arXiv subjects

Chen Wang

Publications and source records attributed to Chen Wang.

At least 397 records · Page 22Linked to original sources

arXiv2024

OG-Mapping: Octree-based Structured 3D Gaussians for Online Dense Mapping

3D Gaussian splatting (3DGS) has recently demonstrated promising advancements in RGB-D online dense mapping. Nevertheless, existing methods excessively rely on per-pixel depth cues to perform map densification, which leads to significant redundancy and increased sensitivity to depth noise. Additionally, explicitly storing 3D Gaussian parameters of room-scale scene poses a significant storage challenge. In this paper, we introduce OG-Mapping, which leverages the robust scene structural representation capability of sparse octrees, combined with structured 3D Gaussian representations, to achieve efficient and robust online dense mapping. Moreover, OG-Mapping employs an anchor-based progressive map refinement strategy to recover the scene structures at multiple levels of detail. Instead of maintaining a small number of active keyframes with a fixed keyframe window as previous approaches do, a dynamic keyframe window is employed to allow OG-Mapping to better tackle false local minima and forgetting issues. Experimental results demonstrate that OG-Mapping delivers more robust and superior realism mapping results than existing Gaussian-based RGB-D online mapping methods with a compact model, and no additional post-processing is required.

cs.CV↗

arXiv2024

A longitudinal sentiment analysis of Sinophobia during COVID-19 using large language models

The COVID-19 pandemic has exacerbated xenophobia, particularly Sinophobia, leading to widespread discrimination against individuals of Chinese descent. Large language models (LLMs) are pre-trained deep learning models used for natural language processing (NLP) tasks. The ability of LLMs to understand and generate human-like text makes them particularly useful for analysing social media data to detect and evaluate sentiments. We present a sentiment analysis framework utilising LLMs for longitudinal sentiment analysis of the Sinophobic sentiments expressed in X (Twitter) during the COVID-19 pandemic. The results show a significant correlation between the spikes in Sinophobic tweets, Sinophobic sentiments and surges in COVID-19 cases, revealing that the evolution of the pandemic influenced public sentiment and the prevalence of Sinophobic discourse. Furthermore, the sentiment analysis revealed a predominant presence of negative sentiments, such as annoyance and denial, which underscores the impact of political narratives and misinformation shaping public opinion. The lack of empathetic sentiment which was present in previous studies related to COVID-19 highlights the way the political narratives in media viewed the pandemic and how it blamed the Chinese community. Our study highlights the importance of transparent communication in mitigating xenophobic sentiments during global crises.

cs.CL↗

arXiv2024

Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach

Vision-language pretraining (VLP) with transformers has demonstrated exceptional performance across numerous multimodal tasks. However, the adversarial robustness of these models has not been thoroughly investigated. Existing multimodal attack methods have largely overlooked cross-modal interactions between visual and textual modalities, particularly in the context of cross-attention mechanisms. In this paper, we study the adversarial vulnerability of recent VLP transformers and design a novel Joint Multimodal Transformer Feature Attack (JMTFA) that concurrently introduces adversarial perturbations in both visual and textual modalities under white-box settings. JMTFA strategically targets attention relevance scores to disrupt important features within each modality, generating adversarial samples by fusing perturbations and leading to erroneous model predictions. Experimental results indicate that the proposed approach achieves high attack success rates on vision-language understanding and reasoning downstream tasks compared to existing baselines. Notably, our findings reveal that the textual modality significantly influences the complex fusion processes within VLP transformers. Moreover, we observe no apparent relationship between model size and adversarial robustness under our proposed attacks. These insights emphasize a new dimension of adversarial robustness and underscore potential risks in the reliable deployment of multimodal AI systems.

cs.CV↗

arXiv2024

Performance Analysis of Photon-Limited Free-Space Optical Communications with Practical Photon-Counting Receivers

The non-perfect factors of practical photon-counting receiver are recognized as a significant challenge for long-distance photon-limited free-space optical (FSO) communication systems. This paper presents a comprehensive analytical framework for modeling the statistical properties of time-gated single-photon avalanche diode (TG-SPAD) based photon-counting receivers in presence of dead time, non-photon-number-resolving and afterpulsing effect. Drawing upon the non-Markovian characteristic of afterpulsing effect, we formulate a closed-form approximation for the probability mass function (PMF) of photon counts, when high-order pulse amplitude modulation (PAM) is used. Unlike the photon counts from a perfect photon-counting receiver, which adhere to a Poisson arrival process, the photon counts from a practical TG-SPAD based receiver are instead approximated by a binomial distribution. Additionally, by employing the maximum likelihood (ML) criterion, we derive a refined closed-form formula for determining the threshold in high-order PAM, thereby facilitating the development of an analytical model for the symbol error rate (SER). Utilizing this analytical SER model, the system performance is investigated. The numerical results underscore the crucial need to suppress background radiation below the tolerated threshold and to maintain a sufficient number of gates in order to achieve a target SER.

