arXiv subjects

Yifan Jiang

Publications and source records attributed to Yifan Jiang.

At least 55 records · Page 3Linked to original sources

arXiv2025

Reconfigurable Airspace: Synergizing Movable Antenna and Intelligent Surface for Low-Altitude ISAC Networks

Low-altitude unmanned aerial vehicle (UAV) networks are integral to future 6G integrated sensing and communication (ISAC) systems. However, their deployment is hindered by challenges stemming from high mobility of UAVs, complex propagation environments, and the inherent trade-offs between coexisting sensing and communication functions. This article proposes a novel framework that leverages movable antennas (MAs) and intelligent reflecting surfaces (IRSs) as dual enablers to overcome these limitations. MAs, through active transceiver reconfiguration, and IRSs, via passive channel reconstruction, can work in synergy to significantly enhance system performance. Our analysis first elaborates on the fundamental gains offered by MAs and IRSs, and provides simulation results that validate the immense potential of the MA-IRS-enabled ISAC architecture. Two core UAV deployment scenarios are then investigated: (i) UAVs as ISAC users, where we focus on achieving high-precision tracking and aerial safety, and (ii) UAVs as aerial network nodes, where we address robust design and complex coupled resource optimization. Finally, key technical challenges and research opportunities are identified and analyzed for each scenario, charting a clear course for the future design of advanced low-altitude ISAC networks.

cs.IT↗

arXiv2025

GPU Memory Requirement Prediction for Deep Learning Task Based on Bidirectional Gated Recurrent Unit Optimization Transformer

In response to the increasingly critical demand for accurate prediction of GPU memory resources in deep learning tasks, this paper deeply analyzes the current research status and innovatively proposes a deep learning model that integrates bidirectional gated recurrent units (BiGRU) to optimize the Transformer architecture, aiming to improve the accuracy of memory demand prediction. To verify the effectiveness of the model, a carefully designed comparative experiment was conducted, selecting four representative basic machine learning models: decision tree, random forest, Adaboost, and XGBoost as benchmarks. The detailed experimental results show that the BiGRU Transformer optimization model proposed in this paper exhibits significant advantages in key evaluation indicators: in terms of mean square error (MSE) and root mean square error (RMSE), the model achieves the lowest value among all comparison models, and its predicted results have the smallest deviation from the actual values; In terms of mean absolute error (MAE) and coefficient of determination (R2) indicators, the model also performs well and the results are balanced and stable, with comprehensive predictive performance far exceeding the benchmark machine learning methods compared. In summary, the Transformer model based on bidirectional gated recurrent unit optimization successfully constructed in this study can efficiently and accurately complete GPU memory demand prediction tasks in deep learning tasks, and its prediction accuracy has been significantly improved compared to traditional machine learning methods. This research provides strong technical support and reliable theoretical basis for optimizing resource scheduling and management of deep learning tasks, and improving the utilization efficiency of computing clusters.

cs.LG↗

arXiv2025

GenLARP: Enabling Immersive Live Action Role-Play through LLM-Generated Worlds and Characters

We introduce GenLARP, a virtual reality (VR) system that transforms personalized stories into immersive live action role-playing (LARP) experiences. GenLARP enables users to act as both creators and players, allowing them to design characters based on their descriptions and live in the story world. Generative AI and agents powered by Large Language Models (LLMs) enrich these experiences.

cs.HC↗

arXiv2025

SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning

Multimodal large language models (MLLMs) have shown promising capabilities in reasoning tasks, yet still struggle with complex problems requiring explicit self-reflection and self-correction, especially compared to their unimodal text-based counterparts. Existing reflection methods are simplistic and struggle to generate meaningful and instructive feedback, as the reasoning ability and knowledge limits of pre-trained models are largely fixed during initial training. To overcome these challenges, we propose Multimodal Self-Reflection enhanced reasoning with Group Relative Policy Optimization (SRPO), a two-stage reflection-aware reinforcement learning (RL) framework explicitly designed to enhance multimodal LLM reasoning. In the first stage, we construct a high-quality, reflection-focused dataset under the guidance of an advanced MLLM, which generates reflections based on initial responses to help the policy model learn both reasoning and self-reflection. In the second stage, we introduce a novel reward mechanism within the GRPO framework that encourages concise and cognitively meaningful reflection while avoiding redundancy. Extensive experiments across multiple multimodal reasoning benchmarks, including MathVista, MathVision, MathVerse, and MMMU-Pro, using Qwen-2.5-VL-7B and Qwen-2.5-VL-32B demonstrate that SRPO significantly outperforms state-of-the-art models, achieving notable improvements in both reasoning accuracy and reflection quality.

