Search

Monitoring and fostering research aligned with the Sustainable Development Goals (SDGs) is crucial for formulating evidence-based policies, identifying best practices, and promoting global collaboration. The key step is developing a labeling system to map research publications to their related SDGs. The SDGs labeling system integrated in Web of Science (WoS), which assigns citation topics instead of individual publication to SDGs, has emerged as a promising tool.However we still lack of a comprehensive evaluation of the performance of WoS labeling system. By comparing with the Bergon approach, we systematically assessed the relatedness between citation topics and SDGs. Our analysis identified 15% of topics showing low relatedness to their assigned SDGs at a 1% threshold. Notably, SDGs such as '11 Cities', '07 Energy', and '13 Climate' exhibited higher percentages of low related topics. In addition, we revealed that certain topics are significantly underrepresented in their relevant SDGs, particularly for '02 Hunger', '12 Consumption', and '15 Land'. This study underscores the critical need for continual refinement and validation of SDGs labeling systems in WoS.

A Software Bill of Materials (SBoM) is a detailed inventory of all components, libraries, and modules in a software artifact, providing traceability throughout the software supply chain. With the increasing popularity of JavaScript in software engineering due to its dynamic syntax and seamless supply chain integration, the exposure to vulnerabilities and attacks has risen significantly. A JavaScript application bundle, which is a consolidated, symbol-stripped, and optimized assembly of code for deployment purpose. Generating a SBoM from a JavaScript application bundle through a reverse-engineering process ensures the integrity, security, and compliance of the supplier's software release, even without access to the original dependency graphs. This paper presents the first study on SBoM generation for JavaScript application bundles. We identify three key challenges for this task, i.e., nested code scopes, extremely long sequences, and large retrieval spaces. To address these challenges, we introduce Chain-of-Experts (CoE), a multi-task deep learning model designed to generate SBoMs through three tasks: code segmentation, code classification, and code clone retrieval. We evaluate CoE against individual task-specific solutions on 500 web application bundles with over 66,000 dependencies. Our experimental results demonstrate that CoE offers competitive outcomes with less training and inference time when compared with combined individual task-specific solutions. Consequently, CoE provides the first scalable, efficient, and end-to-end solution for the SBoM generation of real-world JavaScript application bundles.

3D point clouds are essential for perceiving outdoor scenes, especially within the realm of autonomous driving. Recent advances in 3D LiDAR Object Detection focus primarily on the spatial positioning and distribution of points to ensure accurate detection. However, despite their robust performance in variable conditions, these methods are hindered by their sole reliance on coordinates and point intensity, resulting in inadequate isometric invariance and suboptimal detection outcomes. To tackle this challenge, our work introduces Transformation-Invariant Local (TraIL) features and the associated TraIL-Det architecture. Our TraIL features exhibit rigid transformation invariance and effectively adapt to variations in point density, with a design focus on capturing the localized geometry of neighboring structures. They utilize the inherent isotropic radiation of LiDAR to enhance local representation, improve computational efficiency, and boost detection performance. To effectively process the geometric relations among points within each proposal, we propose a Multi-head self-Attention Encoder (MAE) with asymmetric geometric features to encode high-dimensional TraIL features into manageable representations. Our method outperforms contemporary self-supervised 3D object detection approaches in terms of mAP on KITTI (67.8, 20% label, moderate) and Waymo (68.9, 20% label, moderate) datasets under various label ratios (20%, 50%, and 100%)., Comment: BMVC 2024; 15 pages, 3 figures, 3 tables; Code at https://github.com/l1997i/rapid_seg

In video lane detection, there are rich temporal contexts among successive frames, which is under-explored in existing lane detectors. In this work, we propose LaneTCA to bridge the individual video frames and explore how to effectively aggregate the temporal context. Technically, we develop an accumulative attention module and an adjacent attention module to abstract the long-term and short-term temporal context, respectively. The accumulative attention module continuously accumulates visual information during the journey of a vehicle, while the adjacent attention module propagates this lane information from the previous frame to the current frame. The two modules are meticulously designed based on the transformer architecture. Finally, these long-short context features are fused with the current frame features to predict the lane lines in the current frame. Extensive quantitative and qualitative experiments are conducted on two prevalent benchmark datasets. The results demonstrate the effectiveness of our method, achieving several new state-of-the-art records. The codes and models are available at https://github.com/Alex-1337/LaneTCA

