Diffusion models have been utilized as powerful tools for various image editing tasks, including semantic image painting (SIP), which aims to generate content within masked regions conditioned on a reference image or text. SIP, especially those using images as conditions, often suffers from three issues: semantic inconsistency, unnatural transitions, and style inconsistency, which significantly hinder its practical application. To address these challenges, we propose a novel Semantic Image Painting framework with INdependent INformation INjection (Spin). Specifically, we compute a saliency map to segregate the reference image into salient and non-salient components. We then filter out the non-salient information during the semantic embedding extraction phase and precisely inject the semantic embedding into the masked region instead of the whole image during the semantic generation phase. Furthermore, we impose an additional style guidance to promote style consistency between background and foreground. Experimental results demonstrate that Spin achieve superior semantic similarity and image coherence across various styles, including realistic, pencil drawings, cartoon, and oil painting. Additionally, Spin offers diversity and editability, and can be integrated into other models that meet our prerequisites.

Recent advancements in singing voice conversion (SVC) have focused on achieving zero-shot, any-to-any voice transformation capabilities. Many approaches attempt to modify voice characteristics by incorporating global timbre variables into acoustic models. However, these methods often depend heavily on the capabilities of timbre extractors and lack an understanding of temporal local information. This limitation poses challenges, particularly in replicating specific voice qualities such as those of children. To address this issue, we introduce InvoxSVC, a latent flow matching model (LFM) designed for rapid and precise singing voice conversion with a particular emphasis on capturing temporal local features. While reducing the residual timbral information in the source singing encoding through singer-guidance, InvoxSVC enhances the model’s ability to capture temporal nuances by integrating in-context learning during inference. Additionally, the model employs a pre-trained high-fidelity variational autoencoder (VAE) to improve waveform generation. In comparative evaluations, InvoxSVC outperforms the open-source project So-VITS-SVC in both objective and subjective assessments.

This paper proposes an integrated satellite-Unmanned Aerial Vehicle (UAV)-terrestrial collaborative computing framework that incorporates Low Earth Orbit (LEO) satellite, UAVs equipped with Mobile Edge Computing (MEC) servers, ground infrastructures, and terrestrial users. A novel three-tier hybrid task decomposition and computation architecture is designed to support efficient task offloading in dynamic and heterogeneous environments. By exploiting the complementary advantages of LEO satellite and UAVs in communication coverage and deployment flexibility, and by utilizing remote high-performance servers, the system ensures improved Quality of Service (QoS), enhanced coverage, scalability, and robustness. To address the heterogeneity in computation demand, latency sensitivity, and mobility patterns of ground devices, the cross-regional task offloading and decomposition problem is formulated as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP), enabling efficient collaborative decision-making among agents with overlapping observations. Furthermore, under the centralized training with decentralized execution (CTDE) paradigm, we propose a hierarchical scheduling algorithm based on heterogeneous multi-agent deep reinforcement learning (DRL), allowing LEO satellite and UAVs to jointly learn optimal strategies during training while autonomously executing decisions in real time. To address the challenges posed by high-dimensional state spaces, we introduce an attention-driven UAV and satellite-assisted task offloading algorithm (ADUS). A multi-head attention mechanism is incorporated into the critic networks, allowing agents to focus on critical features and avoid reliance on full joint state-action representations. Experimental results demonstrate that the proposed algorithm significantly outperforms other baseline methods, including ADUS-NAT, ADUS-NPP, MADDPG, DDPG and MATORA, achieving improvements of 5.45%, 11.25%, 12.04%, 19.61%, 33.25%, and 42.35%, respectively.

The controllability of text-to-audio (TTA) systems is constrained due to the exclusive generation of audio from text, leading to issues of temporal disorganization and semantic omission. Some studies have endeavored to integrate conditions, such as frame-level annotation of sound events, to regulate the generated audio content. However, this necessitates a substantial amount of paired data and time for fine-tuning or training the model. This paper introduces a novel, training-free approach for controllable TTA generation based on temporal condition, e.g., the location and duration of corresponding sound events. Through updating latent variables during inference process, our approach ensures that the content generated by pretrained TTA models adheres to the specified temporal conditions, thereby achieving precise temporal control. Experimental results affirm that the proposed approach effectively governs the initiation and conclusion of sound events as indicated by the text, while preserving the high-quality and diverse generation capabilities of the diffusion model

The use of unmanned aerial vehicles (UAVs) is a promising solution for collecting data from wireless Internet of Things (IoT) devices and offloading to mobile edge computing (MEC) server embedded access points (APs) equipped with powerful servers. This article presents a solution to optimize the energy efficiency of UAV relaying in the IoT system, which assists in programming the multiple UAV flight trajectories and bandwidth allocation schemes to scientifically and energy-efficiently transmit the data from IoT devices to MEC servers. Furthermore, in order to ensure the continuous and effective data relaying of the UAVs, we deploy a number of decentralized wireless charging stations (CSs) in the system to replenish the UAVs’ energy and enable them to provide long-term services. Specifically, we propose a deep reinforcement learning-based efficient IoT data relaying method, where we mainly apply deep deterministic policy gradient (DDPG) to solve this dynamic programming problem with large action spaces. Experimental results demonstrate that the DDPG-based method for UAV efficient data collection and offloading (DDPG-UCO) algorithm outperforms other five baseline methods in terms of the UAV energy efficiency, amount of data relayed and data interaction energy consumption rate while maintaining a high level of geographical fairness of the relaying service.

