arXiv subjects

Yun Li

Publications and source records attributed to Yun Li.

At least 109 records · Page 6Linked to original sources

arXiv2024

AI Safety in Generative AI Large Language Models: A Survey

Large Language Model (LLMs) such as ChatGPT that exhibit generative AI capabilities are facing accelerated adoption and innovation. The increased presence of Generative AI (GAI) inevitably raises concerns about the risks and safety associated with these models. This article provides an up-to-date survey of recent trends in AI safety research of GAI-LLMs from a computer scientist's perspective: specific and technical. In this survey, we explore the background and motivation for the identified harms and risks in the context of LLMs being generative language models; our survey differentiates by emphasising the need for unified theories of the distinct safety challenges in the research development and applications of LLMs. We start our discussion with a concise introduction to the workings of LLMs, supported by relevant literature. Then we discuss earlier research that has pointed out the fundamental constraints of generative models, or lack of understanding thereof (e.g., performance and safety trade-offs as LLMs scale in number of parameters). We provide a sufficient coverage of LLM alignment -- delving into various approaches, contending methods and present challenges associated with aligning LLMs with human preferences. By highlighting the gaps in the literature and possible implementation oversights, our aim is to create a comprehensive analysis that provides insights for addressing AI safety in LLMs and encourages the development of aligned and secure models. We conclude our survey by discussing future directions of LLMs for AI safety, offering insights into ongoing research in this critical area.

cs.CY↗

arXiv2024

Self-consistent Deep Geometric Learning for Heterogeneous Multi-source Spatial Point Data Prediction

Multi-source spatial point data prediction is crucial in fields like environmental monitoring and natural resource management, where integrating data from various sensors is the key to achieving a holistic environmental understanding. Existing models in this area often fall short due to their domain-specific nature and lack a strategy for integrating information from various sources in the absence of ground truth labels. Key challenges include evaluating the quality of different data sources and modeling spatial relationships among them effectively. Addressing these issues, we introduce an innovative multi-source spatial point data prediction framework that adeptly aligns information from varied sources without relying on ground truth labels. A unique aspect of our method is the 'fidelity score,' a quantitative measure for evaluating the reliability of each data source. Furthermore, we develop a geo-location-aware graph neural network tailored to accurately depict spatial relationships between data points. Our framework has been rigorously tested on two real-world datasets and one synthetic dataset. The results consistently demonstrate its superior performance over existing state-of-the-art methods.

cs.LG↗

arXiv2024

STimage-1K4M: A histopathology image-gene expression dataset for spatial transcriptomics

Recent advances in multi-modal algorithms have driven and been driven by the increasing availability of large image-text datasets, leading to significant strides in various fields, including computational pathology. However, in most existing medical image-text datasets, the text typically provides high-level summaries that may not sufficiently describe sub-tile regions within a large pathology image. For example, an image might cover an extensive tissue area containing cancerous and healthy regions, but the accompanying text might only specify that this image is a cancer slide, lacking the nuanced details needed for in-depth analysis. In this study, we introduce STimage-1K4M, a novel dataset designed to bridge this gap by providing genomic features for sub-tile images. STimage-1K4M contains 1,149 images derived from spatial transcriptomics data, which captures gene expression information at the level of individual spatial spots within a pathology image. Specifically, each image in the dataset is broken down into smaller sub-image tiles, with each tile paired with 15,000-30,000 dimensional gene expressions. With 4,293,195 pairs of sub-tile images and gene expressions, STimage-1K4M offers unprecedented granularity, paving the way for a wide range of advanced research in multi-modal data analysis an innovative applications in computational pathology, and beyond.

cs.CV↗

arXiv2024

Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

We present Hunyuan-DiT, a text-to-image diffusion transformer with fine-grained understanding of both English and Chinese. To construct Hunyuan-DiT, we carefully design the transformer structure, text encoder, and positional encoding. We also build from scratch a whole data pipeline to update and evaluate data for iterative model optimization. For fine-grained language understanding, we train a Multimodal Large Language Model to refine the captions of the images. Finally, Hunyuan-DiT can perform multi-turn multimodal dialogue with users, generating and refining images according to the context. Through our holistic human evaluation protocol with more than 50 professional human evaluators, Hunyuan-DiT sets a new state-of-the-art in Chinese-to-image generation compared with other open-source models. Code and pretrained models are publicly available at github.com/Tencent/HunyuanDiT

cs.CV↗

arXiv2024

Eigenvector distributions and optimal shrinkage estimators for large covariance and precision matrices

