arXiv subjects

Yijing Liu

Publications and source records attributed to Yijing Liu.

17 recordsLinked to original sources

arXiv2026

Excitation-Energy-Selective Control of Hot-Carrier Cooling via a Resonant Optical-Phonon Bottleneck in Graphene

Understanding and controlling hot-carrier relaxation in graphene is crucial for advancing ultrafast optoelectronic and terahertz technologies. Here, we investigate carrier cooling dynamics in monolayer and bilayer graphene using mid-infrared pump pulses (0.22-0.73 eV) and terahertz probe pulses. We uncover a pronounced, reproducible, and non-monotonic dependence of the carrier relaxation time on excitation photon energy. Remarkably, within a narrow spectral window (0.42 to 0.48 eV), the carrier lifetime increases by an order of magnitude compared to a few picosecond-scale cooling observed at other energies. We show that this anomalous slowdown originates from a resonant enhancement of the optical-phonon lifetime, causing accumulation and reabsorption of hot optical phonons that suppress energy transfer to the lattice. All observed behaviors are captured within a unified carrier-phonon energy-balance framework, where excitation-energy-dependent variations of the effective optical-phonon decay pathway govern the cooling dynamics. These findings demonstrate excitation-energy-selective control of hot-carrier relaxation in graphene and provide new insight into non-equilibrium carrier-phonon interactions near the optical-phonon bottleneck.

cond-mat.mes-hall↗

arXiv2026

Delayed Backdoor Attacks: Exploring the Temporal Dimension as a New Attack Surface in Pre-Trained Models

Backdoor attacks against pre-trained models (PTMs) have traditionally operated under an ``immediacy assumption,'' where malicious behavior manifests instantly upon trigger occurrence. This work revisits and challenges this paradigm by introducing \textit{\textbf{Delayed Backdoor Attacks (DBA)}}, a new class of threats in which activation is temporally decoupled from trigger exposure. We propose that this \textbf{temporal dimension} is the key to unlocking a previously infeasible class of attacks: those that use common, everyday words as triggers. To examine the feasibility of this paradigm, we design and implement a proof-of-concept prototype, termed \underline{D}elayed Backdoor Attacks Based on \underline{N}onlinear \underline{D}ecay (DND). DND embeds a lightweight, stateful logic module that postpones activation until a configurable threshold is reached, producing a distinct latency phase followed by a controlled outbreak. We derive a formal model to characterize this latency behavior and propose a dual-metric evaluation framework (ASR and ASR$_{delay}$) to empirically measure the delay effect. Extensive experiments on four (natural language processing)NLP benchmarks validate the core capabilities of DND: it remains dormant for a controllable duration, sustains high clean accuracy ($\ge$94\%), and achieves near-perfect post-activation attack success rates ($\approx$99\%, The average of other methods is below 95\%.). Moreover, DND exhibits resilience against several state-of-the-art defenses. This study provides the first empirical evidence that the temporal dimension constitutes a viable yet unprotected attack surface in PTMs, underscoring the need for next-generation, stateful, and time-aware defense mechanisms.

cs.CR↗

arXiv2026

State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space

Vision-Language-Action (VLA) models are widely deployed in safety-critical embodied AI applications such as robotics. However, their complex multimodal interactions also expose new security vulnerabilities. In this paper, we investigate a backdoor threat in VLA models, where malicious inputs cause targeted misbehavior while preserving performance on clean data. Existing backdoor methods predominantly rely on inserting visible triggers into visual modality, which suffer from poor robustness and low insusceptibility in real-world settings due to environmental variability. To overcome these limitations, we introduce the State Backdoor, a novel and practical backdoor attack that leverages the robot arm's initial state as the trigger. To optimize trigger for insusceptibility and effectiveness, we design a Preference-guided Genetic Algorithm (PGA) that efficiently searches the state space for minimal yet potent triggers. Extensive experiments on five representative VLA models and five real-world tasks show that our method achieves over 90% attack success rate without affecting benign task performance, revealing an underexplored vulnerability in embodied AI systems.

cs.CR↗

arXiv2025

SoK: Synthesizing Smart Home Privacy Protection Mechanisms Across Academic Proposals and Commercial Documentations

