arXiv subjects

Ning Li

Publications and source records attributed to Ning Li.

At least 55 records · Page 3Linked to original sources

arXiv2025

ColorAgent: Building A Robust, Personalized, and Interactive OS Agent

With the advancements in hardware, software, and large language model technologies, the interaction between humans and operating systems has evolved from the command-line interface to the rapidly emerging AI agent interactions. Building an operating system (OS) agent capable of executing user instructions and faithfully following user desires is becoming a reality. In this technical report, we present ColorAgent, an OS agent designed to engage in long-horizon, robust interactions with the environment while also enabling personalized and proactive user interaction. To enable long-horizon interactions with the environment, we enhance the model's capabilities through step-wise reinforcement learning and self-evolving training, while also developing a tailored multi-agent framework that ensures generality, consistency, and robustness. In terms of user interaction, we explore personalized user intent recognition and proactive engagement, positioning the OS agent not merely as an automation tool but as a warm, collaborative partner. We evaluate ColorAgent on the AndroidWorld and AndroidLab benchmarks, achieving success rates of 77.2% and 50.7%, respectively, establishing a new state of the art. Nonetheless, we note that current benchmarks are insufficient for a comprehensive evaluation of OS agents and propose further exploring directions in future work, particularly in the areas of evaluation paradigms, agent collaboration, and security.

cs.MA↗

arXiv2025

Randomized Neural Network with Adaptive Forward Regularization for Online Task-free Class Incremental Learning

Class incremental learning (CIL) requires an agent to learn distinct tasks consecutively with knowledge retention against forgetting. Problems impeding the practical applications of CIL methods are twofold: (1) non-i.i.d batch streams and no boundary prompts to update, known as the harsher online task-free CIL (OTCIL) scenario; (2) CIL methods suffer from memory loss in learning long task streams, as shown in Fig. 1 (a). To achieve efficient decision-making and decrease cumulative regrets during the OTCIL process, a randomized neural network (Randomized NN) with forward regularization (-F) is proposed to resist forgetting and enhance learning performance. This general framework integrates unsupervised knowledge into recursive convex optimization, has no learning dissipation, and can outperform the canonical ridge style (-R) in OTCIL. Based on this framework, we derive the algorithm of the ensemble deep random vector functional link network (edRVFL) with adjustable forward regularization (-kF), where k mediates the intensity of the intervention. edRVFL-kF generates one-pass closed-form incremental updates and variable learning rates, effectively avoiding past replay and catastrophic forgetting while achieving superior performance. Moreover, to curb unstable penalties caused by non-i.i.d and mitigate intractable tuning of -kF in OTCIL, we improve it to the plug-and-play edRVFL-kF-Bayes, enabling all hard ks in multiple sub-learners to be self-adaptively determined based on Bayesian learning. Experiments were conducted on 2 image datasets including 6 metrics, dynamic performance, ablation tests, and compatibility, which distinctly validates the efficacy of our OTCIL frameworks with -kF-Bayes and -kF styles.

cs.LG↗

arXiv2025

A Simultaneous Synergistic Protection Mechanism in Hybrid Perovskite-Organic Multi-junctions Enables Long-Term Stable and Efficient Tandem Solar Cells

