arXiv subjects

Qi Li

Publications and source records attributed to Qi Li.

At least 235 records · Page 13Linked to original sources

arXiv2024

Re-Examine Distantly Supervised NER: A New Benchmark and a Simple Approach

Distantly-Supervised Named Entity Recognition (DS-NER) uses knowledge bases or dictionaries for annotations, reducing manual efforts but rely on large human labeled validation set. In this paper, we introduce a real-life DS-NER dataset, QTL, where the training data is annotated using domain dictionaries and the test data is annotated by domain experts. This dataset has a small validation set, reflecting real-life scenarios. Existing DS-NER approaches fail when applied to QTL, which motivate us to re-examine existing DS-NER approaches. We found that many of them rely on large validation sets and some used test set for tuning inappropriately. To solve this issue, we proposed a new approach, token-level Curriculum-based Positive-Unlabeled Learning (CuPUL), which uses curriculum learning to order training samples from easy to hard. This method stabilizes training, making it robust and effective on small validation sets. CuPUL also addresses false negative issues using the Positive-Unlabeled learning paradigm, demonstrating improved performance in real-life applications.

cs.CL↗

arXiv2024

Prescribing Decision Conservativeness in Two-Stage Power Markets: A Distributionally Robust End-to-End Approach

This paper presents an end-to-end framework for calibrating wind power forecast models to minimize operational costs in two-stage power markets, where the first stage involves a distributionally robust optimal power flow (DR-OPF) model. Unlike traditional methods that adjust forecast parameters and uncertainty quantification (UQ) separately, this framework jointly optimizes both the forecast model parameters and the decision conservativeness, which determines the size of the ambiguity set in the DR-OPF model. The framework aligns UQ with actual uncertainty realizations by directly optimizing downstream operational costs, a process referred to as cost-oriented calibration. The calibration is achieved using a gradient descent approach. To enable efficient differentiation, the DR-OPF problem is reformulated into a convex form, and the Envelope Theorem is leveraged to simplify gradient derivation in the two-stage setting. Additionally, the framework supports distributed implementation, enhancing data privacy and reducing computational overhead. By proactively calibrating forecast parameters and prescribing optimal decision conservativeness, the framework significantly enhances cost efficiency and reliability in power system operations. Numerical experiments on an IEEE 5-bus system demonstrate the effectiveness and efficiency of the proposed approach.

eess.SY↗

arXiv2024

Detecting outliers by clustering algorithms

Clustering and outlier detection are two important tasks in data mining. Outliers frequently interfere with clustering algorithms to determine the similarity between objects, resulting in unreliable clustering results. Currently, only a few clustering algorithms (e.g., DBSCAN) have the ability to detect outliers to eliminate interference. For other clustering algorithms, it is tedious to introduce another outlier detection task to eliminate outliers before each clustering process. Obviously, how to equip more clustering algorithms with outlier detection ability is very meaningful. Although a common strategy allows clustering algorithms to detect outliers based on the distance between objects and clusters, it is contradictory to improving the performance of clustering algorithms on the datasets with outliers. In this paper, we propose a novel outlier detection approach, called ODAR, for clustering. ODAR maps outliers and normal objects into two separated clusters by feature transformation. As a result, any clustering algorithm can detect outliers by identifying clusters. Experiments show that ODAR is robust to diverse datasets. Compared with baseline methods, the clustering algorithms achieve the best on 7 out of 10 datasets with the help of ODAR, with at least 5% improvement in accuracy.

cs.LG↗

arXiv2024

Bias Voltage Driven Tunneling Magnetoresistance Polarity Reversal in 2D Stripy Antiferromagnet CrOCl

Atomically thin materials with coupled magnetic and electric polarization are critical for developing energy-efficient and high-density spintronic devices, yet they remain scarce due to often conflicting requirements of stabilizing both magnetic and electric orders. The recent discovery of the magnetoelectric effect in the 2D stripy antiferromagnet CrOCl highlights this semiconductor as a promising platform to explore electric field effects on magnetoresistance. In this study, we systematically investigate the magnetoresistance in tunneling junctions of bilayer and monolayer CrOCl. We observe that the transition from antiferromagnetic to ferrimagnetic phases in both cases induces a positive magnetoresistance at low bias voltages, which reverses to a negative value at higher bias voltages. This polarity reversal is attributed to the additional electric dipoles present in the antiferromagnetic state, as supported by our theoretical calculations. These findings suggest a pathway for the electric control of spintronic devices and underscore the potential of 2D magnets like CrOCl in advancing energy-efficient spintronic applications.

