arXiv subjects

Xiaomeng Wang

Publications and source records attributed to Xiaomeng Wang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Towards Rationality in Language and Multimodal Agents: A Survey

This work discusses how to build more rational language and multimodal agents and what criteria define rationality in intelligent systems. Rationality is the quality of being guided by reason, characterized by decision-making that aligns with evidence and logical principles. It plays a crucial role in reliable problem-solving by ensuring well-grounded and consistent solutions. Despite their progress, large language models (LLMs) often fall short of rationality due to their bounded knowledge space and inconsistent outputs. In response, recent efforts have shifted toward developing multimodal and multi-agent systems, as well as integrating modules like external tools, programming codes, symbolic reasoners, utility function, and conformal risk controls rather than relying solely on a single LLM for decision-making. This paper surveys state-of-the-art advancements in language and multimodal agents, assesses their role in enhancing rationality, and outlines open challenges and future research directions. We maintain an open repository at https://github.com/bowen-upenn/Agent_Rationality.

cs.AI↗

arXiv2025

Typographic Attacks in a Multi-Image Setting

Large Vision-Language Models (LVLMs) are susceptible to typographic attacks, which are misclassifications caused by an attack text that is added to an image. In this paper, we introduce a multi-image setting for studying typographic attacks, broadening the current emphasis of the literature on attacking individual images. Specifically, our focus is on attacking image sets without repeating the attack query. Such non-repeating attacks are stealthier, as they are more likely to evade a gatekeeper than attacks that repeat the same attack text. We introduce two attack strategies for the multi-image setting, leveraging the difficulty of the target image, the strength of the attack text, and text-image similarity. Our text-image similarity approach improves attack success rates by 21% over random, non-specific methods on the CLIP model using ImageNet while maintaining stealth in a multi-image scenario. An additional experiment demonstrates transferability, i.e., text-image similarity calculated using CLIP transfers when attacking InstructBLIP.

cs.CR↗

arXiv2025

XR-VIO: High-precision Visual Inertial Odometry with Fast Initialization for XR Applications

This paper presents a novel approach to Visual Inertial Odometry (VIO), focusing on the initialization and feature matching modules. Existing methods for initialization often suffer from either poor stability in visual Structure from Motion (SfM) or fragility in solving a huge number of parameters simultaneously. To address these challenges, we propose a new pipeline for visual inertial initialization that robustly handles various complex scenarios. By tightly coupling gyroscope measurements, we enhance the robustness and accuracy of visual SfM. Our method demonstrates stable performance even with only four image frames, yielding competitive results. In terms of feature matching, we introduce a hybrid method that combines optical flow and descriptor-based matching. By leveraging the robustness of continuous optical flow tracking and the accuracy of descriptor matching, our approach achieves efficient, accurate, and robust tracking results. Through evaluation on multiple benchmarks, our method demonstrates state-of-the-art performance in terms of accuracy and success rate. Additionally, a video demonstration on mobile devices showcases the practical applicability of our approach in the field of Augmented Reality/Virtual Reality (AR/VR).

