arXiv subjects

Bin Guo

Publications and source records attributed to Bin Guo.

At least 73 records · Page 4Linked to original sources

arXiv2025

Correlators for tensionless strings on ${\rm AdS}_3$ orbifolds

The CFT dual of string theory on $({\rm AdS}_3 \times {\rm S}^3)/\mathbb{Z}_k\times \mathbb{T}^4$ is believed to be described by the subspace of the symmetric orbifold of $\mathbb{T}^4$ that comprises the low-lying excitations on top of a certain reference state. (This `non-perturbative' reference state lies in the twisted sector associated to the conjugacy class consisting of only $k$-cycles.) In a recent paper we confirmed this picture by analysing the worldsheet theory of the orbifold at the tensionless NS-NS point, and by showing that the perturbative worldsheet spectrum reproduces precisely the single particle excitations on top of this reference state. In this paper we explain that this identification also holds on the level of the correlators, at least to leading order in $1/N$.

hep-th↗

arXiv2025

3D Gaussian Radiation Field Modeling for Integrated RIS-FAS Systems: Analysis and Optimization

The integration of reconfigurable intelligent surfaces (RIS) and fluid antenna systems (FAS) has attracted considerable attention due to its tremendous potential in enhancing wireless communication performance. However, under fast-fading channel conditions, rapidly and effectively performing joint optimization of the antenna positions in an FAS system and the RIS phase configuration remains a critical challenge. Traditional optimization methods typically rely on complex iterative computations, thus making it challenging to obtain optimal solutions in real time within dynamic channel environments. To address this issue, this paper introduces a field information-driven optimization method based on three-dimensional Gaussian radiation-field modeling for real-time optimization of integrated FAS-RIS systems. In the proposed approach, obstacles are treated as virtual transmitters and, by separately learning the amplitude and phase variations, the model can quickly generate high-precision channel information based on the transmitter's position. This design eliminates the need for extensive pilot overhead and cumbersome computations. On this framework, an alternating optimization scheme is presented to jointly optimize the FAS position and the RIS phase configuration. Simulation results demonstrate that the proposed method significantly outperforms existing approaches in terms of spectrum prediction accuracy, convergence speed, and minimum achievable rate, validating its effectiveness and practicality in fast-fading scenarios.

cs.NI↗

arXiv2025

High-resolution ensemble retrieval of cloud properties for all-day based on geostationary satellite

Clouds play a critical role in Earth's hydrological and energy cycles, and accurately representing their properties is essential for effective numerical modeling and weather forecasting. Machine learning methods have been widely used for cloud property retrieval; however, most existing techniques are deterministic and do not incorporate uncertainty quantification. Generative machine learning has made significant advances in various domains, including natural language processing, image generation, and notably weather forecasting, where it has enabled ensemble predictions and the quantification of forecast uncertainty. This ability to quantify uncertainty offers valuable opportunities for cloud remote sensing. In this study, we propose a novel cloud property retrieval method, CloudDiff, based on a generative diffusion model. By leveraging thermal infrared observations from the Himawari-8 Advanced Himawari Imager (AHI), CloudDiff generates high spatiotemporal resolution cloud properties for both daytime and nighttime conditions, increasing the resolution of Himawari-8/AHI cloud retrievals from 2 km to 1 km. Unlike deterministic retrieval methods, CloudDiff generates multiple samples from the underlying probability distribution, allowing for a diverse range of plausible retrievals and taking steps towards providing uncertainty assessment. Additionally, CloudDiff produces sharper samples and better captures fine local features, enhancing the precision of cloud property retrieval. By averaging over the ensemble of generated samples, we demonstrate that both the accuracy and reliability of the retrievals are significantly improved. These high-resolution cloud properties have been successfully applied to analyze extreme weather events, such as typhoons, providing potentially valuable insights into atmospheric processes.

physics.ao-ph↗

arXiv2025

Joint Optimization of Cooperation Efficiency and Communication Covertness for Target Detection with AUVs