cond-mat.mes-hall↗

arXiv2024

Retrieval Augmented Instruction Tuning for Open NER with Large Language Models

The strong capability of large language models (LLMs) has been applied to information extraction (IE) through either retrieval augmented prompting or instruction tuning (IT). However, the best way to incorporate information with LLMs for IE remains an open question. In this paper, we explore Retrieval Augmented Instruction Tuning (RA-IT) for IE, focusing on the task of open named entity recognition (NER). Specifically, for each training sample, we retrieve semantically similar examples from the training dataset as the context and prepend them to the input of the original instruction. To evaluate our RA-IT approach more thoroughly, we construct a Chinese IT dataset for open NER and evaluate RA-IT in both English and Chinese scenarios. Experimental results verify the effectiveness of RA-IT across various data sizes and in both English and Chinese scenarios. We also conduct thorough studies to explore the impacts of various retrieval strategies in the proposed RA-IT framework. Code and data are available at: https://github.com/Emma1066/Retrieval-Augmented-IT-OpenNER

cs.CL↗

arXiv2024

MaintAGT:Sim2Real-Guided Multimodal Large Model for Intelligent Maintenance with Chain-of-Thought Reasoning

In recent years, large language models have made significant advancements in the field of natural language processing, yet there are still inadequacies in specific domain knowledge and applications. This paper Proposes MaintAGT, a professional large model for intelligent operations and maintenance, aimed at addressing this issue. The system comprises three key components: a signal-to-text model, a pure text model, and a multimodal model. Firstly, the signal-to-text model was designed to convert raw signal data into textual descriptions, bridging the gap between signal data and text-based analysis. Secondly, the pure text model was fine-tuned using the GLM4 model with specialized knowledge to enhance its understanding of domain-specific texts. Finally, these two models were integrated to develop a comprehensive multimodal model that effectively processes and analyzes both signal and textual data.The dataset used for training and evaluation was sourced from academic papers, textbooks, international standards, and vibration analyst training materials, undergoing meticulous preprocessing to ensure high-quality data. As a result, the model has demonstrated outstanding performance across multiple intelligent operations and maintenance tasks, providing a low-cost, high-quality method for constructing large-scale monitoring signal-text description-fault pattern datasets. Experimental results indicate that the model holds significant advantages in condition monitoring, signal processing, and fault diagnosis.In the constructed general test set, MaintAGT achieved an accuracy of 70%, surpassing all existing general large language models and reaching the level of an ISO Level III human vibration analyst.This advancement signifies a crucial step forward from traditional maintenance practices toward intelligent and AI-driven maintenance solutions.

eess.SP↗

arXiv2024

On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks

Large Language Models (LLMs) excel in various applications, including text generation and complex tasks. However, the misuse of LLMs raises concerns about the authenticity and ethical implications of the content they produce, such as deepfake news, academic fraud, and copyright infringement. Watermarking techniques, which embed identifiable markers in machine-generated text, offer a promising solution to these issues by allowing for content verification and origin tracing. Unfortunately, the robustness of current LLM watermarking schemes under potential watermark removal attacks has not been comprehensively explored. In this paper, to fill this gap, we first systematically comb the mainstream watermarking schemes and removal attacks on machine-generated texts, and then we categorize them into pre-text (before text generation) and post-text (after text generation) classes so that we can conduct diversified analyses. In our experiments, we evaluate eight watermarks (five pre-text, three post-text) and twelve attacks (two pre-text, ten post-text) across 87 scenarios. Evaluation results indicate that (1) KGW and Exponential watermarks offer high text quality and watermark retention but remain vulnerable to most attacks; (2) Post-text attacks are found to be more efficient and practical than pre-text attacks; (3) Pre-text watermarks are generally more imperceptible, as they do not alter text fluency, unlike post-text watermarks; (4) Additionally, combined attack methods can significantly increase effectiveness, highlighting the need for more robust watermarking solutions. Our study underscores the vulnerabilities of current techniques and the necessity for developing more resilient schemes.