eess.SP↗

arXiv2024

iMTSP: Solving Min-Max Multiple Traveling Salesman Problem with Imperative Learning

This paper considers a Min-Max Multiple Traveling Salesman Problem (MTSP), where the goal is to find a set of tours, one for each agent, to collectively visit all the cities while minimizing the length of the longest tour. Though MTSP has been widely studied, obtaining near-optimal solutions for large-scale problems is still challenging due to its NP-hardness. Recent efforts in data-driven methods face challenges of the need for hard-to-obtain supervision and issues with high variance in gradient estimations, leading to slow convergence and highly suboptimal solutions. We address these issues by reformulating MTSP as a bilevel optimization problem, using the concept of imperative learning (IL). This involves introducing an allocation network that decomposes the MTSP into multiple single-agent traveling salesman problems (TSPs). The longest tour from these TSP solutions is then used to self-supervise the allocation network, resulting in a new self-supervised, bilevel, end-to-end learning framework, which we refer to as imperative MTSP (iMTSP). Additionally, to tackle the high-variance gradient issues during the optimization, we introduce a control variate-based gradient estimation algorithm. Our experiments showed that these innovative designs enable our gradient estimator to converge 20% faster than the advanced reinforcement learning baseline and find up to 80% shorter tour length compared with Google OR-Tools MTSP solver, especially in large-scale problems (e.g. 1000 cities and 15 agents).

cs.AI↗

arXiv2024

GECO: Generative Image-to-3D within a SECOnd

Recent years have seen significant advancements in 3D generation. While methods like score distillation achieve impressive results, they often require extensive per-scene optimization, which limits their time efficiency. On the other hand, reconstruction-based approaches are more efficient but tend to compromise quality due to their limited ability to handle uncertainty. We introduce GECO, a novel method for high-quality 3D generative modeling that operates within a second. Our approach addresses the prevalent issues of uncertainty and inefficiency in existing methods through a two-stage approach. In the first stage, we train a single-step multi-view generative model with score distillation. Then, a second-stage distillation is applied to address the challenge of view inconsistency in the multi-view generation. This two-stage process ensures a balanced approach to 3D generation, optimizing both quality and efficiency. Our comprehensive experiments demonstrate that GECO achieves high-quality image-to-3D mesh generation with an unprecedented level of efficiency. We will make the code and model publicly available.

cs.CV↗

arXiv2024

A Novel Signal Detection Method for Photon-Counting Communications with Nonlinear Distortion Effects

This paper proposes a method for estimating and detecting optical signals in practical photon-counting receivers. There are two important aspects of non-perfect photon-counting receivers, namely, (i) dead time which results in blocking loss, and (ii) non-photon-number-resolving, which leads to counting loss during the gate-ON interval. These factors introduce nonlinear distortion to the detected photon counts. The detected photon counts depend not only on the optical intensity but also on the signal waveform, and obey a Poisson binomial process. Using the discrete Fourier transform characteristic function (DFT-CF) method, we derive the probability mass function (PMF) of the detected photon counts. Furthermore, unlike conventional methods that assume an ideal rectangle wave, we propose a novel signal estimation and decision method applicable to arbitrary waveform. We demonstrate that the proposed method achieves superior error performance compared to conventional methods. The proposed algorithm has the potential to become an essential signal processing tool for photon-counting receivers.

eess.SP↗

arXiv2024

Determinants and Inverses of banded Toeplitz Matrices over $\mathbb{F}_p$ Are Periodic

Banded Toeplitz matrices over $\mathbb{F}_p$, as a well-known class of matrices, have been extensively studied in the fields of coding theory and automata theory. In this paper, we discover that both determinants and inverses of banded Toeplitz matrices over $\mathbb{F}_p$ exhibit periodicity. For a Toeplitz matrix with bandwidth $k$, The period $P(f)$ is related to the parameters on the band and is independent of the order, with an upper limit of $P(f) \le p^{k-1}-1$. We provide an algorithm which can compute the determinant of any order banded Toeplitz matrix within $O(k^4)$. And its inverse can be represented by three submatrices of size $P(f)*P(f)$ located respectively on the diagonal, above the diagonal, and below the diagonal. Thus, the computational cost for calculating the inverse is fixed, and our algorithm can solve it within $O(k^5)+3kP(f)^2$. This is the first time that the periodicity of determinants and inverses of general banded Toeplitz matrices over $\mathbb{F}_p$ has been computed and proven.

