols to analyze and evaluate the extent of cognitive understanding of video content among different users. Along with the dataset, we designed a Hypergraph Multi-modal Large Language Model (HMLLM) to explore the associations among different demographics, video elements, EEG, and eye-tracking indicators. HMLLM could bridge semantic gaps across rich modalities and integrate information beyond different modalities to perform logical reasoning. Extensive experimental evaluations on SRI-ADV and other additional video-based generative performance benchmarks demonstrate the effectiveness of our method. The codes and dataset will be released at https://github.com/mininglamp-MLLM/HMLLM., Comment: Accepted by ACM MULTIMEDIA 2024

Detecting the coalescences of massive black hole binaries (MBHBs) is one of the primary targets for space-based gravitational wave observatories such as LISA, Taiji, and Tianqin. The fast and accurate parameter estimation of merging MBHBs is of great significance for both astrophysics and the global fitting of all resolvable sources. However, such analyses entail significant computational costs. To address these challenges, inspired by the latest progress in generative models, we proposed a novel artificial intelligence (AI) based parameter estimation method called Variance Preserving Flow Matching Posterior Estimation (VPFMPE). Specifically, we utilize triangular interpolation to maintain variance over time, thereby constructing a transport path for training continuous normalization flows. Compared to the simple linear interpolation method used in flow matching to construct the optimal transport path, our approach better captures continuous temporal variations, making it more suitable for the parameter estimation of MBHBs. Additionally, we creatively introduce a parameter transformation method based on the symmetry in the detector's response function. This transformation is integrated within VPFMPE, allowing us to train the model using a simplified dataset, and then perform parameter estimation on more general data, hence also acting as a crucial factor in improving the training speed. In conclusion, for the first time, within a comprehensive and reasonable parameter range, we have achieved a complete and unbiased 11-dimensional rapid inference for MBHBs in the presence of astrophysical confusion noise using ODE-based generative models. In the experiments based on simulated data, our model produces posterior distributions comparable to those obtained by nested sampling.

Automatic drone landing is an important step for achieving fully autonomous drones. Although there are many works that leverage GPS, video, wireless signals, and active acoustic sensing to perform precise landing, autonomous drone landing remains an unsolved challenge for palm-sized microdrones that may not be able to support the high computational requirements of vision, wireless, or active audio sensing. We propose AIRA, a low-cost infrared light-based platform that targets precise and efficient landing of low-resource microdrones. AIRA consists of an infrared light bulb at the landing station along with an energy efficient hardware photodiode (PD) sensing platform at the bottom of the drone. AIRA costs under 83 USD, while achieving comparable performance to existing vision-based methods at a fraction of the energy cost. AIRA requires only three PDs without any complex pattern recognition models to accurately land the drone, under $10$cm of error, from up to $11.1$ meters away, compared to camera-based methods that require recognizing complex markers using high resolution images with a range of only up to $1.2$ meters from the same height. Moreover, we demonstrate that AIRA can accurately guide drones in low light and partial non line of sight scenarios, which are difficult for traditional vision-based approaches.

Controllability and proactivity are crucial properties of autonomous conversational agents (CAs). Controllability requires the CAs to follow the standard operating procedures (SOPs), such as verifying identity before activating credit cards. Proactivity requires the CAs to guide the conversation towards the goal during user uncooperation, such as persuasive dialogue. Existing research cannot be unified with controllability, proactivity, and low manual annotation. To bridge this gap, we propose a new framework for planning-based conversational agents (PCA) powered by large language models (LLMs), which only requires humans to define tasks and goals for the LLMs. Before conversation, LLM plans the core and necessary SOP for dialogue offline. During the conversation, LLM plans the best action path online referring to the SOP, and generates responses to achieve process controllability. Subsequently, we propose a semi-automatic dialogue data creation framework and curate a high-quality dialogue dataset (PCA-D). Meanwhile, we develop multiple variants and evaluation metrics for PCA, e.g., planning with Monte Carlo Tree Search (PCA-M), which searches for the optimal dialogue action while satisfying SOP constraints and achieving the proactive of the dialogue. Experiment results show that LLMs finetuned on PCA-D can significantly improve the performance and generalize to unseen domains. PCA-M outperforms other CoT and ToT baselines in terms of conversation controllability, proactivity, task success rate, and overall logical coherence, and is applicable in industry dialogue scenarios. The dataset and codes are available at XXXX.