This paper focuses on investigating Stein's invariant shrinkage estimators for large sample covariance matrices and precision matrices in high-dimensional settings. We consider models that have nearly arbitrary population covariance matrices, including those with potential spikes. By imposing mild technical assumptions, we establish the asymptotic limits of the shrinkers for a wide range of loss functions. A key contribution of this work, enabling the derivation of the limits of the shrinkers, is a novel result concerning the asymptotic distributions of the non-spiked eigenvectors of the sample covariance matrices, which can be of independent interest.

math.ST↗

arXiv2024

Prompt-tuning for Clickbait Detection via Text Summarization

Clickbaits are surprising social posts or deceptive news headlines that attempt to lure users for more clicks, which have posted at unprecedented rates for more profit or commercial revenue. The spread of clickbait has significant negative impacts on the users, which brings users misleading or even click-jacking attacks. Different from fake news, the crucial problem in clickbait detection is determining whether the headline matches the corresponding content. Most existing methods compute the semantic similarity between the headlines and contents for detecting clickbait. However, due to significant differences in length and semantic features between headlines and contents, directly calculating semantic similarity is often difficult to summarize the relationship between them. To address this problem, we propose a prompt-tuning method for clickbait detection via text summarization in this paper, text summarization is introduced to summarize the contents, and clickbait detection is performed based on the similarity between the generated summary and the contents. Specifically, we first introduce a two-stage text summarization model to produce high-quality news summaries based on pre-trained language models, and then both the headlines and new generated summaries are incorporated as the inputs for prompt-tuning. Additionally, a variety of strategies are conducted to incorporate external knowledge for improving the performance of clickbait detection. The extensive experiments on well-known clickbait detection datasets demonstrate that our method achieved state-of-the-art performance.

cs.CL↗

arXiv2024

Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data

Augmenting Large Language Models (LLMs) for Question Answering (QA) with domain specific data has attracted wide attention. However, domain data often exists in a hybrid format, including text and semi-structured tables, posing challenges for the seamless integration of information. Table-to-Text Generation is a promising solution by facilitating the transformation of hybrid data into a uniformly text-formatted corpus. Although this technique has been widely studied by the NLP community, there is currently no comparative analysis on how corpora generated by different table-to-text methods affect the performance of QA systems. In this paper, we address this research gap in two steps. First, we innovatively integrate table-to-text generation into the framework of enhancing LLM-based QA systems with domain hybrid data. Then, we utilize this framework in real-world industrial data to conduct extensive experiments on two types of QA systems (DSFT and RAG frameworks) with four representative methods: Markdown format, Template serialization, TPLM-based method, and LLM-based method. Based on the experimental results, we draw some empirical findings and explore the underlying reasons behind the success of some methods. We hope the findings of this work will provide a valuable reference for the academic and industrial communities in developing robust QA systems.

cs.CL↗

arXiv2024

Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey

Large language models (LLMs) have significantly advanced the field of natural language processing (NLP), providing a highly useful, task-agnostic foundation for a wide range of applications. However, directly applying LLMs to solve sophisticated problems in specific domains meets many hurdles, caused by the heterogeneity of domain data, the sophistication of domain knowledge, the uniqueness of domain objectives, and the diversity of the constraints (e.g., various social norms, cultural conformity, religious beliefs, and ethical standards in the domain applications). Domain specification techniques are key to make large language models disruptive in many applications. Specifically, to solve these hurdles, there has been a notable increase in research and practices conducted in recent years on the domain specialization of LLMs. This emerging field of study, with its substantial potential for impact, necessitates a comprehensive and systematic review to better summarize and guide ongoing work in this area. In this article, we present a comprehensive survey on domain specification techniques for large language models, an emerging direction critical for large language model applications. First, we propose a systematic taxonomy that categorizes the LLM domain-specialization techniques based on the accessibility to LLMs and summarizes the framework for all the subcategories as well as their relations and differences to each other. Second, we present an extensive taxonomy of critical application domains that can benefit dramatically from specialized LLMs, discussing their practical significance and open challenges. Last, we offer our insights into the current research status and future trends in this area.

cs.CL↗

arXiv2024

E-Sparse: Boosting the Large Language Model Inference through Entropy-based N:M Sparsity

Traditional pruning methods are known to be challenging to work in Large Language Models (LLMs) for Generative AI because of their unaffordable training process and large computational demands. For the first time, we introduce the information entropy of hidden state features into a pruning metric design, namely E-Sparse, to improve the accuracy of N:M sparsity on LLM. E-Sparse employs the information richness to leverage the channel importance, and further incorporates several novel techniques to put it into effect: (1) it introduces information entropy to enhance the significance of parameter weights and input feature norms as a novel pruning metric, and performs N:M sparsity without modifying the remaining weights. (2) it designs global naive shuffle and local block shuffle to quickly optimize the information distribution and adequately cope with the impact of N:M sparsity on LLMs' accuracy. E-Sparse is implemented as a Sparse-GEMM on FasterTransformer and runs on NVIDIA Ampere GPUs. Extensive experiments on the LLaMA family and OPT models show that E-Sparse can significantly speed up the model inference over the dense model (up to 1.53X) and obtain significant memory saving (up to 43.52%), with acceptable accuracy loss.