cs.CR↗

arXiv2024

Structured Object Language Modeling (SoLM): Native Structured Objects Generation Conforming to Complex Schemas with Self-Supervised Denoising

In this paper, we study the problem of generating structured objects that conform to a complex schema, with intricate dependencies between the different components (facets) of the object. The facets of the object (attributes, fields, columns, properties) can be a mix of short, structured, type-constrained facts, or long natural-language descriptions. The object has to be self-consistent between the different facets in the redundant information it carries (relative consistency), while being grounded with respect to world knowledge (absolute consistency). We frame the problem as a Language Modeling problem (Structured Object Language Modeling) and train an LLM to perform the task natively, without requiring instructions or prompt-engineering. We propose a self-supervised denoising method to train the model from an existing dataset of such objects. The input query can be the existing object itself, in which case the model acts as a regenerator, completing, correcting, normalizing the input, or any unstructured blurb to be structured. We show that the self-supervised denoising training provides a strong baseline, and that additional supervised fine-tuning with small amount of human demonstrations leads to further improvement. Experimental results show that the proposed method matches or outperforms prompt-engineered general-purpose state-of-the-art LLMs (Claude 3, Mixtral-8x7B), while being order-of-magnitude more cost-efficient.

cs.SE↗

arXiv2024

Learning Disentangled Representation for One-shot Progressive Face Swapping

Although face swapping has attracted much attention in recent years, it remains a challenging problem. Existing methods leverage a large number of data samples to explore the intrinsic properties of face swapping without considering the semantic information of face images. Moreover, the representation of the identity information tends to be fixed, leading to suboptimal face swapping. In this paper, we present a simple yet efficient method named FaceSwapper, for one-shot face swapping based on Generative Adversarial Networks. Our method consists of a disentangled representation module and a semantic-guided fusion module. The disentangled representation module comprises an attribute encoder and an identity encoder, which aims to achieve the disentanglement of the identity and attribute information. The identity encoder is more flexible, and the attribute encoder contains more attribute details than its competitors. Benefiting from the disentangled representation, FaceSwapper can swap face images progressively. In addition, semantic information is introduced into the semantic-guided fusion module to control the swapped region and model the pose and expression more accurately. Experimental results show that our method achieves state-of-the-art results on benchmark datasets with fewer training samples. Our code is publicly available at https://github.com/liqi-casia/FaceSwapper.

cs.CV↗

arXiv2024

ReDAN: An Empirical Study on Remote DoS Attacks against NAT Networks

In this paper, we conduct an empirical study on remote DoS attacks targeting NAT networks. We show that Internet attackers operating outside local NAT networks can remotely identify a NAT device and subsequently terminate TCP connections initiated from the identified NAT device to external servers. Our attack involves two steps. First, we identify NAT devices on the Internet by exploiting inadequacies in the PMTUD mechanism within NAT specifications. This deficiency creates a fundamental side channel that allows Internet attackers to distinguish if a public IPv4 address serves a NAT device or a separate IP host, aiding in the identification of target NAT devices. Second, we launch a remote DoS attack to terminate TCP connections on the identified NAT devices. While recent NAT implementations may include protective measures, such as packet legitimacy validation to prevent malicious manipulations on NAT mappings, we discover that these safeguards are not widely adopted in real world. Consequently, attackers can send crafted packets to deceive NAT devices into erroneously removing innocent TCP connection mappings, thereby disrupting the NATed clients to access remote TCP servers. Our experimental results reveal widespread security vulnerabilities in existing NAT devices. After testing 8 types of router firmware and 30 commercial NAT devices from 14 vendors, we identify vulnerabilities in 6 firmware types and 29 NAT devices. Moreover, our measurements reveal a stark reality: 166 out of 180 (over 92%) tested real-world NAT networks, comprising 90 4G LTE/5G networks, 60 public Wi-Fi networks, and 30 cloud VPS networks, are susceptible to exploitation. We responsibly disclosed the vulnerabilities to affected vendors and received a significant number of acknowledgments. Finally, we propose our countermeasures against the identified DoS attack.