Perovskite-organic tandem solar cells (P-O TSCs) hold great promise for next-generation thin-film photovoltaics, with steadily improving power conversion efficiency (PCE). However, the development of optimal interconnecting layers (ICLs) remains one major challenge for further efficiency gains, and progress in understanding the improved long-term stability of P-O tandem configuration has been lagging. In this study, we experimentally investigate the enhanced stability of p-i-n P-O TSCs employing a simplified C60/atomic-layer-deposition (ALD) SnOx/PEDOT: PSS ICL without an additional charge recombination layer (CRL), which achieve an averaged efficiency of 25.12% and a hero efficiency of 25.5%. Our finding discovers that the recrystallization of C60, a widely used electron transport layer in perovskite photovoltaics, leads to the formation of grain boundaries during operation, which act as migration channels for the interdiffusion of halide and Ag ions. Critically, we demonstrate for the first time that the tandem device architecture, incorporating organic semiconductor layers, effectively suppresses the bi-directional ion diffusion and mitigates electrode corrosion. Thus, the P-O TSC establishes a mutual protection system: the organic layers stabilize the perovskite sub-cell by suppressing ion diffusion-induced degradation, and the perovskite layer shields the organic sub-cell from spectrally induced degradation. The simultaneous synergistic protection mechanism enables P-O TSCs to achieve exceptional long-term operational stability, retaining over 91% of their initial efficiency after 1000 hours of continuous metal-halide lamp illumination, and to exhibit minimal fatigue after 86 cycles (2067 hours) of long-term diurnal (12/12-hour) testing. These results demonstrate that tandem cells significantly outperform their single-junction counterparts in both efficiency and stability.

physics.app-ph↗

arXiv2025

Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generation

Recently, visual prompt tuning is introduced to RGB-Thermal (RGB-T) tracking as a parameter-efficient finetuning (PEFT) method. However, these PEFT-based RGB-T tracking methods typically rely solely on spatial domain information as prompts for feature extraction. As a result, they often fail to achieve optimal performance by overlooking the crucial role of frequency-domain information in prompt learning. To address this issue, we propose an efficient Visual Fourier Prompt Tracking (named VFPTrack) method to learn modality-related prompts via Fast Fourier Transform (FFT). Our method consists of symmetric feature extraction encoder with shared parameters, visual fourier prompts, and Modality Fusion Prompt Generator that generates bidirectional interaction prompts through multi-modal feature fusion. Specifically, we first use a frozen feature extraction encoder to extract RGB and thermal infrared (TIR) modality features. Then, we combine the visual prompts in the spatial domain with the frequency domain prompts obtained from the FFT, which allows for the full extraction and understanding of modality features from different domain information. Finally, unlike previous fusion methods, the modality fusion prompt generation module we use combines features from different modalities to generate a fused modality prompt. This modality prompt is interacted with each individual modality to fully enable feature interaction across different modalities. Extensive experiments conducted on three popular RGB-T tracking benchmarks show that our method demonstrates outstanding performance.

cs.CV↗

arXiv2025

Plasmon-driven Ultrafast and Highly Efficient Saturable Absorption for Ultrashort Pulse Generation Based on 2D V2C

Plasmon-driven ultrafast nonlinearities hold promise for advanced photonics but remain challenging to harness in two-dimensional materials at telecommunication wavelengths. Here, we demonstrate few-layer V2C MXene as a high-performance saturable absorber by leveraging its tailored surface plasmon resonance. Combining transient absorption spectroscopy and first-principles calculations, we unveil a plasmon-driven relaxation mechanism dominated by interfacial high-energy hot electron generation (~100 fs), enabling giant ultrafast nonlinearities. Crucially, at the communication band (1550 nm), V2C exhibits a high saturable absorption coefficient of -1.35 cm/GW. Integrating this into an erbium-doped fiber laser, we generate mode-locked pulses with a duration of 486 fs at 1569 nm, a 39.51 MHz repetition rate, and exceptional stability (92 dB SNR). This work establishes plasmonic MXenes as a paradigm for tailored ultrafast photonic devices.

physics.optics↗

arXiv2025

A Shank Angle-Based Control System Enables Soft Exoskeleton to Assist Human Non-Steady Locomotion