cs.LG↗

arXiv2024

E-DoH: Elegantly Detecting the Depths of Open DoH Service on the Internet

In recent years, DNS over Encrypted (DoE) methods have been regarded as a novel trend within the realm of the DNS ecosystem. In these DoE methods, DNS over HTTPS (DoH) provides encryption to protect data confidentiality while providing better obfuscation to avoid censorship by multiplexing port 443 with web services. This development introduced certain inconveniences in discovering publicly available DoH services. In this paper, we propose the E-DoH method for elegant and efficient DoH service detection. First, we optimized the probing mechanism to enable a single DoH connection to accomplish multiple tasks including service discovery, correctness validation and dependency construction. Second, we propose an efficient DoH detection tool. This tool can enhance probing efficiency while significantly reduce the required traffic volume. Third, based on the above optimization methods, we conducted an exploration of the IPv4 space and performed an in-depth analysis of DoH based on the collected information. Through experiments, our approach demonstrates a remarkable 80% improvement in time efficiency, and only requires 4%-20% traffic volume to complete the detection task. In wild detection, our approach discovered 46k DoH services, which nearly doubles the number discovered by the state-of-the-art. Based on the collected data, we present several intriguing conclusions about the current DoH service ecosystem.

cs.CR↗

arXiv2024

Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning

Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object pairs based on a limited set of observed examples. Current CZSL methodologies, despite their advancements, tend to neglect the distinct specificity levels present in attributes. For instance, given images of sliced strawberries, they may fail to prioritize `Sliced-Strawberry' over a generic `Red-Strawberry', despite the former being more informative. They also suffer from ballooning search space when shifting from Close-World (CW) to Open-World (OW) CZSL. To address the issues, we introduce the Context-based and Diversity-driven Specificity learning framework for CZSL (CDS-CZSL). Our framework evaluates the specificity of attributes by considering the diversity of objects they apply to and their related context. This novel approach allows for more accurate predictions by emphasizing specific attribute-object pairs and improves composition filtering in OW-CZSL. We conduct experiments in both CW and OW scenarios, and our model achieves state-of-the-art results across three datasets.

cs.CV↗

arXiv2024

On Secure mmWave RSMA Systems

This work considers a multiple-input-single-output mmWave RSMA system wherein a base station serves two users in the presence of a passive eavesdropper. Different eavesdropping scenarios are considered corresponding to the overlapped resolvable paths between the main and the wiretap channels under the considered transmission schemes. The analytical expressions for the secrecy outage probability are derived respectively through the Gaussian Chebyshev quadrature method. Monte Carlo simulation results are presented to validate the correctness of the derived analytical expressions and demonstrate the effects of system parameters on the SOP of the considered mmWave RSMA systems.

cs.IT↗

arXiv2024

Model Predictive Control Design for Unlocking the Energy Flexibility of Heat Pump and Thermal Energy Storage Systems

Heat pump and thermal energy storage (HPTES) systems, which are widely utilized in modern buildings for providing domestic hot water, contribute to a large share of household electricity consumption. With the increasing integration of renewable energy sources (RES) into modern power grids, demand-side management (DSM) becomes crucial for balancing power generation and consumption by adjusting end users' power consumption. This paper explores an energy flexible Model Predictive Control (MPC) design for a class of HPTES systems to facilitate demand-side management. The proposed DSM strategy comprises two key components: i) flexibility assessment, and ii) flexibility exploitation. Firstly, for flexibility assessment, a tailored MPC formulation, supplemented by a set of auxiliary linear constraints, is developed to quantitatively assess the flexibility potential inherent in HPTES systems. Subsequently, in flexibility exploitation, the energy flexibility is effectively harnessed in response to feasible demand response (DR) requests, which can be formulated as a standard mixed-integer MPC problem. Numerical experiments, based on a real-world HPTES installation, are conducted to demonstrate the efficacy of the proposed design.

eess.SY↗

arXiv2024

Weak Signal Inclusion Under Dependence and Applications in Genome-wide Association Study