With the growing importance of sustainable development goals (SDGs), various labeling systems have emerged for effective monitoring and evaluation. This study assesses six labeling systems across 1.85 million documents at both paper level and topic level. Our findings indicate that the SDGO and SDSN systems are more aggressive, while systems such as Auckland, Aurora, SIRIS, and Elsevier exhibit significant topic consistency, with similarity scores exceeding 0.75 for most SDGs. However, similarities at the paper level generally fall short, particularly for specific SDGs like SDG 10. We highlight the crucial role of contextual information in keyword-based labeling systems, noting that overlooking context can introduce bias in the retrieval of papers (e.g., variations in "migration" between biomedical and geographical contexts). These results reveal substantial discrepancies among SDG labeling systems, emphasizing the need for improved methodologies to enhance the accuracy and relevance of SDG evaluations., Comment: 17 pages, 6 figures

Finding optimal control strategies to suppress quantum thermalization for arbitrarily initial states, the so-called quantum nonergodicity control, is important for quantum information science and technologies. Previous control methods largely relied on theoretical model of the target quantum system, but invertible model approximations and inaccuracies can lead to control failures. We develop a model-free and deep-reinforcement learning (DRL) framework for quantum nonergodicity control. It is a machine-learning method with the unique focus on balancing exploration and exploitation strategies to maximize the cumulative rewards so as to preserve the initial memory in the time-dependent nonergodic metrics over a long stretch of time. We use the paradigmatic one-dimensional tilted Fermi-Hubbard system to demonstrate that the DRL agent can efficiently learn the quantum many-body system solely through the interactions with the environment. The optimal policy obtained by the DRL provides broader control scenarios for managing nonergodicity in the phase diagram as compared to, e.g., the specific protocol for Wannier-Stark localization. The continuous control protocols and observations are experimentally feasible. The model-free nature of DRL and its versatile search space for control functions render promising nonergodicity control in more complex quantum many-body systems., Comment: 19 pages, 8 figures

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

Federated Learning (FL) emerges as a new learning paradigm that enables multiple devices to collaboratively train a shared model while preserving data privacy. However, intensive memory footprint during the training process severely bottlenecks the deployment of FL on resource-constrained devices in real-world cases. In this paper, we propose NeuLite, a framework that breaks the memory wall through elastic progressive training. Unlike traditional FL, which updates the full model during the whole training procedure, NeuLite divides the model into blocks and conducts the training process in a progressive manner. Except for the progressive training paradigm, NeuLite further features the following two key components to guide the training process: 1) curriculum mentor and 2) training harmonizer. Specifically, the Curriculum Mentor devises curriculum-aware training losses for each block, assisting them in learning the expected feature representation and mitigating the loss of valuable information. Additionally, the Training Harmonizer develops a parameter co-adaptation training paradigm to break the information isolation across blocks from both forward and backward propagation. Furthermore, it constructs output modules for each block to strengthen model parameter co-adaptation. Extensive experiments are conducted to evaluate the effectiveness of NeuLite across both simulation and hardware testbeds. The results demonstrate that NeuLite effectively reduces peak memory usage by up to 50.4%. It also enhances model performance by up to 84.2% and accelerates the training process by up to 1.9X.

