arXiv subjects

Qi Zhang

Publications and source records attributed to Qi Zhang.

At least 487 records · Page 27Linked to original sources

arXiv2025

Amplifier: Bringing Attention to Neglected Low-Energy Components in Time Series Forecasting

We propose an energy amplification technique to address the issue that existing models easily overlook low-energy components in time series forecasting. This technique comprises an energy amplification block and an energy restoration block. The energy amplification block enhances the energy of low-energy components to improve the model's learning efficiency for these components, while the energy restoration block returns the energy to its original level. Moreover, considering that the energy-amplified data typically displays two distinct energy peaks in the frequency spectrum, we integrate the energy amplification technique with a seasonal-trend forecaster to model the temporal relationships of these two peaks independently, serving as the backbone for our proposed model, Amplifier. Additionally, we propose a semi-channel interaction temporal relationship enhancement block for Amplifier, which enhances the model's ability to capture temporal relationships from the perspective of the commonality and specificity of each channel in the data. Extensive experiments on eight time series forecasting benchmarks consistently demonstrate our model's superiority in both effectiveness and efficiency compared to state-of-the-art methods.

cs.LG↗

arXiv2025

Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling

Self-improvement methods enable large language models (LLMs) to generate solutions themselves and iteratively train on filtered, high-quality rationales. This process proves effective and reduces the reliance on human supervision in LLMs' reasoning, but the performance soon plateaus. We delve into the process and find that models tend to over-sample on easy queries and under-sample on queries they have yet to master. As iterations proceed, this imbalance in sampling is exacerbated, leading to a long-tail distribution where solutions to difficult queries almost diminish. This phenomenon limits the performance gain of self-improving models. A straightforward solution is brute-force sampling to balance the distribution, which significantly raises computational costs. In this paper, we introduce Guided Self-Improvement (GSI), a strategy aimed at improving the efficiency of sampling challenging heavy-tailed data. It leverages Socratic-style guidance signals to help LLM reasoning with complex queries, reducing the exploration effort and minimizing computational overhead. Experiments on four models across diverse mathematical tasks show that GSI strikes a balance between performance and efficiency, while also being effective on held-out tasks.

cs.CL↗

arXiv2025

Unsupervised CP-UNet Framework for Denoising DAS Data with Decay Noise

Distributed acoustic sensor (DAS) technology leverages optical fiber cables to detect acoustic signals, providing cost-effective and dense monitoring capabilities. It offers several advantages including resistance to extreme conditions, immunity to electromagnetic interference, and accurate detection. However, DAS typically exhibits a lower signal-to-noise ratio (S/N) compared to geophones and is susceptible to various noise types, such as random noise, erratic noise, level noise, and long-period noise. This reduced S/N can negatively impact data analyses containing inversion and interpretation. While artificial intelligence has demonstrated excellent denoising capabilities, most existing methods rely on supervised learning with labeled data, which imposes stringent requirements on the quality of the labels. To address this issue, we develop a label-free unsupervised learning (UL) network model based on Context-Pyramid-UNet (CP-UNet) to suppress erratic and random noises in DAS data. The CP-UNet utilizes the Context Pyramid Module in the encoding and decoding process to extract features and reconstruct the DAS data. To enhance the connectivity between shallow and deep features, we add a Connected Module (CM) to both encoding and decoding section. Layer Normalization (LN) is utilized to replace the commonly employed Batch Normalization (BN), accelerating the convergence of the model and preventing gradient explosion during training. Huber-loss is adopted as our loss function whose parameters are experimentally determined. We apply the network to both the 2-D synthetic and filed data. Comparing to traditional denoising methods and the latest UL framework, our proposed method demonstrates superior noise reduction performance.

