arXiv subjects

Chenyu Zhang

Publications and source records attributed to Chenyu Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2025

Harnessing Deep LLM Participation for Robust Entity Linking

Entity Linking (EL), the task of mapping textual entity mentions to their corresponding entries in knowledge bases, constitutes a fundamental component of natural language understanding. Recent advancements in Large Language Models (LLMs) have demonstrated remarkable potential for enhancing EL performance. Prior research has leveraged LLMs to improve entity disambiguation and input representation, yielding significant gains in accuracy and robustness. However, these approaches typically apply LLMs to isolated stages of the EL task, failing to fully integrate their capabilities throughout the entire process. In this work, we introduce DeepEL, a comprehensive framework that incorporates LLMs into every stage of the entity linking task. Furthermore, we identify that disambiguating entities in isolation is insufficient for optimal performance. To address this limitation, we propose a novel self-validation mechanism that utilizes global contextual information, enabling LLMs to rectify their own predictions and better recognize cohesive relationships among entities within the same sentence. Extensive empirical evaluation across ten benchmark datasets demonstrates that DeepEL substantially outperforms existing state-of-the-art methods, achieving an average improvement of 2.6\% in overall F1 score and a remarkable 4% gain on out-of-domain datasets. These results underscore the efficacy of deep LLM integration in advancing the state-of-the-art in entity linking.

cs.CL↗

arXiv2025

Stacking-orientation and twist-angle control on integer and fractional Chern insulators in moiré rhombohedral graphene

Rhombohedral-stacked multilayer graphene aligned with hexagonal boron nitride has emerged as an excellent platform for investigating exotic quantum phenomena arising from the interplay between electron correlations and nontrivial topology. However, the microscopic mechanism governing the emergence of both the integer and fractional Chern insulator states in this system remains an open question. In this work, we systematically investigate the electrical transport properties of RMG/hBN moiré devices with controlled alignment orientations and twist angles. We demonstrate that alignment orientation strongly modulates correlated phenomena in the moiré-proximal regime, while having negligible influence on the formation of integer and fractional Chern insulators in the moiré-distant regime. Instead, the moiré periodicity, tuned by the twist angle, serves as the key parameter controlling the stability of these correlated topological states in the moiré-distant regime. Furthermore, in the moiré-proximal regime of one specific alignment, we observe anomalous Hall effect and a variety of competing phases near ν = 1, including integer Chern insulator states, extended Chern insulator states, and trivial insulators, whose stability is highly sensitive to both the applied displacement electric field and magnetic field. Our results underscore the critical role of stacking-alignment and twist-angle engineering in exploring novel quantum states based on rhombohedral-stacked multilayer graphene moiré systems.

cond-mat.mes-hall↗

arXiv2025

When One Modality Sabotages the Others: A Diagnostic Lens on Multimodal Reasoning

Despite rapid growth in multimodal large language models (MLLMs), their reasoning traces remain opaque: it is often unclear which modality drives a prediction, how conflicts are resolved, or when one stream dominates. In this paper, we introduce modality sabotage, a diagnostic failure mode in which a high-confidence unimodal error overrides other evidence and misleads the fused result. To analyze such dynamics, we propose a lightweight, model-agnostic evaluation layer that treats each modality as an agent, producing candidate labels and a brief self-assessment used for auditing. A simple fusion mechanism aggregates these outputs, exposing contributors (modalities supporting correct outcomes) and saboteurs (modalities that mislead). Applying our diagnostic layer in a case study on multimodal emotion recognition benchmarks with foundation models revealed systematic reliability profiles, providing insight into whether failures may arise from dataset artifacts or model limitations. More broadly, our framework offers a diagnostic scaffold for multimodal reasoning, supporting principled auditing of fusion dynamics and informing possible interventions.

cs.AI↗

arXiv2025

Ocean Wave Forecasting with Deep Learning as Alternative to Conventional Models

This study presents OceanCastNet (OCN), a machine learning approach for wave forecasting that incorporates wind and wave fields to predict significant wave height, mean wave period, and mean wave direction.We evaluate OCN's performance against the operational ECWAM model using two independent datasets: NDBC buoy and Jason-3 satellite observations. NDBC station validation indicates OCN performs better at 24 stations compared to ECWAM's 10 stations, and Jason-3 satellite validation confirms similar accuracy across 228-hour forecasts. OCN successfully captures wave patterns during extreme weather conditions, demonstrated through Typhoon Goni with prediction errors typically within $\pm$0.5 m. The approach also offers computational efficiency advantages. The results suggest that machine learning approaches can achieve performance comparable to conventional wave forecasting systems for operational wave prediction applications.