In this paper, we propose SmartFreeze, a framework that effectively reduces the memory footprint by conducting the training in a progressive manner. Instead of updating the full model in each training round, SmartFreeze divides the shared model into blocks consisting of a specified number of layers. It first trains the front block with a well-designed output module, safely freezes it after convergence, and then triggers the training of the next one. This process iterates until the whole model has been successfully trained. In this way, the backward computation of the frozen blocks and the corresponding memory space for storing the intermediate outputs and gradients are effectively saved. Except for the progressive training framework, SmartFreeze consists of the following two core components: a pace controller and a participant selector. The pace controller is designed to effectively monitor the training progress of each block at runtime and safely freezes them after convergence while the participant selector selects the right devices to participate in the training for each block by jointly considering the memory capacity, the statistical and system heterogeneity. Extensive experiments are conducted to evaluate the effectiveness of SmartFreeze on both simulation and hardware testbeds. The results demonstrate that SmartFreeze effectively reduces average memory usage by up to 82%. Moreover, it simultaneously improves the model accuracy by up to 83.1% and accelerates the training process up to 2.02X., Comment: Published as a conference paper at IWQoS 2024

Deep video compression has made remarkable process in recent years, with the majority of advancements concentrated on P-frame coding. Although efforts to enhance B-frame coding are ongoing, their compression performance is still far behind that of traditional bi-directional video codecs. In this paper, we introduce a bi-directional deep contextual video compression scheme tailored for B-frames, termed DCVC-B, to improve the compression performance of deep B-frame coding. Our scheme mainly has three key innovations. First, we develop a bi-directional motion difference context propagation method for effective motion difference coding, which significantly reduces the bit cost of bi-directional motions. Second, we propose a bi-directional contextual compression model and a corresponding bi-directional temporal entropy model, to make better use of the multi-scale temporal contexts. Third, we propose a hierarchical quality structure-based training strategy, leading to an effective bit allocation across large groups of pictures (GOP). Experimental results show that our DCVC-B achieves an average reduction of 26.6% in BD-Rate compared to the reference software for H.265/HEVC under random access conditions. Remarkably, it surpasses the performance of the H.266/VVC reference software on certain test datasets under the same configuration.

We investigate the internal dynamics of hairy black holes in the Einstein-Maxwell-vector theory. The development of the charged vector hair necessarily removes the inner Cauchy horizon and results in an anisotropic black hole ending at a spacelike singularity. The far interior evolution is characterized by the chaotic alternations among different Kasner epochs. We show that those late interior time dynamics of bounces and epochs can be captured analytically. In particular, we obtain three distinct types of transformation laws for the alternation of Kasner epochs analytically, including the Kasner inversion, Kasner transition, and Kasner reflection. Our analytical approach is corroborated by numerical solutions to the full equations of motion. Moreover, we provide a clear explanation of the alternation of Kasner epochs found numerically in the literature., Comment: 21 pages, 3 figures

Large language models (LLMs) have achieved unprecedented success in the field of natural language processing. However, the black-box nature of their internal mechanisms has brought many concerns about their trustworthiness and interpretability. Recent research has discovered a class of abnormal tokens in the model's vocabulary space and named them "glitch tokens". Those tokens, once included in the input, may induce the model to produce incorrect, irrelevant, or even harmful results, drastically undermining the reliability and practicality of LLMs. In this work, we aim to enhance the understanding of glitch tokens and propose techniques for their detection and mitigation. We first reveal the characteristic features induced by glitch tokens on LLMs, which are evidenced by significant deviations in the distributions of attention patterns and dynamic information from intermediate model layers. Based on the insights, we develop GlitchProber, a tool for efficient glitch token detection and mitigation. GlitchProber utilizes small-scale sampling, principal component analysis for accelerated feature extraction, and a simple classifier for efficient vocabulary screening. Taking one step further, GlitchProber rectifies abnormal model intermediate layer values to mitigate the destructive effects of glitch tokens. Evaluated on five mainstream open-source LLMs, GlitchProber demonstrates higher efficiency, precision, and recall compared to existing approaches, with an average F1 score of 0.86 and an average repair rate of 50.06%. GlitchProber unveils a novel path to address the challenges posed by glitch tokens and inspires future research toward more robust and interpretable LLMs.