cs.SD↗

arXiv2025

D.Va: Validate Your Demonstration First Before You Use It

In-context learning (ICL) has demonstrated significant potential in enhancing the capabilities of large language models (LLMs) during inference. It's well-established that ICL heavily relies on selecting effective demonstrations to generate outputs that better align with the expected results. As for demonstration selection, previous approaches have typically relied on intuitive metrics to evaluate the effectiveness of demonstrations, which often results in limited robustness and poor cross-model generalization capabilities. To tackle these challenges, we propose a novel method, \textbf{D}emonstration \textbf{VA}lidation (\textbf{D.Va}), which integrates a demonstration validation perspective into this field. By introducing the demonstration validation mechanism, our method effectively identifies demonstrations that are both effective and highly generalizable. \textbf{D.Va} surpasses all existing demonstration selection techniques across both natural language understanding (NLU) and natural language generation (NLG) tasks. Additionally, we demonstrate the robustness and generalizability of our approach across various language models with different retrieval models.

cs.CL↗

arXiv2025

Causal Learning for Trustworthy Recommender Systems: A Survey

Recommender Systems (RS) have significantly advanced online content filtering and personalized decision-making. However, emerging vulnerabilities in RS have catalyzed a paradigm shift towards Trustworthy RS (TRS). Despite substantial progress on TRS, most efforts focus on data correlations while overlooking the fundamental causal nature of recommendations. This drawback hinders TRS from identifying the root cause of trustworthiness issues, leading to limited fairness, robustness, and explainability. To bridge this gap, causal learning emerges as a class of promising methods to augment TRS. These methods, grounded in reliable causality, excel in mitigating various biases and noise while offering insightful explanations for TRS. However, there is a lack of timely and dedicated surveys in this vibrant area. This paper creates an overview of TRS from the perspective of causal learning. We begin by presenting the advantages and common procedures of Causality-oriented TRS (CTRS). Then, we identify potential trustworthiness challenges at each stage and link them to viable causal solutions, followed by a classification of CTRS methods. Finally, we discuss several future directions for advancing this field.

cs.IR↗

arXiv2025

WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models

Despite recent progress achieved by code large language models (LLMs), their remarkable abilities are largely dependent on fine-tuning on the high-quality data, posing challenges for data collection and annotation. To address this, current methods often design various data flywheels to collect complex code instructions, enabling models to handle more intricate tasks. However, these approaches typically rely on off-the-shelf datasets and data augmentation from a limited set of proprietary LLMs (e.g., Claude, GPT4, and so on), which restricts the diversity of the constructed data and makes it prone to systemic biases. In this paper, we propose WarriorCoder, a novel paradigm learns from expert battles to address these limitations. Specifically, we create an arena where leading expert code LLMs challenge each other, with evaluations conducted by impartial judges. This competitive framework generates novel training data from scratch, leveraging the strengths of all participants. Experimental results show that WarriorCoder achieves state-of-the-art performance compared to previous models of the same size, even without relying on proprietary LLMs.

cs.CL↗

arXiv2025

Fully passive quantum key distribution with parametric down-conversion source

The fully passive source is capable of passively generating decoy states and performing passive encoding simultaneously, avoiding the side-channel risks caused by active modulation operations at the source end, thus effectively enhance the security in quantum key distribution (QKD). Existing fully passive QKD protocol and experiments exploit phase-randomized coherent pulses. In this paper, we propose a fully passive QKD protocol using parametric down-conversion source. The decoy state generation and encoding operation can be carried out passively by parameter down-conversion progress. This protocol has several advantages. First, it can also eliminate all side channels in active modulators. Second, compared with fully passive QKD protocol with phase-randomized coherent pulses, our protocol can significantly increase the key rate and extend the communication distance. Meanwhile, in terms of the transmission rate, our protocol is also closer to that of actively modulated QKD and can achieve fully passive modulation with fewer resources. Moreover, combined with measurement-device-independent (MDI) QKD, this protocol can even potentially achieve robustness against side channels in both detectors and modulators.

quant-ph↗

arXiv2025

Superconductivity and a van Hove singularity confined to the surface of a topological semimetal

