arXiv subjects

Xiao Long

Publications and source records attributed to Xiao Long.

10 recordsLinked to original sources

arXiv2026

TeleCom-Bench: How Far Are Large Language Models from Industrial Telecommunication Applications?

While Large Language Models have achieved remarkable integration in various vertical scenarios, their deployment in the telecommunications domain remains exploratory due to the lack of a standardized evaluation framework. Current telecom benchmarks primarily focus on static, foundational knowledge and isolated atomic skills, neglecting the equipment-specific documentation and end-to-end industrial workflows essential for real-world production systems. To bridge this gap, we present TeleCom-Bench, a comprehensive benchmark comprising 12 evaluation sets with 22,678 curated samples, which evaluates LLMs across a synergistic hierarchy: (1) Multi-dimensional Knowledge Comprehension, which integrates telecommunication fundamentals, 3GPP protocols, and 5G network architecture with proprietary product knowledge across wired, core, and wireless networks via knowledge graph-driven synthesis; and (2)End-to-End Knowledge Application, which formalizes six core tasks on authentic trajectories from live network agent workflows, including intent recognition, entity extraction, event verification, tool invocation, root cause analysis, and solution generation-across network optimization and fault maintenance scenarios. Evaluations of eight state-of-the-art LLMs reveal a universal Execution Wall: while models achieve 90% accuracy in linguistic interface tasks such as intent recognition and entity extraction, performance collapses to approximately 30% in procedural execution tasks like solution generation. This capability gap demonstrates that current LLMs function competently as diagnosticians but fail as field engineers. TeleCom-Bench provides standardized diagnostics to precisely pinpoint this deficit, offering actionable guidance for domain-specific alignment toward production-ready telecom agents. The dataset and evaluation code have been released at https://github.com/ZTE-AICloud/TeleCom-Bench.

cs.AI↗

arXiv2026

PerformRecast: Expression and Head Pose Disentanglement for Portrait Video Editing

This paper primarily investigates the task of expression-only portrait video performance editing based on a driving video, which plays a crucial role in animation and film industries. Most existing research mainly focuses on portrait animation, which aims to animate a static portrait image according to the facial motion from the driving video. As a consequence, it remains challenging for them to disentangle the facial expression from head pose rotation and thus lack the ability to edit facial expression independently. In this paper, we propose PerformRecast, a versatile expression-only video editing method which is dedicated to recast the performance in existing film and animation. The key insight of our method comes from the characteristics of 3D Morphable Face Model (3DMM), which models the face identity, facial expression and head pose of 3D face mesh with separate parameters. Therefore, we improve the keypoints transformation formula in previous methods to make it more consistent with 3DMM model, which achieves a better disentanglement and provides users with much more fine-grained control. Furthermore, to avoid the misalignment around the boundary of face in generated results, we decouple the facial and non-facial regions of input portrait images and pre-train a teacher model to provide separate supervision for them. Extensive experiments show that our method produces high-quality results which are more faithful to the driving video, outperforming existing methods in both controllability and efficiency. Our code, data and trained models are available at https://youku-aigc.github.io/PerformRecast.

cs.CV↗

arXiv2025

Enhancing Large Language Models with Reward-guided Tree Search for Knowledge Graph Question and Answering

Recently, large language models (LLMs) have demonstrated impressive performance in Knowledge Graph Question Answering (KGQA) tasks, which aim to find answers based on knowledge graphs (KGs) for natural language questions. Existing LLMs-based KGQA methods typically follow the Graph Retrieval-Augmented Generation (GraphRAG) paradigm, which first retrieves reasoning paths from the large KGs, and then generates the answers based on them. However, these methods emphasize the exploration of new optimal reasoning paths in KGs while ignoring the exploitation of historical reasoning paths, which may lead to sub-optimal reasoning paths. Additionally, the complex semantics contained in questions may lead to the retrieval of inaccurate reasoning paths. To address these issues, this paper proposes a novel and training-free framework for KGQA tasks called Reward-guided Tree Search on Graph (RTSoG). RTSoG decomposes an original question into a series of simpler and well-defined sub-questions to handle the complex semantics. Then, a Self-Critic Monte Carlo Tree Search (SC-MCTS) guided by a reward model is introduced to iteratively retrieve weighted reasoning paths as contextual knowledge. Finally, it stacks the weighted reasoning paths according to their weights to generate the final answers. Extensive experiments on four datasets demonstrate the effectiveness of RTSoG. Notably, it achieves 8.7\% and 7.0\% performance improvement over the state-of-the-art method on the GrailQA and the WebQSP respectively.

cs.CL↗

arXiv2025

Revolutionizing Newcomers' Onboarding Process in OSS Communities: The Future AI Mentor