Exoskeletons have been shown to effectively assist humans during steady locomotion. However, their effects on non-steady locomotion, characterized by nonlinear phase progression within a gait cycle, remain insufficiently explored, particularly across diverse activities. This work presents a shank angle-based control system that enables the exoskeleton to maintain real-time coordination with human gait, even under phase perturbations, while dynamically shaping assistance profiles to match the biological ankle moment patterns across walking, running, stair negotiation tasks. The control system consists of an assistance profile online generation method and a model-based feedforward control method. The assistance profile is formulated as a dual-Gaussian model with the shank angle as the independent variable. Leveraging only IMU measurements, the model parameters are updated online each stride to adapt to inter- and intra-individual biomechanical variability. The profile tracking control employs a human-exoskeleton kinematics and stiffness model as a feedforward component, reducing reliance on historical control data due to the lack of clear and consistent periodicity in non-steady locomotion. Three experiments were conducted using a lightweight soft exoskeleton with multiple subjects. The results validated the effectiveness of each individual method, demonstrated the robustness of the control system against gait perturbations across various activities, and revealed positive biomechanical and physiological responses of human users to the exoskeleton's mechanical assistance.

cs.RO↗

arXiv2025

Efficient Edge LLMs Deployment via HessianAware Quantization and CPU GPU Collaborative

With the breakthrough progress of large language models (LLMs) in natural language processing and multimodal tasks, efficiently deploying them on resource-constrained edge devices has become a critical challenge. The Mixture of Experts (MoE) architecture enhances model capacity through sparse activation, but faces two major difficulties in practical deployment: (1) The presence of numerous outliers in activation distributions leads to severe degradation in quantization accuracy for both activations and weights, significantly impairing inference performance; (2) Under limited memory, efficient offloading and collaborative inference of expert modules struggle to balance latency and throughput. To address these issues, this paper proposes an efficient MoE edge deployment scheme based on Hessian-Aware Quantization (HAQ) and CPU-GPU collaborative inference. First, by introducing smoothed Hessian matrix quantization, we achieve joint 8-bit quantization of activations and weights, which significantly alleviates the accuracy loss caused by outliers while ensuring efficient implementation on mainstream hardware. Second, we design an expert-level collaborative offloading and inference mechanism, which, combined with expert activation path statistics, enables efficient deployment and scheduling of expert modules between CPU and GPU, greatly reducing memory footprint and inference latency. Extensive experiments validate the effectiveness of our method on mainstream large models such as the OPT series and Mixtral 8*7B: on datasets like Wikitext2 and C4, the inference accuracy of the low-bit quantized model approaches that of the full-precision model, while GPU memory usage is reduced by about 60%, and inference latency is significantly improved.

cs.LG↗

arXiv2025

Synthesize, Retrieve, and Propagate: A Unified Predictive Modeling Framework for Relational Databases

Relational databases (RDBs) have become the industry standard for storing massive and heterogeneous data. However, despite the widespread use of RDBs across various fields, the inherent structure of relational databases hinders their ability to benefit from flourishing deep learning methods. Previous research has primarily focused on exploiting the unary dependency among multiple tables in a relational database using the primary key - foreign key relationships, either joining multiple tables into a single table or constructing a graph among them, which leaves the implicit composite relations among different tables and a substantial potential of improvement for predictive modeling unexplored. In this paper, we propose SRP, a unified predictive modeling framework that synthesizes features using the unary dependency, retrieves related information to capture the composite dependency, and propagates messages across a constructed graph to learn adjacent patterns for prediction on relation databases. By introducing a new retrieval mechanism into RDB, SRP is designed to fully capture both the unary and the composite dependencies within a relational database, thereby enhancing the receptive field of tabular data prediction. In addition, we conduct a comprehensive analysis on the components of SRP, offering a nuanced understanding of model behaviors and practical guidelines for future applications. Extensive experiments on five real-world datasets demonstrate the effectiveness of SRP and its potential applicability in industrial scenarios. The code is released at https://github.com/NingLi670/SRP.

cs.DB↗

arXiv2025

CoMoE: Collaborative Optimization of Expert Aggregation and Offloading for MoE-based LLMs at Edge

