arXiv subjects

Fang Liu

Publications and source records attributed to Fang Liu.

At least 91 records · Page 5Linked to original sources

arXiv2025

LLM-Upgraded Graph Reinforcement Learning for Carbon-Aware Job Scheduling in Smart Manufacturing

This paper presents \textsc{Luca}, a \underline{l}arge language model (LLM)-\underline{u}pgraded graph reinforcement learning framework for \underline{c}arbon-\underline{a}ware flexible job shop scheduling. \textsc{Luca} addresses the challenges of dynamic and sustainable scheduling in smart manufacturing systems by integrating a graph neural network and an LLM, guided by a carefully designed in-house prompting strategy, to produce a fused embedding that captures both structural characteristics and contextual semantics of the latest scheduling state. This expressive embedding is then processed by a deep reinforcement learning policy network, which generates real-time scheduling decisions optimized for both makespan and carbon emission objectives. To support sustainability goals, \textsc{Luca} incorporates a dual-objective reward function that encourages both energy efficiency and scheduling timeliness. Experimental results on both synthetic and public datasets demonstrate that \textsc{Luca} consistently outperforms comparison algorithms. For instance, on the synthetic dataset, it achieves an average of 4.1\% and up to 12.2\% lower makespan compared to the best-performing comparison algorithm while maintaining the same emission level. On public datasets, additional gains are observed for both makespan and emission. These results demonstrate that \textsc{Luca} is effective and practical for carbon-aware scheduling in smart manufacturing.

cs.LG↗

arXiv2025

On the Utility of Foundation Models for Fast MRI: Vision-Language-Guided Image Reconstruction

Purpose: To investigate whether a vision-language foundation model can enhance undersampled MRI reconstruction by providing high-level contextual information beyond conventional priors. Methods: We proposed a semantic distribution-guided reconstruction framework that uses a pre-trained vision-language foundation model to encode both the reconstructed image and auxiliary information into high-level semantic features. A contrastive objective aligns the reconstructed representation with the target semantic distribution, ensuring consistency with high-level perceptual cues. The proposed objective works with various deep learning-based reconstruction methods and can flexibly incorporate semantic priors from multimodal sources. To test the effectiveness of these semantic priors, we evaluated reconstruction results guided by priors derived from either image-only or image-language auxiliary information. Results: Experiments on knee and brain datasets demonstrate that semantic priors from images preserve fine anatomical structures and achieve superior perceptual quality, as reflected in lower LPIPS values, higher Tenengrad scores, and improved scores in the reader study, compared with conventional regularization. The image-language information further expands the semantic distribution and enables high-level control over reconstruction attributes. Across all evaluations, the contrastive objective consistently guided the reconstructed features toward the desired semantic distributions while maintaining data fidelity, demonstrating the effectiveness of the proposed optimization framework. Conclusion: The study highlights that vision-language foundation models can improve undersampled MRI reconstruction through semantic-space optimization.

cs.CV↗

arXiv2025

Room-temperature valley-selective emission in Si-MoSe2 heterostructures enabled by high-quality-factor chiroptical cavities

Transition metal dichalcogenides possess valley pseudospin, enabling coupling between photon spin and electron spin for classical and quantum information processing. However, rapid valley-dephasing processes have impeded the development of scalable, high-performance valleytronic devices operating at room temperature. Here we demonstrate that a chiral resonant metasurface can enable room-temperature valley-selective emission in MoSe2 monolayers independent of excitation polarization. This platform provides circular eigen-polarization states with a high quality factor (Q-factor) and strong chiral near-field enhancement. The fabricated Si chiral metasurfaces exhibit chiroptical resonances with Q-factors up to 450 at visible wavelengths. We reveal degrees of circular polarization (DOP) reaching a record high of 0.5 at room temperature. Our measurements show that the high DOP can be attributed to the significantly increased chiroptical local density of states, which enhances valley-specific radiative transition rates by a factor of ~13. Our work could facilitate the development of ultracompact chiral classical and quantum light sources.