cs.CV↗

arXiv2025

Stability of graph pairs involving cycles

A graph pair $(Γ, Σ)$ is called stable if $\aut(Γ)\times\aut(Σ)$ is isomorphic to $\aut(Γ\timesΣ)$ and unstable otherwise, where $Γ\timesΣ$ is the direct product of $Γ$ and $Σ$. A graph is called $R$-thin if distinct vertices have different neighbourhoods. $Γ$ and $Σ$ are said to be coprime if there is no nontrivial graph $Δ$ such that $Γ\cong Γ_1 \times Δ$ and $Σ\cong Σ_1 \times Δ$ for some graphs $Γ_1$ and $Σ_1$. An unstable graph pair $(Γ, Σ)$ is called nontrivially unstable if $Γ$ and $Σ$ are $R$-thin connected coprime graphs and at least one of them is non-bipartite. This paper contributes to the study of the stability of graph pairs with a focus on the case when $Σ= C_n$ is a cycle. We give two sufficient conditions for $(Γ, C_n)$ to be nontrivially unstable, where $n \ne 4$ and $Γ$ is an $R$-thin connected graph. In the case when $Γ$ is an $R$-thin connected non-bipartite graph, we obtain the following results: (i) if $(Γ, K_2)$ is unstable, then $(Γ, C_{n})$ is unstable for every even integer $n \geq 4$; (ii) if an even integer $n \ge 6$ is compatible with $Γ$ in some sense, then $(Γ, C_{n})$ is nontrivially unstable if and only if $(Γ, K_2)$ is unstable; (iii) if there is an even integer $n \ge 6$ compatible with $Γ$ such that $(Γ, C_{n})$ is nontrivially unstable, then $(Γ, C_{m})$ is unstable for all even integers $m \ge 6$. We also prove that if $Γ$ is an $R$-thin connected graph and $n \ge 3$ is an odd integer compatible with $Γ$, then $(Γ, C_{n})$ is stable.

math.CO↗

arXiv2025

Car-GS: Addressing Reflective and Transparent Surface Challenges in 3D Car Reconstruction

3D car modeling is crucial for applications in autonomous driving systems, virtual and augmented reality, and gaming. However, due to the distinctive properties of cars, such as highly reflective and transparent surface materials, existing methods often struggle to achieve accurate 3D car reconstruction.To address these limitations, we propose Car-GS, a novel approach designed to mitigate the effects of specular highlights and the coupling of RGB and geometry in 3D geometric and shading reconstruction (3DGS). Our method incorporates three key innovations: First, we introduce view-dependent Gaussian primitives to effectively model surface reflections. Second, we identify the limitations of using a shared opacity parameter for both image rendering and geometric attributes when modeling transparent objects. To overcome this, we assign a learnable geometry-specific opacity to each 2D Gaussian primitive, dedicated solely to rendering depth and normals. Third, we observe that reconstruction errors are most prominent when the camera view is nearly orthogonal to glass surfaces. To address this issue, we develop a quality-aware supervision module that adaptively leverages normal priors from a pre-trained large-scale normal model.Experimental results demonstrate that Car-GS achieves precise reconstruction of car surfaces and significantly outperforms prior methods. The project page is available at https://lcc815.github.io/Car-GS.

cs.CV↗

arXiv2025

Towards a performance characteristic curve for model evaluation: an application in information diffusion prediction

The information diffusion prediction on social networks aims to predict future recipients of a message, with practical applications in marketing and social media. While different prediction models all claim to perform well, general frameworks for performance evaluation remain limited. Here, we aim to identify a performance characteristic curve for a model, which captures its performance on tasks of different complexity. We propose a metric based on information entropy to quantify the randomness in diffusion data. We then identify a scaling pattern between the randomness and the prediction accuracy of the model. By properly adjusting the variables, data points by different sequence lengths, system sizes, and randomness can all collapse into a single curve. The curve captures a model's inherent capability of making correct predictions against increased uncertainty, which we regard as the performance characteristic curve of the model. The validity of the curve is tested by three prediction models in the same family, reaching conclusions in line with existing studies. In addition, we apply the curve to successfully assess the performance of eight state-of-the-art models, providing a clear and comprehensive evaluation even for models that are challenging to differentiate with conventional metrics. Our work reveals a pattern underlying the data randomness and prediction accuracy. The performance characteristic curve provides a new way to evaluate models' performance systematically, and sheds light on future studies on other frameworks for model evaluation.

cs.SI↗

arXiv2025

SynDCIM: A Performance-Aware Digital Computing-in-Memory Compiler with Multi-Spec-Oriented Subcircuit Synthesis