The proliferation of large language models (LLMs) has driven the adoption of Mixture-of-Experts (MoE) architectures as a promising solution to scale model capacity while controlling computational costs. However, deploying MoE models in resource-constrained mobile edge computing environments presents significant challenges due to their large memory footprint and dynamic expert activation patterns. To address these challenges, we propose a novel dynamic resource-aware collaborative optimization framework that jointly optimizes expert aggregation granularity and offloading strategies based on real-time device resource states, network conditions, and input characteristics in mobile edge environments, denoted as CoMoE. In CoMoE, we first systematically analyze existing expert aggregation techniques, including expert parameter merging,knowledge distillation,and parameter sharing decomposition, identifying their limitations in dynamic mobile environments.We then investigate expert offloading strategies encompassing expert prediction and prefetching, expert caching and scheduling, and multi-tier storage architectures, revealing the interdependencies between routing decisions and offloading performance.The CoMoE incorporates adaptive scheduling mechanisms that respond to user mobility and varying network conditions, enabling efficient MoE deployment across heterogeneous edge devices. Extensive experiments on real mobile edge testbeds demonstrate that CoMoE achieves approximately 70% reduction in memory usage compared to baseline methods, 10.5% lower inference latency than existing expert offloading techniques, while maintaining model performance stability. For large-scale MoE models (e.g,7.4B-parameter Switch-Base-128), the CoMoE reduces memory requirements from 15.6GB to 4.7GB, enabling deployment on resource-constrained mobile edge devices that previously could only support much smaller models.

cs.NI↗

arXiv2025

ArXivBench: When You Should Avoid Using ChatGPT for Academic Writing

Large language models (LLMs) demonstrate strong capabilities in reasoning and question answering, yet their tendency to generate factually incorrect content remains a critical challenge. This study evaluates proprietary and open-source LLMs on generating relevant research papers with accurate arXiv links. Our evaluation reveals critical academic risks: LLMs frequently generate incorrect arXiv links or references to non-existent papers, fundamentally undermining their ability to properly attribute research contributions to the actual authors. We introduce arXivBench, a benchmark specifically designed to assess LLM performance across eight major subject categories on arXiv and five subfields within computer science, one of the most popular categories among them. Our findings show concerning accuracy variations across subjects, with Claude-3.5-Sonnet exhibiting a substantial advantage in generating both relevant and accurate responses. Notably, most LLMs perform significantly better in Artificial Intelligence than other subfields. This benchmark provides a standardized tool for evaluating LLM reliability in scientific contexts, promoting more dependable academic use in research environments. Our code and dataset are available at https://github.com/liningresearch/arXivBench and https://huggingface.co/datasets/arXivBenchLLM/arXivBench.

cs.IR↗

arXiv2025

Retrieval and Distill: A Temporal Data Shift-Free Paradigm for Online Recommendation System

Current recommendation systems are significantly affected by a serious issue of temporal data shift, which is the inconsistency between the distribution of historical data and that of online data. Most existing models focus on utilizing updated data, overlooking the transferable, temporal data shift-free information that can be learned from shifting data. We propose the Temporal Invariance of Association theorem, which suggests that given a fixed search space, the relationship between the data and the data in the search space keeps invariant over time. Leveraging this principle, we designed a retrieval-based recommendation system framework that can train a data shift-free relevance network using shifting data, significantly enhancing the predictive performance of the original model in the recommendation system. However, retrieval-based recommendation models face substantial inference time costs when deployed online. To address this, we further designed a distill framework that can distill information from the relevance network into a parameterized module using shifting data. The distilled model can be deployed online alongside the original model, with only a minimal increase in inference time. Extensive experiments on multiple real datasets demonstrate that our framework significantly improves the performance of the original model by utilizing shifting data.

cs.IR↗

arXiv2025

MobileUse: A GUI Agent with Hierarchical Reflection for Autonomous Mobile Operation