physics.optics↗

arXiv2025

CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation

Large Language Models (LLMs) have demonstrated exceptional performance in code generation tasks and have become indispensable programming assistants for developers. However, existing code generation benchmarks primarily assess the functional correctness of code generated by LLMs in single-turn interactions. They offer limited insight into LLMs' abilities to generate code that strictly follows users' instructions in multi-turn interaction scenarios. In this paper, we introduce CodeIF-Bench, a benchmark for evaluating the instruction-following capabilities of LLMs in interactive code generation. Specifically, CodeIF-Bench incorporates nine types of verifiable instructions aligned with the real-world software development requirements, which can be independently and objectively validated through specified test cases, facilitating the evaluation of instruction-following capability in multi-turn interactions. In both Static Conversation and Dynamic Conversation settings, we evaluate the performance of 6 state-of-the-art LLMs and summarize the important factors, additional repository context and gradually increasing interaction history influencing the instruction-following ability of LLMs in multi-turn interactions. Furthermore, we identify the potential direction for improvement: context management. The code and data are available at \href{https://github.com/zhu-zhu-ding/CodeIF-Bench}{https://github.com/zhu-zhu-ding/CodeIF-Bench}.

cs.SE↗

arXiv2025

LLMs4All: A Review of Large Language Models Across Academic Disciplines

Cutting-edge Artificial Intelligence (AI) techniques keep reshaping our view of the world. For example, Large Language Models (LLMs) based applications such as ChatGPT have shown the capability of generating human-like conversation on extensive topics. Due to the impressive performance on a variety of language-related tasks (e.g., open-domain question answering, translation, and document summarization), one can envision the far-reaching impacts that can be brought by the LLMs with broader real-world applications (e.g., customer service, education and accessibility, and scientific discovery). Inspired by their success, this paper will offer an overview of state-of-the-art LLMs and their integration into a wide range of academic disciplines, including: (1) arts, letters, and law (e.g., history, philosophy, political science, arts and architecture, law), (2) economics and business (e.g., finance, economics, accounting, marketing), and (3) science and engineering (e.g., mathematics, physics and mechanical engineering, chemistry and chemical engineering, life sciences and bioengineering, earth sciences and civil engineering, computer science and electrical engineering). Integrating humanity and technology, in this paper, we will explore how LLMs are shaping research and practice in these fields, while also discussing key limitations, open challenges, and future directions in the era of generative AI. The review of how LLMs are engaged across disciplines-along with key observations and insights-can help researchers and practitioners interested in exploiting LLMs to advance their works in diverse real-world applications.

cs.CL↗

arXiv2025

On-chip Time-bin to Path Qubit Encoding Converter via Thin Film Lithium Niobate Photonics Chip

The development of quantum internet demands on-chip quantum processor nodes and interconnection between the nodes. Path-encoded photonic qubits are suitable for on-chip quantum information processors, while time-bin encoded ones are good at long-distance communication. It is necessary to develop an on-chip converter between the two encodings to satisfy the needs of the quantum internet. In this work, a quantum photonic circuit is proposed to convert time-bin-encoded photonic qubits to path-encoded ones via a thin-film lithium niobate high-speed optical switch and low-loss matched optical delay lines. The performance of the encoding converter is demonstrated by the experiment of time-bin to path encoding conversion on the fabricated sample chip. The converted path qubits have an average fidelity higher than 97%. The potential of the encoding converter on applications in quantum networks is demonstrated by the experiments of entanglement distribution and quantum key distribution. The results show that the on-chip encoding converter can serve as a foundational component in the future quantum internet, bridging the gap between quantum information transmission and on-chip processing based on photons.

quant-ph↗

arXiv2025

Seizure-NGCLNet: Representation Learning of SEEG Spatial Pathological Patterns for Epileptic Seizure Detection via Node-Graph Dual Contrastive Learning