Digital Computing-in-Memory (DCIM) is an innovative technology that integrates multiply-accumulation (MAC) logic directly into memory arrays to enhance the performance of modern AI computing. However, the need for customized memory cells and logic components currently necessitates significant manual effort in DCIM design. Existing tools for facilitating DCIM macro designs struggle to optimize subcircuit synthesis to meet user-defined performance criteria, thereby limiting the potential system-level acceleration that DCIM can offer. To address these challenges and enable agile design of DCIM macros with optimal architectures, we present SynDCIM, a performance-aware DCIM compiler that employs multi-spec-oriented subcircuit synthesis. SynDCIM features an automated performance-to-layout generation process that aligns with user-defined performance expectations. This is supported by a scalable subcircuit library and a multi-spec-oriented searching algorithm for effective subcircuit synthesis. The effectiveness of SynDCIM is demonstrated through extensive experiments and validated with a test chip fabricated in a 40nm CMOS process. Testing results reveal that designs generated by SynDCIM exhibit competitive performance when compared to state-of-the-art manually designed DCIM macros.

cs.AR↗

arXiv2025

AHMSA-Net: Adaptive Hierarchical Multi-Scale Attention Network for Micro-Expression Recognition

Micro-expression recognition (MER) presents a significant challenge due to the transient and subtle nature of the motion changes involved. In recent years, deep learning methods based on attention mechanisms have made some breakthroughs in MER. However, these methods still suffer from the limitations of insufficient feature capture and poor dynamic adaptation when coping with the instantaneous subtle movement changes of micro-expressions. Therefore, in this paper, we design an Adaptive Hierarchical Multi-Scale Attention Network (AHMSA-Net) for MER. Specifically, we first utilize the onset and apex frames of the micro-expression sequence to extract three-dimensional (3D) optical flow maps, including horizontal optical flow, vertical optical flow, and optical flow strain. Subsequently, the optical flow feature maps are inputted into AHMSA-Net, which consists of two parts: an adaptive hierarchical framework and a multi-scale attention mechanism. Based on the adaptive downsampling hierarchical attention framework, AHMSA-Net captures the subtle changes of micro-expressions from different granularities (fine and coarse) by dynamically adjusting the size of the optical flow feature map at each layer. Based on the multi-scale attention mechanism, AHMSA-Net learns micro-expression action information by fusing features from different scales (channel and spatial). These two modules work together to comprehensively improve the accuracy of MER. Additionally, rigorous experiments demonstrate that the proposed method achieves competitive results on major micro-expression databases, with AHMSA-Net achieving recognition accuracy of up to 78.21% on composite databases (SMIC, SAMM, CASMEII) and 77.08% on the CASME^{}3 database.

cs.CV↗

arXiv2024

XRDSLAM: A Flexible and Modular Framework for Deep Learning based SLAM

In this paper, we propose a flexible SLAM framework, XRDSLAM. It adopts a modular code design and a multi-process running mechanism, providing highly reusable foundational modules such as unified dataset management, 3d visualization, algorithm configuration, and metrics evaluation. It can help developers quickly build a complete SLAM system, flexibly combine different algorithm modules, and conduct standardized benchmarking for accuracy and efficiency comparison. Within this framework, we integrate several state-of-the-art SLAM algorithms with different types, including NeRF and 3DGS based SLAM, and even odometry or reconstruction algorithms, which demonstrates the flexibility and extensibility. We also conduct a comprehensive comparison and evaluation of these integrated algorithms, analyzing the characteristics of each. Finally, we contribute all the code, configuration and data to the open-source community, which aims to promote the widespread research and development of SLAM technology within the open-source ecosystem.

cs.CV↗

arXiv2024

A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners

This study introduces a hypothesis-testing framework to assess whether large language models (LLMs) possess genuine reasoning abilities or primarily depend on token bias. We go beyond evaluating LLMs on accuracy; rather, we aim to investigate their token bias in solving logical reasoning tasks. Specifically, we develop carefully controlled synthetic datasets, featuring conjunction fallacy and syllogistic problems. Our framework outlines a list of hypotheses where token biases are readily identifiable, with all null hypotheses assuming genuine reasoning capabilities of LLMs. The findings in this study suggest, with statistical guarantee, that most LLMs still struggle with logical reasoning. While they may perform well on classic problems, their success largely depends on recognizing superficial patterns with strong token bias, thereby raising concerns about their actual reasoning and generalization abilities. Codes and data are open-sourced at https://github.com/bowen-upenn/llm_token_bias.