cs.CR↗

arXiv2024

Data Lineage Inference: Uncovering Privacy Vulnerabilities of Dataset Pruning

In this work, we systematically explore the data privacy issues of dataset pruning in machine learning systems. Our findings reveal, for the first time, that even if data in the redundant set is solely used before model training, its pruning-phase membership status can still be detected through attacks. Since this is a fully upstream process before model training, traditional model output-based privacy inference methods are completely unsuitable. To address this, we introduce a new task called Data-Centric Membership Inference and propose the first ever data-centric privacy inference paradigm named Data Lineage Inference (DaLI). Under this paradigm, four threshold-based attacks are proposed, named WhoDis, CumDis, ArraDis and SpiDis. We show that even without access to downstream models, adversaries can accurately identify the redundant set with only limited prior knowledge. Furthermore, we find that different pruning methods involve varying levels of privacy leakage, and even the same pruning method can present different privacy risks at different pruning fractions. We conducted an in-depth analysis of these phenomena and introduced a metric called the Brimming score to offer guidance for selecting pruning methods with privacy protection in mind.

cs.CR↗

arXiv2024

Exploiting Cross-Layer Vulnerabilities: Off-Path Attacks on the TCP/IP Protocol Suite

After more than 40 years of development, the fundamental TCP/IP protocol suite, serving as the backbone of the Internet, is widely recognized for having achieved an elevated level of robustness and security. Distinctively, we take a new perspective to investigate the security implications of cross-layer interactions within the TCP/IP protocol suite caused by ICMP error messages. Through a comprehensive analysis of interactions among Wi-Fi, IP, ICMP, UDP, and TCP due to ICMP errors, we uncover several significant vulnerabilities, including information leakage, desynchronization, semantic gaps, and identity spoofing. These vulnerabilities can be exploited by off-path attackers to manipulate network traffic stealthily, affecting over 20% of popular websites and more than 89% of public Wi-Fi networks, thus posing risks to the Internet. By responsibly disclosing these vulnerabilities to affected vendors and proposing effective countermeasures, we enhance the robustness of the TCP/IP protocol suite, receiving acknowledgments from well-known organizations such as the Linux community, the OpenWrt community, the FreeBSD community, Wi-Fi Alliance, Qualcomm, HUAWEI, China Telecom, Alibaba, and H3C.

cs.CR↗

arXiv2024

Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging

Model merging is a promising lightweight model empowerment technique that does not rely on expensive computing devices (e.g., GPUs) or require the collection of specific training data. Instead, it involves editing different upstream model parameters to absorb their downstream task capabilities. However, uncertified model merging can infringe upon the Intellectual Property (IP) rights of the original upstream models. In this paper, we conduct the first study on the robustness of IP protection methods under model merging scenarios. Specifically, we investigate two state-of-the-art IP protection techniques: Quantization Watermarking and Instructional Fingerprint, along with various advanced model merging technologies, such as Task Arithmetic, TIES-MERGING, and so on. Experimental results indicate that current Large Language Model (LLM) watermarking techniques cannot survive in the merged models, whereas model fingerprinting techniques can. Our research aims to highlight that model merging should be an indispensable consideration in the robustness assessment of model IP protection techniques, thereby promoting the healthy development of the open-source LLM community. Our code is available at https://github.com/ThuCCSLab/MergeGuard.

cs.CR↗

arXiv2024

Benchmarking Badminton Action Recognition with a New Fine-Grained Dataset

In the dynamic and evolving field of computer vision, action recognition has become a key focus, especially with the advent of sophisticated methodologies like Convolutional Neural Networks (CNNs), Convolutional 3D, Transformer, and spatial-temporal feature fusion. These technologies have shown promising results on well-established benchmarks but face unique challenges in real-world applications, particularly in sports analysis, where the precise decomposition of activities and the distinction of subtly different actions are crucial. Existing datasets like UCF101, HMDB51, and Kinetics have offered a diverse range of video data for various scenarios. However, there's an increasing need for fine-grained video datasets that capture detailed categorizations and nuances within broader action categories. In this paper, we introduce the VideoBadminton dataset derived from high-quality badminton footage. Through an exhaustive evaluation of leading methodologies on this dataset, this study aims to advance the field of action recognition, particularly in badminton sports. The introduction of VideoBadminton could not only serve for badminton action recognition but also provide a dataset for recognizing fine-grained actions. The insights gained from these evaluations are expected to catalyze further research in action comprehension, especially within sports contexts.

