Efficient robot control often requires balancing task performance with energy expenditure. A common approach in reinforcement learning (RL) is to penalize energy use directly as part of the reward function. This requires carefully tuning weight terms to avoid undesirable trade-offs where energy minimization harms task success. In this work, we propose a hyperparameter-free gradient optimization method to minimize energy expenditure without conflicting with task performance. Inspired by recent works in multitask learning, our method applies policy gradient projection between task and energy objectives to derive policy updates that minimize energy expenditure in ways that do not impact task performance. We evaluate this technique on standard locomotion benchmarks of DM-Control and HumanoidBench and demonstrate a reduction of 64% energy usage while maintaining comparable task performance. Further, we conduct experiments on a Unitree GO2 quadruped showcasing Sim2Real transfer of energy efficient policies. Our method is easy to implement in standard RL pipelines with minimal code changes, is applicable to any policy gradient method, and offers a principled alternative to reward shaping for energy efficient control policies.

Visual SLAM has regained attention due to its ability to provide perceptual capabilities and simulation test data for Embodied AI. However, traditional SLAM methods struggle to meet the demands of high-quality scene reconstruction, and Gaussian SLAM systems, despite their rapid rendering and high-quality mapping capabilities, lack effective pose optimization methods and face challenges in geometric reconstruction. To address these issues, we introduce FGO-SLAM, a Gaussian SLAM system that employs an opacity radiance field as the scene representation to enhance geometric mapping performance. After initial pose estimation, we apply global adjustment to optimize camera poses and sparse point cloud, ensuring robust tracking of our approach. Additionally, we maintain a globally consistent opacity radiance field based on 3D Gaussians and introduce depth distortion and normal consistency terms to refine the scene representation. Furthermore, after constructing tetrahedral grids, we identify level sets to directly extract surfaces from 3D Gaussians. Results across various real-world and large-scale synthetic datasets demonstrate that our method achieves state-of-the-art tracking accuracy and mapping performance.

The recent development of Large Language Models (LLMs) has been accompanied by an effervescence of novel ideas and methods to better optimize the loss of deep learning models. Claims from those methods are myriad: from faster convergence to removing reliance on certain hyperparameters. However, the diverse experimental protocols used to validate these claims make direct comparisons between methods challenging. This study presents a comprehensive evaluation of recent optimization techniques across standardized LLM pretraining scenarios, systematically varying model size, batch size, and training duration. Through careful tuning of each method, we provide guidance to practitioners on which optimizer is best suited for each scenario. For researchers, our work highlights promising directions for future optimization research. Finally, by releasing our code and making all experiments fully reproducible, we hope our efforts can help the development and rigorous benchmarking of future methods.

--Community detection in graphs is crucial for understanding the organization of nodes into densely connected clusters. While numerous strategies have been developed to identify these clusters, the success of community detection can lead to privacy and information security concerns, as individuals may not want their personal information exposed. T o address this, community deception methods have been proposed to reduce the effectiveness of detection algorithms. Nevertheless, several limitations, such as the rationality of evaluation metrics and the unnoticeability of attacks, have been ignored in current deception methods. Therefore, in this work, we first investigate the limitations of the widely used deception metric, i.e., the decrease of modularity, through empirical studies. Then, we propose a new deception metric, and combine this new metric together with the attack budget to model the unnoticeable community deception task as a multi-objective optimization problem. T o further improve the deception performance, we propose two variant methods by incorporating the degree-biased and community-biased candidate node selection mechanisms. Extensive experiments on three benchmark datasets demonstrate the superiority of the proposed community deception strategies. RAPHS or networks, which consist of a series of nodes and links, have been widely employed to model complex relationships in modern social systems. The typical examples of networks include social networks which illustrate the social relationships between people, financial networks which represent the transaction records between accounts, power networks which indicate the transmission relationship between power nodes, among others [1]-[4]. In these years, significant efforts have been put into investigating the abundant information behind graph-based systems, such as community detection for clustering nodes in the graph into different groups, node classification for identifying the labels of nodes, link prediction for predicting possible future connections between nodes, etc [5]-[7]. Specifically, in this work, we focus on the task of community detection. Junyuan Fang and Chi K. Tse are with the Department of Electrical Engineering, City University of Hong Kong, Hong Kong SAR, China. Huimin Liu and Y ueqi Peng are with the School of Computer Science and Engineering, Sun Y at-sen University, Guangzhou 510006, China.

