arXiv subjects

Geyong Min

Publications and source records attributed to Geyong Min.

At least 19 recordsLinked to original sources

arXiv2026

Confusion-Geometry Rebalancing for Long-Tailed Adversarial Training

Adversarial training under long tailed distributions suffers from a dual imbalance: the class imbalance skews the training objective toward head classes, and the adversarial inner maximization may further amplify this bias. Existing methods mitigate this issue by correcting class priors or adapting class wise robust supervision, yet they treat each class in isolation and fail to identify which boundaries drive long tailed collapse. We propose a Confusion Geometry Rebalancing method (CGRm) for long tail adversarial training, a plug in framework that leverages directed robust errors as training signals. CGRm leverages periodic robust evaluations to derive source class loss weights, class wise robust coefficients, and a directed confusion geometry graph. The method then couples feedback weighted robust optimization with graph guided margin correction, thereby boosting the robustness of vulnerable classes and sharpening the critical boundaries that drive long tailed performance degradation. Experiments on long tailed benchmarks show that CGRm achieves consistent robust performance gains over existing methods, with ablations validating the contribution of each component. We provide the code in the supplement.

cs.LG↗

arXiv2026

Towards Dual-Brain Minimal Sufficient Representation for Vision-Language Navigation

Vision-and-Language Navigation in continuous environments (VLN-CE) requires an agent to ground language in egocentric observations and plan in unseen scenes. Although recent multimodal large models and world-model-based methods have improved navigation, they often preserve excessive task-irrelevant detail, weakening generalization and increasing computational burden. We propose BrainNav, a navigation framework grounded in the Principle of Minimal Sufficiency. BrainNav consists of three components: a Logical Anchor Model that implements instruction-aware selective perception to suppress environmental noise, a Minimalist Constraint Alignment module that serves as a compact cross-modal bottleneck, efficiently synchronizing discrete linguistic intent with continuous latent dynamics while filtering out redundant information, and a Compression World Model that predicts action-conditioned states within a condensed, low-rank latent space. These modules align semantic intent with spatial perception, enhancing the agent's robustness and efficiency in complex tasks. Experiments show that BrainNav improves over prior SOTA by 2.0 % / 1.0 in SR/SPL on R2R-CE val-unseen and 0.94 % / 0.78 on RxR-CE val-unseen. These results indicate that minimally sufficient world representations provide an effective foundation for robust VLN.

cs.CV↗

arXiv2026

Mitigating Error Amplification in Fast Adversarial Training

Fast Adversarial Training (FAT) has proven effective in enhancing model robustness by encouraging networks to learn perturbation-invariant representations. However, FAT often suffers from catastrophic overfitting (CO), where the model overfits to the training attack and fails to generalize to unseen ones. Moreover, robustness oriented optimization typically leads to notable performance degradation on clean inputs, and such degradation becomes increasingly severe as the perturbation budget grows. In this work, we conduct a comprehensive analysis of how guidance strength affects model performance by modulating perturbation and supervision levels across distinct confidence groups. The findings reveal that low confidence samples are the primary contributors to CO and the robustness accuracy trade off. Building on this insight, we propose a Distribution-aware Dynamic Guidance (DDG) strategy that dynamically adjusts both the perturbation budget and supervision signal. Specifically, DDG scales the perturbation magnitude according to the sample confidence at the ground truth class, thereby guiding samples toward consistent decision boundaries while mitigating the influence of learning spurious correlations. Simultaneously, it dynamically adjusts the supervision signal based on the prediction state of each sample, preventing overemphasis on incorrect signals. To alleviate potential gradient instability arising from dynamic guidance, we further design a weighted regularization constraint. Extensive experiments on standard benchmarks demonstrate that DDG effectively alleviates both CO and the robustness accuracy trade off.

cs.LG↗

arXiv2026

Semantic-aware Token Selection and Resource Optimization for Communication-efficient Split Federated Fine-tuning in Edge Intelligence