This paper investigates underwater cooperative target detection using autonomous underwater vehicles (AUVs), with a focus on the critical trade-off between cooperation efficiency and communication covertness. To tackle this challenge, we first formulate a joint trajectory and power control optimization problem, and then present an innovative hierarchical action management framework to solve it. According to the hierarchical formulation, at the macro level, the master AUV models the agent selection process as a Markov decision process and deploys the proximal policy optimization algorithm for strategic task allocation. At the micro level, each selected agent's decentralized decision-making is modeled as a partially observable Markov decision process, and a multi-agent proximal policy optimization algorithm is used to dynamically adjust its trajectory and transmission power based on its local observations. Under the centralized training and decentralized execution paradigm, our target detection framework enables adaptive covert cooperation while satisfying both energy and mobility constraints. By comprehensively modeling the considered system, the involved signals and tasks, as well as energy consumption, theoretical insights and practical solutions for the efficient and secure operation of multiple AUVs are provided, offering significant implications for the execution of underwater covert communication tasks.

cs.LG↗

arXiv2025

Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs

Multi-head Latent Attention (MLA) is an innovative architecture proposed by DeepSeek, designed to ensure efficient and economical inference by significantly compressing the Key-Value (KV) cache into a latent vector. Compared to MLA, standard LLMs employing Multi-Head Attention (MHA) and its variants such as Grouped-Query Attention (GQA) exhibit significant cost disadvantages. Enabling well-trained LLMs (e.g., Llama) to rapidly adapt to MLA without pre-training from scratch is both meaningful and challenging. This paper proposes the first data-efficient fine-tuning method for transitioning from MHA to MLA (MHA2MLA), which includes two key components: for partial-RoPE, we remove RoPE from dimensions of queries and keys that contribute less to the attention scores, for low-rank approximation, we introduce joint SVD approximations based on the pre-trained parameters of keys and values. These carefully designed strategies enable MHA2MLA to recover performance using only a small fraction (0.3% to 0.6%) of the data, significantly reducing inference costs while seamlessly integrating with compression techniques such as KV cache quantization. For example, the KV cache size of Llama2-7B is reduced by 92.19%, with only a 0.5% drop in LongBench performance.

cs.CL↗

arXiv2025

Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey

Foundation models have reshaped AI by unifying fragmented architectures into scalable backbones with multimodal reasoning and contextual adaptation. In parallel, the long-standing notion of AI agents, defined by the sensing-decision-action loop, is entering a new paradigm: with FMs as their cognitive core, agents transcend rule-based behaviors to achieve autonomy, generalization, and self-reflection. This dual shift is reinforced by real-world demands such as autonomous driving, robotics, virtual assistants, and GUI agents, as well as ecosystem advances in embedded hardware, edge computing, mobile deployment platforms, and communication protocols that together enable large-scale deployment. Yet this convergence collides with reality: while applications demand long-term adaptability and real-time interaction, mobile and edge deployments remain constrained by memory, energy, bandwidth, and latency. This creates a fundamental tension between the growing complexity of FMs and the limited resources of deployment environments. This survey provides the first systematic characterization of adaptive, resource-efficient agentic AI systems. We summarize enabling techniques into elastic inference, test-time adaptation, dynamic multimodal integration, and agentic AI applications, and identify open challenges in balancing accuracy-latency-communication trade-offs and sustaining robustness under distribution shifts. We further highlight future opportunities in algorithm-system co-design, cognitive adaptation, and collaborative edge deployment. By mapping FM structures, cognition, and hardware resources, this work establishes a unified perspective toward scalable, adaptive, and resource-efficient agentic AI. We believe this survey can help readers to understand the connections between enabling technologies while promoting further discussions on the fusion of agentic intelligence and intelligent agents.

cs.LG↗

arXiv2025

MMPlanner: Zero-Shot Multimodal Procedural Planning with Chain-of-Thought Object State Reasoning