Recent advances in Multimodal Large Language Models (MLLMs) have enabled the development of mobile agents that can understand visual inputs and follow user instructions, unlocking new possibilities for automating complex tasks on mobile devices. However, applying these models to real-world mobile scenarios remains a significant challenge due to the long-horizon task execution, difficulty in error recovery, and the cold-start problem in unfamiliar environments. To address these challenges, we propose MobileUse, a GUI agent designed for robust and adaptive mobile task execution. To improve resilience in long-horizon tasks and dynamic environments, we introduce a hierarchical reflection architecture that enables the agent to self-monitor, detect, and recover from errors across multiple temporal scales-ranging from individual actions to overall task completion-while maintaining efficiency through a reflection-on-demand strategy. To tackle cold-start issues, we further introduce a proactive exploration module, which enriches the agent's understanding of the environment through self-planned exploration. Evaluations on AndroidWorld and AndroidLab benchmarks demonstrate that MobileUse establishes new state-of-the-art performance, achieving success rates of 62.9% and 44.2%, respectively. To facilitate real-world applications, we release an out-of-the-box toolkit for automated task execution on physical mobile devices, which is available at https://github.com/MadeAgents/mobile-use.

cs.RO↗

arXiv2025

Spectroscopic evidence of symmetry breaking in the superconducting vortices of UTe2

The recently discovered heavy-fermion superconductor, UTe2, is an excellent candidate for spin-triplet superconductors where electrons form spin-triplet Cooper pairs with spin S = 1 and odd parity. Unconventional superconductivity often hosts unconventional vortices. Yet, the vortex core and lattice in UTe2 have not been directly visualized and characterized. Here, by using ultralow-temperature scanning tunneling microscopy and spectroscopy, we study the superconducting vortices on the (0-11) surface termination of UTe2 with an out-of-plane external magnetic field. At the center of the vortex core, we observe a robust zero-energy vortex-core state which exhibits a cigar-shaped spatial distribution and extends to ~30 nm along the [100] direction (crystallographic a axis) of UTe2. Along the direction perpendicular to [100], the superconducting gap is deeper and the coherence peak on one side of the vortex core is stronger than on the opposite side, and they are even enhanced in comparison with those under zero field. Due to the anisotropy of magnetic susceptibility in UTe2, the asymmetric dI/dV spectra on the two sides of the vortex core result from the interplay between the magnetization-induced bound current and supercurrent around the vortex core. Our work reveals the important role of magnetization in the vortex behaviors of UTe2 and provides essential microscopic information for understanding its superconducting properties in magnetic field.

cond-mat.supr-con↗

arXiv2025

A Survey of AI Agent Protocols

The rapid development of large language models (LLMs) has led to the widespread deployment of LLM agents across diverse industries, including customer service, content generation, data analysis, and even healthcare. However, as more LLM agents are deployed, a major issue has emerged: there is no standard way for these agents to communicate with external tools or data sources. This lack of standardized protocols makes it difficult for agents to work together or scale effectively, and it limits their ability to tackle complex, real-world tasks. A unified communication protocol for LLM agents could change this. It would allow agents and tools to interact more smoothly, encourage collaboration, and triggering the formation of collective intelligence. In this paper, we provide the first comprehensive analysis of existing agent protocols, proposing a systematic two-dimensional classification that differentiates context-oriented versus inter-agent protocols and general-purpose versus domain-specific protocols. Additionally, we conduct a comparative performance analysis of these protocols across key dimensions such as security, scalability, and latency. Finally, we explore the future landscape of agent protocols by identifying critical research directions and characteristics necessary for next-generation protocols. These characteristics include adaptability, privacy preservation, and group-based interaction, as well as trends toward layered architectures and collective intelligence infrastructures. We expect this work to serve as a practical reference for both researchers and engineers seeking to design, evaluate, or integrate robust communication infrastructures for intelligent agents.

cs.AI↗

arXiv2025

Can Large Language Models Replace Human Subjects? A Large-Scale Replication of Scenario-Based Experiments in Psychology and Management