Deploying large Transformer-based vision models on resource-limited mobile devices at network edge is severely constrained by hardware limitations and dynamic wireless environments. While federated learning (FL) enables collaborative training without sharing raw data, strictly local fine-tuning of such massive models remains computationally prohibitive for edge devices. Split federated learning (SFL) alleviates this burden by offloading deep layers to the edge server, yet it suffers from heavy communication overhead when transmitting high-dimensional activation tokens. To address this bottleneck, we propose ST-SFLora, a semantic token-based split federated LoRA fine-tuning framework. We introduce a new metric, \emph{Semantic Transmission Efficiency} (STE), to balance semantic retention and transmission cost. Based on STE, we formulate a joint resource optimization problem that dynamically determines token selection, uplink bandwidth allocation, and transmit power under latency and energy constraints. The resulting mixed-integer nonconvex problem is efficiently solved via an alternating algorithm. Experiments on multiple benchmarks demonstrate that ST-SFLora achieves the lowest client-side resource consumption among baselines while delivering a favorable trade-off between communication efficiency and model performance.

cs.DC↗

arXiv2026

Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models

Token pruning has emerged as an effective approach to reduce the substantial computational overhead of Large Vision-Language Models (LVLMs) by discarding less informative visual tokens while preserving performance. However, existing methods typically rely on individual attention sources from different LVLM components, resulting in incomplete and suboptimal pruning decisions due to biased attention distributions. To address this problem, we propose DeSAP, a novel Decoupled Similarity-Aware Pruning method for precise, task-aware token pruning within the visual encoder. Specifically, DeSAP introduces a decoupled similarity to capture fine-grained cross-modal relevance between visual features and text tokens, providing explicit task-related guidance for pruning. By integrating decoupled similarity with visual saliency signals derived from visual attention, DeSAP performs token pruning under the guidance of both task-related and visual cues, enabling robust pruning even under aggressive pruning ratios. Extensive experiments across diverse benchmarks and architectures show that DeSAP consistently outperforms SOTA methods in both accuracy and efficiency. On LLaVA-1.5-7B, DeSAP achieves a 10 times FLOPs reduction and a 2.3 times prefill speedup by retaining only 11.1% of visual tokens, while maintaining 98.1% of the original performance.

cs.CV↗

arXiv2026

TRACE: Trajectory Recovery with State Propagation Diffusion for Urban Mobility

High-quality GPS trajectories are essential for location-based web services and smart city applications, including navigation, ride-sharing and delivery. However, due to low sampling rates and limited infrastructure coverage during data collection, real-world trajectories are often sparse and feature unevenly distributed location points. Recovering these trajectories into dense and continuous forms is essential but challenging, given their complex and irregular spatio-temporal patterns. In this paper, we introduce a novel diffusion model for trajectory recovery named TRACE, which reconstruct dense and continuous trajectories from sparse and incomplete inputs. At the core of TRACE, we propose a State Propagation Diffusion Model (SPDM), which integrates a novel memory mechanism, so that during the denoising process, TRACE can retain and leverage intermediate results from previous steps to effectively reconstruct those hard-to-recover trajectory segments. Extensive experiments on multiple real-world datasets show that TRACE outperforms the state-of-the-art, offering $>$26\% accuracy improvement without significant inference overhead. Our work strengthens the foundation for mobile and web-connected location services, advancing the quality and fairness of data-driven urban applications. Code is available at: https://github.com/JinmingWang/TRACE

cs.LG↗

arXiv2026

Adaptive RAN Slicing Control via Reward-Free Self-Finetuning Agents

The integration of Generative AI models into AI-native network systems offers a transformative path toward achieving autonomous and adaptive control. However, the application of such models to continuous control tasks is impeded by intrinsic architectural limitations, including finite context windows, the lack of explicit reward signals, and the degradation of the long context. This paper posits that the key to unlocking robust continuous control is enabling agents to internalize experience by distilling it into their parameters, rather than relying on prompt-based memory. To this end, we propose a novel self-finetuning framework that enables agentic systems to learn continuously through direct interaction with the environment, bypassing the need for handcrafted rewards. Our framework implements a bi-perspective reflection mechanism that generates autonomous linguistic feedback to construct preference datasets from interaction history. A subsequent preference-based fine-tuning process distills long-horizon experiences into the model's parameters. We evaluate our approach on a dynamic Radio Access Network (RAN) slicing task, a challenging multi-objective control problem that requires the resolution of acute trade-offs between spectrum efficiency, service quality, and reconfiguration stability under volatile network conditions. Experimental results show that our framework outperforms standard Reinforcement Learning (RL) baselines and existing Large Language Model (LLM)-based agents in sample efficiency, stability, and multi-metric optimization. These findings demonstrate the potential of self-improving generative agents for continuous control tasks, paving the way for future AI-native network infrastructure.