This report describes the submitted system to the In-Car Multi-Channel Automatic Speech Recognition (ICMC-ASR) challenge, which considers the ASR task with multi-speaker overlapping and Mandarin accent dynamics in the ICMC case. We implement the front-end speaker diarization using the self-supervised learning representation based multi-speaker embedding and beamforming using the speaker position, respectively. For ASR, we employ an iterative pseudo-label generation method based on fusion model to obtain text labels of unsupervised data. To mitigate the impact of accent, an Accent-ASR framework is proposed, which captures pronunciation-related accent features at a fine-grained level and linguistic information at a coarse-grained level. On the ICMC-ASR eval set, the proposed system achieves a CER of 13.16% on track 1 and a cpCER of 21.48% on track 2, which significantly outperforms the official baseline system and obtains the first rank on both tracks., Comment: Accepted at ICASSP 2024

Multi-wavelength switchable single-frequency microlasers in a broad spectral range are highly desirable for integrated photonic applications due to their dynamic switching functionality, narrow linewidth, and high side-mode-suppression-ratio (SMSR). Here, a strategy based on highly efficient successive excitation of different stimulated multi-photon hyper-Raman scattering (SMPHRS) processes is proposed to generate multi-wavelength switchable single-frequency hyper-Raman microlasers. This is achieved through collective precise dispersion management for arranging excitation wavelengths to trigger different phase-matched SMPHRS processes in order, mode-hopping-free tuning of the pump wavelength within a wide range of 0.75 nm by leveraging strong thermo-optical broadening of ultra-high Q modes, and simultaneously suppressing harmonics generation in a lithium niobate microcavity with high second-order nonlinearity. As a result, under continuous-wave laser pump at a low level of only 3.9 mW, SMPHRS processes from two- to five-photons emerged step by step and almost depleted previously generated multi-photon Raman signal. Consequently, four-wavelength dynamically switchable single-mode lasing from near infrared (857 nm) to ultraviolet (350 nm) spanning beyond the record range (~500 nm) with high SMSRs >35 dB is reported., Comment: 17 pages,5 figures, and 1 table

With the widespread adoption of blockchain technology, the transaction fee mechanism (TFM) in blockchain systems has become a prominent research topic. An ideal TFM should satisfy user incentive compatibility (UIC), miner incentive compatibility (MIC), and miner-user side contract proofness ($c$-SCP). However, state-of-the-art works either fail to meet these three properties simultaneously or only satisfy them under certain conditions. In this paper, we propose a burning $N$-price auction TFM named BNP. This mechanism divides the transaction fee into a base fee, which is burned, and a priority fee, which is allocated to miners. Theoretical proofs and experimental analyses demonstrate that, even under conditions of significant transaction congestion, this mechanism satisfies UIC, MIC, and $c$-SCP simultaneously. Furthermore, the BNP mechanism is not constrained by the type of blockchain consensus, making it widely applicable.

We present the phase-connected timing solutions of all the five pulsars in globular cluster (GC) M3 (NGC 5272), namely PSRs M3A to F (PSRs J1342+2822A to F), with the exception of PSR M3C, from FAST archival data. In these timing solutions, those of PSRs M3E, and F are obtained for the first time. We find that PSRs M3E and F have low mass companions, and are in circular orbits with periods of 7.1 and 3.0 days, respectively. For PSR M3C, we have not detected it in all the 41 observations. We found no X-ray counterparts for these pulsars in archival Chandra images in the band of 0.2-20 keV. We noticed that the pulsars in M3 seem to be native. From the Auto-Correlation Function (ACF) analysis of the M3A's and M3B's dynamic spectra, the scintillation timescale ranges from $7.0\pm0.3$ min to $60.0\pm0.6$ min, and the scintillation bandwidth ranges from $4.6\pm0.2$ MHz to $57.1\pm1.1$ MHz. The measured scintillation bandwidths from the dynamic spectra indicate strong scintillation, and the scattering medium is anisotropic. From the secondary spectra, we captured a scintillation arc only for PSR M3B with a curvature of $649\pm23 {\rm m}^{-1} {\rm mHz}^{-2}$., Comment: 14 pages, 4 figures, accepted for publication in The Astrophysical Journal