Neural code generation systems have recently attracted increasing attention to improve developer productivity and speed up software development. Typically, these systems maintain a pre-trained neural model and make it available to general users as a service (e.g., through remote APIs) and incorporate a feedback mechanism to extensively collect and utilize the users' reaction to the generated code, i.e., user feedback. However, the security implications of such feedback have not yet been explored. With a systematic study of current feedback mechanisms, we find that feedback makes these systems vulnerable to feedback data injection (FDI) attacks. We discuss the methodology of FDI attacks and present a pre-attack profiling strategy to infer the attack constraints of a targeted system in the black-box setting. We demonstrate two proof-of-concept examples utilizing the FDI attack surface to implement prompt injection attacks and backdoor attacks on practical neural code generation systems. The attacker may stealthily manipulate a neural code generation system to generate code with vulnerabilities, attack payload, and malicious and spam messages. Our findings reveal the security implications of feedback mechanisms in neural code generation systems, paving the way for increasing their security., Comment: Accepted by ISSTA'24

Shadow detection is a fundamental and challenging task in many computer vision applications. Intuitively, most shadows come from the occlusion of light by the object itself, resulting in the object and its shadow being contiguous (referred to as the adjacent shadow in this paper). In this case, when the color of the object is similar to that of the shadow, existing methods struggle to achieve accurate detection. To address this problem, we present SwinShadow, a transformer-based architecture that fully utilizes the powerful shifted window mechanism for detecting adjacent shadows. The mechanism operates in two steps. Initially, it applies local self-attention within a single window, enabling the network to focus on local details. Subsequently, it shifts the attention windows to facilitate inter-window attention, enabling the capture of a broader range of adjacent information. These combined steps significantly improve the network's capacity to distinguish shadows from nearby objects. And the whole process can be divided into three parts: encoder, decoder, and feature integration. During encoding, we adopt Swin Transformer to acquire hierarchical features. Then during decoding, for shallow layers, we propose a deep supervision (DS) module to suppress the false positives and boost the representation capability of shadow features for subsequent processing, while for deep layers, we leverage a double attention (DA) module to integrate local and shifted window in one stage to achieve a larger receptive field and enhance the continuity of information. Ultimately, a new multi-level aggregation (MLA) mechanism is applied to fuse the decoded features for mask prediction. Extensive experiments on three shadow detection benchmark datasets, SBU, UCF, and ISTD, demonstrate that our network achieves good performance in terms of balance error rate (BER).

This paper introduces the Unique Citing Documents Journal Impact Factor(Uniq-JIF) as a supplement to the traditional Journal Impact Factor(JIF). The Uniq-JIF counts each citing document only once, aiming to reduce the effects of citation manipulations. Analysis of 2023 Journal Citation Reports data shows that for most journals, the Uniq-JIF is less than 20% lower than the JIF, though some journals show a drop of over 75%. The Uniq-JIF also highlights significant reductions for journals suppressed due to citation issues, indicating its effectiveness in identifying problematic journals. The Uniq-JIF offers a more nuanced view of a journal's influence and can help reveal journals needing further scrutiny., Comment: 2 figures

Let $(F,G)$ be a Jacobian pair with $d=w\text{-deg}(F)$ and $e=w\text{-deg}(G)$ for some direction $w$. A generalized Magnus' formula approximates $G$ as $\sum_{\gamma\ge 0} c_\gamma F^{\frac{e-\gamma}{d}}$ for some complex numbers $c_\gamma$. We develop an approach to the two-dimensional Jacobian conjecture, aiming to minimize the use of terms corresponding to $\gamma>0$. As an initial step in this approach, we define and study the inner polynomials of $F$ and $G$. The main result of this paper shows that the northeastern vertex of the Newton polygon of each inner polynomial is located within a specific region. As applications of this result, we introduce several conjectures and prove some of them for special cases.

