arXiv subjects

Bo Yang

Publications and source records attributed to Bo Yang.

At least 217 records · Page 12Linked to original sources

arXiv2025

Adversarial Example Soups: Improving Transferability and Stealthiness for Free

Transferable adversarial examples cause practical security risks since they can mislead a target model without knowing its internal knowledge. A conventional recipe for maximizing transferability is to keep only the optimal adversarial example from all those obtained in the optimization pipeline. In this paper, for the first time, we revisit this convention and demonstrate that those discarded, sub-optimal adversarial examples can be reused to boost transferability. Specifically, we propose ``Adversarial Example Soups'' (AES), with AES-tune for averaging discarded adversarial examples in hyperparameter tuning and AES-rand for stability testing. In addition, our AES is inspired by ``model soups'', which averages weights of multiple fine-tuned models for improved accuracy without increasing inference time. Extensive experiments validate the global effectiveness of our AES, boosting 10 state-of-the-art transfer attacks and their combinations by up to 13\% against 10 diverse (defensive) target models. We also show the possibility of generalizing AES to other types, \textit{e.g.}, directly averaging multiple in-the-wild adversarial examples that yield comparable success. A promising byproduct of AES is the improved stealthiness of adversarial examples since the perturbation variances are naturally reduced.

cs.CV↗

arXiv2025

Triangular rogue clusters associated with multiple roots of Adler--Moser polynomials in integrable systems

Rogue patterns associated with multiple roots of Adler--Moser polynomials under general multiple large parameters are studied in integrable systems. It is first shown that the multiplicity of any multiple root in any Adler--Moser polynomial is a triangular number (i.e., its multiplicity is equal to $n(n+1)/2$ for a certain integer $n$). Then, it is shown that corresponding to a nonzero multiple root of the Adler--Moser polynomial, a triangular rogue cluster would appear on the spatial-temporal plane. This triangular rogue cluster comprises $n(n+1)/2$ fundamental rogue waves forming a triangular shape, and space-time locations of fundamental rogue waves in this triangle are a linear transformation of the Yablonskii--Vorob'ev polynomial $Q_{n}(z)$'s root structure. In the special case where this multiple root of the Adler--Moser polynomial is zero, the associated rogue pattern is found to be a $n$-th order rogue wave in the $O(1)$ neighborhood of the spatial-temporal origin. These general results are demonstrated on two integrable systems: the nonlinear Schrödinger equation and the generalized derivative nonlinear Schrödinger equation. For these equations, asymptotic predictions of rogue patterns are compared with true rogue solutions and good agreement between them is illustrated.

nlin.SI↗

arXiv2025

Dynamics and lifetime of geometric excitations in moiré systems

We show that spin-2 geometric excitations, known as graviton modes, generally exhibit vanishing lifetimes in lattice Chern bands, including in moiré systems. In contrast to the Landau levels, we first numerically demonstrate that the prominent graviton peaks in spectral functions diminish rapidly with increasing system sizes. We explore how the choice of interaction affects the strength of these peaks, with short-ranged interactions pushing the graviton mode far into the continuum of excitations, where it can be significantly scattered due to the increased density of states. We also analytically investigate the short lifetime of the graviton mode. In lattice systems, continuous rotational symmetry is broken, leading to highly anisotropic gapped excitations that mix different angular momentum or ``spins''. This is despite the surprising emergence of a ``guiding center" continuous rotational symmetry in the ground state, which is shared by the graviton mode. Consequently, the graviton mode in Chern bands can be strongly scattered by the anisotropic gapped excitations. However, the emergent rotational symmetry implies that gravitons can be robust in principle, and we propose experimental tuning strategies to lower the graviton mode energy below the continuum. We argue this is a necessary condition enabling the observation of graviton modes and geometric excitations in realistic moiré systems.

cond-mat.str-el↗

arXiv2025

Multi-Agent Deep Reinforcement Learning for Safe Autonomous Driving with RICS-Assisted MEC