The combination of deep learning and ab initio materials calculations is emerging as a trending frontier of materials science research, with deep-learning density functional theory (DFT) electronic structure being particularly promising. In this work, we introduce a neural-network method for modeling the DFT density matrix, a fundamental yet previously unexplored quantity in deep-learning electronic structure. Utilizing an advanced neural network framework that leverages the nearsightedness and equivariance properties of the density matrix, the method demonstrates high accuracy and excellent generalizability in multiple example studies, as well as capability to precisely predict charge density and reproduce other electronic structure properties. Given the pivotal role of the density matrix in DFT as well as other computational methods, the current research introduces a novel approach to the deep-learning study of electronic structure properties, opening up new opportunities for deep-learning enhanced computational materials study.

Generative retrieval, which has demonstrated effectiveness in text-to-text retrieval, utilizes a sequence-to-sequence model to directly generate candidate identifiers based on natural language queries. Without explicitly computing the similarity between queries and candidates, generative retrieval surpasses dual-tower models in both speed and accuracy on large-scale corpora, providing new insights for cross-modal retrieval. However, constructing identifiers for multimodal data remains an untapped problem, and the modality gap between natural language queries and multimodal candidates hinders retrieval performance due to the absence of additional encoders. To this end, we propose a pioneering generAtive Cross-modal rEtrieval framework (ACE), which is a comprehensive framework for end-to-end cross-modal retrieval based on coarse-to-fine semantic modeling. We propose combining K-Means and RQ-VAE to construct coarse and fine tokens, serving as identifiers for multimodal data. Correspondingly, we design the coarse-to-fine feature fusion strategy to efficiently align natural language queries and candidate identifiers. ACE is the first work to comprehensively demonstrate the feasibility of generative approach on text-to-image/audio/video retrieval, challenging the dominance of the embedding-based dual-tower architecture. Extensive experiments show that ACE achieves state-of-the-art performance in cross-modal retrieval and outperforms the strong baselines on Recall@1 by 15.27% on average.

This demo showcases a simple tool that utilizes AIGC technology, enabling both professional designers and regular users to easily customize clothing for their digital avatars. Customization options include changing clothing colors, textures, logos, and patterns. Compared with traditional 3D modeling processes, our approach significantly enhances efficiency and interactivity and reduces production costs.

We propose an efficacious approach to derive the generalized parton distributions for the pion and proton, based upon prior knowledge of their respective parton distribution functions (PDFs). Our method leverages on integral representations of the electromagnetic form factors derived from the light-front holographic QCD (LFHQCD) formalism, coupled with PDFs computed from continuum Schwinger functional methods at the hadronic scale. Using these techniques, we calculate gravitational form factors and associated mass distributions for each hadron. Remarkably, our calculations yield results that closely match recent lattice QCD simulations conducted near the physical pion mass. This work not only deepens our understanding of hadronic structure but also highlights the efficacy of the LFHQCD approach in modeling fundamental properties of hadrons., Comment: 6 pages, 5 figures

Previous foundation models for retinal images were pre-trained with limited disease categories and knowledge base. Here we introduce RetiZero, a vision-language foundation model that leverages knowledge from over 400 fundus diseases. To RetiZero's pre-training, we compiled 341,896 fundus images paired with text descriptions, sourced from public datasets, ophthalmic literature, and online resources, encompassing a diverse range of diseases across multiple ethnicities and countries. RetiZero exhibits superior performance in several downstream tasks, including zero-shot disease recognition, image-to-image retrieval, and internal- and cross-domain disease identification. In zero-shot scenarios, RetiZero achieves Top5 accuracy scores of 0.8430 for 15 fundus diseases and 0.7561 for 52 fundus diseases. For image retrieval, it achieves Top5 scores of 0.9500 and 0.8860 for the same disease sets, respectively. Clinical evaluations show that RetiZero's Top3 zero-shot performance surpasses the average of 19 ophthalmologists from Singapore, China and the United States. Furthermore, RetiZero significantly enhances clinicians' accuracy in diagnosing fundus disease. These findings underscore the value of integrating the RetiZero foundation model into clinical settings, where a variety of fundus diseases are encountered.