cs.CL↗

arXiv2025

Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation

Data contamination has received increasing attention in the era of large language models (LLMs) due to their reliance on vast Internet-derived training corpora. To mitigate the risk of potential data contamination, LLM benchmarking has undergone a transformation from static to dynamic benchmarking. In this work, we conduct an in-depth analysis of existing static to dynamic benchmarking methods aimed at reducing data contamination risks. We first examine methods that enhance static benchmarks and identify their inherent limitations. We then highlight a critical gap-the lack of standardized criteria for evaluating dynamic benchmarks. Based on this observation, we propose a series of optimal design principles for dynamic benchmarking and analyze the limitations of existing dynamic benchmarks. This survey provides a concise yet comprehensive overview of recent advancements in data contamination research, offering valuable insights and a clear guide for future research efforts. We maintain a GitHub repository to continuously collect both static and dynamic benchmarking methods for LLMs. The repository can be found at this link.

cs.LG↗

arXiv2025

Audio-centric Video Understanding Benchmark without Text Shortcut

Audio often serves as an auxiliary modality in video understanding tasks of audio-visual large language models (LLMs), merely assisting in the comprehension of visual information. However, a thorough understanding of videos significantly depends on auditory information, as audio offers critical context, emotional cues, and semantic meaning that visual data alone often lacks. This paper proposes an audio-centric video understanding benchmark (AVUT) to evaluate the video comprehension capabilities of multimodal LLMs with a particular focus on auditory information. AVUT introduces a suite of carefully designed audio-centric tasks, holistically testing the understanding of both audio content and audio-visual interactions in videos. Moreover, this work points out the text shortcut problem that largely exists in other benchmarks where the correct answer can be found from question text alone without needing videos. AVUT addresses this problem by proposing a answer permutation-based filtering mechanism. A thorough evaluation across a diverse range of open-source and proprietary multimodal LLMs is performed, followed by the analyses of deficiencies in audio-visual LLMs. Demos and data are available at https://github.com/lark-png/AVUT.

cs.CV↗

arXiv2025

ZS-Puffin: Design, Modeling and Implementation of an Unmanned Aerial-Aquatic Vehicle with Amphibious Wings

Unmanned aerial-aquatic vehicles (UAAVs) can operate both in the air and underwater, giving them broad application prospects. Inspired by the dual-function wings of puffins, we propose a UAAV with amphibious wings to address the challenge posed by medium differences on the vehicle's propulsion system. The amphibious wing, redesigned based on a fixed-wing structure, features a single degree of freedom in pitch and requires no additional components. It can generate lift in the air and function as a flapping wing for propulsion underwater, reducing disturbance to marine life and making it environmentally friendly. Additionally, an artificial central pattern generator (CPG) is introduced to enhance the smoothness of the flapping motion. This paper presents the prototype, design details, and practical implementation of this concept.

cs.RO↗

arXiv2025

Lung-DDPM: Semantic Layout-guided Diffusion Models for Thoracic CT Image Synthesis

With the rapid development of artificial intelligence (AI), AI-assisted medical imaging analysis demonstrates remarkable performance in early lung cancer screening. However, the costly annotation process and privacy concerns limit the construction of large-scale medical datasets, hampering the further application of AI in healthcare. To address the data scarcity in lung cancer screening, we propose Lung-DDPM, a thoracic CT image synthesis approach that effectively generates high-fidelity 3D synthetic CT images, which prove helpful in downstream lung nodule segmentation tasks. Our method is based on semantic layout-guided denoising diffusion probabilistic models (DDPM), enabling anatomically reasonable, seamless, and consistent sample generation even from incomplete semantic layouts. Our results suggest that the proposed method outperforms other state-of-the-art (SOTA) generative models in image quality evaluation and downstream lung nodule segmentation tasks. Specifically, Lung-DDPM achieved superior performance on our large validation cohort, with a Fréchet inception distance (FID) of 0.0047, maximum mean discrepancy (MMD) of 0.0070, and mean squared error (MSE) of 0.0024. These results were 7.4$\times$, 3.1$\times$, and 29.5$\times$ better than the second-best competitors, respectively. Furthermore, the lung nodule segmentation model, trained on a dataset combining real and Lung-DDPM-generated synthetic samples, attained a Dice Coefficient (Dice) of 0.3914 and sensitivity of 0.4393. This represents 8.8% and 18.6% improvements in Dice and sensitivity compared to the model trained solely on real samples. The experimental results highlight Lung-DDPM's potential for a broader range of medical imaging applications, such as general tumor segmentation, cancer survival estimation, and risk prediction. The code and pretrained models are available at https://github.com/Manem-Lab/Lung-DDPM/.