physics.ao-ph↗

arXiv2025

Ensembling Large Language Models to Characterize Affective Dynamics in Student-AI Tutor Dialogues

While recent studies have examined the leaning impact of large language model (LLM) in educational contexts, the affective dynamics of LLM-mediated tutoring remain insufficiently understood. This work introduces the first ensemble-LLM framework for large-scale affect sensing in tutoring dialogues, advancing the conversation on responsible pathways for integrating generative AI into education by attending to learners' evolving affective states. To achieve this, we analyzed two semesters' worth of 16,986 conversational turns exchanged between PyTutor, an LLM-powered AI tutor, and 261 undergraduate learners across three U.S. institutions. To investigate learners' emotional experiences, we generate zero-shot affect annotations from three frontier LLMs (Gemini, GPT-4o, Claude), including scalar ratings of valence, arousal, and learning-helpfulness, along with free-text emotion labels. These estimates are fused through rank-weighted intra-model pooling and plurality consensus across models to produce robust emotion profiles. Our analysis shows that during interaction with the AI tutor, students typically report mildly positive affect and moderate arousal. Yet learning is not uniformly smooth: confusion and curiosity are frequent companions to problem solving, and frustration, while less common, still surfaces in ways that can derail progress. Emotional states are short-lived--positive moments last slightly longer than neutral or negative ones, but they are fragile and easily disrupted. Encouragingly, negative emotions often resolve quickly, sometimes rebounding directly into positive states. Neutral moments frequently act as turning points, more often steering students upward than downward, suggesting opportunities for tutors to intervene at precisely these junctures.

cs.CL↗

arXiv2025

TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models

Recent advances in text-to-image diffusion models enable photorealistic image generation, but they also risk producing malicious content, such as NSFW images. To mitigate risk, concept erasure methods are studied to facilitate the model to unlearn specific concepts. However, current studies struggle to fully erase malicious concepts implicitly embedded in prompts (e.g., metaphorical expressions or adversarial prompts) while preserving the model's normal generation capability. To address this challenge, our study proposes TRCE, using a two-stage concept erasure strategy to achieve an effective trade-off between reliable erasure and knowledge preservation. Firstly, TRCE starts by erasing the malicious semantics implicitly embedded in textual prompts. By identifying a critical mapping objective(i.e., the [EoT] embedding), we optimize the cross-attention layers to map malicious prompts to contextually similar prompts but with safe concepts. This step prevents the model from being overly influenced by malicious semantics during the denoising process. Following this, considering the deterministic properties of the sampling trajectory of the diffusion model, TRCE further steers the early denoising prediction toward the safe direction and away from the unsafe one through contrastive learning, thus further avoiding the generation of malicious content. Finally, we conduct comprehensive evaluations of TRCE on multiple malicious concept erasure benchmarks, and the results demonstrate its effectiveness in erasing malicious concepts while better preserving the model's original generation ability. The code is available at: http://github.com/ddgoodgood/TRCE. CAUTION: This paper includes model-generated content that may contain offensive material.

cs.CV↗

arXiv2025

Comparative Performance Analysis of Different Hybrid NOMA Schemes

Hybrid non-orthogonal multiple access (H-NOMA), which combines the advantages of pure NOMA and conventional OMA organically, has emerged as a highly promising multiple access technology for future wireless networks. Recent studies have proposed various H-NOMA systems by employing different successive interference cancellation (SIC) methods for the NOMA transmission phase. However, existing analyses typically assume a fixed channel gain order between paired users, despite the fact that channel coefficients follow random distribution, leading to their magnitude relationships inherently stochastic and time varying. This paper analyzes the performance of three H-NOMA schemes under stochastic channel gain ordering: a) fixed order SIC (FSIC) aided H-NOMA scheme; b) hybrid SIC with non-power adaptation (HSIC-NPA) aided H-NOMA scheme; c) hybrid SIC with power adaptation (HSIC-PA) aided H-NOMA scheme. Theoretical analysis derives closed-form expressions for the probability that H-NOMA schemes underperform conventional OMA. Asymptotic results in the high signal-to-noise ratio (SNR) regime are also developed. Simulation results validate our analysis and demonstrate the performance of H-NOMA schemes across different SNR scenarios, providing a theoretical foundation for the deployment of H-NOMA in next-generation wireless systems.

eess.SP↗

arXiv2025

Multi-label Scene Classification for Autonomous Vehicles: Acquiring and Accumulating Knowledge from Diverse Datasets