cs.AI↗

arXiv2026

All Cities are Equal: A Unified Human Mobility Generation Model Enabled by LLMs

Synthetic human mobility generation is gaining traction as an ethical and practical approach to supporting the data needs of intelligent urban systems. Existing methods perform well primarily in data-rich cities, while their effectiveness declines significantly in cities with limited data resources. However, the ability to generate reliable human mobility data should not depend on a city's size or available resources, all cities deserve equal consideration. To address this open issue, we propose UniMob, a unified human mobility generation model across cities. UniMob is composed of three main components: an LLM-powered travel planner that derives high-level, temporally-aware, and semantically meaningful travel plans; a unified spatial embedding module that projects the spatial regions of various cities into a shared representation space; and a diffusion-based mobility generator that captures the joint spatiotemporal characteristics of human movement, guided by the derived travel plans. We evaluate UniMob extensively using two real-world datasets covering five cities. Comprehensive experiments show that UniMob significantly outperforms state-of-the-art baselines, achieving improvements of over 30\% across multiple evaluation metrics. Further analysis demonstrates UniMob's robustness in both zero- and few-shot scenarios, underlines the importance of LLM guidance, verifies its privacy-preserving nature, and showcases its applicability for downstream tasks.

cs.ET↗

arXiv2026

DeepFusion: Accelerating MoE Training via Federated Knowledge Distillation from Heterogeneous Edge Devices

Recent Mixture-of-Experts (MoE)-based large language models (LLMs) such as Qwen-MoE and DeepSeek-MoE are transforming generative AI in natural language processing. However, these models require vast and diverse training data. Federated learning (FL) addresses this challenge by leveraging private data from heterogeneous edge devices for privacy-preserving MoE training. Nonetheless, traditional FL approaches require devices to host local MoE models, which is impractical for resource-constrained devices due to large model sizes. To address this, we propose DeepFusion, the first scalable federated MoE training framework that enables the fusion of heterogeneous on-device LLM knowledge via federated knowledge distillation, yielding a knowledge-abundant global MoE model. Specifically, DeepFusion features each device to independently configure and train an on-device LLM tailored to its own needs and hardware limitations. Furthermore, we propose a novel View-Aligned Attention (VAA) module that integrates multi-stage feature representations from the global MoE model to construct a predictive perspective aligned with on-device LLMs, thereby enabling effective cross-architecture knowledge distillation. By explicitly aligning predictive perspectives, VAA resolves the view-mismatch problem in traditional federated knowledge distillation, which arises from heterogeneity in model architectures and prediction behaviors between on-device LLMs and the global MoE model. Experiments with industry-level MoE models (Qwen-MoE and DeepSeek-MoE) and real-world datasets (medical and finance) demonstrate that DeepFusion achieves performance close to centralized MoE training. Compared with key federated MoE baselines, DeepFusion reduces communication costs by up to 71% and improves token perplexity by up to 5.28%.

cs.LG↗

arXiv2026

Preventing Rank Collapse in Federated Low-Rank Adaptation with Client Heterogeneity

Federated low-rank adaptation (FedLoRA) has facilitated communication-efficient and privacy-preserving fine-tuning of foundation models for downstream tasks. In practical federated learning scenarios, client heterogeneity in system resources and data distributions motivates the use of heterogeneous LoRA ranks across clients. However, we identify a previously overlooked phenomenon in heterogeneous FedLoRA with SVD-based allocation, termed rank collapse, where the energy of the global update becomes concentrated in the minimum shared rank, resulting in suboptimal performance and high sensitivity to rank configurations. Through theoretical analysis, we reveal the root cause of rank collapse: a mismatch between rank-agnostic aggregation weights and rank-dependent client contributions, which systematically suppresses higher-rank updates at a geometric rate over rounds. Motivated by this insight, we propose raFLoRA, a rank-partitioned aggregation method that decomposes local updates into rank partitions and then aggregates each partition weighted by its effective client contributions. Extensive experiments across vision, language, and reasoning tasks show that raFLoRA prevents rank collapse, improves model performance, and enhances robustness across diverse heterogeneous configurations compared with strong FedLoRA baselines.