eess.IV↗

arXiv2025

Harmonic balance-automatic differentiation method: an out-of-the-box and efficient solver for general nonlinear dynamics simulation

The Harmonic Balance-Alternating Frequency-Time domain (HB-AFT) method is extensively employed for dynamic response analysis of nonlinear systems. However, its application to high-dimensional complex systems is constrained by the manual derivation of Jacobian matrices during Newton-Raphson iterations, which become computationally intractable or error-prone for intricate nonlinearities. The Harmonic Balance-Automatic Differentiation (HB-AD) method is proposed to address this limitation, in which AD is integrated with the harmonic balance framework. This approach eliminates all manual derivations by leveraging AD to compute exact Jacobians numerically, enabling generic and efficient analysis of high-dimensional complex nonlinear systems. The implementation utilizes advanced deep learning frameworks for native parallel computing and CUDA acceleration, and combines AD with arc-length continuation, establishing an out-of-the-box and high efficiency computational architecture. Users need only supply the system's dynamic equations, HB-AD then autonomously trace the complete panorama of periodic responses -- including stable/unstable solution branches. Computational experiments on a rotor system with squeeze-film damper (SFD) demonstrate HB-AD's capability in handling complex nonlinear expressions with automated Jacobian calculations. For a high-dimensional aero-engine rotor-bearing-casing system with complex bearing nonlinearities, HB-AD achieves 17-fold higher efficiency than traditional HB-AFT and 144-fold acceleration over the Newmark method. The HB-AD method is a synergistic merger of computational mechanics and machine learning primitives, delivers an easy to use, general-purpose, high efficiency platform for high-fidelity dynamic characterization of high-dimensional engineering systems.

cs.CE↗

arXiv2025

Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation

3D point cloud segmentation aims to assign semantic labels to individual points in a scene for fine-grained spatial understanding. Existing methods typically adopt data augmentation to alleviate the burden of large-scale annotation. However, most augmentation strategies only focus on local transformations or semantic recomposition, lacking the consideration of global structural dependencies within scenes. To address this limitation, we propose a graph-guided data augmentation framework with dual-level constraints for realistic 3D scene synthesis. Our method learns object relationship statistics from real-world data to construct guiding graphs for scene generation. Local-level constraints enforce geometric plausibility and semantic consistency between objects, while global-level constraints maintain the topological structure of the scene by aligning the generated layout with the guiding graph. Extensive experiments on indoor and outdoor datasets demonstrate that our framework generates diverse and high-quality augmented scenes, leading to consistent improvements in point cloud segmentation performance across various models.

cs.CV↗

arXiv2025

Animation Needs Attention: A Holistic Approach to Slides Animation Comprehension with Visual-Language Models

Slide animations, such as fade-in, fly-in, and wipe, are critical for audience engagement, efficient information delivery, and vivid visual expression. However, most AI-driven slide-generation tools still lack native animation support, and existing vision-language models (VLMs) struggle with animation tasks due to the absence of public datasets and limited temporal-reasoning capabilities. To address this gap, we release the first public dataset for slide-animation modeling: 12,000 triplets of natural-language descriptions, animation JSON files, and rendered videos, collectively covering every built-in PowerPoint effect. Using this resource, we fine-tune Qwen-2.5-VL-7B with Low-Rank Adaptation (LoRA) and achieve consistent improvements over GPT-4.1 and Gemini-2.5-Pro in BLEU-4, ROUGE-L, SPICE, and our Coverage-Order-Detail Assessment (CODA) metric, which evaluates action coverage, temporal order, and detail fidelity. On a manually created test set of slides, the LoRA model increases BLEU-4 by around 60%, ROUGE-L by 30%, and shows significant improvements in CODA-detail. This demonstrates that low-rank adaptation enables reliable temporal reasoning and generalization beyond synthetic data. Overall, our dataset, LoRA-enhanced model, and CODA metric provide a rigorous benchmark and foundation for future research on VLM-based dynamic slide generation.