Environment sensing and fusion via onboard sensors are envisioned to be widely applied in future autonomous driving networks. This paper considers a vehicular system with multiple self-driving vehicles that is assisted by multi-access edge computing (MEC), where image data collected by the sensors is offloaded from cellular vehicles to the MEC server using vehicle-to-infrastructure (V2I) links. Sensory data can also be shared among surrounding vehicles via vehicle-to-vehicle (V2V) communication links. To improve spectrum utilization, the V2V links may reuse the same frequency spectrum with V2I links, which may cause severe interference. To tackle this issue, we leverage reconfigurable intelligent computational surfaces (RICSs) to jointly enable V2I reflective links and mitigate interference appearing at the V2V links. Considering the limitations of traditional algorithms in addressing this problem, such as the assumption for quasi-static channel state information, which restricts their ability to adapt to dynamic environmental changes and leads to poor performance under frequently varying channel conditions, in this paper, we formulate the problem at hand as a Markov game. Our novel formulation is applied to time-varying channels subject to multi-user interference and introduces a collaborative learning mechanism among users. The considered optimization problem is solved via a driving safety-enabled multi-agent deep reinforcement learning (DS-MADRL) approach that capitalizes on the RICS presence. Our extensive numerical investigations showcase that the proposed reinforcement learning approach achieves faster convergence and significant enhancements in both data rate and driving safety, as compared to various state-of-the-art benchmarks.

cs.LG↗

arXiv2025

Equivalence of Chern bands and Landau levels from projected Interactions

We introduce a universal formulation of the generalized real space interactions with translational invariance, when projected into a single Landau level, can be equivalent to density-density interaction projected into any Chern bands (e.g. Landau levels, continuous moire Chern bands and discrete lattice Chern bands). By constructing a complete basis of generalized pseudopotentials, we define the projected interaction range that can be used to characterize important features of different Chern bands relevant to the robustness of interacting topological phases. The analytical construction allows us to study general Chern bands beyond the torus geometry, for example on the disk or spherical geometry where the edge dynamics and curvature effects can be explored. For moire systems (and lattice Chern bands with large incompressibility gap) one can see transparently the topological Hall viscosity for the fractional states are identical to those in the Landau levels. The physical unprojected interaction also provides a natural embedding for lattice systems, shedding light on the concerns of relying on quantum geometric tensor (varying with lattice embedding in real space) to understand the properties of interacting phases of matters.

cond-mat.str-el↗

arXiv2025

Improving Adversarial Transferability on Vision Transformers via Forward Propagation Refinement

Vision Transformers (ViTs) have been widely applied in various computer vision and vision-language tasks. To gain insights into their robustness in practical scenarios, transferable adversarial examples on ViTs have been extensively studied. A typical approach to improving adversarial transferability is by refining the surrogate model. However, existing work on ViTs has restricted their surrogate refinement to backward propagation. In this work, we instead focus on Forward Propagation Refinement (FPR) and specifically refine two key modules of ViTs: attention maps and token embeddings. For attention maps, we propose Attention Map Diversification (AMD), which diversifies certain attention maps and also implicitly imposes beneficial gradient vanishing during backward propagation. For token embeddings, we propose Momentum Token Embedding (MTE), which accumulates historical token embeddings to stabilize the forward updates in both the Attention and MLP blocks. We conduct extensive experiments with adversarial examples transferred from ViTs to various CNNs and ViTs, demonstrating that our FPR outperforms the current best (backward) surrogate refinement by up to 7.0\% on average. We also validate its superiority against popular defenses and its compatibility with other transfer methods. Codes and appendix are available at https://github.com/RYC-98/FPR.

cs.CV↗

arXiv2025

Probing the hollowing transition of a shell-shaped BEC with collective excitation

We investigate the hollowing transition of a shell-shaped Bose-Einstein condensate using collective excitations. The shell is created using an immiscible dual-species BEC mixture, with its hollowness controlled by tuning the repulsive interspecies interaction via a Feshbach resonance. Our results reveal two distinct monopole modes in which the two condensates oscillate either in-phase or out-of-phase. The spectrum of the out-of-phase mode exhibits a non-monotonic dependence on the interspecies interaction, providing a clear signature of the topology change from a filled to a hollow condensate. Furthermore, we find that the critical point of the hollowing transition depends strongly on the number ratio of the two species. Our findings provide a detailed understanding of the topology change in shell-shaped quantum gases and pave the way for future study of quantum many-body phenomena in curved spaces.