Complex spatial connectivity patterns, such as interictal suppression and ictal propagation, complicate accurate drug-resistant epilepsy (DRE) seizure detection using stereotactic electroencephalography (SEEG) and traditional machine learning methods. Two critical challenges remain:(1)a low signal-to-noise ratio in functional connectivity estimates, making it difficult to learn seizure-related interactions; and (2)expert labels for spatial pathological connectivity patterns are difficult to obtain, meanwhile lacking the patterns' representation to improve seizure detection. To address these issues, we propose a novel node-graph dual contrastive learning framework, Seizure-NGCLNet, to learn SEEG interictal suppression and ictal propagation patterns for detecting DRE seizures with high precision. First, an adaptive graph augmentation strategy guided by centrality metrics is developed to generate seizure-related brain networks. Second, a dual-contrastive learning approach is integrated, combining global graph-level contrast with local node-graph contrast, to encode both spatial structural and semantic epileptogenic features. Third, the pretrained embeddings are fine-tuned via a top-k localized graph attention network to perform the final classification. Extensive experiments on a large-scale public SEEG dataset from 33 DRE patients demonstrate that Seizure-NGCLNet achieves state-of-the-art performance, with an average accuracy of 95.93%, sensitivity of 96.25%, and specificity of 94.12%. Visualizations confirm that the learned embeddings clearly separate ictal from interictal states, reflecting suppression and propagation patterns that correspond to the clinical mechanisms. These results highlight Seizure-NGCLNet's ability to learn interpretable spatial pathological patterns, enhancing both seizure detection and seizure onset zone localization.

eess.SP↗

arXiv2025

GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generation

Writing code requires significant time and effort in software development. To automate this process, researchers have made substantial progress for code generation. Recently, large language models (LLMs) have demonstrated remarkable proficiency in function-level code generation, yet their performance significantly degrades in the real-world software development process, where coding tasks are deeply embedded within specific repository contexts. Existing studies attempt to use retrieval-augmented code generation (RACG) approaches to mitigate this demand. However, there is a gap between natural language (NL) requirements and programming implementations. This results in the failure to retrieve the relevant code of these fine-grained subtasks. To address this challenge, we propose GraphCodeAgent, a dual graph-guided LLM agent for retrieval-augmented repo-level code generation, bridging the gap between NL requirements and programming implementations. Our approach constructs two interconnected graphs: a Requirement Graph (RG) to model requirement relations of code snippets within the repository, as well as the relations between the target requirement and the requirements of these code snippets, and a Structural-Semantic Code Graph (SSCG) to capture the repository's intricate code dependencies. Guided by this, an LLM-powered agent performs multi-hop reasoning to systematically retrieve all context code snippets, including implicit and explicit code snippets, even if they are not explicitly expressed in requirements. We evaluated GraphCodeAgent on three advanced LLMs with the two widely-used repo-level code generation benchmarks DevEval and CoderEval. Extensive experiment results show that GraphCodeAgent significantly outperforms state-of-the-art baselines.

cs.SE↗

arXiv2025

Temperature-dependent excitonic light manipulation with atomically-thin optical elements

Monolayer 2D semiconductors, such as WS2, exhibit uniquely strong light-matter interactions due to exciton resonances that enable atomically-thin optical elements. Similar to geometry-dependent plasmon and Mie resonances, these intrinsic material resonances offer coherent and tunable light scattering. Thus far, the impact of the excitons temporal dynamics on the performance of such excitonic metasurfaces remains unexplored. Here, we show how the excitonic decay rates dictate the focusing efficiency of an atomically-thin lens carved directly out of exfoliated monolayer WS2. By isolating the coherent exciton radiation from the incoherent background in the focus of the lens, we obtain a direct measure of the role of exciton radiation in wavefront shaping. Furthermore, we investigate the influence of exciton-phonon scattering by characterizing the focusing efficiency as a function of temperature, demonstrating an increased optical efficiency at cryogenic temperatures. Our results provide valuable insights in the role of excitonic light scattering in 2D nanophotonic devices.