math.NA↗

arXiv2024

Leveraging Inter-Chunk Interactions for Enhanced Retrieval in Large Language Model-Based Question Answering

Retrieving external knowledge and prompting large language models with relevant information is an effective paradigm to enhance the performance of question-answering tasks. Previous research typically handles paragraphs from external documents in isolation, resulting in a lack of context and ambiguous references, particularly in multi-document and complex tasks. To overcome these challenges, we propose a new retrieval framework IIER, that leverages Inter-chunk Interactions to Enhance Retrieval. This framework captures the internal connections between document chunks by considering three types of interactions: structural, keyword, and semantic. We then construct a unified Chunk-Interaction Graph to represent all external documents comprehensively. Additionally, we design a graph-based evidence chain retriever that utilizes previous paths and chunk interactions to guide the retrieval process. It identifies multiple seed nodes based on the target question and iteratively searches for relevant chunks to gather supporting evidence. This retrieval process refines the context and reasoning chain, aiding the large language model in reasoning and answer generation. Extensive experiments demonstrate that IIER outperforms strong baselines across four datasets, highlighting its effectiveness in improving retrieval and reasoning capabilities.

cs.CL↗

arXiv2024

Quantum coherence effects on inelastic thermoelectric devices: From diodes to transistors

We present a study on inelastic thermoelectric devices, wherein charge currents and electronic and phononic heat currents are intricately interconnected. The employment of double quantum dots in conjunction with a phonon bath positions them as promising candidates for quantum thermoelectric diodes and transistors. Within this study, we illustrate that quantum coherence effects yield significant charge and Seebeck rectification effects. It's worth noting that, while the thermal transistor effect is observable in the linear response regime, especially when phonon-assisted inelastic processes dominate the transport, quantum coherence does not enhance thermal amplification. Our work provides valuable insights for the optimization of general thermoelectric devices.

cond-mat.mes-hall↗

arXiv2024

Supercongruences involving binomial coefficients and Euler polynomials

Let $p$ be an odd prime and let $x$ be a $p$-adic integer. In this paper, we establish supercongruences for $$ \sum_{k=0}^{p-1}\frac{\binom{x}{k}\binom{x+k}{k}(-4)^k}{(dk+1)\binom{2k}{k}}\pmod{p^2} $$ and $$ \sum_{k=0}^{p-1}\frac{\binom{x}{k}\binom{x+k}{k}(-2)^k}{(dk+1)\binom{2k}{k}}\pmod{p^2}, $$ where $d\in\{0,1,2\}$. As consequences, we extend some known results. For example, for $p>3$ we show $$ \sum_{k=0}^{p-1}\binom{3k}{k}\left(\frac{4}{27}\right)^k\equiv\frac19+\frac89p+\frac{4}{27}pE_{p-2}\left(\frac13\right)\pmod{p^2}, $$ where $E_n(x)$ denotes the Euler polynomial of degree $n$. This generalizes a known congruence of Z.-W. Sun.

math.NT↗

arXiv2024

Two Graphs: Resolving the Periodic Reversibility of One-dimensional Finite Cellular Automata

Finite cellular automata (FCA) are widely used in simulating nonlinear complex systems, and their reversibility is closely related to information loss during the evolution. However, only a relatively small portion of their reversibility problems has been solved. In this paper, we perform calculations on two graphs and discover that the reversibility of any one-dimensional FCA exhibits periodicity as the number of cells increases. We also successfully provide a method to compute the reversibility sequence that encompasses the reversibility of one-dimensional FCA with any number of cells. Additionally, the calculations in this paper are applicable to FCA with various types of boundaries. This means that we will have an efficient method to determine the reversibility of almost all one-dimensional FCA, with a complexity independent of cell number.

nlin.CG↗

arXiv2024

Efficient Algorithms for Injectivity and Bounded Surjectivity of One-dimensional Nonlinear Cellular Automata

Nonlinear cellular automata are extensively used in simulations, image processing, cryptography, and so on. The determination of their fundamental properties, injectivity and surjectivity, related to information loss during the evolution, is necessary in various applications. Currently, people still use Amoroso's algorithms for injectivity and surjectivity determinations, but this incurs significant computational costs when applied to complex nonlinear cellular automata. We have optimized Amoroso's surjectivity algorithm, improving its operational efficiency greatly and extended its applicability to various boundaries. Furthermore, we have introduced new theorems and algorithms for determining injectivity, which offer substantial improvements over Amoroso's algorithm in both time and space. With these new algorithms, we are equipped to determine the properties of larger and more complex cellular automata, thereby employing more advanced cellular automata to achieve increasingly complex functionalities.