Onboarding newcomers is vital for the sustainability of open-source software (OSS) projects. To lower barriers and increase engagement, OSS projects have dedicated experts who provide guidance for newcomers. However, timely responses are often hindered by experts' busy schedules. The recent rapid advancements of AI in software engineering have brought opportunities to leverage AI as a substitute for expert mentoring. However, the potential role of AI as a comprehensive mentor throughout the entire onboarding process remains unexplored. To identify design strategies of this ``AI mentor'', we applied Design Fiction as a participatory method with 19 OSS newcomers. We investigated their current onboarding experience and elicited 32 design strategies for future AI mentor. Participants envisioned AI mentor being integrated into OSS platforms like GitHub, where it could offer assistance to newcomers, such as ``recommending projects based on personalized requirements'' and ``assessing and categorizing project issues by difficulty''. We also collected participants' perceptions of a prototype, named ``OSSerCopilot'', that implemented the envisioned strategies. They found the interface useful and user-friendly, showing a willingness to use it in the future, which suggests the design strategies are effective. Finally, in order to identify the gaps between our design strategies and current research, we conducted a comprehensive literature review, evaluating the extent of existing research support for this concept. We find that research is relatively scarce in certain areas where newcomers highly anticipate AI mentor assistance, such as ``discovering an interested project''. Our study has the potential to revolutionize the current newcomer-expert mentorship and provides valuable insights for researchers and tool designers aiming to develop and enhance AI mentor systems.

cs.SE↗

arXiv2025

EPERM: An Evidence Path Enhanced Reasoning Model for Knowledge Graph Question and Answering

Due to the remarkable reasoning ability, Large language models (LLMs) have demonstrated impressive performance in knowledge graph question answering (KGQA) tasks, which find answers to natural language questions over knowledge graphs (KGs). To alleviate the hallucinations and lack of knowledge issues of LLMs, existing methods often retrieve the question-related information from KGs to enrich the input context. However, most methods focus on retrieving the relevant information while ignoring the importance of different types of knowledge in reasoning, which degrades their performance. To this end, this paper reformulates the KGQA problem as a graphical model and proposes a three-stage framework named the Evidence Path Enhanced Reasoning Model (EPERM) for KGQA. In the first stage, EPERM uses the fine-tuned LLM to retrieve a subgraph related to the question from the original knowledge graph. In the second stage, EPERM filters out the evidence paths that faithfully support the reasoning of the questions, and score their importance in reasoning. Finally, EPERM uses the weighted evidence paths to reason the final answer. Since considering the importance of different structural information in KGs for reasoning, EPERM can improve the reasoning ability of LLMs in KGQA tasks. Extensive experiments on benchmark datasets demonstrate that EPERM achieves superior performances in KGQA tasks.

cs.CL↗

arXiv2025

Flatness Guided Test-Time Adaptation for Vision-Language Models

Test-time adaptation (TTA) of Vision-Language Models (VLMs) has emerged as a technique for tackling distribution shifts during the test time. Recent research indicates that the test-time adaptation is intrinsically linked to the model's training history. However, existing TTA methods, such as Test-time Prompt Tuning, often design adaptation strategies in isolation from the models' training characteristics, which degrade their performance. This paper argues that the flatness acquired via sharpness-aware training is an efficient clue for the test-time adaptation of VLMs. Built on this insight, this paper proposes a novel Flatness-Guided Adaptation framework (FGA) for VLMs to cohesively unify training and test-time procedures. Its core idea is to leverage the alignment between the training minimum and test loss flat regions to guide the adaptation process. Specifically, our FGA consists of a prompt-tuning stage and a test-time adaptation stage. In the tuning stage, a Sharpness-Aware Prompt Tuning method is utilized to identify the training flat minimum, offering a geometric clue of flatness for subsequent adaptation. In the test stage, a Sharpness-based Test Sample Selection approach is proposed to ensure the alignment of flat minima between the training and each augmented test sample's loss landscape. In comparison to existing TTA methods, our FGA avoids the expensive prompt parameter updates during test time, and substantially reduces the computation overhead. Extensive experiments on both domain generalization and cross-dataset benchmarks demonstrate that our FGA achieves superior performance over prevalent TTA methods. Notably, when employing a ViT-B/16 image encoder, FGA even outperforms TPT+CoOp by an average of 4.88% across all four ImageNet out-of-domain variants.

cs.CV↗

arXiv2025

Comparative Analysis of Pre-trained Deep Learning Models and DINOv2 for Cushing's Syndrome Diagnosis in Facial Analysis