Unanticipated runtime errors, lacking predefined handlers, can abruptly terminate execution and lead to severe consequences, such as data loss or system crashes. Despite extensive efforts to identify potential errors during the development phase, such unanticipated errors remain a challenge to to be entirely eliminated, making the runtime mitigation measurements still indispensable to minimize their impact. Automated self-healing techniques, such as reusing existing handlers, have been investigated to reduce the loss coming through with the execution termination. However, the usability of existing methods is retained by their predefined heuristic rules and they fail to handle diverse runtime errors adaptively. Recently, the advent of Large Language Models (LLMs) has opened new avenues for addressing this problem. Inspired by their remarkable capabilities in understanding and generating code, we propose to deal with the runtime errors in a real-time manner using LLMs. Specifically, we propose Healer, the first LLM-assisted self-healing framework for handling runtime errors. When an unhandled runtime error occurs, Healer will be activated to generate a piece of error-handling code with the help of its internal LLM and the code will be executed inside the runtime environment owned by the framework to obtain a rectified program state from which the program should continue its execution. Our exploratory study evaluates the performance of Healer using four different code benchmarks and three state-of-the-art LLMs, GPT-3.5, GPT-4, and CodeQwen-7B. Results show that, without the need for any fine-tuning, GPT-4 can successfully help programs recover from 72.8% of runtime errors, highlighting the potential of LLMs in handling runtime errors.

The emerging large models have achieved notable progress in the fields of natural language processing and computer vision. However, large models for neural video coding are still unexplored. In this paper, we try to explore how to build a large neural video coding model. Based on a small baseline model, we gradually scale up the model sizes of its different coding parts, including the motion encoder-decoder, motion entropy model, contextual encoder-decoder, contextual entropy model, and temporal context mining module, and analyze the influence of model sizes on video compression performance. Then, we explore to use different architectures, including CNN, mixed CNN-Transformer, and Transformer architectures, to implement the neural video coding model and analyze the influence of model architectures on video compression performance. Based on our exploration results, we design the first neural video coding model with more than 1 billion parameters -- NVC-1B. Experimental results show that our proposed large model achieves a significant video compression performance improvement over the small baseline model, and represents the state-of-the-art compression efficiency. We anticipate large models may bring up the video coding technologies to the next level.

Accurately and promptly predicting accidents among surrounding traffic agents from camera footage is crucial for the safety of autonomous vehicles (AVs). This task presents substantial challenges stemming from the unpredictable nature of traffic accidents, their long-tail distribution, the intricacies of traffic scene dynamics, and the inherently constrained field of vision of onboard cameras. To address these challenges, this study introduces a novel accident anticipation framework for AVs, termed CRASH. It seamlessly integrates five components: object detector, feature extractor, object-aware module, context-aware module, and multi-layer fusion. Specifically, we develop the object-aware module to prioritize high-risk objects in complex and ambiguous environments by calculating the spatial-temporal relationships between traffic agents. In parallel, the context-aware is also devised to extend global visual information from the temporal to the frequency domain using the Fast Fourier Transform (FFT) and capture fine-grained visual features of potential objects and broader context cues within traffic scenes. To capture a wider range of visual cues, we further propose a multi-layer fusion that dynamically computes the temporal dependencies between different scenes and iteratively updates the correlations between different visual features for accurate and timely accident prediction. Evaluated on real-world datasets--Dashcam Accident Dataset (DAD), Car Crash Dataset (CCD), and AnAn Accident Detection (A3D) datasets--our model surpasses existing top baselines in critical evaluation metrics like Average Precision (AP) and mean Time-To-Accident (mTTA). Importantly, its robustness and adaptability are particularly evident in challenging driving scenarios with missing or limited training data, demonstrating significant potential for application in real-world autonomous driving systems.

As autonomous driving systems increasingly become part of daily transportation, the ability to accurately anticipate and mitigate potential traffic accidents is paramount. Traditional accident anticipation models primarily utilizing dashcam videos are adept at predicting when an accident may occur but fall short in localizing the incident and identifying involved entities. Addressing this gap, this study introduces a novel framework that integrates Large Language Models (LLMs) to enhance predictive capabilities across multiple dimensions--what, when, and where accidents might occur. We develop an innovative chain-based attention mechanism that dynamically adjusts to prioritize high-risk elements within complex driving scenes. This mechanism is complemented by a three-stage model that processes outputs from smaller models into detailed multimodal inputs for LLMs, thus enabling a more nuanced understanding of traffic dynamics. Empirical validation on the DAD, CCD, and A3D datasets demonstrates superior performance in Average Precision (AP) and Mean Time-To-Accident (mTTA), establishing new benchmarks for accident prediction technology. Our approach not only advances the technological framework for autonomous driving safety but also enhances human-AI interaction, making predictive insights generated by autonomous systems more intuitive and actionable.