physics.optics↗

arXiv2025

Towards Realistic Project-Level Code Generation via Multi-Agent Collaboration and Semantic Architecture Modeling

In recent years, Large Language Models (LLMs) have achieved remarkable progress in automated code generation. In real-world software engineering, the growing demand for rapid iteration and continuous delivery underscores the importance of project-level code generation, where LLMs are expected to generate complete software projects directly from complex user requirements. Although existing studies have made initial explorations, they still face key limitations, including unrealistic datasets and unreliable evaluation metrics that fail to reflect real-world complexity, the semantic gap between human-written requirements and machine-interpretable structures, and difficulties in managing hierarchical dependencies and maintaining quality throughout the generation process. To address these limitations, we first introduce CodeProjectEval, a project-level code generation dataset built from 18 real-world repositories with 12.7 files and 2,388.6 lines of code per task on average, supplemented with documentation and executable test cases for automatic evaluation. We further propose ProjectGen, a multi-agent framework that decomposes projects into architecture design, skeleton generation, and code filling stages with iterative refinement and memory-based context management. Within this framework, we introduce the Semantic Software Architecture Tree (SSAT), a structured and semantically rich representation that effectively bridges user requirements and source code implementation. Experiments show that ProjectGen achieves state-of-the-art performance, passing 52/124 test cases on the small-scale project-level code generation dataset DevBench, a 57% improvement over the baseline approaches, and 310 test cases on CodeProjectEval, representing an improvement of roughly tenfold compared to the baselines.

cs.SE↗

arXiv2025

RepoScope: Leveraging Call Chain-Aware Multi-View Context for Repository-Level Code Generation

Repository-level code generation aims to generate code within the context of a specified repository. Existing approaches typically employ retrieval-augmented generation (RAG) techniques to provide LLMs with relevant contextual information extracted from the repository. However, these approaches often struggle with effectively identifying truly relevant contexts that capture the rich semantics of the repository, and their contextual perspectives remains narrow. Moreover, most approaches fail to account for the structural relationships in the retrieved code during prompt construction, hindering the LLM's ability to accurately interpret the context. To address these issues, we propose RepoScope, which leverages call chain-aware multi-view context for repository-level code generation. RepoScope constructs a Repository Structural Semantic Graph (RSSG) and retrieves a comprehensive four-view context, integrating both structural and similarity-based contexts. We propose a novel call chain prediction method that utilizes the repository's structural semantics to improve the identification of callees in the target function. Additionally, we present a structure-preserving serialization algorithm for prompt construction, ensuring the coherence of the context for the LLM. Notably, RepoScope relies solely on static analysis, eliminating the need for additional training or multiple LLM queries, thus ensuring both efficiency and generalizability. Evaluation on widely-used repository-level code generation benchmarks (CoderEval and DevEval) demonstrates that RepoScope outperforms state-of-the-art methods, achieving up to a 36.35% relative improvement in pass@1 scores. Further experiments emphasize RepoScope's potential to improve code generation across different tasks and its ability to integrate effectively with existing approaches.

cs.SE↗

arXiv2025

SecureReviewer: Enhancing Large Language Models for Secure Code Review through Secure-aware Fine-tuning

