arXiv subjects

Xiaoqian Li

Publications and source records attributed to Xiaoqian Li.

11 recordsLinked to original sources

arXiv2025

Heimdall++: Optimizing GPU Utilization and Pipeline Parallelism for Efficient Single-Pulse Detection

With the increasing time and frequency resolution of modern radio telescopes and the exponential growth in observational data volumes, real-time single-pulse detection has become a critical requirement for time-domain radio astronomy. Heimdall, as a representative GPU-accelerated single-pulse search tool, offers substantial performance advantages over CPU-based approaches. However, its sequential execution model and resource contention in intermediate processing stages limit GPU utilization, leading to suboptimal throughput and increased computational latency. To address these limitations, we present Heimdall++, an optimized successor to Heimdall that incorporates fine-grained GPU parallelization, enhanced memory management, and a multi-threaded framework to decouple CPU-bound and GPU-bound processing stages. This design mitigates the GPU stall problem and improves end-to-end efficiency. We evaluated Heimdall++ on a system equipped with NVIDIA RTX 3080 Ti GPUs using both a single large-scale observational file and multiple files. Experimental results demonstrate that Heimdall++ achieves up to 2.66x speedup in single-file processing and 2.05x speedup in multi-file batch processing, while maintaining full consistency with the original Heimdall's search results.

cs.DC↗

arXiv2025

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation

Text-to-image (T2I) models have demonstrated remarkable generative capabilities but remain vulnerable to producing not-safe-for-work (NSFW) content, such as violent or explicit imagery. While recent moderation efforts have introduced soft prompt-guided tuning by appending defensive tokens to the input, these approaches often rely on large-scale curated image-text datasets and apply static, one-size-fits-all defenses at inference time. However, this results not only in high computational cost and degraded benign image quality, but also in limited adaptability to the diverse and nuanced safety requirements of real-world prompts. To address these challenges, we propose PromptSafe, a gated prompt tuning framework that combines a lightweight, text-only supervised soft embedding with an inference-time gated control network. Instead of training on expensive image-text datasets, we first rewrite unsafe prompts into semantically aligned but safe alternatives using an LLM, constructing an efficient text-only training corpus. Based on this, we optimize a universal soft prompt that repels unsafe and attracts safe embeddings during the diffusion denoising process. To avoid over-suppressing benign prompts, we introduce a gated mechanism that adaptively adjusts the defensive strength based on estimated prompt toxicity, thereby aligning defense intensity with prompt risk and ensuring strong protection for harmful inputs while preserving benign generation quality. Extensive experiments across multiple benchmarks and T2I models show that PromptSafe achieves a SOTA unsafe generation rate (2.36%), while preserving high benign fidelity. Furthermore, PromptSafe demonstrates strong generalization to unseen harmful categories, robust transferability across diffusion model architectures, and resilience under adaptive adversarial attacks, highlighting its practical value for safe and scalable deployment.

cs.CV↗

arXiv2025

PRJ: Perception-Retrieval-Judgement for Generated Images

The rapid progress of generative AI has enabled remarkable creative capabilities, yet it also raises urgent concerns regarding the safety of AI-generated visual content in real-world applications such as content moderation, platform governance, and digital media regulation. This includes unsafe material such as sexually explicit images, violent scenes, hate symbols, propaganda, and unauthorized imitations of copyrighted artworks. Existing image safety systems often rely on rigid category filters and produce binary outputs, lacking the capacity to interpret context or reason about nuanced, adversarially induced forms of harm. In addition, standard evaluation metrics (e.g., attack success rate) fail to capture the semantic severity and dynamic progression of toxicity. To address these limitations, we propose Perception-Retrieval-Judgement (PRJ), a cognitively inspired framework that models toxicity detection as a structured reasoning process. PRJ follows a three-stage design: it first transforms an image into descriptive language (perception), then retrieves external knowledge related to harm categories and traits (retrieval), and finally evaluates toxicity based on legal or normative rules (judgement). This language-centric structure enables the system to detect both explicit and implicit harms with improved interpretability and categorical granularity. In addition, we introduce a dynamic scoring mechanism based on a contextual toxicity risk matrix to quantify harmfulness across different semantic dimensions. Experiments show that PRJ surpasses existing safety checkers in detection accuracy and robustness while uniquely supporting structured category-level toxicity interpretation.