The observation of a kilonova AT2017gfo associated with the gravitational wave event GW170817 provides the first strong evidence that neutron star mergers are dominant contributors to the production of heavy $r$-process elements. Radioactive gamma-ray lines emitted from neutron star merger remnants provide a unique probe for investigating the nuclide composition and tracking its evolution. In this work, we studied the gamma-ray line features arising from the radioactive decay of heavy nuclei in the merger remnants based on the $r$-process nuclear reaction network and the astrophysical inputs derived from numerical relativity simulations. The decay chain of $^{126}_{50}$Sn ($T_{1/2}=230$ kyr) $\to$ $^{126}_{51}$Sb ($T_{1/2}=12.35$ days) $\to$ $^{126}_{52}$Te (stable) produces several bright gamma-ray lines with energies of $415$, $667$, and $695$ keV, making it the most promising decay chain during the remnant phase. The photon fluxes of these bright gamma-ray lines reach $\sim10^{-5}$ $\gamma$ cm$^{-2}$ s$^{-1}$ for Galactic merger remnants with ages less than $100$~kyr, which can be detected by the high energy resolution MeV gamma-ray detectors like the MASS mission., Comment: 9 pages, 5 figures, 1 table. Accepted for publication in ApJ

Inter prediction is a key technology to reduce the temporal redundancy in video coding. In natural videos, there are usually multiple moving objects with variable velocity, resulting in complex motion fields that are difficult to represent compactly. In Versatile Video Coding (VVC), existing inter prediction methods usually assume uniform speed motion between consecutive frames and use the linear models for motion estimation (ME) and motion compensation (MC), which may not well handle the complex motion fields in the real world. To address these issues, we introduce a uniformly accelerated motion model (UAMM) to exploit motion-related elements (velocity, acceleration) of moving objects between the video frames, and further combine them to assist the inter prediction methods to handle the variable motion in the temporal domain. Specifically, first, the theory of UAMM is mentioned. Second, based on that, we propose the UAMM-based parameter derivation and extrapolation schemes in the coding process. Third, we integrate the UAMM into existing inter prediction modes (Merge, MMVD, CIIP) to achieve higher prediction accuracy. The proposed method is implemented into the VVC reference software, VTM version 12.0. Experimental results show that the proposed method achieves up to 0.38% and on average 0.13% BD-rate reduction compared to the VTM anchor, under the Low-delay P configuration, with a slight increase of time complexity on the encoding/decoding side., Comment: 5 pages, 4 figures

Data has been increasingly recognized as a critical factor in the future economy. However, constructing an efficient data trading market faces challenges such as privacy breaches, data monopolies, and misuse. Despite numerous studies proposing algorithms to protect privacy and methods for pricing data, a comprehensive understanding of these issues and systemic solutions remain elusive. This paper provides an extensive review and evaluation of data trading research, aiming to identify existing problems, research gaps, and propose potential solutions. We categorize the challenges into three main areas: Compliance Challenges, Collateral Consequences, and Costly Transactions (the "3C problems"), all stemming from ambiguity in data rights. Through a quantitative analysis of the literature, we observe a paradigm shift from isolated solutions to integrated approaches. Addressing the unresolved issue of right ambiguity, we introduce the novel concept of "data usufruct," which allows individuals to use and benefit from data they do not own. This concept helps reframe data as a more conventional factor of production and aligns it with established economic theories, paving the way for a comprehensive framework of research theories, technical tools, and platforms. We hope this survey provides valuable insights and guidance for researchers, practitioners, and policymakers, thereby contributing to digital economy advancements.