cs.LG↗

arXiv2026

Communication-Efficient Federated Learning by Exploiting Spatio-Temporal Correlations of Gradients

Communication overhead is a critical challenge in federated learning, particularly in bandwidth-constrained networks. Although many methods have been proposed to reduce communication overhead, most focus solely on compressing individual gradients, overlooking the temporal correlations among them. Prior studies have shown that gradients exhibit spatial correlations, typically reflected in low-rank structures. Through empirical analysis, we further observe a strong temporal correlation between client gradients across adjacent rounds. Based on these observations, we propose GradESTC, a compression technique that exploits both spatial and temporal gradient correlations. GradESTC exploits spatial correlations to decompose each full gradient into a compact set of basis vectors and corresponding combination coefficients. By exploiting temporal correlations, only a small portion of the basis vectors need to be dynamically updated in each round. GradESTC significantly reduces communication overhead by transmitting lightweight combination coefficients and a limited number of updated basis vectors instead of the full gradients. Extensive experiments show that, upon reaching a target accuracy level near convergence, GradESTC reduces uplink communication by an average of 39.79% compared to the strongest baseline, while maintaining comparable convergence speed and final accuracy to uncompressed FedAvg. By effectively leveraging spatio-temporal gradient structures, GradESTC offers a practical and scalable solution for communication-efficient federated learning.

cs.LG↗

arXiv2025

OptiVote: Non-Coherent FSO Over-the-Air Majority Vote for Communication-Efficient Distributed Federated Learning in Space Data Centers

The rapid deployment of mega-constellations is driving the long-term vision of space data centers (SDCs), where interconnected satellites form in-orbit distributed computing and learning infrastructures. Enabling distributed federated learning in such systems is challenging because iterative training requires frequent aggregation over inter-satellite links that are bandwidth- and energy-constrained, and the link conditions can be highly dynamic. In this work, we exploit over-the-air computation (AirComp) as an in-network aggregation primitive. However, conventional coherent AirComp relies on stringent phase alignment, which is difficult to maintain in space environments due to satellite jitter and Doppler effects. To overcome this limitation, we propose OptiVote, a robust and communication-efficient non-coherent free-space optical (FSO) AirComp framework for federated learning toward Space Data Centers. OptiVote integrates sign stochastic gradient descent (signSGD) with a majority-vote (MV) aggregation principle and pulse-position modulation (PPM), where each satellite conveys local gradient signs by activating orthogonal PPM time slots. The aggregation node performs MV detection via non-coherent energy accumulation, transforming phase-sensitive field superposition into phase-agnostic optical intensity combining, thereby eliminating the need for precise phase synchronization and improving resilience under dynamic impairments. To mitigate aggregation bias induced by heterogeneous FSO channels, we further develop an importance-aware, channel state information (CSI)-free dynamic power control scheme that balances received energies without additional signaling. We provide theoretical analysis by characterizing the aggregate error probability under statistical FSO channels and establishing convergence guarantees for non-convex objectives.

eess.SP↗

arXiv2025

Towards 6G Native-AI Edge Networks: A Semantic-Aware and Agentic Intelligence Paradigm