Multimodal Procedural Planning (MPP) aims to generate step-by-step instructions that combine text and images, with the central challenge of preserving object-state consistency across modalities while producing informative plans. Existing approaches often leverage large language models (LLMs) to refine textual steps; however, visual object-state alignment and systematic evaluation are largely underexplored. We present MMPlanner, a zero-shot MPP framework that introduces Object State Reasoning Chain-of-Thought (OSR-CoT) prompting to explicitly model object-state transitions and generate accurate multimodal plans. To assess plan quality, we design LLM-as-a-judge protocols for planning accuracy and cross-modal alignment, and further propose a visual step-reordering task to measure temporal coherence. Experiments on RECIPEPLAN and WIKIPLAN show that MMPlanner achieves state-of-the-art performance, improving textual planning by +6.8%, cross-modal alignment by +11.9%, and visual step ordering by +26.7%

cs.LG↗

arXiv2025

Experimental Evaluation of Distributed k-Core Decomposition

Given an undirected graph, the $k$-core is a subgraph in which each node has at least $k$ connections. This is widely used in graph analytics to identify core subgraphs within a larger graph. The sequential $k$-core decomposition algorithm faces limitations due to memory constraints, and many data graphs are inherently distributed. A distributed approach is proposed to overcome limitations by allowing each vertex to compute its core number independently using only local information. This work explores the experimental evaluation of a distributed $k$-core decomposition algorithm. By assuming that each vertex is a client as a single computing unit, we simulate the process using Golang, leveraging its Goroutines and message passing. Since real-world data graphs can be large with millions of vertices, it is expensive to build a distributed environment with millions of clients if experiments were run in a real distributed environment. Therefore, our experimental simulation can effectively evaluate the running time and message passing for the distributed $k$-core decomposition.

cs.DC↗

arXiv2025

Hölder estimates for degenerate complex Monge-Ampère equations

Uniform $L^\infty$ and Hölder estimates were proved by the Kolodziej for complex Monge-Ampère equations on compact Kähler manifolds with $L^p$ volume measure with $p>1$. On the other hand, establishing Hölder estimates on singular Kähler varieties has remained open. In this paper, we establish uniform Hölder continuity for a family of complex Monge-Ampère equations on Kähler varieties, by developing a geometric regularization based on the partial $C^0$ estimate, i.e., quantitive Kodaira embeddings. As an application, we prove that local potentials of smoothable Kähler-Einstein varieties are Hölder continuous.

math.CV↗

arXiv2025

MemoCue: Empowering LLM-Based Agents for Human Memory Recall via Strategy-Guided Querying

Agent-assisted memory recall is one critical research problem in the field of human-computer interaction. In conventional methods, the agent can retrieve information from its equipped memory module to help the person recall incomplete or vague memories. The limited size of memory module hinders the acquisition of complete memories and impacts the memory recall performance in practice. Memory theories suggest that the person's relevant memory can be proactively activated through some effective cues. Inspired by this, we propose a novel strategy-guided agent-assisted memory recall method, allowing the agent to transform an original query into a cue-rich one via the judiciously designed strategy to help the person recall memories. To this end, there are two key challenges. (1) How to choose the appropriate recall strategy for diverse forgetting scenarios with distinct memory-recall characteristics? (2) How to obtain the high-quality responses leveraging recall strategies, given only abstract and sparsely annotated strategy patterns? To address the challenges, we propose a Recall Router framework. Specifically, we design a 5W Recall Map to classify memory queries into five typical scenarios and define fifteen recall strategy patterns across the corresponding scenarios. We then propose a hierarchical recall tree combined with the Monte Carlo Tree Search algorithm to optimize the selection of strategy and the generation of strategy responses. We construct an instruction tuning dataset and fine-tune multiple open-source large language models (LLMs) to develop MemoCue, an agent that excels in providing memory-inspired responses. Experiments on three representative datasets show that MemoCue surpasses LLM-based methods by 17.74% in recall inspiration. Further human evaluation highlights its advantages in memory-recall applications.