Pervasive data collection by Smart Home Devices (SHDs) demands robust Privacy Protection Mechanisms (PPMs). The effectiveness of many PPMs, particularly user-facing controls, depends on user awareness and adoption, which are shaped by manufacturers' public documentations. However, the landscape of academic proposals and commercial disclosures remains underexplored. To address this gap, we investigate: (1) What PPMs have academics proposed, and how are these PPMs evaluated? (2) What PPMs do manufacturers document and what factors affect these documentation? To address these questions, we conduct a two-phase study, synthesizing a systematic review of 117 academic papers with an empirical analysis of 86 SHDs' publicly disclosed documentations. Our review of academic literature reveals a strong focus on novel system- and algorithm-based PPMs. However, these proposals neglect deployment barriers (e.g., cost, interoperability), and lack real-world field validation and legal analysis. Concurrently, our analysis of commercial SHDs finds that advanced academic proposals are absent from public discourse. Industry postures are fundamentally reactive, prioritizing compliance via post-hoc data management (e.g., deletion options), rather than the preventative controls favored by academia. The documented protections correspondingly converge on a small set of practical mechanisms, such as physical buttons and localized processing. By synthesizing these findings, we advocate for research to analyze challenges, provide deployable frameworks, real-world field validation, and interoperability solutions to advance practical PPMs.

cs.HC↗

arXiv2025

Graph-Guided Concept Selection for Efficient Retrieval-Augmented Generation

Graph-based RAG constructs a knowledge graph (KG) from text chunks to enhance retrieval in Large Language Model (LLM)-based question answering. It is especially beneficial in domains such as biomedicine, law, and political science, where effective retrieval often involves multi-hop reasoning over proprietary documents. However, these methods demand numerous LLM calls to extract entities and relations from text chunks, incurring prohibitive costs at scale. Through a carefully designed ablation study, we observe that certain words (termed concepts) and their associated documents are more important. Based on this insight, we propose Graph-Guided Concept Selection (G2ConS). Its core comprises a chunk selection method and an LLM-independent concept graph. The former selects salient document chunks to reduce KG construction costs; the latter closes knowledge gaps introduced by chunk selection at zero cost. Evaluations on multiple real-world datasets show that G2ConS outperforms all baselines in construction cost, retrieval effectiveness, and answering quality.

cs.LG↗

arXiv2025

BadTime: An Effective Backdoor Attack on Multivariate Long-Term Time Series Forecasting

Multivariate long-term time series forecasting (MLTSF) models are increasingly deployed in critical domains such as climate, finance, and transportation. Despite their growing importance, the security of MLTSF models against backdoor attacks remains entirely unexplored. To bridge this gap, we propose BadTime, the first effective backdoor attack tailored for MLTSF. BadTime can manipulate hundreds of future predictions toward a target pattern by injecting a subtle trigger. BadTime addresses two key challenges that arise uniquely in MLTSF: (i) the rapid dilution of local triggers over long horizons, and (ii) the extreme sparsity of backdoor signals under stealth constraints. To counter dilution, BadTime leverages inter-variable correlations, temporal lags, and data-driven initialization to design a distributed, lag-aware trigger that ensures effective influence over long-range forecasts. To overcome sparsity, it introduces a hybrid strategy to select valuable poisoned samples and a decoupled backdoor training objective that adaptively adjusts the model's focus on the sparse backdoor signal, ensuring reliable learning at a poisoning rate as low as 1%. Extensive experiments show that BadTime significantly outperforms state-of-the-art (SOTA) backdoor attacks on time series forecasting by extending the attackable horizon from at most 12 timesteps to 720 timesteps (a 60-fold improvement), reducing MAE by over 50% on target variables, and boosting stealthiness by more than 3-fold under anomaly detection.

cs.CR↗

arXiv2025

Wan: Open and Advanced Large-Scale Video Generative Models

This report presents Wan, a comprehensive and open suite of video foundation models designed to push the boundaries of video generation. Built upon the mainstream diffusion transformer paradigm, Wan achieves significant advancements in generative capabilities through a series of innovations, including our novel VAE, scalable pre-training strategies, large-scale data curation, and automated evaluation metrics. These contributions collectively enhance the model's performance and versatility. Specifically, Wan is characterized by four key features: Leading Performance: The 14B model of Wan, trained on a vast dataset comprising billions of images and videos, demonstrates the scaling laws of video generation with respect to both data and model size. It consistently outperforms the existing open-source models as well as state-of-the-art commercial solutions across multiple internal and external benchmarks, demonstrating a clear and significant performance superiority. Comprehensiveness: Wan offers two capable models, i.e., 1.3B and 14B parameters, for efficiency and effectiveness respectively. It also covers multiple downstream applications, including image-to-video, instruction-guided video editing, and personal video generation, encompassing up to eight tasks. Consumer-Grade Efficiency: The 1.3B model demonstrates exceptional resource efficiency, requiring only 8.19 GB VRAM, making it compatible with a wide range of consumer-grade GPUs. Openness: We open-source the entire series of Wan, including source code and all models, with the goal of fostering the growth of the video generation community. This openness seeks to significantly expand the creative possibilities of video production in the industry and provide academia with high-quality video foundation models. All the code and models are available at https://github.com/Wan-Video/Wan2.1.