Identifying and addressing security issues during the early phase of the development lifecycle is critical for mitigating the long-term negative impacts on software systems. Code review serves as an effective practice that enables developers to check their teammates' code before integration into the codebase. To streamline the generation of review comments, various automated code review approaches have been proposed, where LLM-based methods have significantly advanced the capabilities of automated review generation. However, existing models primarily focus on general-purpose code review, their effectiveness in identifying and addressing security-related issues remains underexplored. Moreover, adapting existing code review approaches to target security issues faces substantial challenges, including data scarcity and inadequate evaluation metrics. To address these limitations, we propose SecureReviewer, a new approach designed for enhancing LLMs' ability to identify and resolve security-related issues during code review. Specifically, we first construct a dataset tailored for training and evaluating secure code review capabilities. Leveraging this dataset, we fine-tune LLMs to generate code review comments that can effectively identify security issues and provide fix suggestions with our proposed secure-aware fine-tuning strategy. To mitigate hallucination in LLMs and enhance the reliability of their outputs, we integrate the RAG technique, which grounds the generated comments in domain-specific security knowledge. Additionally, we introduce SecureBLEU, a new evaluation metric designed to assess the effectiveness of review comments in addressing security issues. Experimental results demonstrate that SecureReviewer outperforms state-of-the-art baselines in both security issue detection accuracy and the overall quality and practical utility of generated review comments.

cs.SE↗

arXiv2025

10 quick tips for making your software outlive your job

Loss of key personnel has always been a risk for research software projects. Key members of the team may have to step away due to illness or burnout, to care for a family member, from a loss of financial support, or because their career is going in a new direction. Today, though, political and financial changes are putting large numbers of researchers out of work simultaneously, potentially leaving large amounts of research software abandoned. This article presents ten tips to help researchers ensure that the software they have built will continue to be usable after they have left their present job -- whether in the course of voluntary career moves or researcher mobility, but particularly in cases of involuntary departure due to political or institutional changes.

cs.SE↗

arXiv2025

SAFES: Sequential Privacy and Fairness Enhancing Data Synthesis for Responsible AI

As data-driven and AI-based decision making gains widespread adoption across disciplines, it is crucial that both data privacy and decision fairness are appropriately addressed. Although differential privacy (DP) provides a robust framework for guaranteeing privacy and methods are available to improve fairness, most prior work treats the two concerns separately. Even though there are existing approaches that consider privacy and fairness simultaneously, they typically focus on a single specific learning task, limiting their generalizability. In response, we introduce SAFES, a Sequential PrivAcy and Fairness Enhancing data Synthesis procedure that sequentially combines DP data synthesis with a fairness-aware data preprocessing step. SAFES allows users flexibility in navigating the privacy-fairness-utility trade-offs. We illustrate SAFES with different DP synthesizers and fairness-aware data preprocessing methods and run extensive experiments on multiple real datasets to examine the privacy-fairness-utility trade-offs of synthetic data generated by SAFES. Empirical evaluations demonstrate that for reasonable privacy loss, SAFES-generated synthetic data can achieve significantly improved fairness metrics with relatively low utility loss.

cs.LG↗

arXiv2025

Edit-Your-Interest: Efficient Video Editing via Feature Most-Similar Propagation

Text-to-image (T2I) diffusion models have recently demonstrated significant progress in video editing. However, existing video editing methods are severely limited by their high computational overhead and memory consumption. Furthermore, these approaches often sacrifice visual fidelity, leading to undesirable temporal inconsistencies and artifacts such as blurring and pronounced mosaic-like patterns. We propose Edit-Your-Interest, a lightweight, text-driven, zero-shot video editing method. Edit-Your-Interest introduces a spatio-temporal feature memory to cache features from previous frames, significantly reducing computational overhead compared to full-sequence spatio-temporal modeling approaches. Specifically, we first introduce a Spatio-Temporal Feature Memory bank (SFM), which is designed to efficiently cache and retain the crucial image tokens processed by spatial attention. Second, we propose the Feature Most-Similar Propagation (FMP) method. FMP propagates the most relevant tokens from previous frames to subsequent ones, preserving temporal consistency. Finally, we introduce an SFM update algorithm that continuously refreshes the cached features, ensuring their long-term relevance and effectiveness throughout the video sequence. Furthermore, we leverage cross-attention maps to automatically extract masks for the instances of interest. These masks are seamlessly integrated into the diffusion denoising process, enabling fine-grained control over target objects and allowing Edit-Your-Interest to perform highly accurate edits while robustly preserving the background integrity. Extensive experiments decisively demonstrate that the proposed Edit-Your-Interest outperforms state-of-the-art methods in both efficiency and visual fidelity, validating its superior effectiveness and practicality.