cs.AI↗

arXiv2025

DeepTraverse: A Depth-First Search Inspired Network for Algorithmic Visual Understanding

Conventional vision backbones, despite their success, often construct features through a largely uniform cascade of operations, offering limited explicit pathways for adaptive, iterative refinement. This raises a compelling question: can principles from classical search algorithms instill a more algorithmic, structured, and logical processing flow within these networks, leading to representations built through more interpretable, perhaps reasoning-like decision processes? We introduce DeepTraverse, a novel vision architecture directly inspired by algorithmic search strategies, enabling it to learn features through a process of systematic elucidation and adaptive refinement distinct from conventional approaches. DeepTraverse operationalizes this via two key synergistic components: recursive exploration modules that methodically deepen feature analysis along promising representational paths with parameter sharing for efficiency, and adaptive calibration modules that dynamically adjust feature salience based on evolving global context. The resulting algorithmic interplay allows DeepTraverse to intelligently construct and refine feature patterns. Comprehensive evaluations across a diverse suite of image classification benchmarks show that DeepTraverse achieves highly competitive classification accuracy and robust feature discrimination, often outperforming conventional models with similar or larger parameter counts. Our work demonstrates that integrating such algorithmic priors provides a principled and effective strategy for building more efficient, performant, and structured vision backbones.

cs.CV↗

arXiv2025

Federated k-Core Decomposition: A Secure Distributed Approach

As one of the most well-studied cohesive subgraph models, the $k$-core is widely used to find graph nodes that are ``central'' or ``important'' in many applications, such as biological networks, social networks, ecological networks, and financial networks. For Decentralized Online Social Networks (DOSNs), where each vertex is a client as a single computing unit, distributed k-core decomposition algorithms have already been proposed. However, current distributed approaches fail to adequately protect privacy and security. In today's data-driven world, data privacy and security have attracted more and more attention, e.g., DOSNs are proposed to protect privacy by storing user information locally without using a single centralized server. In this work, we are the first to propose the secure version of the distributed $k$-core decomposition.

cs.DC↗

arXiv2025

Four-twist effects on excitations in symmetric orbifold CFTs

Symmetric orbifold CFTs contain twist operators that can join and split copies of the CFT. In this paper, we study the effects of four twist-2 operators on two copies of a single free boson. A recent study analyzed their effects on the vacuum, finding a nontrivial left-right mixing that arises from the fact that the covering surface is a torus, while the effects of one or two twist-2 operators do not produce such mixing. Here, we extend this analysis to excited states and find a similar left-right mixing. Furthermore, we explore the continuum, or high-energy, limit and show that the left-right mixing becomes negligible in this limit.

hep-th↗

arXiv2025

JointDistill: Adaptive Multi-Task Distillation for Joint Depth Estimation and Scene Segmentation

Depth estimation and scene segmentation are two important tasks in intelligent transportation systems. A joint modeling of these two tasks will reduce the requirement for both the storage and training efforts. This work explores how the multi-task distillation could be used to improve such unified modeling. While existing solutions transfer multiple teachers' knowledge in a static way, we propose a self-adaptive distillation method that can dynamically adjust the knowledge amount from each teacher according to the student's current learning ability. Furthermore, as multiple teachers exist, the student's gradient update direction in the distillation is more prone to be erroneous where knowledge forgetting may occur. To avoid this, we propose a knowledge trajectory to record the most essential information that a model has learnt in the past, based on which a trajectory-based distillation loss is designed to guide the student to follow the learning curve similarly in a cost-effective way. We evaluate our method on multiple benchmarking datasets including Cityscapes and NYU-v2. Compared to the state-of-the-art solutions, our method achieves a clearly improvement. The code is provided in the supplementary materials.

cs.LG↗

arXiv2025

A class of thin-film equations with space-time dependent gradient nonlinearity and its application to image sharpening

