arXiv subjects

Wei Song

Publications and source records attributed to Wei Song.

At least 127 records · Page 7Linked to original sources

arXiv2024

Multi-task multi-constraint differential evolution with elite-guided knowledge transfer for coal mine integrated energy system dispatching

The dispatch optimization of coal mine integrated energy system is challenging due to high dimensionality, strong coupling constraints, and multiobjective. Existing constrained multiobjective evolutionary algorithms struggle with locating multiple small and irregular feasible regions, making them inaplicable to this problem. To address this issue, we here develop a multitask evolutionary algorithm framework that incorporates the dispatch correlated domain knowledge to effectively deal with strong constraints and multiobjective optimization. Possible evolutionary multitask construction strategy based on complex constraint relationship analysis and handling, i.e., constraint coupled spatial decomposition, constraint strength classification and constraint handling technique, is first explored. Within the multitask evolutionary optimization framework, two strategies, i.e., an elite guided knowledge transfer by designing a special crowding distance mechanism to select dominant individuals from each task, and an adaptive neighborhood technology based mutation to effectively balance the diversity and convergence of each optimized task for the differential evolution algorithm, are further developed. The performance of the proposed algorithm in feasibility, convergence, and diversity is demonstrated in a case study of a coal mine integrated energy system by comparing with CPLEX solver and seven constrained multiobjective evolutionary algorithms.

cs.NE↗

arXiv2024

M3GIA: A Cognition Inspired Multilingual and Multimodal General Intelligence Ability Benchmark

As recent multi-modality large language models (MLLMs) have shown formidable proficiency on various complex tasks, there has been increasing attention on debating whether these models could eventually mirror human intelligence. However, existing benchmarks mainly focus on evaluating solely on task performance, such as the accuracy of identifying the attribute of an object. Combining well-developed cognitive science to understand the intelligence of MLLMs beyond superficial achievements remains largely unexplored. To this end, we introduce the first cognitive-driven multi-lingual and multi-modal benchmark to evaluate the general intelligence ability of MLLMs, dubbed M3GIA. Specifically, we identify five key cognitive factors based on the well-recognized Cattell-Horn-Carrol (CHC) model of intelligence and propose a novel evaluation metric. In addition, since most MLLMs are trained to perform in different languages, a natural question arises: is language a key factor influencing the cognitive ability of MLLMs? As such, we go beyond English to encompass other languages based on their popularity, including Chinese, French, Spanish, Portuguese and Korean, to construct our M3GIA. We make sure all the data relevant to the cultural backgrounds are collected from their native context to avoid English-centric bias. We collected a significant corpus of data from human participants, revealing that the most advanced MLLM reaches the lower boundary of human intelligence in English. Yet, there remains a pronounced disparity in the other five languages assessed. We also reveals an interesting winner takes all phenomenon that are aligned with the discovery in cognitive studies. Our benchmark will be open-sourced, with the aspiration of facilitating the enhancement of cognitive capabilities in MLLMs.

cs.AI↗

arXiv2024

Garbage Segmentation and Attribute Analysis by Robotic Dogs

Efficient waste management and recycling heavily rely on garbage exploration and identification. In this study, we propose GSA2Seg (Garbage Segmentation and Attribute Analysis), a novel visual approach that utilizes quadruped robotic dogs as autonomous agents to address waste management and recycling challenges in diverse indoor and outdoor environments. Equipped with advanced visual perception system, including visual sensors and instance segmentators, the robotic dogs adeptly navigate their surroundings, diligently searching for common garbage items. Inspired by open-vocabulary algorithms, we introduce an innovative method for object attribute analysis. By combining garbage segmentation and attribute analysis techniques, the robotic dogs accurately determine the state of the trash, including its position and placement properties. This information enhances the robotic arm's grasping capabilities, facilitating successful garbage retrieval. Additionally, we contribute an image dataset, named GSA2D, to support evaluation. Through extensive experiments on GSA2D, this paper provides a comprehensive analysis of GSA2Seg's effectiveness. Dataset available: \href{https://www.kaggle.com/datasets/hellob/gsa2d-2024}{https://www.kaggle.com/datasets/hellob/gsa2d-2024}.