Cushing's syndrome is a condition caused by excessive glucocorticoid secretion from the adrenal cortex, often manifesting with moon facies and plethora, making facial data crucial for diagnosis. Previous studies have used pre-trained convolutional neural networks (CNNs) for diagnosing Cushing's syndrome using frontal facial images. However, CNNs are better at capturing local features, while Cushing's syndrome often presents with global facial features. Transformer-based models like ViT and SWIN, which utilize self-attention mechanisms, can better capture long-range dependencies and global features. Recently, DINOv2, a foundation model based on visual Transformers, has gained interest. This study compares the performance of various pre-trained models, including CNNs, Transformer-based models, and DINOv2, in diagnosing Cushing's syndrome. We also analyze gender bias and the impact of freezing mechanisms on DINOv2. Our results show that Transformer-based models and DINOv2 outperformed CNNs, with ViT achieving the highest F1 score of 85.74%. Both the pre-trained model and DINOv2 had higher accuracy for female samples. DINOv2 also showed improved performance when freezing parameters. In conclusion, Transformer-based models and DINOv2 are effective for Cushing's syndrome classification.

cs.LG↗

arXiv2024

Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes

Domain generalization aims to learn a model from multiple training domains and generalize it to unseen test domains. Recent theory has shown that seeking the deep models, whose parameters lie in the flat minima of the loss landscape, can significantly reduce the out-of-domain generalization error. However, existing methods often neglect the consistency of loss landscapes in different domains, resulting in models that are not simultaneously in the optimal flat minima in all domains, which limits their generalization ability. To address this issue, this paper proposes an iterative Self-Feedback Training (SFT) framework to seek consistent flat minima that are shared across different domains by progressively refining loss landscapes during training. It alternatively generates a feedback signal by measuring the inconsistency of loss landscapes in different domains and refines these loss landscapes for greater consistency using this feedback signal. Benefiting from the consistency of the flat minima within these refined loss landscapes, our SFT helps achieve better out-of-domain generalization. Extensive experiments on DomainBed demonstrate superior performances of SFT when compared to state-of-the-art sharpness-aware methods and other prevalent DG baselines. On average across five DG benchmarks, SFT surpasses the sharpness-aware minimization by 2.6% with ResNet-50 and 1.5% with ViT-B/16, respectively. The code will be available soon.

cs.CV↗

arXiv2024

How far are AI-powered programming assistants from meeting developers' needs?

Recent In-IDE AI coding assistant tools (ACATs) like GitHub Copilot have significantly impacted developers' coding habits. While some studies have examined their effectiveness, there lacks in-depth investigation into the actual assistance process. To bridge this gap, we simulate real development scenarios encompassing three typical types of software development tasks and recruit 27 computer science students to investigate their behavior with three popular ACATs. Our goal is to comprehensively assess ACATs' effectiveness, explore characteristics of recommended code, identify reasons for modifications, and understand users' challenges and expectations. To facilitate the study, we develop an experimental platform that includes a data collection plugin for VSCode IDE and provides functions for screen recording, code evaluation, and automatic generation of personalized interview and survey questions. Through analysis of the collected data, we find that ACATs generally enhance task completion rates, reduce time, improve code quality, and increase self-perceived productivity. However, the improvement is influenced by both the nature of coding tasks and users' experience level. Notably, for experienced participants, the use of ACATs may even increase completion time. We observe that "edited line completion" is the most frequently recommended way, while "comments completion" and "string completion" have the lowest acceptance rates. The primary reasons for modifying recommended code are disparities between output formats and requirements, flawed logic, and inconsistent code styles. In terms of challenges and expectations, optimization of service access and help documentation is also concerned by participants except for functionality and performance. Our study provides valuable insights into the effectiveness and usability of ACATs, informing further improvements in their design and implementation.

cs.SE↗

arXiv2020

Unraveling ferroelectric polarization and ionic contributions to electroresistance in epitaxial Hf0.5Zr0.5O2 tunnel junctions

Tunnel devices based on ferroelectric Hf0.5Zr0.5O2 (HZO) barriers hold great promises for emerging data storage and computing technologies. The resistance state of the device can be changed by a suitable writing voltage. However, the microscopic mechanisms leading to the resistance change are an intricate interplay between ferroelectric polarization controlled barrier properties and defect-related transport mechanisms. Here is shown the fundamental role of the microstructure of HZO films setting the balance between those contributions. The oxide film presents coherent or incoherent grain boundaries, associated to the existence of monoclinic and orthorhombic phases in HZO films, which are dictated by the mismatch with the substrates for epitaxial growth. These grain boundaries are the toggle that allows to obtain either large (up to 450 %) and fully reversible genuine polarization controlled electroresistance when only the orthorhombic phase is present or an irreversible and extremely large (1000-100000 %) electroresistance when both phases coexist.

cond-mat.mtrl-sci↗