Industrial manipulators have extensively collaborated with human operators to execute tasks, e.g., disassembly of end-of-use products, in intelligent remanufacturing. A safety task execution requires real-time path planning for the manipulator's end-effector to autonomously avoid human operators. This is even more challenging when the end-effector needs to follow a planned path while avoiding the collision between the manipulator body and human operators, which is usually computationally expensive and limits real-time application. This paper proposes an efficient hybrid motion planning algorithm that consists of an A$^*$ algorithm and an online manipulator reconfiguration mechanism (OMRM) to tackle such challenges in task and configuration spaces respectively. The A$^*$ algorithm is first leveraged to plan the shortest collision-free path of the end-effector in task space. When the manipulator body is risky to the human operator, our OMRM then selects an alternative joint configuration with minimum reconfiguration effort from a database to assist the manipulator to follow the planned path and avoid the human operator simultaneously. The database of manipulator reconfiguration establishes the relationship between the task and configuration space offline using forward kinematics, and is able to provide multiple reconfiguration candidates for a desired end-effector's position. The proposed new hybrid algorithm plans safe manipulator motion during the whole task execution. Extensive numerical and experimental studies, as well as comparison studies between the proposed one and the state-of-the-art ones, have been conducted to validate the proposed motion planning algorithm.

In this paper, we present ControlSpeech, a text-to-speech (TTS) system capable of fully cloning the speaker's voice and enabling arbitrary control and adjustment of speaking style, merely based on a few seconds of audio prompt and a simple textual style description prompt. Prior zero-shot TTS models and controllable TTS models either could only mimic the speaker's voice without further control and adjustment capabilities or were unrelated to speaker-specific voice generation. Therefore, ControlSpeech focuses on a more challenging new task-a TTS system with controllable timbre, content, and style at the same time. ControlSpeech takes speech prompts, content prompts, and style prompts as inputs and utilizes bidirectional attention and mask-based parallel decoding to capture corresponding codec representations in a discrete decoupling codec space. Moreover, we discovered the issue of text style controllability in a many-to-many mapping fashion and proposed the Style Mixture Semantic Density (SMSD) model to resolve this problem. SMSD module which is based on Gaussian mixture density networks, is designed to enhance the fine-grained partitioning and sampling capabilities of style semantic information and generate speech with more diverse styles. In terms of experiments, we make available a controllable model toolkit called ControlToolkit with a new style controllable dataset, some replicated baseline models and propose new metrics to evaluate both the control capability and the quality of generated audio in ControlSpeech. The relevant ablation studies validate the necessity of each component in ControlSpeech is necessary. We hope that ControlSpeech can establish the next foundation paradigm of controllable speech synthesis. The relevant code and demo are available at https://github.com/jishengpeng/ControlSpeech .

Near-space airship-borne communication network is recognized to be an indispensable component of the future integrated ground-air-space network thanks to airships' advantage of long-term residency at stratospheric altitudes, but it urgently needs reliable and efficient Airship-to-X link. To improve the transmission efficiency and capacity, this paper proposes to integrate semantic communication with massive multiple-input multiple-output (MIMO) technology. Specifically, we propose a deep joint semantic coding and beamforming (JSCBF) scheme for airship-based massive MIMO image transmission network in space, in which semantics from both source and channel are fused to jointly design the semantic coding and physical layer beamforming. First, we design two semantic extraction networks to extract semantics from image source and channel state information, respectively. Then, we propose a semantic fusion network that can fuse these semantics into complex-valued semantic features for subsequent physical-layer transmission. To efficiently transmit the fused semantic features at the physical layer, we then propose the hybrid data and model-driven semantic-aware beamforming networks. At the receiver, a semantic decoding network is designed to reconstruct the transmitted images. Finally, we perform end-to-end deep learning to jointly train all the modules, using the image reconstruction quality at the receivers as a metric. The proposed deep JSCBF scheme fully combines the efficient source compressibility and robust error correction capability of semantic communication with the high spectral efficiency of massive MIMO, achieving a significant performance improvement over existing approaches., Comment: Major Revision by IEEE JSAC