cs.CV↗

arXiv2024

Aligning Knowledge Graph with Visual Perception for Object-goal Navigation

Object-goal navigation is a challenging task that requires guiding an agent to specific objects based on first-person visual observations. The ability of agent to comprehend its surroundings plays a crucial role in achieving successful object finding. However, existing knowledge-graph-based navigators often rely on discrete categorical one-hot vectors and vote counting strategy to construct graph representation of the scenes, which results in misalignment with visual images. To provide more accurate and coherent scene descriptions and address this misalignment issue, we propose the Aligning Knowledge Graph with Visual Perception (AKGVP) method for object-goal navigation. Technically, our approach introduces continuous modeling of the hierarchical scene architecture and leverages visual-language pre-training to align natural language description with visual perception. The integration of a continuous knowledge graph architecture and multimodal feature alignment empowers the navigator with a remarkable zero-shot navigation capability. We extensively evaluate our method using the AI2-THOR simulator and conduct a series of experiments to demonstrate the effectiveness and efficiency of our navigator. Code available: https://github.com/nuoxu/AKGVP.

cs.CV↗

arXiv2024

MLDT: Multi-Level Decomposition for Complex Long-Horizon Robotic Task Planning with Open-Source Large Language Model

In the realm of data-driven AI technology, the application of open-source large language models (LLMs) in robotic task planning represents a significant milestone. Recent robotic task planning methods based on open-source LLMs typically leverage vast task planning datasets to enhance models' planning abilities. While these methods show promise, they struggle with complex long-horizon tasks, which require comprehending more context and generating longer action sequences. This paper addresses this limitation by proposing MLDT, theMulti-Level Decomposition Task planning method. This method innovatively decomposes tasks at the goal-level, task-level, and action-level to mitigate the challenge of complex long-horizon tasks. In order to enhance open-source LLMs' planning abilities, we introduce a goal-sensitive corpus generation method to create high-quality training data and conduct instruction tuning on the generated corpus. Since the complexity of the existing datasets is not high enough, we construct a more challenging dataset, LongTasks, to specifically evaluate planning ability on complex long-horizon tasks. We evaluate our method using various LLMs on four datasets in VirtualHome. Our results demonstrate a significant performance enhancement in robotic task planning, showcasing MLDT's effectiveness in overcoming the limitations of existing methods based on open-source LLMs as well as its practicality in complex, real-world scenarios.

cs.RO↗

arXiv2024

Flickr30K-CFQ: A Compact and Fragmented Query Dataset for Text-image Retrieval

With the explosive growth of multi-modal information on the Internet, unimodal search cannot satisfy the requirement of Internet applications. Text-image retrieval research is needed to realize high-quality and efficient retrieval between different modalities. Existing text-image retrieval research is mostly based on general vision-language datasets (e.g. MS-COCO, Flickr30K), in which the query utterance is rigid and unnatural (i.e. verbosity and formality). To overcome the shortcoming, we construct a new Compact and Fragmented Query challenge dataset (named Flickr30K-CFQ) to model text-image retrieval task considering multiple query content and style, including compact and fine-grained entity-relation corpus. We propose a novel query-enhanced text-image retrieval method using prompt engineering based on LLM. Experiments show that our proposed Flickr30-CFQ reveals the insufficiency of existing vision-language datasets in realistic text-image tasks. Our LLM-based Query-enhanced method applied on different existing text-image retrieval models improves query understanding performance both on public dataset and our challenge set Flickr30-CFQ with over 0.9% and 2.4% respectively. Our project can be available anonymously in https://sites.google.com/view/Flickr30K-cfq.

cs.IR↗

arXiv2024

Asymptotic symmetries from the string worldsheet

In IIB string theory on AdS$_3$ background with NS-NS fluxes, we show that Brown-Henneaux asymptotic Killing vectors can be derived by requiring both the worldsheet equations of motion and Virasoro constraints are preserved near the asymptotic boundary of the target spacetime. The charges on the worldsheet that generate the corresponding transformations can be written down in both the Lagrangian formalism and Hamiltonian formalism. This provides a method of studying asymptotic symmetry of the target spacetime directly from worldsheet string theories, without using results from the supergravity limit. As an example, we apply this method to flat spacetime in three dimensions and obtain the BMS$_3$ generators on the worldsheet theory.