The evolution toward sixth-generation wireless systems positions intelligence as a native network capability, fundamentally transforming the design of radio access networks (RANs). Within this vision, Semantic-native communication and agentic intelligence are expected to play central roles. SemCom departs from bit-level fidelity and instead emphasizes task-oriented meaning exchange, enabling compact SC and introducing new performance measures such as semantic fidelity and task success rate. Agentic intelligence endows distributed RAN entities with goal-driven autonomy, reasoning, planning, and multi-agent collaboration, increasingly supported by foundation models and knowledge graphs. In this work, we first introduce the conceptual foundations of SemCom and agentic networking, and discuss why existing AI-driven O-RAN solutions remain largely bit-centric and task-siloed. We then present a unified taxonomy that organizes recent research along three axes: i) semantic abstraction level (symbol/feature/intent/knowledge), ii) agent autonomy and coordination granularity (single-, multi-, and hierarchical-agent), and iii) RAN control placement across PHY/MAC, near-real-time RIC, and non-real-time RIC. Based on this taxonomy, we systematically introduce enabling technologies including task-oriented semantic encoders/decoders, multi-agent reinforcement learning, foundation-model-assisted RAN agents, and knowledge-graph-based reasoning for cross-layer awareness. Representative 6G use cases, such as immersive XR, vehicular V2X, and industrial digital twins, are analyzed to illustrate the semantic-agentic convergence in practice. Finally, we identify open challenges in semantic representation standardization, scalable trustworthy agent coordination, O-RAN interoperability, and energy-efficient AI deployment, and outline research directions toward operational semantic-agentic AI-RAN.

eess.SP↗

arXiv2025

Achieving Equilibrium under Utility Heterogeneity: An Agent-Attention Framework for Multi-Agent Multi-Objective Reinforcement Learning

Multi-agent multi-objective systems (MAMOS) have emerged as powerful frameworks for modelling complex decision-making problems across various real-world domains, such as robotic exploration, autonomous traffic management, and sensor network optimisation. MAMOS offers enhanced scalability and robustness through decentralised control and more accurately reflects inherent trade-offs between conflicting objectives. In MAMOS, each agent uses utility functions that map return vectors to scalar values. Existing MAMOS optimisation methods face challenges in handling heterogeneous objective and utility function settings, where training non-stationarity is intensified due to private utility functions and the associated policies. In this paper, we first theoretically prove that direct access to, or structured modeling of, global utility functions is necessary for the Bayesian Nash Equilibrium under decentralised execution constraints. To access the global utility functions while preserving the decentralised execution, we propose an Agent-Attention Multi-Agent Multi-Objective Reinforcement Learning (AA-MAMORL) framework. Our approach implicitly learns a joint belief over other agents' utility functions and their associated policies during centralised training, effectively mapping global states and utilities to each agent's policy. In execution, each agent independently selects actions based on local observations and its private utility function to approximate a BNE, without relying on inter-agent communication. We conduct comprehensive experiments in both a custom-designed MAMO Particle environment and the standard MOMALand benchmark. The results demonstrate that access to global preferences and our proposed AA-MAMORL significantly improve performance and consistently outperform state-of-the-art methods.

cs.MA↗

arXiv2025

SARC: Sentiment-Augmented Deep Role Clustering for Fake News Detection

Fake news detection has been a long-standing research focus in social networks. Recent studies suggest that incorporating sentiment information from both news content and user comments can enhance detection performance. However, existing approaches typically treat sentiment features as auxiliary signals, overlooking role differentiation, that is, the same sentiment polarity may originate from users with distinct roles, thereby limiting their ability to capture nuanced patterns for effective detection. To address this issue, we propose SARC, a Sentiment-Augmented Role Clustering framework which utilizes sentiment-enhanced deep clustering to identify user roles for improved fake news detection. The framework first generates user features through joint comment text representation (with BiGRU and Attention mechanism) and sentiment encoding. It then constructs a differentiable deep clustering module to automatically categorize user roles. Finally, unlike existing approaches which take fake news label as the unique supervision signal, we propose a joint optimization objective integrating role clustering and fake news detection to further improve the model performance. Experimental results on two benchmark datasets, RumourEval-19 and Weibo-comp, demonstrate that SARC achieves superior performance across all metrics compared to baseline models. The code is available at: https://github.com/jxshang/SARC.