The interplay between electronic topology and superconductivity is the subject of great current interest in condensed matter physics. For example, superconductivity induced on the surface of topological insulators is predicted to be triplet in nature, while the interplay between electronic correlations and topology may lead to unconventional superconductivity as in twisted bilayer graphene. Here, we unveil an unconventional two-dimensional superconducting state in the recently discovered Dirac nodal line semimetal ZrAs2 which is exclusively confined to the top and bottom surfaces within the crystal's ab plane. As a remarkable consequence of this emergent state, we observe a Berezinskii-Kosterlitz-Thouless (BKT) transition, the hallmark of two-dimensional superconductivity. Notably, this is the first observation of a BKT transition on the surface of a three-dimensional system. Furthermore, employing angle-resolved photoemission spectroscopy and first-principles calculations, we find that these same surfaces also host a two-dimensional van Hove singularity near the Fermi energy. The proximity of van Hove singularity to the Fermi level leads to enhanced electronic correlations contributing to the stabilization of superconductivity at the surface of ZrAs2, a unique phenomenon among topological semimetals. The surface-confined nature of the van Hove singularity, and associated superconductivity, realized for the first time, opens new avenues to explore the interplay between low-dimensional quantum topology, correlations, and superconductivity in a bulk material without resorting to the superconducting proximity effect.

cond-mat.supr-con↗

arXiv2025

Self-Consistency of the Internal Reward Models Improves Self-Rewarding Language Models

Aligning Large Language Models (LLMs) with human preferences is crucial for their deployment in real-world applications. Recent advancements in Self-Rewarding Language Models suggest that an LLM can use its internal reward models (such as LLM-as-a-Judge) \cite{yuanself} to generate preference data, improving alignment performance without costly human annotation. However, we find that different internal reward models within the same LLM often generate inconsistent preferences. This inconsistency raises concerns about the reliability of self-generated preference data, hinders overall alignment performance, and highlights the need for further research to ensure reliable and coherent alignment with human preferences. To address this limitation, we propose Self-Consistent Internal Rewards (SCIR), a novel framework designed to enhance consistency among internal reward models during training. In each training step, we collect preference predictions from multiple pre-defined internal reward models and enforce consistency and confidence through an inconsistency penalty mechanism, thereby improving the reliability of these internal reward models. We selectively use data with consistent predictions for preference optimization, ensuring the quality of the preference data. By employing self-consistent internal rewards, our method significantly improves the alignment performance and reward modeling capability of LLMs, outperforming baseline methods by a notable margin.

cs.AI↗

arXiv2025

Broken symmetries associated with a Kagome chiral charge order

Chirality or handedness manifests in all fields of science, ranging from cell biology, molecular interaction, and catalysis to different branches of physics. In condensed matter physics, chirality is intrinsic to enigmatic quantum phases, such as chiral charge density waves and chiral superconductivity. Here, the underlying chiral response is subtle and leads to broken symmetries in the ground state. Detection of subtle broken symmetries is the key to understand these quantum states but they are extremely challenging to expose leading to debate and controversy. Here, using second-order optical response, we uncover the broken symmetries of a chiral charge density wave in the Kagome lattice KV3Sb5, revealing the relevant broken symmetries of its charge order. KV3Sb5 undergoes a phase transition to a charge-ordered state at low temperatures. Our polarization-dependent mid-infrared photocurrent microscopy reveals an intrinsic, longitudinal helicity-dependent photocurrent associated with the charge order. Our measurements, supported by our theoretical analysis, provide direct evidence for broken inversion and mirror symmetries at the charge order transition, indicating a chiral charge ordered state. On the other hand, we do not observe a circular photogalvanic effect along the direction perpendicular to that of the incident light, imposing stringent constraints on the rotational and point group symmetries of the charge order. Our study not only visualizes the chiral nature of the Kagome charge order revealing its broken symmetries, but also highlights the nonlinear photogalvanic effect as a sensitive probe for detecting subtle symmetry breakings.