hep-th↗

arXiv2024

Target Recognition Algorithm for Monitoring Images in Electric Power Construction Process

To enhance precision and comprehensiveness in identifying targets in electric power construction monitoring video, a novel target recognition algorithm utilizing infrared imaging is explored. This algorithm employs a color processing technique based on a local linear mapping method to effectively recolor monitoring images. The process involves three key steps: color space conversion, color transfer, and pseudo-color encoding. It is designed to accentuate targets in the infrared imaging. For the refined identification of these targets, the algorithm leverages a support vector machine approach, utilizing an optimal hyperplane to accurately predict target types. We demonstrate the efficacy of the algorithm, which achieves high target recognition accuracy in both outdoor and indoor electric power construction monitoring scenarios. It maintains a false recognition rate below 3% across various environments.

cs.CV↗

arXiv2024

Transmission Line Detection Based on Improved Hough Transform

To address the challenges of low detection accuracy and high false positive rates of transmission lines in UAV (Unmanned Aerial Vehicle) images, we explore the linear features and spatial distribution. We introduce an enhanced stochastic Hough transform technique tailored for detecting transmission lines in complex backgrounds. By employing the Hessian matrix for initial preprocessing of transmission lines, and utilizing boundary search and pixel row segmentation, our approach distinguishes transmission line areas from the background. We significantly reduce both false positives and missed detections, thereby improving the accuracy of transmission line identification. Experiments demonstrate that our method not only processes images more rapidly, but also yields superior detection results compared to conventional and random Hough transform methods.

cs.CV↗

arXiv2024

Extremal surfaces in glue-on AdS/$T\bar T$ holography

$T\bar T$ deformed CFTs with positive deformation parameter have been proposed to be holographically dual to Einstein gravity in a glue-on $\mathrm{AdS}_3$ spacetime. The latter is constructed from AdS$_3$ by gluing a patch of an auxiliary AdS$_3^*$ spacetime to its asymptotic boundary. In this work, we propose a glue-on version of the Ryu-Takayanagi formula, which is given by the signed area of an extremal surface. The extremal surface is anchored at the endpoints of an interval on a cutoff surface in the glue-on geometry. It consists of an RT surface lying in the AdS$_3$ part of the spacetime and its extension to the AdS$_3^*$ region. The signed area is the length of the RT surface minus the length of the segments in AdS$_3^*$. We find that the Ryu-Takayanagi formula with the signed area reproduces the entanglement entropy of a half interval for $T\bar T$-deformed CFTs on the sphere. We then study the properties of extremal surfaces on various glue-on geometries, including Poincaré $\mathrm{AdS}_3$, global $\mathrm{AdS}_3$, and the BTZ black hole. When anchored on multiple intervals at the boundary, the signed area of the minimal surfaces undergoes phase transitions with novel properties. In all of these examples, we find that the glue-on extremal surfaces exhibit a minimum length related to the deformation parameter of $T\bar T$-deformed CFTs.

hep-th↗

arXiv2023

A Privacy-Preserving Trajectory Synthesis Method Based on Vector Translation Invariance Supporting Traffic Constraints

With the popularization of different kinds of smart terminals and the development of autonomous driving technology, more and more services based on spatio-temporal data have emerged in our lives, such as online taxi services, traffic flow prediction, and tracking virus propagation. However, the privacy concerns of spatio-temporal data greatly limit the use of them. To address this issue, differential privacy method based on spatio-temporal data has been proposed. In differential privacy, a good aggregation query can highly improve the data utility. But the mainstream aggregation query methods are based on area partitioning, which is difficult to generate trajectory with high utility for they are hard to take time and constraints into account. Motivated by this, we propose an aggregation query based on the relationships between trajectories, so it can greatly improve the data utility as compared to the existing methods. The trajectory synthesis task can be regarded as an optimization problem of finding trajectories that match the relationships between trajectories. We adopt gradient descent to find new trajectories that meet the conditions, and during the gradient descent, we can easily take the constraints into account by adding penalty terms which area partitioning based query is hard to achieve. We carry out extensive experiments to validate that the trajectories generated by our method have higher utility and the theoretic analysis shows that our method is safe and reliable.