cs.DS↗

arXiv2024

Efficient Calculations for Inverse of $k$-diagonal Circulant Matrices and Cyclic Banded Matrices

$k$-diagonal circulant matrices and cyclic banded matrices are widely used in numerical simulations and signal processing of circular linear systems. Algorithms that directly involve or specify linear or quadratic complexity for the inverses of these two types of matrices are rare. We find that the inverse of a $k$-diagonal circulant matrix can be uniquely determined by a recursive formula, which can be derived within $O(k^3 \log n+k^4)$. Similarly for the inverse of a cyclic banded matrix, its inverse can be uniquely determined by a series of recursive formulas, with the initial terms of these recursions computable within $O(k^3 n+k^5)$. The additional costs for solving the complete inverses of these two types of matrices are $kn$ and $kn^2$. Our calculations enable rapid representation with most processes defined by explicit formulas. Additionally, most algorithms for inverting $k$-diagonal circulant matrices rely on the Fast Fourier Transform, which is not applicable to finite fields, while our algorithms can be applied to computations in finite fields.

cs.MS↗

arXiv2024

Prompt Perturbation in Retrieval-Augmented Generation based Large Language Models

The robustness of large language models (LLMs) becomes increasingly important as their use rapidly grows in a wide range of domains. Retrieval-Augmented Generation (RAG) is considered as a means to improve the trustworthiness of text generation from LLMs. However, how the outputs from RAG-based LLMs are affected by slightly different inputs is not well studied. In this work, we find that the insertion of even a short prefix to the prompt leads to the generation of outputs far away from factually correct answers. We systematically evaluate the effect of such prefixes on RAG by introducing a novel optimization technique called Gradient Guided Prompt Perturbation (GGPP). GGPP achieves a high success rate in steering outputs of RAG-based LLMs to targeted wrong answers. It can also cope with instructions in the prompts requesting to ignore irrelevant context. We also exploit LLMs' neuron activation difference between prompts with and without GGPP perturbations to give a method that improves the robustness of RAG-based LLMs through a highly effective detector trained on neuron activation triggered by GGPP generated prompts. Our evaluation on open-sourced LLMs demonstrates the effectiveness of our methods.

cs.CL↗

arXiv2024

Learning-augmented Maximum Independent Set

We study the Maximum Independent Set (MIS) problem on general graphs within the framework of learning-augmented algorithms. The MIS problem is known to be NP-hard and is also NP-hard to approximate to within a factor of $n^{1-δ}$ for any $δ>0$. We show that we can break this barrier in the presence of an oracle obtained through predictions from a machine learning model that answers vertex membership queries for a fixed MIS with probability $1/2+\varepsilon$. In the first setting we consider, the oracle can be queried once per vertex to know if a vertex belongs to a fixed MIS, and the oracle returns the correct answer with probability $1/2 + \varepsilon$. Under this setting, we show an algorithm that obtains an $\tilde{O}(\sqrtΔ/\varepsilon)$-approximation in $O(m)$ time where $Δ$ is the maximum degree of the graph. In the second setting, we allow multiple queries to the oracle for a vertex, each of which is correct with probability $1/2 + \varepsilon$. For this setting, we show an $O(1)$-approximation algorithm using $O(n/\varepsilon^2)$ total queries and $\tilde{O}(m)$ runtime.

cs.DS↗

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

Variational and Explanatory Neural Networks for Encoding Cancer Profiles and Predicting Drug Responses

Human cancers present a significant public health challenge and require the discovery of novel drugs through translational research. Transcriptomics profiling data that describes molecular activities in tumors and cancer cell lines are widely utilized for predicting anti-cancer drug responses. However, existing AI models face challenges due to noise in transcriptomics data and lack of biological interpretability. To overcome these limitations, we introduce VETE (Variational and Explanatory Transcriptomics Encoder), a novel neural network framework that incorporates a variational component to mitigate noise effects and integrates traceable gene ontology into the neural network architecture for encoding cancer transcriptomics data. Key innovations include a local interpretability-guided method for identifying ontology paths, a visualization tool to elucidate biological mechanisms of drug responses, and the application of centralized large scale hyperparameter optimization. VETE demonstrated robust accuracy in cancer cell line classification and drug response prediction. Additionally, it provided traceable biological explanations for both tasks and offers insights into the mechanisms underlying its predictions. VETE bridges the gap between AI-driven predictions and biologically meaningful insights in cancer research, which represents a promising advancement in the field.

q-bio.QM↗