cond-mat.str-el↗

arXiv2025

IN-Flow: Instance Normalization Flow for Non-stationary Time Series Forecasting

Due to the non-stationarity of time series, the distribution shift problem largely hinders the performance of time series forecasting. Existing solutions either rely on using certain statistics to specify the shift, or developing specific mechanisms for certain network architectures. However, the former would fail for the unknown shift beyond simple statistics, while the latter has limited compatibility on different forecasting models. To overcome these problems, we first propose a decoupled formulation for time series forecasting, with no reliance on fixed statistics and no restriction on forecasting architectures. This formulation regards the removing-shift procedure as a special transformation between a raw distribution and a desired target distribution and separates it from the forecasting. Such a formulation is further formalized into a bi-level optimization problem, to enable the joint learning of the transformation (outer loop) and forecasting (inner loop). Moreover, the special requirements of expressiveness and bi-direction for the transformation motivate us to propose instance normalization flow (IN-Flow), a novel invertible network for time series transformation. Different from the classic "normalizing flow" models, IN-Flow does not aim for normalizing input to the prior distribution (e.g., Gaussian distribution) for generation, but creatively transforms time series distribution by stacking normalization layers and flow-based invertible networks, which is thus named "normalization" flow. Finally, we have conducted extensive experiments on both synthetic data and real-world data, which demonstrate the superiority of our method.

cs.LG↗

arXiv2025

MEETING DELEGATE: Benchmarking LLMs on Attending Meetings on Our Behalf

In contemporary workplaces, meetings are essential for exchanging ideas and ensuring team alignment but often face challenges such as time consumption, scheduling conflicts, and inefficient participation. Recent advancements in Large Language Models (LLMs) have demonstrated their strong capabilities in natural language generation and reasoning, prompting the question: can LLMs effectively delegate participants in meetings? To explore this, we develop a prototype LLM-powered meeting delegate system and create a comprehensive benchmark using real meeting transcripts. Our evaluation reveals that GPT-4/4o maintain balanced performance between active and cautious engagement strategies. In contrast, Gemini 1.5 Pro tends to be more cautious, while Gemini 1.5 Flash and Llama3-8B/70B display more active tendencies. Overall, about 60\% of responses address at least one key point from the ground-truth. However, improvements are needed to reduce irrelevant or repetitive content and enhance tolerance for transcription errors commonly found in real-world settings. Additionally, we implement the system in practical settings and collect real-world feedback from demos. Our findings underscore the potential and challenges of utilizing LLMs as meeting delegates, offering valuable insights into their practical application for alleviating the burden of meetings.

cs.CL↗

arXiv2025

Parareal Algorithms for Stochastic Maxwell Equations Driven by Multiplicative Noise

This paper investigates the parareal algorithms for solving the stochastic Maxwell equations driven by multiplicative noise, focusing on their convergence, computational efficiency and numerical performance. The algorithms use the stochastic exponential integrator as the coarse propagator, while both the exact integrator and the stochastic exponential integrator are used as fine propagators. Theoretical analysis shows that the mean square convergence rates of the two algorithms selected above are proportional to $k/2$, depending on the iteration number of the algorithms. Numerical experiments validate these theoretical findings, demonstrating that larger iteration numbers $k$ improve convergence rates, while larger damping coefficients $σ$ accelerate the convergence of the algorithms. Furthermore, the algorithms maintain high accuracy and computational efficiency, highlighting their significant advantages over traditional exponential methods in long-term simulations.

math.NA↗

arXiv2025

A Comprehensive Framework for Semantic Similarity Analysis of Human and AI-Generated Text Using Transformer Architectures and Ensemble Techniques

The rapid advancement of large language models (LLMs) has made detecting AI-generated text an increasingly critical challenge. Traditional methods often fail to capture the nuanced semantic differences between human and machine-generated content. We therefore propose a novel approach based on semantic similarity analysis, leveraging a multi-layered architecture that combines a pre-trained DeBERTa-v3-large model, Bi-directional LSTMs, and linear attention pooling to capture both local and global semantic patterns. To enhance performance, we employ advanced input and output augmentation techniques such as sector-level context integration and wide output configurations. These techniques enable the model to learn more discriminative features and generalize across diverse domains. Experimental results show that this approach works better than traditional methods, proving its usefulness for AI-generated text detection and other text comparison tasks.