cs.CR↗

arXiv2023

Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering

Despite their competitive performance on knowledge-intensive tasks, large language models (LLMs) still have limitations in memorizing all world knowledge especially long tail knowledge. In this paper, we study the KG-augmented language model approach for solving the knowledge graph question answering (KGQA) task that requires rich world knowledge. Existing work has shown that retrieving KG knowledge to enhance LLMs prompting can significantly improve LLMs performance in KGQA. However, their approaches lack a well-formed verbalization of KG knowledge, i.e., they ignore the gap between KG representations and textual representations. To this end, we propose an answer-sensitive KG-to-Text approach that can transform KG knowledge into well-textualized statements most informative for KGQA. Based on this approach, we propose a KG-to-Text enhanced LLMs framework for solving the KGQA task. Experiments on several KGQA benchmarks show that the proposed KG-to-Text augmented LLMs approach outperforms previous KG-augmented LLMs approaches regarding answer accuracy and usefulness of knowledge statements.

cs.CL↗

arXiv2023

Fine-grained Text and Image Guided Point Cloud Completion with CLIP Model

This paper focuses on the recently popular task of point cloud completion guided by multimodal information. Although existing methods have achieved excellent performance by fusing auxiliary images, there are still some deficiencies, including the poor generalization ability of the model and insufficient fine-grained semantic information for extracted features. In this work, we propose a novel multimodal fusion network for point cloud completion, which can simultaneously fuse visual and textual information to predict the semantic and geometric characteristics of incomplete shapes effectively. Specifically, to overcome the lack of prior information caused by the small-scale dataset, we employ a pre-trained vision-language model that is trained with a large amount of image-text pairs. Therefore, the textual and visual encoders of this large-scale model have stronger generalization ability. Then, we propose a multi-stage feature fusion strategy to fuse the textual and visual features into the backbone network progressively. Meanwhile, to further explore the effectiveness of fine-grained text descriptions for point cloud completion, we also build a text corpus with fine-grained descriptions, which can provide richer geometric details for 3D shapes. The rich text descriptions can be used for training and evaluating our network. Extensive quantitative and qualitative experiments demonstrate the superior performance of our method compared to state-of-the-art point cloud completion networks.

cs.CV↗

arXiv2023

Multivariate Time Series characterization and forecasting of VoIP traffic in real mobile networks

Predicting the behavior of real-time traffic (e.g., VoIP) in mobility scenarios could help the operators to better plan their network infrastructures and to optimize the allocation of resources. Accordingly, in this work the authors propose a forecasting analysis of crucial QoS/QoE descriptors (some of which neglected in the technical literature) of VoIP traffic in a real mobile environment. The problem is formulated in terms of a multivariate time series analysis. Such a formalization allows to discover and model the temporal relationships among various descriptors and to forecast their behaviors for future periods. Techniques such as Vector Autoregressive models and machine learning (deep-based and tree-based) approaches are employed and compared in terms of performance and time complexity, by reframing the multivariate time series problem into a supervised learning one. Moreover, a series of auxiliary analyses (stationarity, orthogonal impulse responses, etc.) are performed to discover the analytical structure of the time series and to provide deep insights about their relationships. The whole theoretical analysis has an experimental counterpart since a set of trials across a real-world LTE-Advanced environment has been performed to collect, post-process and analyze about 600,000 voice packets, organized per flow and differentiated per codec.