cs.CV↗

arXiv2023

Crosslingual Retrieval Augmented In-context Learning for Bangla

The promise of Large Language Models (LLMs) in Natural Language Processing has often been overshadowed by their limited performance in low-resource languages such as Bangla. To address this, our paper presents a pioneering approach that utilizes cross-lingual retrieval augmented in-context learning. By strategically sourcing semantically similar prompts from high-resource language, we enable multilingual pretrained language models (MPLMs), especially the generative model BLOOMZ, to successfully boost performance on Bangla tasks. Our extensive evaluation highlights that the cross-lingual retrieval augmented prompts bring steady improvements to MPLMs over the zero-shot performance.

cs.CL↗

arXiv2023

From Classification to Generation: Insights into Crosslingual Retrieval Augmented ICL

The remarkable ability of Large Language Models (LLMs) to understand and follow instructions has sometimes been limited by their in-context learning (ICL) performance in low-resource languages. To address this, we introduce a novel approach that leverages cross-lingual retrieval-augmented in-context learning (CREA-ICL). By extracting semantically similar prompts from high-resource languages, we aim to improve the zero-shot performance of multilingual pre-trained language models (MPLMs) across diverse tasks. Though our approach yields steady improvements in classification tasks, it faces challenges in generation tasks. Our evaluation offers insights into the performance dynamics of retrieval-augmented in-context learning across both classification and generation domains.

cs.CL↗

arXiv2023

Joint User Association and Bandwidth Allocation in Semantic Communication Networks

Semantic communication (SemCom) has recently been considered a promising solution to guarantee high resource utilization and transmission reliability for future wireless networks. Nevertheless, the unique demand for background knowledge matching makes it challenging to achieve efficient wireless resource management for multiple users in SemCom-enabled networks (SC-Nets). To this end, this paper investigates SemCom from a networking perspective, where two fundamental problems of user association (UA) and bandwidth allocation (BA) are systematically addressed in the SC-Net. First, considering varying knowledge matching states between mobile users and associated base stations, we identify two general SC-Net scenarios, namely perfect knowledge matching-based SC-Net and imperfect knowledge matching-based SC-Net. Afterward, for each SC-Net scenario, we describe its distinctive semantic channel model from the semantic information theory perspective, whereby a concept of bit-rate-to-message-rate transformation is developed along with a new semantics-level metric, namely system throughput in message (STM), to measure the overall network performance. In this way, we then formulate a joint STM-maximization problem of UA and BA for each SC-Net scenario, followed by a corresponding optimal solution proposed. Numerical results in both scenarios demonstrate significant superiority and reliability of our solutions in the STM performance compared with two benchmarks.

eess.SY↗

arXiv2022

Fast Quasi-Optimal Power Flow of Flexible DC Traction Power Systems

This paper proposes a quasi-optimal power flow (OPF) algorithm for flexible DC traction power systems (TPSs). Near-optimal solutions can be solved with high computational efficiency by the proposed quasi-OPF. Unlike conventional OPF utilizing mathematical optimization algorithms, the proposed quasi-OPF adopts analytical mapping from load information to near-optimal solutions, hence considerably accelerating the computation. First, we study the mechanism and physical meaning interpretation of conventional OPF based on a new modeling method and successfully interpret the mechanism of conventional OPF in flexible DC TPSs. Then, the analytical mapping from load information to near-optimal solutions is obtained inspired by the mechanism of conventional OPF, and the quasi-OPF algorithm is designed based on the mapping. Since the mapping is based on simple arithmetic, the quasi-OPF algorithm can solve OPF with much less execution time, achieving subsecond level calculation and a speed-up of 57 times compared to conventional OPF. The effectiveness is verified by mathematical proofs and a case study with Beijing Metro Line 13. It provides an insight into the mechanism and physical meaning of OPF, and is a powerful tool for flexible DC TPSs to analyze the effects of coordinated control, design real-time control strategies, and solve operational problems in planning.