cond-mat.quant-gas↗

arXiv2025

CE-U: Cross Entropy Unlearning

Large language models memorize sensitive data from their pretraining corpora. In this work, we propose CE-U (Cross Entropy Unlearning), a loss function for unlearning. CE-U addresses fundamental limitations of gradient ascent approaches that suffer from vanishing gradients when model confidence is high and exploding gradients when confidence is low. We also unify standard cross entropy learning and unlearning into a single framework. On the TOFU benchmark for unlearning, CE-U achieves state-of-the-art results on LLaMA2-7B models without using an extra oracle model or additional positive samples. Our analysis reveals that the problematic gradient ascent component also exists in reinforcement learning algorithms like DPO and GRPO. This suggests that applying CE-U approach to reinforcement learning could be promising to improve stability and convergence.

cs.LG↗

arXiv2025

Generative Artificial Intelligence in Robotic Manipulation: A Survey

This survey provides a comprehensive review on recent advancements of generative learning models in robotic manipulation, addressing key challenges in the field. Robotic manipulation faces critical bottlenecks, including significant challenges in insufficient data and inefficient data acquisition, long-horizon and complex task planning, and the multi-modality reasoning ability for robust policy learning performance across diverse environments. To tackle these challenges, this survey introduces several generative model paradigms, including Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), diffusion models, probabilistic flow models, and autoregressive models, highlighting their strengths and limitations. The applications of these models are categorized into three hierarchical layers: the Foundation Layer, focusing on data generation and reward generation; the Intermediate Layer, covering language, code, visual, and state generation; and the Policy Layer, emphasizing grasp generation and trajectory generation. Each layer is explored in detail, along with notable works that have advanced the state of the art. Finally, the survey outlines future research directions and challenges, emphasizing the need for improved efficiency in data utilization, better handling of long-horizon tasks, and enhanced generalization across diverse robotic scenarios. All the related resources, including research papers, open-source data, and projects, are collected for the community in https://github.com/GAI4Manipulation/AwesomeGAIManipulation

cs.RO↗

arXiv2025

Robust Simulations of Many-Body Symmetry-Protected Topological Phase Transitions on a Quantum Processor

Topology and symmetry play critical roles in characterizing quantum phases of matter. Recent advancements have unveiled symmetry-protected topological (SPT) phases in many-body systems as a unique class of short-range entangled states, notable for their nontrivial edge modes and characteristic ground-state entanglement gap. In this study, we demonstrate the robust simulation of many-body ground states of an Ising-cluster model on a quantum computer. By employing the method of quantum imaginary-time evolution (QITE) combined with enhanced zero-noise extrapolation techniques, we achieve accurate measurements of the transition between trivial and cluster SPT phases. Furthermore, we measured the characteristic edge modes and their associated topological entanglement properties, such as the second Rényi entropy, reduced density matrix, and entanglement spectral gap. Our work demonstrates the potential of using QITE in investigating sophisticated quantum phase transitions and critical phenomena on quantum computers.

quant-ph↗

arXiv2025

DiffSG: A Generative Solver for Network Optimization with Diffusion Model

Generative diffusion models, famous for their performance in image generation, are popular in various cross-domain applications. However, their use in the communication community has been mostly limited to auxiliary tasks like data modeling and feature extraction. These models hold greater promise for fundamental problems in network optimization compared to traditional machine learning methods. Discriminative deep learning often falls short due to its single-step input-output mapping and lack of global awareness of the solution space, especially given the complexity of network optimization's objective functions. In contrast, generative diffusion models can consider a broader range of solutions and exhibit stronger generalization by learning parameters that describe the distribution of the underlying solution space, with higher probabilities assigned to better solutions. We propose a new framework Diffusion Model-based Solution Generation (DiffSG), which leverages the intrinsic distribution learning capabilities of generative diffusion models to learn high-quality solution distributions based on given inputs. The optimal solution within this distribution is highly probable, allowing it to be effectively reached through repeated sampling. We validate the performance of DiffSG on several typical network optimization problems, including mixed-integer non-linear programming, convex optimization, and hierarchical non-convex optimization. Our results demonstrate that DiffSG outperforms existing baseline methods not only on in-domain inputs but also on out-of-domain inputs. In summary, we demonstrate the potential of generative diffusion models in tackling complex network optimization problems and outline a promising path for their broader application in the communication community. Our code is available at https://github.com/qiyu3816/DiffSG.