Driving scenes are inherently heterogeneous and dynamic. Multi-attribute scene identification, as a high-level visual perception capability, provides autonomous vehicles (AVs) with essential contextual awareness to understand, reason through, and interact with complex driving environments. Although scene identification is best modeled as a multi-label classification problem via multitask learning, it faces two major challenges: the difficulty of acquiring balanced, comprehensively annotated datasets and the need to re-annotate all training data when new attributes emerge. To address these challenges, this paper introduces a novel deep learning method that integrates Knowledge Acquisition and Accumulation (KAA) with Consistency-based Active Learning (CAL). KAA leverages monotask learning on heterogeneous single-label datasets to build a knowledge foundation, while CAL bridges the gap between single- and multi-label data, adapting the foundation model for multi-label scene classification. An ablation study on the newly developed Driving Scene Identification (DSI) dataset demonstrates a 56.1% improvement over an ImageNet-pretrained baseline. Moreover, KAA-CAL outperforms state-of-the-art multi-label classification methods on the BDD100K and HSD datasets, achieving this with 85% less data and even recognizing attributes unseen during foundation model training. The DSI dataset and KAA-CAL implementation code are publicly available at https://github.com/KELISBU/KAA-CAL .

cs.CV↗

arXiv2025

asLLR: LLM based Leads Ranking in Auto Sales

In the area of commercial auto sales system, high-quality lead score sequencing determines the priority of a sale's work and is essential for optimizing the efficiency of the sales system. Since CRM (Customer Relationship Management) system contains plenty of textual interaction features between sales and customers, traditional techniques such as Click Through Rate (CTR) prediction struggle with processing the complex information inherent in natural language features, which limits their effectiveness in sales lead ranking. Bridging this gap is critical for enhancing business intelligence and decision-making. Recently, the emergence of large language models (LLMs) has opened new avenues for improving recommendation systems, this study introduces asLLR (LLM-based Leads Ranking in Auto Sales), which integrates CTR loss and Question Answering (QA) loss within a decoder-only large language model architecture. This integration enables the simultaneous modeling of both tabular and natural language features. To verify the efficacy of asLLR, we constructed an innovative dataset derived from the customer lead pool of a prominent new energy vehicle brand, with 300,000 training samples and 40,000 testing samples. Our experimental results demonstrate that asLLR effectively models intricate patterns in commercial datasets, achieving the AUC of 0.8127, surpassing traditional CTR estimation methods by 0.0231. Moreover, asLLR enhances CTR models when used for extracting text features by 0.0058. In real-world sales scenarios, after rigorous online A/B testing, asLLR increased the sales volume by about 9.5% compared to the traditional method, providing a valuable tool for business intelligence and operational decision-making.

cs.IR↗

arXiv2025

Integrated Detection and Tracking Based on Radar Range-Doppler Feature

Detection and tracking are the basic tasks of radar systems. Current joint detection tracking methods, which focus on dynamically adjusting detection thresholds from tracking results, still present challenges in fully utilizing the potential of radar signals. These are mainly reflected in the limited capacity of the constant false-alarm rate model to accurately represent information, the insufficient depiction of complex scenes, and the limited information acquired by the tracker. We introduce the Integrated Detection and Tracking based on radar feature (InDT) method, which comprises a network architecture for radar signal detection and a tracker that leverages detection assistance. The InDT detector extracts feature information from each Range-Doppler (RD) matrix and then returns the target position through the feature enhancement module and the detection head. The InDT tracker adaptively updates the measurement noise covariance of the Kalman filter based on detection confidence. The similarity of target RD features is measured by cosine distance, which enhances the data association process by combining location and feature information. Finally, the efficacy of the proposed method was validated through testing on both simulated data and publicly available datasets.

eess.SP↗

arXiv2025

A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyond

Artificial Intelligence (AI) agents have rapidly evolved from specialized, rule-based programs to versatile, learning-driven autonomous systems capable of perception, reasoning, and action in complex environments. The explosion of data, advances in deep learning, reinforcement learning, and multi-agent coordination have accelerated this transformation. Yet, designing and deploying unified AI agents that seamlessly integrate cognition, planning, and interaction remains a grand challenge. In this review, we systematically examine the architectural principles, foundational components, and emergent paradigms that define the landscape of contemporary AI agents. We synthesize insights from cognitive science-inspired models, hierarchical reinforcement learning frameworks, and large language model-based reasoning. Moreover, we discuss the pressing ethical, safety, and interpretability concerns associated with deploying these agents in real-world scenarios. By highlighting major breakthroughs, persistent challenges, and promising research directions, this review aims to guide the next generation of AI agent systems toward more robust, adaptable, and trustworthy autonomous intelligence.