cs.CV↗

arXiv2024

Evidence of Floquet electronic steady states in graphene under continuous-wave mid-infrared irradiation

Light-induced phenomena in materials can exhibit exotic behavior that extends beyond equilibrium properties, offering new avenues for understanding and controlling electronic phases. So far, non-equilibrium phenomena in solids have been predominantly explored using femtosecond laser pulses, which generate transient, ultra-fast dynamics. Here, we investigate the steady non-equilibrium regime in graphene induced by a continuous-wave (CW) mid-infrared laser. Our transport measurements reveal signatures of a long-lived Floquet phase, where a non-equilibrium electronic population is stabilized by the interplay between coherent photoexcitation and incoherent phonon cooling. The observation of non-equilibrium steady states using CW lasers opens a new regime for low-temperature Floquet phenomena, paving the way toward Floquet engineering of steady-state phases of matter.

cond-mat.mes-hall↗

arXiv2024

MetaDD: Boosting Dataset Distillation with Neural Network Architecture-Invariant Generalization

Dataset distillation (DD) entails creating a refined, compact distilled dataset from a large-scale dataset to facilitate efficient training. A significant challenge in DD is the dependency between the distilled dataset and the neural network (NN) architecture used. Training a different NN architecture with a distilled dataset distilled using a specific architecture often results in diminished trainning performance for other architectures. This paper introduces MetaDD, designed to enhance the generalizability of DD across various NN architectures. Specifically, MetaDD partitions distilled data into meta features (i.e., the data's common characteristics that remain consistent across different NN architectures) and heterogeneous features (i.e., the data's unique feature to each NN architecture). Then, MetaDD employs an architecture-invariant loss function for multi-architecture feature alignment, which increases meta features and reduces heterogeneous features in distilled data. As a low-memory consumption component, MetaDD can be seamlessly integrated into any DD methodology. Experimental results demonstrate that MetaDD significantly improves performance across various DD methods. On the Distilled Tiny-Imagenet with Sre2L (50 IPC), MetaDD achieves cross-architecture NN accuracy of up to 30.1\%, surpassing the second-best method (GLaD) by 1.7\%.

cs.CV↗

arXiv2024

Fully Exploiting Every Real Sample: SuperPixel Sample Gradient Model Stealing

Model stealing (MS) involves querying and observing the output of a machine learning model to steal its capabilities. The quality of queried data is crucial, yet obtaining a large amount of real data for MS is often challenging. Recent works have reduced reliance on real data by using generative models. However, when high-dimensional query data is required, these methods are impractical due to the high costs of querying and the risk of model collapse. In this work, we propose using sample gradients (SG) to enhance the utility of each real sample, as SG provides crucial guidance on the decision boundaries of the victim model. However, utilizing SG in the model stealing scenario faces two challenges: 1. Pixel-level gradient estimation requires extensive query volume and is susceptible to defenses. 2. The estimation of sample gradients has a significant variance. This paper proposes Superpixel Sample Gradient stealing (SPSG) for model stealing under the constraint of limited real samples. With the basic idea of imitating the victim model's low-variance patch-level gradients instead of pixel-level gradients, SPSG achieves efficient sample gradient estimation through two steps. First, we perform patch-wise perturbations on query images to estimate the average gradient in different regions of the image. Then, we filter the gradients through a threshold strategy to reduce variance. Exhaustive experiments demonstrate that, with the same number of real samples, SPSG achieves accuracy, agreements, and adversarial success rate significantly surpassing the current state-of-the-art MS methods. Codes are available at https://github.com/zyl123456aB/SPSG_attack.

cs.CV↗

arXiv2024

Graph Diffusion Policy Optimization

Recent research has made significant progress in optimizing diffusion models for downstream objectives, which is an important pursuit in fields such as graph generation for drug design. However, directly applying these models to graph presents challenges, resulting in suboptimal performance. This paper introduces graph diffusion policy optimization (GDPO), a novel approach to optimize graph diffusion models for arbitrary (e.g., non-differentiable) objectives using reinforcement learning. GDPO is based on an eager policy gradient tailored for graph diffusion models, developed through meticulous analysis and promising improved performance. Experimental results show that GDPO achieves state-of-the-art performance in various graph generation tasks with complex and diverse objectives. Code is available at https://github.com/sail-sg/GDPO.