Motivated by the inquiries of weak signals in underpowered genome-wide association studies (GWASs), we consider the problem of retaining true signals that are not strong enough to be individually separable from a large amount of noise. We address the challenge from the perspective of false negative control and present false negative control (FNC) screening, a data-driven method to efficiently regulate false negative proportion at a user-specified level. FNC screening is developed in a realistic setting with arbitrary covariance dependence between variables. We calibrate the overall dependence through a parameter whose scale is compatible with the existing phase diagram in high-dimensional sparse inference. Utilizing the new calibration, we asymptotically explicate the joint effect of covariance dependence, signal sparsity, and signal intensity on the proposed method. We interpret the results using a new phase diagram, which shows that FNC screening can efficiently select a set of candidate variables to retain a high proportion of signals even when the signals are not individually separable from noise. Finite sample performance of FNC screening is compared to those of several existing methods in simulation studies. The proposed method outperforms the others in adapting to a user-specified false negative control level. We implement FNC screening to empower a two-stage GWAS procedure, which demonstrates substantial power gain when working with limited sample sizes in real applications.

stat.ME↗

arXiv2024

FADI-AEC: Fast Score Based Diffusion Model Guided by Far-end Signal for Acoustic Echo Cancellation

Despite the potential of diffusion models in speech enhancement, their deployment in Acoustic Echo Cancellation (AEC) has been restricted. In this paper, we propose DI-AEC, pioneering a diffusion-based stochastic regeneration approach dedicated to AEC. Further, we propose FADI-AEC, fast score-based diffusion AEC framework to save computational demands, making it favorable for edge devices. It stands out by running the score model once per frame, achieving a significant surge in processing efficiency. Apart from that, we introduce a novel noise generation technique where far-end signals are utilized, incorporating both far-end and near-end signals to refine the score model's accuracy. We test our proposed method on the ICASSP2023 Microsoft deep echo cancellation challenge evaluation dataset, where our method outperforms some of the end-to-end methods and other diffusion based echo cancellation methods.

eess.AS↗

arXiv2023

Robust Optimal Control With Binary Adjustable Uncertainties

Robust Optimal Control (ROC) with adjustable uncertainties has proven to be effective in addressing critical challenges within modern energy networks, especially the reserve and provision problem. However, prior research on ROC with adjustable uncertainties has predominantly focused on the scenario of uncertainties modeled as continuous variables. In this paper, we explore ROC with binary adjustable uncertainties, where the uncertainties are modeled by binary decision variables, marking the first investigation of its kind. To tackle this new challenge, firstly we introduce a metric designed to quantitatively measure the extent of binary adjustable uncertainties. Then, to balance computational tractability and adaptability, we restrict control policies to be affine functions with respect to uncertainties, and propose a general design framework for ROC with binary adjustable uncertainties. To address the inherent computational demands of the original ROC problem, especially in large-scale applications, we employ strong duality (SD) and big-M-based reformulations to create a scalable and computationally efficient Mixed-Integer Linear Programming (MILP) formulation. Numerical simulations are conducted to showcase the performance of our proposed approach, demonstrating its applicability and effectiveness in handling binary adjustable uncertainties within the context of modern energy networks.

eess.SY↗

arXiv2023

Direct visualization of molecular stacking in quasi-2D hexagonal ice

The structure and properties of water or ice are of great interest to researchers due to their importance in the biological, cryopreservation and environmental fields. Hexagonal ice (Ih) is a common ice phase in nature and has been extensively studied; however, microstructural investigations at the atomic or molecular scale are still lacking. In this paper, the fine structure of quasi-2-dimensional ice Ih films was directly examined using cryogenic transmission electron microscopy. Two types of thin Ih films were observed: perfect single crystals growing along the [0001] direction and crystals with stacking faults, including both basal (BSF) and prismatic (PSF) ones, along the orientation of [11-20]; these results were further confirmed by theoretical calculations. Importantly, for the first time, the stacking faults in ice Ih were directly visualized and resolved. In light of the extension behavior of the chair conformation composed of the water molecules, we elucidated the formation mechanism of BSF in Ih, namely, the Ic phase. This study not only determined the structural characteristics of ice structure at the molecular scale but also provided important concepts for researchers to more fully understand the growth kinetics of ice crystals at the atomic scale.

cond-mat.mtrl-sci↗

arXiv2023

Unlocking Energy Flexibility From Thermal Inertia of Buildings: A Robust Optimization Approach

Towards integrating renewable electricity generation sources into the grid, an important facilitator is the energy flexibility provided by buildings' thermal inertia. Most of the existing research follows a single-step price- or incentive-based scheme for unlocking the flexibility potential of buildings. In contrast, this paper proposes a novel two-step design approach for better harnessing buildings' energy flexibility. In a first step, a robust optimization model is formulated for assessing the energy flexibility of buildings in the presence of uncertain predictions of external conditions, such as ambient temperature, solar irradiation, etc. In a second step, energy flexibility is activated in response to a feasible demand response (DR) request from grid operators without violating indoor temperature constraints, even in the presence of uncertain external conditions. The proposed approach is tested on a high-fidelity Modelica simulator to evaluate its effectiveness. Simulation results show that, compared with price-based demand-side management, the proposed approach achieves greater energy reduction during peak hours.

eess.SY↗