cs.CL↗

arXiv2024

On regular sets in Cayley graphs

Let $\Ga = (V, E)$ be a graph and $a, b$ nonnegative integers. An $(a, b)$-regular set in $\Ga$ is a nonempty proper subset $D$ of $V$ such that every vertex in $D$ has exactly $a$ neighbours in $D$ and every vertex in $V \setminus D$ has exactly $b$ neighbours in $D$. A $(0,1)$-regular set is called a perfect code, an efficient dominating set, or an independent perfect dominating set. A subset $D$ of a group $G$ is called an $(a,b)$-regular set of $G$ if it is an $(a, b)$-regular set in some Cayley graph of $G$, and an $(a, b)$-regular set in a Cayley graph of $G$ is called a subgroup $(a, b)$-regular set if it is also a subgroup of $G$. In this paper we study $(a, b)$-regular sets in Cayley graphs with a focus on $(0, k)$-regular sets, where $k \ge 1$ is an integer. Among other things we determine when a non-trivial proper normal subgroup of a group is a $(0, k)$-regular set of the group. We also determine all subgroup $(0, k)$-regular sets of dihedral groups and generalized quaternion groups. We obtain necessary and sufficient conditions for a hypercube or the Cartesian product of $n$ copies of the cycle of length $p$ to admit $(0, k)$-regular sets, where $p$ is an odd prime. Our results generalize several known results from perfect codes to $(0, k)$-regular sets.

math.CO↗

arXiv2024

Perfect codes in circulant graphs of degree $p^l-1$

A perfect code in a graph is an independent set of the graph such that every vertex outside the set is adjacent to exactly one vertex in the set. A circulant graph is a Cayley graph of a cyclic group. In this paper we study perfect codes in circulant graphs of degree $p^l - 1$, where $p$ is a prime and $l \ge 1$. We obtain a necessary and sufficient condition for such a circulant graph to admit perfect codes, give a construction of all such circulant graphs which admit perfect codes, and prove a lower bound on the number of distinct perfect codes in such a circulant graph. This extends known results for the case $l=1$ and provides insight on the general problem on the existence and structure of perfect codes in circulant graphs.

math.CO↗

arXiv2024

Data Distribution Dynamics in Real-World WiFi-Based Patient Activity Monitoring for Home Healthcare

This paper examines the application of WiFi signals for real-world monitoring of daily activities in home healthcare scenarios. While the state-of-the-art of WiFi-based activity recognition is promising in lab environments, challenges arise in real-world settings due to environmental, subject, and system configuration variables, affecting accuracy and adaptability. The research involved deploying systems in various settings and analyzing data shifts. It aims to guide realistic development of robust, context-aware WiFi sensing systems for elderly care. The findings suggest a shift in WiFi-based activity sensing, bridging the gap between academic research and practical applications, enhancing life quality through technology.

eess.SP↗

arXiv2023

A 137.5 TOPS/W SRAM Compute-in-Memory Macro with 9-b Memory Cell-Embedded ADCs and Signal Margin Enhancement Techniques for AI Edge Applications

In this paper, we propose a high-precision SRAM-based CIM macro that can perform 4x4-bit MAC operations and yield 9-bit signed output. The inherent discharge branches of SRAM cells are utilized to apply time-modulated MAC and 9-bit ADC readout operations on two bit-line capacitors. The same principle is used for both MAC and A-to-D conversion ensuring high linearity and thus supporting large number of analog MAC accumulations. The memory cell-embedded ADC eliminates the use of separate ADCs and enhances energy and area efficiency. Additionally, two signal margin enhancement techniques, namely the MAC-folding and boosted-clipping schemes, are proposed to further improve the CIM computation accuracy.

cs.AR↗

arXiv2023

An Interpretable Loan Credit Evaluation Method Based on Rule Representation Learner