cs.NI↗

arXiv2025

Personalized Recommendation Models in Federated Settings: A Survey

Federated recommender systems (FedRecSys) have emerged as a pivotal solution for privacy-aware recommendations, balancing growing demands for data security and personalized experiences. Current research efforts predominantly concentrate on adapting traditional recommendation architectures to federated environments, optimizing communication efficiency, and mitigating security vulnerabilities. However, user personalization modeling, which is essential for capturing heterogeneous preferences in this decentralized and non-IID data setting, remains underexplored. This survey addresses this gap by systematically exploring personalization in FedRecSys, charting its evolution from centralized paradigms to federated-specific innovations. We establish a foundational definition of personalization in a federated setting, emphasizing personalized models as a critical solution for capturing fine-grained user preferences. The work critically examines the technical hurdles of building personalized FedRecSys and synthesizes promising methodologies to meet these challenges. As the first consolidated study in this domain, this survey serves as both a technical reference and a catalyst for advancing personalized FedRecSys research.

cs.IR↗

arXiv2025

Spin-1/2 kagome Heisenberg antiferromagnet: Machine learning discovery of the spinon pair density wave ground state

Spin-1/2 kagome antiferromagnet (AFM) is one of the most studied models in frustrated magnetism since it is a promising candidate to host exotic spin liquid states. However, despite numerous studies using both analytical and numerical approaches, the nature of the ground state and low-energy excitations in this system remain elusive. This is related to the difficulty in determining the spin gap in various calculations. We present the results of our investigation of the Kagome AFM using the recently developed group equivariant convolutional neural networks, a novel machine learning technique for studying strongly frustrated models. The approach, combined with variational Monte Carlo, introduces significant improvement of the achievable results accuracy for frustrated spin systems in comparison with approaches based on other neural network architectures. Contrary to the results obtained previously with various methods, that predicted $Z_2$ or U(1) Dirac spin liquid states, our results strongly indicate that the ground state of the kagome lattice antiferromagnet is a spinon pair density wave that does not break time-reversal symmetry or any of the lattice symmetries. The found state appears due to the spinon Cooper pairing instability close to two Dirac points in the spinon energy spectrum and resembles the pair density wave state studied previously in the context of underdoped cuprate superconductors in connection with the pseudogap phase. The state has significantly lower energy than the lowest energy states found by the SU(2) symmetric density matrix renormalization group calculations and other methods.

cond-mat.str-el↗

arXiv2025

Large-Scale AI in Telecom: Charting the Roadmap for Innovation, Scalability, and Enhanced Digital Experiences

This white paper discusses the role of large-scale AI in the telecommunications industry, with a specific focus on the potential of generative AI to revolutionize network functions and user experiences, especially in the context of 6G systems. It highlights the development and deployment of Large Telecom Models (LTMs), which are tailored AI models designed to address the complex challenges faced by modern telecom networks. The paper covers a wide range of topics, from the architecture and deployment strategies of LTMs to their applications in network management, resource allocation, and optimization. It also explores the regulatory, ethical, and standardization considerations for LTMs, offering insights into their future integration into telecom infrastructure. The goal is to provide a comprehensive roadmap for the adoption of LTMs to enhance scalability, performance, and user-centric innovation in telecom networks.

cs.NI↗

arXiv2025

A Novel Neural-symbolic System under Statistical Relational Learning

A key objective in the field of artificial intelligence is to develop cognitive models that can exhibit human-like intellectual capabilities. One promising approach to achieving this is through neural-symbolic systems, which combine the strengths of deep learning and symbolic reasoning. However, current methodologies in this area face limitations in integration, generalization, and interpretability. To address these challenges, we propose a neural-symbolic framework based on statistical relational learning, referred to as NSF-SRL. This framework effectively integrates deep learning models with symbolic reasoning in a mutually beneficial manner.In NSF-SRL, the results of symbolic reasoning are utilized to refine and correct the predictions made by deep learning models, while deep learning models enhance the efficiency of the symbolic reasoning process. Through extensive experiments, we demonstrate that our approach achieves high performance and exhibits effective generalization in supervised learning, weakly supervised and zero-shot learning tasks. Furthermore, we introduce a quantitative strategy to evaluate the interpretability of the model's predictions, visualizing the corresponding logic rules that contribute to these predictions and providing insights into the reasoning process. We believe that this approach sets a new standard for neural-symbolic systems and will drive future research in the field of general artificial intelligence.