Digital watermarking methods are commonly used to safeguard digital media copyrights by confirming ownership and deterring unauthorized use. However, without reliable third-party oversight, these methods risk security vulnerabilities during watermark extraction. Furthermore, digital media lacks tangible ownership attributes, posing challenges for secure copyright transfer and tracing. This study introduces DataSafe, a copyright protection scheme that combines physical unclonable functions (PUFs) and blockchain technology. PUF devices use their unique fingerprints for blockchain registration. Subsequently, these devices incorporate invisible watermarking techniques to embed digital watermarks into media for copyright protection. The watermark verification process is confined within the devices, preserving confidentiality during extraction, validating identities during copyright exchanges, and facilitating blockchain-based traceability of copyright transfers. The implementation of a prototype system on the LPC55S69-EVK development board is detailed, illustrating the practicality and effectiveness of the proposed solution.

We present the discovery of 8 isolated millisecond pulsars in Globular Cluster (GC) NGC 6517 using the Five-Hundred-meter Aperture Spherical radio Telescope (FAST). The spin periods of those pulsars (namely PSR J1801-0857K to R, or, NGC 6517K to R) are all shorter than 10 ms. With these discoveries, NGC 6517 is currently the GC with the most known pulsars in the FAST sky. The largest difference in dispersion measure of the pulsars in NGC 6517 is 11.2 cm$^{-3}$ pc, the second among all GCs. The fraction of isolated pulsars in this GC (16 of 17, 94$\%$) is consistent with previous studies indicating an overabundance of isolated pulsars in the densest GCs, especially in those undergoing cluster core collapse. Considering the FAST GC pulsar discoveries, we modeled the GC pulsar population using the empirical Bayesian method described by Turk and Lorimer with the recent counts. Using this approach, we find that the expected number of potential pulsars in GCs seems to be correlated with the central escape velocity, hence, the GCs Liller 1, NGC 6441, M54 (NGC 6715), and $\omega$-Cen (NGC 5139) are expected to host the largest numbers of pulsars., Comment: 21 pages, 2 figures, accepted for publication in The Astrophysical Journal Letters

While large multi-modal models (LMMs) have exhibited impressive capabilities across diverse tasks, their effectiveness in handling complex tasks has been limited by the prevailing single-step reasoning paradigm. To this end, this paper proposes VoCoT, a multi-step Visually grounded object-centric Chain-of-Thought reasoning framework tailored for inference with LMMs. VoCoT is characterized by two key features: (1) object-centric reasoning paths that revolve around cross-modal shared object-level information, and (2) visually grounded representation of object concepts in a multi-modal interleaved and aligned manner, which effectively bridges the modality gap within LMMs during long-term generation. Additionally, we construct an instruction dataset to facilitate LMMs in adapting to reasoning with VoCoT. By introducing VoCoT into the prevalent open-source LMM architecture, we introduce VolCano. With only 7B parameters and limited input resolution, VolCano demonstrates excellent performance across various scenarios, surpassing SOTA models, including GPT-4V, in tasks requiring complex reasoning. Our code, data and model will be available at https://github.com/RupertLuo/VoCoT.

Open source software (OSS) has been playing a fundamental role in not only information technology but also our social lives. Attracted by various advantages of OSS, increasing commercial companies take extensive participation in open source development and have had a broad impact. This paper provides a comprehensive systematic literature review (SLR) of existing research on company participation in OSS. We collected 92 papers and organized them based on their research topics, which cover three main directions, i.e., participation motivation, contribution model, and impact on OSS development. We found the explored motivations of companies are mainly from economic, technological, and social aspects. Existing studies categorize companies' contribution models in OSS projects mainly through their objectives and how they shape OSS communities. Researchers also explored how commercial participation affects OSS development. We conclude with research challenges and promising research directions on commercial participation in OSS. This study contributes to a comprehensive understanding of commercial participation in OSS development.