eess.SY↗

arXiv2022

Wireless Resource Management in Intelligent Semantic Communication Networks

The prosperity of artificial intelligence (AI) has laid a promising paradigm of communication system, i.e., intelligent semantic communication (ISC), where semantic contents, instead of traditional bit sequences, are coded by AI models for efficient communication. Due to the unique demand of background knowledge for semantic recovery, wireless resource management faces new challenges in ISC. In this paper, we address the user association (UA) and bandwidth allocation (BA) problems in an ISC-enabled heterogeneous network (ISC-HetNet). We first introduce the auxiliary knowledge base (KB) into the system model, and develop a new performance metric for the ISC-HetNet, named system throughput in message (STM). Joint optimization of UA and BA is then formulated with the aim of STM maximization subject to KB matching and wireless bandwidth constraints. To this end, we propose a two-stage solution, including a stochastic programming method in the first stage to obtain a deterministic objective with semantic confidence, and a heuristic algorithm in the second stage to reach the optimality of UA and BA. Numerical results show great superiority and reliability of our proposed solution on the STM performance when compared with two baseline algorithms.

cs.NI↗

arXiv2020

Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings

We present JueWu-SL, the first supervised-learning-based artificial intelligence (AI) program that achieves human-level performance in playing multiplayer online battle arena (MOBA) games. Unlike prior attempts, we integrate the macro-strategy and the micromanagement of MOBA-game-playing into neural networks in a supervised and end-to-end manner. Tested on Honor of Kings, the most popular MOBA at present, our AI performs competitively at the level of High King players in standard 5v5 games.

cs.AI↗

arXiv2019

Ground-state properties of spin-orbit-coupled dipolar Bose-Einstein condensates with in-plane gradient magnetic field

We investigate the ground-state properties of spin-orbit-coupled pseudo-spin-1/2 dipolar Bose-Einstein condensates (BECs) in a two-dimensional harmonic trap and an in-plane quadrupole field. The effects of spin-orbit coupling (SOC), dipole-dipole interaction (DDI) and the in-plane quadrupole field on the ground-state structures and spin textures of the system are systematically analyzed and discussed. For fixed SOC and DDI strengths, the system shows a quadrupole stripe phase with a half-quantum vortex, or a quadrupole Thomas-Fermi phase with a half-quantum antivortex for small quadrupole field strength, depending on the ratio between inter- and intraspecies interaction. As the quadrupole field strength enhances, the system realizes a ring mixed phase with a hidden vortex-antivortex cluster rather than an ordinary giant vortex in each component. Of particular interest, when the strengths of DDI and quadrupole field are fixed, strong SOC leads to the formation of criss-crossed vortex string structure. For given SOC and quadrupole field, the system for strong DDI displays a sandwich-like structure, or a special delaminated structure with a prolate antivortex in the spin-up component. In addition, typical spin textures for the ground states of the system are analyzed. It is shown that the system sustains exotic topological structures, such as a hyperbolic spin domain wall, skyrmion-half-antiskyrmion-antiskyrmion lattice, half-skyrmion-skyrmion-half-antiskyrmion lattice, and a drum-shaped antimeron.

cond-mat.quant-gas↗

arXiv2018

Hierarchical Macro Strategy Model for MOBA Game AI

The next challenge of game AI lies in Real Time Strategy (RTS) games. RTS games provide partially observable gaming environments, where agents interact with one another in an action space much larger than that of GO. Mastering RTS games requires both strong macro strategies and delicate micro level execution. Recently, great progress has been made in micro level execution, while complete solutions for macro strategies are still lacking. In this paper, we propose a novel learning-based Hierarchical Macro Strategy model for mastering MOBA games, a sub-genre of RTS games. Trained by the Hierarchical Macro Strategy model, agents explicitly make macro strategy decisions and further guide their micro level execution. Moreover, each of the agents makes independent strategy decisions, while simultaneously communicating with the allies through leveraging a novel imitated cross-agent communication mechanism. We perform comprehensive evaluations on a popular 5v5 Multiplayer Online Battle Arena (MOBA) game. Our 5-AI team achieves a 48% winning rate against human player teams which are ranked top 1% in the player ranking system.

cs.MA↗