Large Language Models (LLMs) are increasingly integrated into diverse industries, posing substantial security risks due to unauthorized replication and misuse. To mitigate these concerns, robust identification mechanisms are widely acknowledged as an effective strategy. Identification systems for LLMs now rely heavily on watermarking technology to manage and protect intellectual property and ensure data security. However, previous studies have primarily concentrated on the basic principles of algorithms and lacked a comprehensive analysis of watermarking theory and practice from the perspective of intelligent identification. To bridge this gap, firstly, we explore how a robust identity recognition system can be effectively implemented and managed within LLMs by various participants using watermarking technology. Secondly, we propose a mathematical framework based on mutual information theory, which systematizes the identification process to achieve more precise and customized watermarking. Additionally, we present a comprehensive evaluation of performance metrics for LLM watermarking, reflecting participant preferences and advancing discussions on its identification applications. Lastly, we outline the existing challenges in current watermarking technologies and theoretical frameworks, and provide directional guidance to address these challenges. Our systematic classification and detailed exposition aim to enhance the comparison and evaluation of various methods, fostering further research and development toward a transparent, secure, and equitable LLM ecosystem., Comment: 59 pages, 7 figures

In-loop filtering (ILF) is a key technology for removing the artifacts in image/video coding standards. Recently, neural network-based in-loop filtering methods achieve remarkable coding gains beyond the capability of advanced video coding standards, which becomes a powerful coding tool candidate for future video coding standards. However, the utilization of deep neural networks brings heavy time and computational complexity, and high demands of high-performance hardware, which is challenging to apply to the general uses of coding scene. To address this limitation, inspired by explorations in image restoration, we propose an efficient and practical in-loop filtering scheme by adopting the Look-up Table (LUT). We train the DNN of in-loop filtering within a fixed filtering reference range, and cache the output values of the DNN into a LUT via traversing all possible inputs. At testing time in the coding process, the filtered pixel is generated by locating input pixels (to-be-filtered pixel with reference pixels) and interpolating cached filtered pixel values. To further enable the large filtering reference range with the limited storage cost of LUT, we introduce the enhanced indexing mechanism in the filtering process, and clipping/finetuning mechanism in the training. The proposed method is implemented into the Versatile Video Coding (VVC) reference software, VTM-11.0. Experimental results show that the ultrafast, very fast, and fast mode of the proposed method achieves on average 0.13%/0.34%/0.51%, and 0.10%/0.27%/0.39% BD-rate reduction, under the all intra (AI) and random access (RA) configurations. Especially, our method has friendly time and computational complexity, only 101%/102%-104%/108% time increase with 0.13-0.93 kMACs/pixel, and only 164-1148 KB storage cost for a single model. Our solution may shed light on the journey of practical neural network-based coding tool evolution., Comment: 11 pages, 6 figures

3D point clouds play a pivotal role in outdoor scene perception, especially in the context of autonomous driving. Recent advancements in 3D LiDAR segmentation often focus intensely on the spatial positioning and distribution of points for accurate segmentation. However, these methods, while robust in variable conditions, encounter challenges due to sole reliance on coordinates and point intensity, leading to poor isometric invariance and suboptimal segmentation. To tackle this challenge, our work introduces Range-Aware Pointwise Distance Distribution (RAPiD) features and the associated RAPiD-Seg architecture. Our RAPiD features exhibit rigid transformation invariance and effectively adapt to variations in point density, with a design focus on capturing the localized geometry of neighboring structures. They utilize inherent LiDAR isotropic radiation and semantic categorization for enhanced local representation and computational efficiency, while incorporating a 4D distance metric that integrates geometric and surface material reflectivity for improved semantic segmentation. To effectively embed high-dimensional RAPiD features, we propose a double-nested autoencoder structure with a novel class-aware embedding objective to encode high-dimensional features into manageable voxel-wise embeddings. Additionally, we propose RAPiD-Seg which incorporates a channel-wise attention fusion and two effective RAPiD-Seg variants, further optimizing the embedding for enhanced performance and generalization. Our method outperforms contemporary LiDAR segmentation work in terms of mIoU on SemanticKITTI (76.1) and nuScenes (83.6) datasets., Comment: ECCV 2024 (Oral); 18 pages, 6 figures, 7 tables; Code at https://github.com/l1997i/rapid_seg