The emergence of Hive greatly facilitates the management of massive data stored in various places. Meanwhile, data scientists face challenges during HiveQL programming - they may not use correct and/or efficient HiveQL statements in their programs; developers may also introduce anti-patterns indeliberately into HiveQL programs, leading to poor performance, low maintainability, and/or program crashes. This paper presents an empirical study on HiveQL programming, in which 38 HiveQL anti-patterns are revealed. We then design and implement DeFiHap, the first tool for automatically detecting and fixing HiveQL anti-patterns. DeFiHap detects HiveQL anti-patterns via analyzing the abstract syntax trees of HiveQL statements and Hive configurations, and generates fix suggestions by rule-based rewriting and performance tuning techniques. The experimental results show that DeFiHap is effective. In particular, DeFiHap detects 25 anti-patterns and generates fix suggestions for 17 of them.

Users frequently raise feedback when using software products. Feedback from users regarding their experiences and expectations and software defects they found adds values to software maintenance and evolution — software managers collect user feedback and then dispatch feedback issues that developers (and/or maintainers) need to track and process. Feedback tracking is often supported by open source platforms and collaborative software systems. Meanwhile, there still exists a gap between feedback issues and source code: since user feedback is usually informal and arbitrary, engineers have to spend much effort on comprehending issues and identifying which source code files need to be improved or fixed. This paper introduces a deep learning approach, Feedback2Code , which facilitates identification of user-feedback-related source code files. The core idea is to (1) explore latent semantics of user feedback and source code using several deep learning techniques such as Multi-Layer Perceptron (MLP), Convolutional Neutral Network (CNN) and skip-gram and (2) establish a multi-correlation model to explore linkages between feedback issues and source code files. Given a feedback issue, the linkages then allow engineers to identify source code files that are highly relevant to the issue. We have implemented Feedback2Code and evaluated it against ChangeAdvisor (a state-of-the-art approach) on 24 open source projects. The evaluation results clearly show the strength of Feedback2Code : for 103793 feedback issues, Feedback2Code successfully established 101190 feedback-code linkages and achieved a precision that is [Formula: see text] higher than that of ChangeAdvisor . Feedback2Code also achieved an MRR and an MAP that are [Formula: see text] and [Formula: see text] higher than those of ChangeAdvisor , respectively. Furthermore, we also found that a Feedback2Code -trained model can be easily transferred, allowing feedback-code linkages to be established in new projects with a little history data.

Coding convention plays an important role in guaranteeing software quality. However, coding conventions are usually informally presented and inconvenient for programmers to use. In this paper, we present CocoQa, a system that answers programmer's questions about coding conventions. CocoQa answers questions by querying a knowledge graph for coding conventions. It employs 1) a subgraph matching algorithm that parses the question into a SPARQL query, and 2) a machine comprehension algorithm that uses an end-to-end neural network to detect answers from searched paragraphs. We have implemented CocoQa, and evaluated it on a coding convention QA dataset. The results show that CocoQa can answer questions about coding conventions precisely. In particular, CocoQa can achieve a precision of 82.92% and a recall of 91.10%. Repository: https://github.com/14dtj/CocoQa/ Video: https://youtu.be/VQaXi1WydAU.

Coding conventions are a set of coding guidelines used by software developers to improve the readability of source code, increase software maintainability, and promote the reuse of coding patterns.In this paper, we introduce CCBase, a knowledge base of coding conventions, that was constructed from online resources.Specifically, CCBase was constructed as follows.We designed the ontology of the coding convention domain, crawled data related to coding conventions from a variety of online resources, and then extracted entities and relations using an NLP-enabled rule matching method.To uncover the latent relations, we further proposed a similarity metric to reveal the similar-to and relate-to relations, and developed a RCE algorithm to establish a unified type hierarchy of coding conventions.The resulting knowledge base contains 3139 coding conventions for Java and C++, with 3761 entities and 767 relations.Furthermore, we have extended the usability of CCBase by developing a question answering system on the base.We have conducted experiments to evaluate CCBase.The experimental results show that CCBase has a wide coverage on entities and relations in coding conventions domain, and the QA system achieves an F1 score of 84.5% on 214 questions raised in StackOverflow.