cs.MA↗

arXiv2025

An Energy Efficient Design of Hybrid NOMA Based on Hybrid SIC with Power Adaptation

Recently, hybrid non-orthogonal multiple access (H-NOMA) technology, which effectively utilizes both NOMA and orthogonal multiple access (OMA) technologies through flexible resource allocation in a single transmission, has demonstrated immense potential for enhancing the performance of wireless communication systems. To further release the potential of HNOMA, this paper proposes a novel design of H-NOMA which jointly incorporates hybrid successive interference cancellation (HSIC) and power adaptation (PA) in the NOMA transmission phase. To reveal the potential of the proposed HSIC-PA aided H-NOMA scheme, closed-form expression for the probability of the event that H-NOMA can achieve a higher data rate than pure OMA by consuming less energy is rigorously derived. Furthermore, the asymptotic analysis demonstrates that the probability of the proposed H-NOMA scheme approaches 1 in the high signal-to-noise ratio (SNR) regime without any constraints on either users' target rates or transmit power ratios. This represents a significant improvement over conventional H-NOMA schemes, which require specific restrictive conditions to achieve probability 1 at high SNRs as shown in existing work. The above observation indicates that with less energy consumption, the proposed HSIC-PA aided H-NOMA can achieve a higher data rate than pure OMA with probability 1 at high SNRs, and hence a higher energy efficiency. Finally, numerical results are provided to verify the accuracy of the analysis and also demonstrate the superior performance of the proposed H-NOMA scheme.

eess.SP↗

arXiv2025

MoFE-Time: Mixture of Frequency Domain Experts for Time-Series Forecasting Models

As a prominent data modality task, time series forecasting plays a pivotal role in diverse applications. With the remarkable advancements in Large Language Models (LLMs), the adoption of LLMs as the foundational architecture for time series modeling has gained significant attention. Although existing models achieve some success, they rarely both model time and frequency characteristics in a pretraining-finetuning paradigm leading to suboptimal performance in predictions of complex time series, which requires both modeling periodicity and prior pattern knowledge of signals. We propose MoFE-Time, an innovative time series forecasting model that integrates time and frequency domain features within a Mixture of Experts (MoE) network. Moreover, we use the pretraining-finetuning paradigm as our training framework to effectively transfer prior pattern knowledge across pretraining and finetuning datasets with different periodicity distributions. Our method introduces both frequency and time cells as experts after attention modules and leverages the MoE routing mechanism to construct multidimensional sparse representations of input signals. In experiments on six public benchmarks, MoFE-Time has achieved new state-of-the-art performance, reducing MSE and MAE by 6.95% and 6.02% compared to the representative methods Time-MoE. Beyond the existing evaluation benchmarks, we have developed a proprietary dataset, NEV-sales, derived from real-world business scenarios. Our method achieves outstanding results on this dataset, underscoring the effectiveness of the MoFE-Time model in practical commercial applications.

cs.LG↗

arXiv2025

In-Context Meta LoRA Generation

Low-rank Adaptation (LoRA) has demonstrated remarkable capabilities for task specific fine-tuning. However, in scenarios that involve multiple tasks, training a separate LoRA model for each one results in considerable inefficiency in terms of storage and inference. Moreover, existing parameter generation methods fail to capture the correlations among these tasks, making multi-task LoRA parameter generation challenging. To address these limitations, we propose In-Context Meta LoRA (ICM-LoRA), a novel approach that efficiently achieves task-specific customization of large language models (LLMs). Specifically, we use training data from all tasks to train a tailored generator, Conditional Variational Autoencoder (CVAE). CVAE takes task descriptions as inputs and produces task-aware LoRA weights as outputs. These LoRA weights are then merged with LLMs to create task-specialized models without the need for additional fine-tuning. Furthermore, we utilize in-context meta-learning for knowledge enhancement and task mapping, to capture the relationship between tasks and parameter distributions. As a result, our method achieves more accurate LoRA parameter generation for diverse tasks using CVAE. ICM-LoRA enables more accurate LoRA parameter reconstruction than current parameter reconstruction methods and is useful for implementing task-specific enhancements of LoRA parameters. At the same time, our method occupies 283MB, only 1\% storage compared with the original LoRA.