cs.CL↗

arXiv2025

Enabling Autonomic Microservice Management through Self-Learning Agents

The increasing complexity of modern software systems necessitates robust autonomic self-management capabilities. While Large Language Models (LLMs) demonstrate potential in this domain, they often face challenges in adapting their general knowledge to specific service contexts. To address this limitation, we propose ServiceOdyssey, a self-learning agent system that autonomously manages microservices without requiring prior knowledge of service-specific configurations. By leveraging curriculum learning principles and iterative exploration, ServiceOdyssey progressively develops a deep understanding of operational environments, reducing dependence on human input or static documentation. A prototype built with the Sock Shop microservice demonstrates the potential of this approach for autonomic microservice management.

cs.SE↗

arXiv2025

Discovery of a topological exciton insulator with tunable momentum order

Correlated topological materials often maintain a delicate balance among physical symmetries: many topological orders are symmetry protected, while most correlated phenomena arise from spontaneous symmetry breaking. It is rare to find cases where symmetry breaking induces a non-trivial topological phase. Here, we present the discovery of such a phase in Ta2Pd3Te5, where Coulomb interactions form excitons, which condense below 100 K, opening a topological gap and creating a topological excitonic insulator. Our spectroscopy reveals the full spectral bulk gap stemming from exciton condensation. This excitonic insulator state spontaneously breaks mirror symmetries but involves a very weak structural coupling, as indicated by photoemission spectroscopy, thermodynamic measurements, and a detailed structural analysis. Notably, scanning tunneling microscopy uncovers gapless boundary modes in the bulk insulating phase. Their magnetic field response, together with theoretical modeling, suggests a topological origin. These observations establish Ta2Pd3Te5 as the first confirmed topological excitonic insulator in a three-dimensional crystal. This allows to access the associated physics through bulk-sensitive techniques. Furthermore, we uncover another surprising aspect of the topological excitonic insulator, a secondary excitonic instability near 5 K that breaks the translational symmetry. The wavevector of this state shows an unprecedented magnetic field tunability. Thus, we unveil a unique sequence of topological exciton condensations in a bulk crystal, offering new opportunities to study critical behavior and excitations.

cond-mat.str-el↗

arXiv2025

LLM-powered Multi-agent Framework for Goal-oriented Learning in Intelligent Tutoring System

Intelligent Tutoring Systems (ITSs) have revolutionized education by offering personalized learning experiences. However, as goal-oriented learning, which emphasizes efficiently achieving specific objectives, becomes increasingly important in professional contexts, existing ITSs often struggle to deliver this type of targeted learning experience. In this paper, we propose GenMentor, an LLM-powered multi-agent framework designed to deliver goal-oriented, personalized learning within ITS. GenMentor begins by accurately mapping learners' goals to required skills using a fine-tuned LLM trained on a custom goal-to-skill dataset. After identifying the skill gap, it schedules an efficient learning path using an evolving optimization approach, driven by a comprehensive and dynamic profile of learners' multifaceted status. Additionally, GenMentor tailors learning content with an exploration-drafting-integration mechanism to align with individual learner needs. Extensive automated and human evaluations demonstrate GenMentor's effectiveness in learning guidance and content quality. Furthermore, we have deployed it in practice and also implemented it as an application. Practical human study with professional learners further highlights its effectiveness in goal alignment and resource targeting, leading to enhanced personalization. Supplementary resources are available at https://github.com/GeminiLight/gen-mentor.

cs.AI↗

arXiv2025

Optimizing Sentence Embedding with Pseudo-Labeling and Model Ensembles: A Hierarchical Framework for Enhanced NLP Tasks

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble techniques to improve sentence embeddings. We use external data from SimpleWiki, Wikipedia, and BookCorpus to make sure the training data is consistent. The framework includes a hierarchical model with an encoding layer, refinement layer, and ensemble prediction layer, using ALBERT-xxlarge, RoBERTa-large, and DeBERTa-large models. Cross-attention layers combine external context, and data augmentation techniques like synonym replacement and back-translation increase data variety. Experimental results show large improvements in accuracy and F1-score compared to basic models, and studies confirm that cross-attention and data augmentation make a difference. This work presents an effective way to improve sentence embedding tasks and lays the groundwork for future NLP research.

cs.CL↗