cs.AI↗

arXiv2025

Diffusion Models as Network Optimizers: Explorations and Analysis

Network optimization is a fundamental challenge in the Internet of Things (IoT) network, often characterized by complex features that make it difficult to solve these problems. Recently, generative diffusion models (GDMs) have emerged as a promising new approach to network optimization, with the potential to directly address these optimization problems. However, the application of GDMs in this field is still in its early stages, and there is a noticeable lack of theoretical research and empirical findings. In this study, we first explore the intrinsic characteristics of generative models. Next, we provide a concise theoretical proof and intuitive demonstration of the advantages of generative models over discriminative models in network optimization. Based on this exploration, we implement GDMs as optimizers aimed at learning high-quality solution distributions for given inputs, sampling from these distributions during inference to approximate or achieve optimal solutions. Specifically, we utilize denoising diffusion probabilistic models (DDPMs) and employ a classifier-free guidance mechanism to manage conditional guidance based on input parameters. We conduct extensive experiments across three challenging network optimization problems. By investigating various model configurations and the principles of GDMs as optimizers, we demonstrate the ability to overcome prediction errors and validate the convergence of generated solutions to optimal solutions. We provide code and data at https://github.com/qiyu3816/DiffSG.

cs.LG↗

arXiv2025

Incomplete Graph Learning: A Comprehensive Survey

Graph learning is a prevalent field that operates on ubiquitous graph data. Effective graph learning methods can extract valuable information from graphs. However, these methods are non-robust and affected by missing attributes in graphs, resulting in sub-optimal outcomes. This has led to the emergence of incomplete graph learning, which aims to process and learn from incomplete graphs to achieve more accurate and representative results. In this paper, we conducted a comprehensive review of the literature on incomplete graph learning. Initially, we categorize incomplete graphs and provide precise definitions of relevant concepts, terminologies, and techniques, thereby establishing a solid understanding for readers. Subsequently, we classify incomplete graph learning methods according to the types of incompleteness: (1) attribute-incomplete graph learning methods, (2) attribute-missing graph learning methods, and (3) hybrid-absent graph learning methods. By systematically classifying and summarizing incomplete graph learning methods, we highlight the commonalities and differences among existing approaches, aiding readers in selecting methods and laying the groundwork for further advancements. In addition, we summarize the datasets, incomplete processing modes, evaluation metrics, and application domains used by the current methods. Lastly, we discuss the current challenges and propose future directions for incomplete graph learning, with the aim of stimulating further innovations in this crucial field. To our knowledge, this is the first review dedicated to incomplete graph learning, aiming to offer valuable insights for researchers in related fields.We developed an online resource to follow relevant research based on this review, available at https://github.com/cherry-a11y/Incomplete-graph-learning.git

cs.LG↗

arXiv2025

Fundus2Globe: Generative AI-Driven 3D Digital Twins for Personalized Myopia Management

Myopia, projected to affect 50% population globally by 2050, is a leading cause of vision loss. Eyes with pathological myopia exhibit distinctive shape distributions, which are closely linked to the progression of vision-threatening complications. Recent understanding of eye-shape-based biomarkers requires magnetic resonance imaging (MRI), however, it is costly and unrealistic in routine ophthalmology clinics. We present Fundus2Globe, the first AI framework that synthesizes patient-specific 3D eye globes from ubiquitous 2D color fundus photographs (CFPs) and routine metadata (axial length, spherical equivalent), bypassing MRI dependency. By integrating a 3D morphable eye model (encoding biomechanical shape priors) with a latent diffusion model, our approach achieves submillimeter accuracy in reconstructing posterior ocular anatomy efficiently. Fundus2Globe uniquely quantifies how vision-threatening lesions (e.g., staphylomas) in CFPs correlate with MRI-validated 3D shape abnormalities, enabling clinicians to simulate posterior segment changes in response to refractive shifts. External validation demonstrates its robust generation performance, ensuring fairness across underrepresented groups. By transforming 2D fundus imaging into 3D digital replicas of ocular structures, Fundus2Globe is a gateway for precision ophthalmology, laying the foundation for AI-driven, personalized myopia management.

eess.IV↗