cs.CL↗

arXiv2025

GWQ: Gradient-Aware Weight Quantization for Large Language Models

Large language models (LLMs) show impressive performance in solving complex language tasks. However, its large number of parameters presents significant challenges for the deployment. So, compressing LLMs to low bits can enable to deploy on resource-constrained devices. To address this problem, we propose gradient-aware weight quantization (GWQ), the first quantization approach for low-bit weight quantization that leverages gradients to localize outliers, requiring only a minimal amount of calibration data for outlier detection. GWQ retains the top 1\% outliers preferentially at FP16 precision, while the remaining non-outlier weights are stored in a low-bit. We widely evaluate GWQ on different task include language modeling, grounding detection, massive multitask language understanding and vision-language question and answering. Results show that models quantified by GWQ performs better than other quantization method. During quantization process, GWQ only need one calibration set to realize effective quant. Also, GWQ achieves 1.2x inference speedup in comparison to the original model and effectively reduces the inference memory.

cs.LG↗

arXiv2025

Riemannian Adaptive Regularized Newton Methods with Hölder Continuous Hessians

This paper presents strong worst-case iteration and operation complexity guarantees for Riemannian adaptive regularized Newton methods, a unified framework encompassing both Riemannian adaptive regularization (RAR) methods and Riemannian trust region (RTR) methods. We comprehensively characterize the sources of approximation in second-order manifold optimization methods: the objective function's smoothness, retraction's smoothness, and subproblem solver's inexactness. Specifically, for a function with a $μ$-Hölder continuous Hessian, when equipped with a retraction featuring a $ν$-Hölder continuous differential and a $θ$-inexact subproblem solver, both RTR and RAR with $2+α$ regularization (where $α=\min\{μ,ν,θ\}$) locate an $(ε,ε^{α/(1+α)})$-approximate second-order stationary point within at most $O(ε^{-(2+α)/(1+α)})$ iterations and at most $\tilde{O}(ε^{-(4+3α)/(2(1+α))})$ Hessian-vector products. These complexity results are novel and sharp, and reduce to an iteration complexity of $O(ε^{-3/2})$ and an operation complexity of $\tilde{O}(ε^{-7/4})$ when $α=1$.

math.OC↗

arXiv2025

Adaptive Physics-Informed System Modeling with Control for Nonlinear Structural System Estimation

Accurately capturing the nonlinear dynamic behavior of structures remains a significant challenge in mechanics and engineering. Traditional physics-based models and data-driven approaches often struggle to simultaneously ensure model interpretability, noise robustness, and estimation optimality. To address this issue, this paper proposes an Adaptive Physics-Informed System Modeling with Control (APSMC) framework. By integrating Kalman filter-based state estimation with physics-constrained proximal gradient optimization, the framework adaptively updates time-varying state-space model parameters while processing real-time input-output data under white noise disturbances. Theoretically, this process is equivalent to real-time tracking of the Jacobian matrix of a nonlinear dynamical system. Within this framework, we leverage the theoretical foundation of stochastic subspace identification to demonstrate that, as observational data accumulates, the APSMC algorithm yields state-space model estimates that converge to the theoretically optimal solution. The effectiveness of the proposed framework is validated through numerical simulations of a Duffing oscillator and the seismic response of a frame structure, as well as experimental tests on a scaled bridge model. Experimental results show that, under noisy conditions, APSMC successfully predicts 19 consecutive 10-second time series using only a single initial 10-second segment for model updating, achieving a minimum normalized mean square error (NMSE) of 0.398%. These findings demonstrate that the APSMC framework not only offers superior online identification and denoising performance but also provides a reliable foundation for downstream applications such as structural health monitoring, real-time control, adaptive filtering, and system identification.

nlin.AO↗

arXiv2025

Spreading Depolarization Detection in Electrocorticogram Spectrogram Imaging by Deep Learning: Is It Just About Delta Band?

Prevention of secondary brain injury is a core aim of neurocritical care, with Spreading Depolarizations (SDs) recognized as a significant independent cause. SDs are typically monitored through invasive, high-frequency electrocorticography (ECoG); however, detection remains challenging due to signal artifacts that obscure critical SD-related electrophysiological changes, such as power attenuation and DC drifting. Recent studies suggest spectrogram analysis could improve SD detection; however, brain injury patients often show power reduction across all bands except delta, causing class imbalance. Previous methods focusing solely on delta mitigates imbalance but overlooks features in other frequencies, limiting detection performance. This study explores using multi-frequency spectrogram analysis, revealing that essential SD-related features span multiple frequency bands beyond the most active delta band. This study demonstrated that further integration of both alpha and delta bands could result in enhanced SD detection accuracy by a deep learning model.

eess.SP↗