Spotforming is a target-speaker extraction technique that uses multiple microphone arrays. This method applies beamforming (BF) to each microphone array, and the common components among the BF outputs are estimated as the target source. This study proposes a new common component extraction method based on nonnegative tensor factorization (NTF) for higher model interpretability and more robust spotforming against hyperparameters. Moreover, attractor-based regularization was introduced to facilitate the automatic selection of optimal target bases in the NTF. Experimental results show that the proposed method performs better than conventional methods in spotforming performance and also shows some characteristics suitable for practical use., Comment: Accepted at EUSIPCO2024

Let $X\subset\mathbb{P}^r$ be an integral linearly normal variety and $R=k[x_0,\cdots,x_r]$ the coordinate ring of $\mathbb{P}^r$. It is known that the syzygies of $X$ contain some geometric information. In recent years the syzygies of non-projectively normal varieties or in other words, the projection $X'$ of $X$ away from a linear subspace $W\subset\mathbb{P}^r$, were taken into considerations. Assuming that the coordinate ring of the ambient space that $X'$ lives in is $S$, there are two types of vanishing properties of the Betti diagrams of the projected varieties, the so-called $N_{d,p}^S$ and $\widetilde{N}_{d,p}$. The former one have been widely discussed for general varieties, for example by S. Kwak, Y. Choi and E. Park, while the latter one was discussed by W. Lee and E. Park for curves of very large degree. In this paper I will discuss about the $\widetilde{N}_{d,p}$ properties of the projection of a generic canonical and paracanonical curve away from a generic point and in particular whether they are cut out by quadrics. Some conjectures will be claimed based on the tests on Macaulay2., Comment: 20 pages

In this paper, we propose the task of \textit{Ranked Video Moment Retrieval} (RVMR) to locate a ranked list of matching moments from a collection of videos, through queries in natural language. Although a few related tasks have been proposed and studied by CV, NLP, and IR communities, RVMR is the task that best reflects the practical setting of moment search. To facilitate research in RVMR, we develop the TVR-Ranking dataset, based on the raw videos and existing moment annotations provided in the TVR dataset. Our key contribution is the manual annotation of relevance levels for 94,442 query-moment pairs. We then develop the $NDCG@K, IoU\geq \mu$ evaluation metric for this new task and conduct experiments to evaluate three baseline models. Our experiments show that the new RVMR task brings new challenges to existing models and we believe this new dataset contributes to the research on multi-modality search. The dataset is available at \url{https://github.com/Ranking-VMR/TVR-Ranking}

When mobile meets LLMs, mobile app users deserve to have more intelligent usage experiences. For this to happen, we argue that there is a strong need to appl LLMs for the mobile ecosystem. We therefore provide a research roadmap for guiding our fellow researchers to achieve that as a whole. In this roadmap, we sum up six directions that we believe are urgently required for research to enable native intelligence in mobile devices. In each direction, we further summarize the current research progress and the gaps that still need to be filled by our fellow researchers.

Synthesizing realistic 3D indoor scenes is a challenging task that traditionally relies on manual arrangement and annotation by expert designers. Recent advances in autoregressive models have automated this process, but they often lack semantic understanding of the relationships and hierarchies present in real-world scenes, yielding limited performance. In this paper, we propose Forest2Seq, a framework that formulates indoor scene synthesis as an order-aware sequential learning problem. Forest2Seq organizes the inherently unordered collection of scene objects into structured, ordered hierarchical scene trees and forests. By employing a clustering-based algorithm and a breadth-first traversal, Forest2Seq derives meaningful orderings and utilizes a transformer to generate realistic 3D scenes autoregressively. Experimental results on standard benchmarks demonstrate Forest2Seq's superiority in synthesizing more realistic scenes compared to top-performing baselines, with significant improvements in FID and KL scores. Our additional experiments for downstream tasks and ablation studies also confirm the importance of incorporating order as a prior in 3D scene generation., Comment: ECCV 2024