The interpretability of model has become one of the obstacles to its wide application in the high-stake fields. The usual way to obtain interpretability is to build a black-box first and then explain it using the post-hoc methods. However, the explanations provided by the post-hoc method are not always reliable. Instead, we design an intrinsically interpretable model based on RRL(Rule Representation Learner) for the Lending Club dataset. Specifically, features can be divided into three categories according to their characteristics of themselves and build three sub-networks respectively, each of which is similar to a neural network with a single hidden layer but can be equivalently converted into a set of rules. During the training, we learned tricks from previous research to effectively train binary weights. Finally, our model is compared with the tree-based model. The results show that our model is much better than the interpretable decision tree in performance and close to other black-box, which is of practical significance to both financial institutions and borrowers. More importantly, our model is used to test the correctness of the explanations generated by the post-hoc method, the results show that the post-hoc method is not always reliable.

cs.LG↗

arXiv2023

Record-high-Tc elemental superconductivity in scandium

Elemental materials provide clean and fundamental platforms for studying superconductivity. However, the highest superconducting critical temperature (Tc) yet observed in elements has not exceeded 30 K. Discovering elemental superconductors with a higher Tc is one of the most fundamental and challenging tasks in condensed matter physics. In this study, by applying high pressure up to approximately 260 GPa, we demonstrate that the superconducting transition temperature of elemental scandium (Sc) can be increased to 36 K, which is a record-high Tc for superconducting elements. The pressure dependence of Tc implies the occurrence of multiple phase transitions in Sc, which is in agreement with previous X-ray diffraction results. Optimization of Tc is achieved in the Sc-V phase, which can be attributed to the strong coupling between d electrons and moderate-frequency phonons, as suggested by our first-principles calculations. This study provides insights for exploring new high-Tc elemental metals.

cond-mat.supr-con↗

arXiv2022

Author Name Disambiguation via Heterogeneous Network Embedding from Structural and Semantic Perspectives

Name ambiguity is common in academic digital libraries, such as multiple authors having the same name. This creates challenges for academic data management and analysis, thus name disambiguation becomes necessary. The procedure of name disambiguation is to divide publications with the same name into different groups, each group belonging to a unique author. A large amount of attribute information in publications makes traditional methods fall into the quagmire of feature selection. These methods always select attributes artificially and equally, which usually causes a negative impact on accuracy. The proposed method is mainly based on representation learning for heterogeneous networks and clustering and exploits the self-attention technology to solve the problem. The presentation of publications is a synthesis of structural and semantic representations. The structural representation is obtained by meta-path-based sampling and a skip-gram-based embedding method, and meta-path level attention is introduced to automatically learn the weight of each feature. The semantic representation is generated using NLP tools. Our proposal performs better in terms of name disambiguation accuracy compared with baselines and the ablation experiments demonstrate the improvement by feature selection and the meta-path level attention in our method. The experimental results show the superiority of our new method for capturing the most attributes from publications and reducing the impact of redundant information.

cs.LG↗

arXiv2022

Independent Asymmetric Embedding for Information Diffusion Prediction on Social Networks

The prediction for information diffusion on social networks has great practical significance in marketing and public opinion control. It aims to predict the individuals who will potentially repost the message on the social network. One type of method is based on demographics, complex networks and other prior knowledge to establish an interpretable model to simulate and predict the propagation process, while the other type of method is completely data-driven and maps the nodes to a latent space for propagation prediction. Existing latent space design and embedding methods lack consideration for the intervene among users. In this paper, we propose an independent asymmetric embedding method to embed each individual into one latent influence space and multiple latent susceptibility spaces. Based on the similarity between information diffusion and heat diffusion phenomenon, the heat diffusion kernel is exploited in our model and establishes the embedding rules. Furthermore, our method captures the co-occurrence regulation of user combinations in cascades to improve the calculating effectiveness. The results of extensive experiments conducted on real-world datasets verify both the predictive accuracy and cost-effectiveness of our approach.

cs.LG↗