cs.LG↗

arXiv2023

CluBear: A Subsampling Package for Interactive Statistical Analysis with Massive Data on A Single Machine

This article introduces CluBear, a Python-based open-source package for interactive massive data analysis. The key feature of CluBear is that it enables users to conduct convenient and interactive statistical analysis of massive data with only a traditional single-computer system. Thus, CluBear provides a cost-effective solution when mining large-scale datasets. In addition, the CluBear package integrates many commonly used statistical and graphical tools, which are useful for most commonly encountered data analysis tasks.

stat.ME↗

arXiv2021

Using Terminal Circuit for Power System Electromagnetic Transient Simulation

The modern power system is evolving with increasing penetration of power electronics introducing complicated electromagnetic phenomenon. Electromagnetic transient (EMT) simulation is essential to understand power system behavior under disturbance which however is one of the most sophisticated and time-consuming applications in power system. To improve the electromagnetic transient simulation efficiency while keeping the simulation accuracy, this paper proposes to model and simulate power system electromagnetic transients by very large-scale integrated circuit (VLSI) as a preliminary exploration to eventually represent power system by VLSI circuit chip avoiding numerical calculation. To proof the concept, a simple 5 bus system is modeled and simulated to verify the feasibility of the proposed approach.

eess.SY↗

arXiv2021

Power System Transient Modeling and Simulation using Integrated Circuit

Transient stability analysis (TSA) plays an important role in power system analysis to investigate the stability of power system. Traditionally, transient stability analysis methods have been developed using time domain simulation by means of numerical integration method. In this paper, a new approach is proposed to model power systems as an integrated circuit and simulate the power system dynamic behavior by integrated circuit simulator. The proposed method modeled power grid, generator, governor, and exciter with high fidelity. The power system dynamic simulation accuracy and efficiency of the proposed approach are verified and demonstrated by case study on an IEEE standard system.

eess.SY↗

arXiv2021

Integration of Renewable Generators in Synthetic Electric Grids for Dynamic Analysis

This paper presents a method to better integrate dynamic models for renewable resources into synthetic electric grids. An automated dynamic models assignment process is proposed for wind and solar generators. A realistic composition ratio for different types of wind turbine generators (WTG) is assigned to each wind generator. Statistics summarized from real electric grid data form the bases in assigning proper models with reasonable parameters to each WTG. A similar process is used to assign appropriate models and parameters to each photovoltaic (PV) generator. Multiple control strategies of the renewable resources are considered and tested in case studies. Two large-scale synthetic network test cases are used as examples of modeling the dynamics of renewable generators. Several transient stability metrics are adopted to assess the stability level after being subject to N-1 contingency event. Representative contingency events are given to demonstrate the performance of the synthetic renewable generator models.

eess.SY↗

arXiv2020

GraphFederator: Federated Visual Analysis for Multi-party Graphs

This paper presents GraphFederator, a novel approach to construct joint representations of multi-party graphs and supports privacy-preserving visual analysis of graphs. Inspired by the concept of federated learning, we reformulate the analysis of multi-party graphs into a decentralization process. The new federation framework consists of a shared module that is responsible for joint modeling and analysis, and a set of local modules that run on respective graph data. Specifically, we propose a federated graph representation model (FGRM) that is learned from encrypted characteristics of multi-party graphs in local modules. We also design multiple visualization views for joint visualization, exploration, and analysis of multi-party graphs. Experimental results with two datasets demonstrate the effectiveness of our approach.

cs.HC↗

arXiv2019

Ambient Effects on Photogating in MoS2 Photodetectors

Atomically thin transition metal dichalcogenides (TMDs) are ideal candidates for ultrathin optoelectronics that is flexible and semitransparent. Photodetectors based on TMDs show remarkable performance, with responsivity and detectivity higher than 10^3 A/W and 10^12 Jones, respectively, but they are plagued by response times as slow as several tens of seconds. Although it is well established that gas adsorbates such as water and oxygen create charge traps and significantly increase both the responsivity and the response time, the underlying mechanism is still unclear. Here we study the influence of adsorbates on MoS2 photodetectors under ambient conditions, vacuum and illumination at different wavelengths. We show that, for wavelengths sufficiently short to excite electron-hole pairs in the MoS2, light illumination causes desorption of water and oxygen molecules. The change in the molecular gating provided by the physisorbed molecules is the dominant contribution to the device photoresponse in ambient conditions.

cond-mat.mes-hall↗