The study of social emergence has long been a central focus in social science. Traditional modeling approaches, such as rule-based Agent-Based Models (ABMs), struggle to capture the diversity and complexity of human behavior, particularly the irrational factors emphasized in behavioral economics. Recently, large language model (LLM) agents have gained traction as simulation tools for modeling human behavior in social science and role-playing applications. Studies suggest that LLMs can account for cognitive biases, emotional fluctuations, and other non-rational influences, enabling more realistic simulations of socio-economic dynamics. In this work, we introduce TwinMarket, a novel multi-agent framework that leverages LLMs to simulate socio-economic systems. Specifically, we examine how individual behaviors, through interactions and feedback mechanisms, give rise to collective dynamics and emergent phenomena. Through experiments in a simulated stock market environment, we demonstrate how individual actions can trigger group behaviors, leading to emergent outcomes such as financial bubbles and recessions. Our approach provides valuable insights into the complex interplay between individual decision-making and collective socio-economic patterns.

We propose the first character-level white-box adversarial attack method against transformer models.The intuition of our method comes from the observation that words are split into subtokens before being fed into the transformer models and the substitution between two close subtokens has a similar effect to the character modification.Our method mainly contains three steps.First, a gradient-based method is adopted to find the most vulnerable words in the sentence.Then we split the selected words into subtokens to replace the origin tokenization result from the transformer tokenizer.Finally, we utilize an adversarial loss to guide the substitution of attachable subtokens in which the Gumbel-softmax trick is introduced to ensure gradient propagation.Meanwhile, we introduce the visual and length constraint in the optimization process to achieve minimum character modifications.Extensive experiments on both sentence-level and token-level tasks demonstrate that our method could outperform the previous attack methods in terms of success rate and edit distance.Furthermore, human evaluation verifies our adversarial examples could preserve their origin labels.

Bipartite graphs have been proven useful in modeling a wide range of relationship networks. Finding the maximum edge biclique within a bipartite graph is a well-known problem in graph theory and data mining, with numerous real-world applications across different domains. We propose a probabilistic algorithm for finding the maximum edge biclique using a Monte Carlo subspace clustering approach. Extensive experimentation with both artificial and real-world datasets shows that the algorithm is significantly better than the state-of-the-art technique. We prove that there are solid theoretical reasons for the algorithm's efficacy that manifest in a polynomial complexity of time and space.

In this paper, we propose a novel robust hashing algorithm based on signal-to-noise ratio (SNR) maximization to learn binary codes. We first motivate SNR maximization for robust hashing in a statistical model, under which maximizing SNR minimizes the robust hashing error probability. A globally optimal solution can be obtained by solving a generalized eigenvalue problem. The proposed algorithm is tested on both synthetic and real datasets, showing significant performance gain over existing hashing algorithms.

Hashing algorithms which encode signal content into compact binary codes to preserve similarity, have been extensively studied for applications such as large-scale visual search. However, most existing hashing algorithms work with a single feature type, while combining multiple features is helpful in many vision tasks. In this paper, we propose two multi-feature hashing algorithms based on signal-to-noise ratio (SNR) maximization, where a globally optimal solution is obtained by solving a generalized eigenvalue problem. The first one jointly considers all feature correlations and learns uncorrelated hash functions that maximize SNR, and the second algorithm separately learns hash functions on each individual feature and selects the final hash functions based on the SNR associated with each hash function. The proposed algorithms perform favorably compared to other state-of-the-art multi-feature hashing algorithms on several benchmark datasets.

We propose a novel robust hashing algorithm based on signal-to-noise ratio (SNR) maximization to learn compact binary codes, where the SNR metric is used to select a set of projection directions, and one hash bit is extracted from each projection direction. We first motivate this approach under a Gaussian model for the underlying signals, in which case maximizing SNR is equivalent to minimizing the robust hashing error probability. A globally optimal solution can be obtained by solving a generalized eigenvalue problem. We also develop a multibit per projection algorithm to learn longer hash codes when the number of high-SNR projections is limited. The proposed algorithms are tested on both synthetic and real data sets, showing significant performance gains over existing hashing algorithms.

This paper proposes a regularized Adaboost algorithm to learn and extract binary fingerprints of time-varying content by filtering and quantizing perceptually significant features. The proposed algorithm extends the recent symmetric pairwise boosting (SPB) algorithm by taking feature sequence correlation into account. An information-theoretic analysis of the SPB algorithm is given, showing that each iteration of SPB maximizes a lower bound on the mutual information between matching fingerprint pairs. Based on the analysis, two practical regularizers are proposed to penalize those filters generating highly correlated filter responses. A learning-theoretic analysis of the regularized Adaboost algorithm is given. The proposed algorithm demonstrates significant performance gains over SPB for both audio and video content identification systems.

This paper proposes a regularized Adaboost learning algorithm to extract binary fingerprints by filtering and quantizing perceptually significant features. The proposed algorithm extends the recent symmetric pairwise boosting (SPB) algorithm by taking feature sequence correlation into account. Information and learning theoretic analysis is given. Significant performance gains over SPB are demonstrated for both audio and video fingerprinting.

This paper proposes the first content identification (ID) system for depth video as well as a first hybrid content ID system for synchronized RGB and depth (RGB-D) video. The proposed systems are tested on a public RGB-D dataset. The hybrid system demonstrates significant performance gains over RGB-alone or depth-alone systems, while depth and RGB perform comparably. Moreover, a statistical interpretation of the hybrid system's superior performance is provided.