cs.AI↗

arXiv2025

The Anytime Convergence of Stochastic Gradient Descent with Momentum: From a Continuous-Time Perspective

We study the stochastic optimization problem from a continuous-time perspective, with a focus on the Stochastic Gradient Descent with Momentum (SGDM) method. We show that the trajectory of SGDM, despite its \emph{stochastic} nature, converges in $L_2$-norm to a \emph{deterministic} second-order Ordinary Differential Equation (ODE) as the stepsize goes to zero. The connection between the ODE and the algorithm results in a useful development for the discrete-time convergence analysis. More specifically, we develop, through the construction of a suitable Lyapunov function, convergence results for the ODE, which are then translated to the corresponding convergence results for the discrete-time case. This approach yields a novel \emph{anytime} convergence guarantee for stochastic gradient methods. In particular, we prove that the sequence $\{ x_k \}$, governed by running SGDM on a smooth convex function $f$, satisfies \begin{align*} \mathbb{P}\left(f (x_k) - f^* \le C\left(1+\log\frac{1}β\right)\frac{\log k}{\sqrt{k}},\;\text{for all $k$}\right)\ge 1-β\quad\text{ for any $β>0$,} \end{align*} where $f^*=\min_{x\in\mathbb{R}^n} f(x)$, and $C$ is a constant. Rather than at a single step, this result captures the convergence behavior across the entire trajectory of the algorithm.

math.OC↗

arXiv2025

Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods

This work provides a novel convergence analysis for stochastic optimization in terms of stopping times, addressing the practical reality that algorithms are often terminated adaptively based on observed progress. Unlike prior approaches, our analysis: 1. Directly characterizes convergence in terms of stopping times adapted to the underlying stochastic process. 2. Breaks a logarithmic barrier in existing results. Key to our results is the development of a lemma to control the large deviation property of almost super-martingales. This lemma might be of broader interest.

math.OC↗

arXiv2025

Transport Evidence for Wigner Crystals in Monolayer MoTe2

The crystallization of charge carriers, dubbed the Wigner crystal, is anticipated at low densities in clean two-dimensional electronic systems (2DES). While there has been extensive investigation across diverse platforms, probing spontaneous charge and spin ordering is hindered by disorder effects and limited interaction energies. Here, we report transport evidence for Wigner crystals with antiferromagnetic exchange interactions in high-quality, hexagonal boron nitride encapsulated monolayer MoTe2, a system that achieves a large interaction parameter (r_s) at proper hole densities. A density-tuned metal-insulator transition (MIT) occurring at 3.1E10^11 cm-2 (corresponding to r_s~32) and pronounced nonlinear charge transport in the insulating regime at low temperatures signify the formation of Wigner crystals. Thermal melting of the crystalline phase is observed below approximately 2 K via temperature-dependent nonlinear transport. Magnetoresistance measurements further reveal a substantial enhancement of spin susceptibility as approaching the MIT. The temperature dependence of spin susceptibility in the Wigner crystal phase closely follows the Curie-Weiss law, with the extracted negative Weiss constant illustrating antiferromagnetic exchange interactions. Furthermore, we have found the system exhibits metallic-like differential resistivity under finite DC bias, possibly indicating the existence of a non-equilibrium coherent state in the depinning of Wigner crystals. Our observations establish monolayer MoTe2 as a promising platform for exploring magnetic and dynamic properties of Wigner crystals.

cond-mat.str-el↗

arXiv2025

A modified Newmark/Newton-Raphson method with automatic differentiation for general nonlinear dynamics analysis