cs.CV↗

arXiv2024

Magnetic Milli-spinner for Robotic Endovascular Surgery

Vascular diseases such as thrombosis, atherosclerosis, and aneurysm, which can lead to blockage of blood flow or blood vessel rupture, are common and life-threatening. Conventional minimally invasive treatments utilize catheters, or long tubes, to guide small devices or therapeutic agents to targeted regions for intervention. Unfortunately, catheters suffer from difficult and unreliable navigation in narrow, winding vessels such as those found in the brain. Magnetically actuated untethered robots, which have been extensively explored as an alternative, are promising for navigation in complex vasculatures and vascular disease treatments. Most current robots, however, cannot swim against high flows or are inadequate in treating certain conditions. Here, we introduce a multifunctional and magnetically actuated milli-spinner robot for rapid navigation and performance of various treatments in complicated vasculatures. The milli-spinner, with a unique hollow structure including helical fins and slits for propulsion, generates a distinct flow field upon spinning. The milli-spinner is the fastest-ever untethered magnetic robot for movement in tubular environments, easily achieving speeds of 23 cm/s, demonstrating promise as an untethered medical device for effective navigation in blood vessels and robotic treatment of numerous vascular diseases.

cs.RO↗

arXiv2024

Simba-EoR: Early galaxy formation in the Simba simulation including a new sub-grid interstellar medium model

We update the dust model present within the Simba galaxy simulations with a self-consistent framework for the co-evolution of dust and molecular hydrogen populations in the interstellar medium, and use this to explore $z \geq 6$ galaxy evolution. In addition to tracking the evolution of dust and molecular hydrogen abundances, our model fully integrates these species into the Simba simulation, explicitly modelling their impact on physical processes such as star formation and cooling through the inclusion of a novel two-phase sub-grid model for interstellar gas. In running two high-resolution simulations down to $z \sim 6$ we find that our Simba-EoR model displays a generally tighter concordance with observational data than fiducial Simba. Additionally we observe that our Simba-EoR models increase star formation activity at early epochs, producing larger dust-to-gas ratios consequently. Finally, we discover a significant population of hot dust at $\sim 100$ K, aligning with contemporaneous observations of high-redshift dusty galaxies, alongside the large $\sim 20$ K population typically identified.

astro-ph.GA↗

arXiv2024

Should We Really Edit Language Models? On the Evaluation of Edited Language Models

Model editing has become an increasingly popular alternative for efficiently updating knowledge within language models. Current methods mainly focus on reliability, generalization, and locality, with many methods excelling across these criteria. Some recent works disclose the pitfalls of these editing methods such as knowledge distortion or conflict. However, the general abilities of post-edited language models remain unexplored. In this paper, we perform a comprehensive evaluation on various editing methods and different language models, and have following findings. (1) Existing editing methods lead to inevitable performance deterioration on general benchmarks, indicating that existing editing methods maintain the general abilities of the model within only a few dozen edits. When the number of edits is slightly large, the intrinsic knowledge structure of the model is disrupted or even completely damaged. (2) Instruction-tuned models are more robust to editing, showing less performance drop on general knowledge after editing. (3) Language model with large scale is more resistant to editing compared to small model. (4) The safety of the edited model, is significantly weakened, even for those safety-aligned models. Our findings indicate that current editing methods are only suitable for small-scale knowledge updates within language models, which motivates further research on more practical and reliable editing methods. The details of code and reproduction can be found in https://github.com/lqinfdim/EditingEvaluation.

cs.AI↗

arXiv2024

Observation of Giant Nernst plateau in ideal 1D Weyl Phase

The search for a giant Nernst effect beyond conventional mechanisms offers advantages for developing advanced thermoelectric devices and understanding charge-entropy conversion. Here, we study the Seebeck and Nernst effects of HfTe5 over a wide range of magnetic fields. By tracking the unusual magneto-thermoelectric responses, we reveal two magnetic-field-driven phase transitions proposed for weak topological insulators: the gap-closing transition of the zeroth Landau bands and the topological Lifshitz transition. After the magnetic fields exceed approximately ten times the quantum limit, we observe that the Nernst signal no longer varies with the fields, forming a plateau with a remarkably large value, reaching up to 50 μV/K at 2 K. We theoretically explain the giant Nernst plateau as a unique signature of the ideal 1D Weyl phase formed in such high fields. Our findings expand the understanding of ideal Weyl physics and open new avenues for realizing novel thermoelectric effects without fundamental constraints.

cond-mat.mtrl-sci↗