cs.CV↗

arXiv2025

MC BTS: simultaneously resolving magnetization transfer effect and relaxation for multiple components

We propose a signal acquisition and modeling framework for multi-component tissue quantification that encompasses transmit field inhomogeneity, multi-component relaxation and magnetization transfer (MT) effects. By applying off-resonance irradiation between excitation and acquisition within an RF-spoiled gradient-echo scheme, in combination with multiple echo-time acquisitions, both Bloch-Siegert shift and magnetization transfer effects are simultaneously induced while relaxation and spin exchange processes occur concurrently. Simulation results showed excellent agreement with the derived analytical signal equation across a wide range of flip angles and echo times. Monte Carlo analyses further validated that the three-pool parameter estimation pipeline performed robustly over various signal-to-noise ratio conditions. Multi-parameter fitting results from in vivo brain and knee studies yielded values consistent with previously reported literature. Collectively, these findings confirm that the proposed method can reliably characterize multi-component tissue parameters in macromolecule-rich environments while effectively compensating for $B_1^+$ inhomogeneity.

physics.med-ph↗

arXiv2025

Tracking the photoinduced dynamics of a dark excitonic state in single-layer WS$_2$ via resonant Autler-Townes splitting

Excitons in a monolayer transition metal dichalcogenide (1L-TMD) are highly bound states characterized by a Rydberg-like spectrum of discrete energy levels. Among these, states with odd-parity are known as dark excitons due to selection rules, which make their stationary and transient characterization challenging using linear optical techniques. Here, we demonstrate that the dynamics of a 2p dark excitonic state in 1L-WS$_2$ can be directly retrieved by measuring the Autler-Townes splitting of bright states in a three-pulse experiment. The splitting of the bright 1s excitonic state, observed by detuning a mid-infrared control field across the 1s-2p transition, provides an accurate characterization of the 2p state. Following carrier photoinjection, we observe a qualitatively different dynamics of the 1s and 2p levels, which is indicative of symmetry-dependent screening and exciton-exciton interactions. These findings provide new insights into many-body effects in TMDs, offering potential avenues for advancing the next generation optoelectronics.

cond-mat.mes-hall↗

arXiv2025

FastCoder: Accelerating Repository-level Code Generation via Efficient Retrieval and Verification

Code generation is a latency-sensitive task that demands high timeliness. However, with the growing interest and inherent difficulty in repository-level code generation, most existing code generation studies focus on improving the correctness of generated code while overlooking the inference efficiency, which is substantially affected by the overhead during LLM generation. Although there has been work on accelerating LLM inference, these approaches are not tailored to the specific characteristics of code generation; instead, they treat code the same as natural language sequences and ignore its unique syntax and semantic characteristics, which are also crucial for improving efficiency. Consequently, these approaches exhibit limited effectiveness in code generation tasks, particularly for repository-level scenarios with considerable complexity and difficulty. To alleviate this issue, following draft-verification paradigm, we propose FastCoder, a simple yet highly efficient inference acceleration approach specifically designed for code generation, without compromising the quality of the output. FastCoder constructs a multi-source datastore, providing access to both general and project-specific knowledge, facilitating the retrieval of high-quality draft sequences. Moreover, FastCoder reduces the retrieval cost by controlling retrieval timing, and enhances efficiency through parallel retrieval and a context- and LLM preference-aware cache. Experimental results show that FastCoder can reach up to 2.53x and 2.54x speedup compared to autoregressive decoding in repository-level and standalone code generation tasks, respectively, outperforming state-of-the-art inference acceleration approaches by up to 88%. FastCoder can also be integrated with existing correctness-focused code generation approaches to accelerate the LLM generation process, and reach a speedup exceeding 2.6x.

cs.AI↗