cs.CL↗

arXiv2025

BoHA: Blockwise Hadamard Product Adaptation for Parameter-Efficient Fine-Tuning

Parameter-efficient fine-tuning (PEFT) of large language models trains a small task-specific parameter set while keeping the pretrained model frozen. The dominant Low-Rank Adaptation (LoRA) family makes this trade-off practical; however, evaluations under the same parameter budget assess single-task accuracy. In sequential adaptation settings, such evaluations should also measure how well performance on the first-stage task is retained after subsequent fine-tuning. To address this gap, we introduce BoHA, a blockwise $W_0$-coupled Hadamard product adapter that treats spatial support as an explicit design axis. BoHA partitions the frozen weight $W_0$ into a $b{\times}b$ grid and learns an independent low-rank Hadamard product factor in each block, preserving a matched LoRA-equivalent total rank with adapter-free merged inference. On a synthetic target, BoHA at per-block rank $r_b{=}1$ exactly reconstructs an update that requires rank $b^2$ under the global $W_0$-coupled Hadamard parameterization. Across Llama-3.2-1B/3B, Mistral-7B, and Gemma-2-9B on commonsense and arithmetic reasoning tasks, BoHA outperforms LoRA across all matched-budget single-task averages and remains competitive with the strongest Hadamard baseline. On a Llama-3.2-3B commonsense $\to$ arithmetic continual-learning diagnostic, BoHA retains $57.66\%$ first-stage accuracy and exceeds the $W_0$-free additive-control mean by $15.23\%$ under matched second-stage plasticity. These results demonstrate that blockwise $W_0$-coupled Hadamard adaptation is a competitive PEFT design choice when retention under sequential adaptation is part of the objective.

cs.LG↗

arXiv2025

Spectral Efficiency-Aware Codebook Design for Task-Oriented Semantic Communications

Digital task-oriented semantic communication (ToSC) aims to transmit only task-relevant information, significantly reducing communication overhead. Existing ToSC methods typically rely on learned codebooks to encode semantic features and map them to constellation symbols. However, these codebooks are often sparsely activated, resulting in low spectral efficiency and underutilization of channel capacity. This highlights a key challenge: how to design a codebook that not only supports task-specific inference but also approaches the theoretical limits of channel capacity. To address this challenge, we construct a spectral efficiency-aware codebook design framework that explicitly incorporates the codebook activation probability into the optimization process. Beyond maximizing task performance, we introduce the Wasserstein (WS) distance as a regularization metric to minimize the gap between the learned activation distribution and the optimal channel input distribution. Furthermore, we reinterpret WS theory from a generative perspective to align with the semantic nature of ToSC. Combining the above two aspects, we propose a WS-based adaptive hybrid distribution scheme, termed WS-DC, which learns compact, task-driven and channel-aware latent representations. Experimental results demonstrate that WS-DC not only outperforms existing approaches in inference accuracy but also significantly improves codebook efficiency, offering a promising direction toward capacity-approaching semantic communication systems.

eess.SP↗

arXiv2025

FedCD: A Fairness-aware Federated Cognitive Diagnosis Framework

Online intelligent education platforms have generated a vast amount of distributed student learning data. This influx of data presents opportunities for cognitive diagnosis (CD) to assess students' mastery of knowledge concepts while also raising significant data privacy and security challenges. To cope with this issue, federated learning (FL) becomes a promising solution by jointly training models across multiple local clients without sharing their original data. However, the data quality problem, caused by the ability differences and educational context differences between different groups/schools of students, further poses a challenge to the fairness of models. To address this challenge, this paper proposes a fairness-aware federated cognitive diagnosis framework (FedCD) to jointly train CD models built upon a novel parameter decoupling-based personalization strategy, preserving privacy of data and achieving precise and fair diagnosis of students on each client. As an FL paradigm, FedCD trains a local CD model for the students in each client based on its local student learning data, and each client uploads its partial model parameters to the central server for parameter aggregation according to the devised innovative personalization strategy. The main idea of this strategy is to decouple model parameters into two parts: the first is used as locally personalized parameters, containing diagnostic function-related model parameters, to diagnose each client's students fairly; the second is the globally shared parameters across clients and the server, containing exercise embedding parameters, which are updated via fairness-aware aggregation, to alleviate inter-school unfairness. Experiments on three real-world datasets demonstrate the effectiveness of the proposed FedCD framework and the personalization strategy compared to five FL approaches under three CD models.

cs.LG↗