We introduce a class of thin-film equations with space-time dependent gradient nonlinearity and apply them to image sharpening. By modifying the potential well method, we overcome the challenges arising from variable exponents and the "moving" Nehari manifold, thereby providing a classification of global existence and finite time blow-up of solutions under different initial conditions. Decay rates for global solutions and lifespan estimates for blow-up solutions are also established. Numerical experiments demonstrate the effectiveness of this class of equations as image sharpening models.

math.AP↗

arXiv2025

AGCo-MATA: Air-Ground Collaborative Multi-Agent Task Allocation in Mobile Crowdsensing

Rapid progress in intelligent unmanned systems has presented new opportunities for mobile crowd sensing (MCS). Today, heterogeneous air-ground collaborative multi-agent framework, which comprise unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs), have presented superior flexibility and efficiency compared to traditional homogeneous frameworks in complex sensing tasks. Within this context, task allocation among different agents always play an important role in improving overall MCS quality. In order to better allocate tasks among heterogeneous collaborative agents, in this paper, we investigated two representative complex multi-agent task allocation scenarios with dual optimization objectives: (1) For AG-FAMT (Air-Ground Few Agents More Tasks) scenario, the objectives are to maximize the task completion while minimizing the total travel distance; (2) For AG-MAFT (Air-Ground More Agents Few Tasks) scenario, where the agents are allocated based on their locations, has the optimization objectives of minimizing the total travel distance while reducing travel time cost. To achieve this, we proposed a Multi-Task Minimum Cost Maximum Flow (MT-MCMF) optimization algorithm tailored for AG-FAMT, along with a multi-objective optimization algorithm called W-ILP designed for AG-MAFT, with a particular focus on optimizing the charging path planning of UAVs. Our experiments based on a large-scale real-world dataset demonstrated that the proposed two algorithms both outperform baseline approaches under varying experimental settings, including task quantity, task difficulty, and task distribution, providing a novel way to improve the overall quality of mobile crowdsensing tasks.

cs.MA↗

arXiv2025

SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity

Despite the growing integration of deep models into mobile terminals, the accuracy of these models declines significantly due to various deployment interferences. Test-time adaptation (TTA) has emerged to improve the performance of deep models by adapting them to unlabeled target data online. Yet, the significant memory cost, particularly in resource-constrained terminals, impedes the effective deployment of most backward-propagation-based TTA methods. To tackle memory constraints, we introduce SURGEON, a method that substantially reduces memory cost while preserving comparable accuracy improvements during fully test-time adaptation (FTTA) without relying on specific network architectures or modifications to the original training procedure. Specifically, we propose a novel dynamic activation sparsity strategy that directly prunes activations at layer-specific dynamic ratios during adaptation, allowing for flexible control of learning ability and memory cost in a data-sensitive manner. Among this, two metrics, Gradient Importance and Layer Activation Memory, are considered to determine the layer-wise pruning ratios, reflecting accuracy contribution and memory efficiency, respectively. Experimentally, our method surpasses the baselines by not only reducing memory usage but also achieving superior accuracy, delivering SOTA performance across diverse datasets, architectures, and tasks.

cs.CV↗

arXiv2025

RCD structures on singular Kahler spaces of complex dimension three

Let X be a projective variety of complex dimension 3 with log terminal singularities. We prove that every singular Kahler metric on X with bounded Nash entropy and Ricci curvature bounded below induces a compact RCD space homeomorphic to the projective variety X itself. In particular, singular Kahler-Einstein spaces of complex dimension 3 with bounded Nash entropy are compact RCD spaces topologically and holomorphically equivalent to the underlying projective variety. Various compactness theorems are also obtained for 3-dimensional projective varieties with bounded Ricci curvature. Such results establish connections among algebraic, geometric and analytic structures of klt singularities from birational geometry and provide abundant examples of RCD spaces from algebraic geometry via complex Monge-Ampere equations.

math.DG↗