cs.NI↗

arXiv2023

Glue-on AdS holography for $T\bar T$-deformed CFTs

The $T\bar T$ deformation is a solvable irrelevant deformation whose properties depend on the sign of the deformation parameter $μ$. In particular, $T\bar T$-deformed CFTs with $μ<0$ have been proposed to be holographically dual to Einstein gravity where the metric satisfies Dirichlet boundary conditions at a finite cutoff surface. In this paper, we put forward a holographic proposal for $T\bar T$-deformed CFTs with $μ>0$, in which case the bulk geometry is constructed by gluing a patch of AdS$_3$ to the original spacetime. As evidence, we show that the $T\bar T$ trace flow equation, the spectrum on the cylinder, and the partition function on the torus and the sphere, among other results, can all be reproduced from bulk calculations in glue-on AdS$_3$.

hep-th↗

arXiv2023

On the universal behavior of $T\bar T$-deformed CFTs: single and double-trace partition functions at large $c$

We study universal properties of the torus partition function of $T\bar T$-deformed CFTs under the assumption of modular invariance, for both the original version, referred to as the double-trace version in this paper, and the single-trace version defined as the symmetric product orbifold of double-trace $T\bar T$-deformed CFTs. In the double-trace case, we specify sparseness conditions for the light states for which the partition function at low temperatures is dominated by the vacuum when the central charge of the undeformed CFT is large. Using modular invariance, this implies a universal density of high energy states, in analogy with the behavior of holographic CFTs. For the single-trace $T\bar T$ deformation, we show that modular invariance implies that the torus partition function can be written in terms of the untwisted partition function and its modular images, the latter of which can be obtained from the action of a generalized Hecke operator. The partition function and the energy of twisted states match holographic calculations in previous literature, thus providing further evidence for the conjectured holographic correspondence. In addition, we show that the single-trace partition function is universal when the central charge of the undeformed CFT is large, without needing to assume a sparse density of light states. Instead, the density of light states is shown to always saturate the sparseness condition.

hep-th↗

arXiv2023

MaskedSpeech: Context-aware Speech Synthesis with Masking Strategy

Humans often speak in a continuous manner which leads to coherent and consistent prosody properties across neighboring utterances. However, most state-of-the-art speech synthesis systems only consider the information within each sentence and ignore the contextual semantic and acoustic features. This makes it inadequate to generate high-quality paragraph-level speech which requires high expressiveness and naturalness. To synthesize natural and expressive speech for a paragraph, a context-aware speech synthesis system named MaskedSpeech is proposed in this paper, which considers both contextual semantic and acoustic features. Inspired by the masking strategy in the speech editing research, the acoustic features of the current sentence are masked out and concatenated with those of contextual speech, and further used as additional model input. The phoneme encoder takes the concatenated phoneme sequence from neighboring sentences as input and learns fine-grained semantic information from contextual text. Furthermore, cross-utterance coarse-grained semantic features are employed to improve the prosody generation. The model is trained to reconstruct the masked acoustic features with the augmentation of both the contextual semantic and acoustic features. Experimental results demonstrate that the proposed MaskedSpeech outperformed the baseline system significantly in terms of naturalness and expressiveness.

cs.SD↗

arXiv2023

Correlation Functions in the TsT/$T{\bar T}$ Correspondence

We investigate the proposed holographic duality between the TsT transformation of IIB string theory on AdS$_3\times {\cal N}$ with NS-NS flux and a single-trace $T\bar{T}$ deformation of the symmetric orbifold CFT. We present a non-perturbative calculation of two-point correlation functions using string theory and demonstrate their consistency with those of the $T\bar{T}$ deformation. The two-point correlation function of the deformed theory on the plane, written in momentum space, is obtained from that of the undeformed theory by replacing $h$ with $h+2{\tilde λ\over w} p\bar p$, where $h$ is the spacetime conformal weight, $\tilde λ$ is a deformation parameter, $p$ and $\bar p$ are the momenta, and $w$ labels the twisted sectors in the deformed symmetric product. At $w=1$, the non-perturbative result satisfies the Callan-Symanzik equation for double-trace $T\bar T$ deformed CFT derived in \cite{Cardy:2019qao}. We also perform conformal perturbations on both the worldsheet CFT and the symmetric orbifold CFT as a sanity check. The perturbative and non-perturbative matching between results on the two sides provides further evidence of the conjectured TsT/$T\bar{T}$ correspondence.

hep-th↗