Artificial Intelligence (AI) is increasingly being integrated into scientific research, particularly in the social sciences, where understanding human behavior is critical. Large Language Models (LLMs) have shown promise in replicating human-like responses in various psychological experiments. We conducted a large-scale study replicating 156 psychological experiments from top social science journals using three state-of-the-art LLMs (GPT-4, Claude 3.5 Sonnet, and DeepSeek v3). Our results reveal that while LLMs demonstrate high replication rates for main effects (73-81%) and moderate to strong success with interaction effects (46-63%), They consistently produce larger effect sizes than human studies, with Fisher Z values approximately 2-3 times higher than human studies. Notably, LLMs show significantly lower replication rates for studies involving socially sensitive topics such as race, gender and ethics. When original studies reported null findings, LLMs produced significant results at remarkably high rates (68-83%) - while this could reflect cleaner data with less noise, as evidenced by narrower confidence intervals, it also suggests potential risks of effect size overestimation. Our results demonstrate both the promise and challenges of LLMs in psychological research, offering efficient tools for pilot testing and rapid hypothesis validation while enriching rather than replacing traditional human subject studies, yet requiring more nuanced interpretation and human validation for complex social phenomena and culturally sensitive research questions.

cs.CL↗

arXiv2025

Single-dislocation phonons: atomic-scale measurement and their thermal properties

Nanoscale defects such as dislocations, have a significant impact on the phonon thermal transport properties in non-metallic materials. To unravel these effects, understanding of defect phonon modes is essential. Herein, at the atomic scale, the localized phonons of individual dislocation at a Si/Ge interface are measured via monochromated electron energy loss spectroscopy in a scanning transmission electron microscope. These modes are then correlated with the local microstructure, further revealing the dislocation effects on the local thermal transport properties. The dislocation causes phonon redshift in several milli-electron-volts within about two to four nanometers of the core, where both of the strain field and Ge-segregation play roles. With the presence of dislocation, the local interfacial thermal conductance can be either enhanced or reduced, depending on the complex interaction and competition between lattice-disorder (dislocation) and element-disorder (heterointerface mixing and Ge-segregation) at the interface. These findings provide valuable insights to improve the thermal properties of thermoelectric generators and thermal management systems through proper defect engineering.

cond-mat.mtrl-sci↗

arXiv2025

Towards real-time additive-free dopamine detection at $10^{-8}$ mM with hardware accelerated platform integrated on camera

Tracing physiological neurotransmitters such as dopamine (DA) with detection limits down to $\mathrm{1\times10^{-8}}$ mM is a critical goal in neuroscience for studying brain functions and progressing the understanding of cerebral disease. Addressing this problem requires enhancing the current state-of-the-art additive-free electrochemical workstation methods by over two orders of magnitude. In this work, we implement an ultra-sensitive, additive-free platform exploiting suitably engineered light-scattering membranes and optical accelerators integrated into commercial vision cameras, reporting real-time detection of DA in uric and ascorbic acid below the concentration of $\mathrm{10^{-8}}$ mM. These performances improve the current best technology by over two orders of magnitude in resolution while providing continuous, real-time detection at video rates. This technology also upgrades the bulk form factor of an electrochemical workstation with an imaging camera's compact and portable footprint. The optical accelerator implemented in this work is universal and trainable to detect a wide range of biological analytes. This technology's wide adoption could help enable early disease detection and personalized treatment adjustments while improving the management of neurological, mental, and immune-related conditions.

physics.ins-det↗

arXiv2025

Scheduling of Flexible Manufacturing Systems Based on Place-Timed Petri Nets and Basis Reachability Graphs

Scheduling is a key decision-making process to improve the performance of flexible manufacturing systems. Place-timed Petri nets provide a formal method for graphically modeling and analyzing such systems. By generating reachability graphs and combining intelligent search algorithms, operation sequences from the initial state to the target state can be found for the underlying system. However, the reachability graph grows exponentially with the system size increases, which is the main challenge of existing methods for scheduling large systems. To this end, we develop an efficient improved beam search algorithm to optimize the makespan based on a compact representation of reachability graph called basis reachability graph. The key idea behind the proposed method is to form a state together with the basis markings and its corresponding transition sequences, and evaluate the cost of the state based on the resource idle time. Experimental results are conducted on several benchmark systems which show that the developed method improves the search efficiency while ensuring the quality of the solution compared with existing methods.

eess.SY↗