As the size and context length of Large Language Models (LLMs) grow, weight-activation quantization has emerged as a crucial technique for efficient deployment of LLMs. Compared to weight-only quantization, weight-activation quantization presents greater challenges due to the presence of outliers in activations. Existing methods have made significant progress by exploring mixed-precision quantization and outlier suppression. However, these methods primarily focus on optimizing the results of single matrix multiplication, neglecting the bidirectional propagation of quantization errors in LLMs. Specifically, errors accumulate vertically within the same token through layers, and diffuse horizontally across different tokens due to self-attention mechanisms. To address this issue, we introduce BiSup, a Bidirectional quantization error Suppression method. By constructing appropriate optimizable parameter spaces, BiSup utilizes a small amount of data for quantization-aware parameter-efficient fine-tuning to suppress the error vertical accumulation. Besides, BiSup employs prompt mixed-precision quantization strategy, which preserves high precision for the key-value cache of system prompts, to mitigate the error horizontal diffusion. Extensive experiments on Llama and Qwen families demonstrate that BiSup can improve performance over two state-of-the-art methods (the average WikiText2 perplexity decreases from 13.26 to 9.41 for Atom and from 14.33 to 7.85 for QuaRot under the W3A3-g128 configuration), further facilitating the practical applications of low-bit weight-activation quantization.

Generative retrieval, a promising new paradigm in information retrieval, employs a seq2seq model to encode document features into parameters and decode relevant document identifiers (IDs) based on search queries. Existing generative retrieval solutions typically rely on a preprocessing stage to pre-define document IDs, which can suffer from a semantic gap between these IDs and the retrieval task. However, end-to-end training for both ID assignments and retrieval tasks is challenging due to the long-tailed distribution characteristics of real-world data, resulting in inefficient and unbalanced ID space utilization. To address these issues, we propose ASI++, a novel fully end-to-end generative retrieval method that aims to simultaneously learn balanced ID assignments and improve retrieval performance. ASI++ builds on the fully end-to-end training framework of vanilla ASI and introduces several key innovations. First, a distributionally balanced criterion addresses the imbalance in ID assignments, promoting more efficient utilization of the ID space. Next, a representation bottleneck criterion enhances dense representations to alleviate bottlenecks in learning ID assignments. Finally, an information consistency criterion integrates these processes into a joint optimization framework grounded in information theory. We further explore various module structures for learning ID assignments, including neural quantization, differentiable product quantization, and residual quantization. Extensive experiments on both public and industrial datasets demonstrate the effectiveness of ASI++ in improving retrieval performance and achieving balanced ID assignments.

A signed graph $\Sigma=(G,\sigma)$ consists of an underlying graph $G=(V,E)$ with a sign function $\sigma:E\rightarrow\{-1,1\}$. Let $A(\Sigma)$ be the adjacency matrix of $\Sigma$ and $\lambda_1(\Sigma)$ denote the largest eigenvalue (index) of $\Sigma$.Define $(K_n,H^-)$ as a signed complete graph whose negative edges induce a subgraph $H$. In this paper, we focus on the following problem: which spanning tree $T$ with a given number of pendant vertices makes the $\lambda_1(A(\Sigma))$ of the unbalanced $(K_n,T^-)$ as large as possible? To answer the problem, we characterize the extremal signed graph with maximum $\lambda_1(A(\Sigma))$ among graphs of type $(K_n,T^-)$.

There has been a growing utilization of industrial robots as complementary collaborators for human workers in re-manufacturing sites. Such a human-robot collaboration (HRC) aims to assist human workers in improving the flexibility and efficiency of labor-intensive tasks. In this paper, we propose a human-aware motion planning framework for HRC to effectively compute collision-free motions for manipulators when conducting collaborative tasks with humans. We employ a neural human motion prediction model to enable proactive planning for manipulators. Particularly, rather than blindly trusting and utilizing predicted human trajectories in the manipulator planning, we quantify uncertainties of the neural prediction model to further ensure human safety. Moreover, we integrate the uncertainty-aware prediction into a graph that captures key workspace elements and illustrates their interconnections. Then a graph neural network is leveraged to operate on the constructed graph. Consequently, robot motion planning considers both the dependencies among all the elements in the workspace and the potential influence of future movements of human workers. We experimentally validate the proposed planning framework using a 6-degree-of-freedom manipulator in a shared workspace where a human is performing disassembling tasks. The results demonstrate the benefits of our approach in terms of improving the smoothness and safety of HRC. A brief video introduction of this work is available as the supplemental materials.