The Newmark/Newton-Raphson (NNR) method is widely employed for solving nonlinear dynamic systems. However, the current NNR method exhibits limited applicability in complex nonlinear dynamic systems, as the acquisition of the Jacobian matrix required for Newton iterations incurs substantial computational costs and may even prove intractable in certain cases. To address these limitations, we integrate automatic differentiation (AD) into the NNR method, proposing a modified NNR method with AD (NNR-AD) to significantly improve its capability for effectively handling complex nonlinear systems. We have demonstrated that the NNR-AD method can directly solve dynamic systems with complex nonlinear characteristics, and its accuracy and generality have been rigorously validated. Furthermore, automatic differentiation significantly simplifies the computation of Jacobian matrices for such complex nonlinear dynamic systems. This improvement endows the NNR method with enhanced modularity, thereby enabling convenient and effective solutions for complex nonlinear dynamic systems.

cs.CE↗

arXiv2025

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented performance across various applications. As LLMs continue to gain prominence in both research and commercial domains, their security and safety implications have become a growing concern, not only for researchers and corporations but also for every nation. Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e.g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs. To address this gap, this paper introduces, for the first time, the concept of "full-stack" safety to systematically consider safety issues throughout the entire process of LLM training, deployment, and eventual commercialization. Compared to the off-the-shelf LLM safety surveys, our work demonstrates several distinctive advantages: (I) Comprehensive Perspective. We define the complete LLM lifecycle as encompassing data preparation, pre-training, post-training, deployment and final commercialization. To our knowledge, this represents the first safety survey to encompass the entire lifecycle of LLMs. (II) Extensive Literature Support. Our research is grounded in an exhaustive review of over 800+ papers, ensuring comprehensive coverage and systematic organization of security issues within a more holistic understanding. (III) Unique Insights. Through systematic literature analysis, we have developed reliable roadmaps and perspectives for each chapter. Our work identifies promising research directions, including safety in data generation, alignment techniques, model editing, and LLM-based agent systems. These insights provide valuable guidance for researchers pursuing future work in this field.

cs.CR↗

arXiv2025

RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking

The rapid progress of Large Language Models (LLMs) has opened up new opportunities across various domains and applications; yet it also presents challenges related to potential misuse. To mitigate such risks, red teaming has been employed as a proactive security measure to probe language models for harmful outputs via jailbreak attacks. However, current jailbreak attack approaches are single-turn with explicit malicious queries that do not fully capture the complexity of real-world interactions. In reality, users can engage in multi-turn interactions with LLM-based chat assistants, allowing them to conceal their true intentions in a more covert manner. To bridge this gap, we, first, propose a new jailbreak approach, RED QUEEN ATTACK. This method constructs a multi-turn scenario, concealing the malicious intent under the guise of preventing harm. We craft 40 scenarios that vary in turns and select 14 harmful categories to generate 56k multi-turn attack data points. We conduct comprehensive experiments on the RED QUEEN ATTACK with four representative LLM families of different sizes. Our experiments reveal that all LLMs are vulnerable to RED QUEEN ATTACK, reaching 87.62% attack success rate on GPT-4o and 75.4% on Llama3-70B. Further analysis reveals that larger models are more susceptible to the RED QUEEN ATTACK, with multi-turn structures and concealment strategies contributing to its success. To prioritize safety, we introduce a straightforward mitigation strategy called RED QUEEN GUARD, which aligns LLMs to effectively counter adversarial attacks. This approach reduces the attack success rate to below 1% while maintaining the model's performance across standard benchmarks. Full implementation and dataset are publicly accessible at https://github.com/kriti-hippo/red_queen.

cs.CR↗

arXiv2025

A transfer principle for computing the adapted Wasserstein distance between stochastic processes

We propose a transfer principle to study the adapted 2-Wasserstein distance between stochastic processes. First, we obtain an explicit formula for the distance between real-valued mean-square continuous Gaussian processes by introducing the causal factorization as an infinite-dimensional analogue of the Cholesky decomposition for operators on Hilbert spaces. We discuss the existence and uniqueness of this causal factorization and link it to the canonical representation of Gaussian processes. As a byproduct, we characterize mean-square continuous Gaussian Volterra processes in terms of their natural filtrations. Moreover, for real-valued fractional stochastic differential equations, we show that the synchronous coupling between the driving fractional noises attains the adapted Wasserstein distance under some monotonicity conditions. Our results cover a wide class of stochastic processes which are neither Markov processes nor semi-martingales, including fractional Brownian motions and fractional Ornstein--Uhlenbeck processes.

math.PR↗