Reward maximization, safe exploration, and intrinsic motivation are often studied as separate objectives in reinforcement learning (RL). We present a unified geometric framework, that views these goals as instances of a single optimization problem on the space of achievable long-term behavior in an environment. Within this framework, classical methods such as policy mirror descent, natural policy gradient, and trust-region algorithms naturally generalize to nonlinear utilities and convex constraints. We illustrate how this perspective captures robustness, safety, exploration, and diversity objectives, and outline open challenges at the interface of geometry and deep RL.

Modern optimization faces a fundamental challenge: local gradient-based methods provide no global information about the objective function $L$ landscape, often leading to suboptimal convergence and sensitivity to initialization. We introduce a novel optimization framework that leverages resurgence theory from complex analysis to extract global structural information from divergent asymptotic series. Our key insight is that the factorially divergent perturbative expansions of parameter space partition functions encode precise information about all critical objective function value in the landscape through their Borel transform singularities. The algorithm works by computing the statistical mechanical partition function $Z(g) = \int e^{-L(θ)/g} dθ$ for small coupling $g\ll 1$, extracting its asymptotic series coefficients, and identifying Borel plane singularities that correspond one-to-one with critical objective function values. These target values provide global guidance to local optimizers, enabling principled learning rate adaptation and escape from suboptimal regions. Unlike heuristic adaptive methods, targets are theoretically grounded in the geometry of the optimization landscape.

This work explores the integration of Quantum Machine Learning (QML) and Quantum-Inspired (QI) techniques for optimizing end-to-end (E2E) network services in telecommunication systems, particularly focusing on 5G networks and beyond. The application of QML and QI algorithms is investigated, comparing their performance with classical Machine Learning (ML) approaches. The present study employs a hybrid framework combining quantum and classical computing leveraging the strengths of QML and QI, without the penalty of quantum hardware availability. This is particularized for the optimization of the Quality of Experience (QoE) over cellular networks. The framework comprises an estimator for obtaining the expected QoE based on user metrics, service settings, and cell configuration, and an optimizer that uses the estimation to choose the best cell and service configuration. Although the approach is applicable to any QoE-based network management, its implementation is particularized for the optimization of network configurations for Cloud Gaming services. Then, it is evaluated via performance metrics such as accuracy and model loading and inference times for the estimator, and time to solution and solution score for the optimizer. The results indicate that QML models achieve similar or superior accuracy to classical ML models for estimation, while decreasing inference and loading times. Furthermore, potential for better performance is observed for higher-dimensional data, highlighting promising results for higher complexity problems. Thus, the results demonstrate the promising potential of QML in advancing network optimization, although challenges related to data availability and integration complexities between quantum and classical ML are identified as future research lines.

Efficient adversarial attack methods are critical for assessing the robustness of computer vision models. In this paper, we reconstruct the optimization objective for generating adversarial examples as "maximizing the difference between the non-true labels' probability upper bound and the true label's probability," and propose a gradient-based attack method termed Sequential Difference Maximization (SDM). SDM establishes a three-layer optimization framework of "cycle-stage-step." The processes between cycles and between iterative steps are respectively identical, while optimization stages differ in terms of loss functions: in the initial stage, the negative probability of the true label is used as the loss function to compress the solution space; in subsequent stages, we introduce the Directional Probability Difference Ratio (DPDR) loss function to gradually increase the non-true labels' probability upper bound by compressing the irrelevant labels' probabilities. Experiments demonstrate that compared with previous SOTA methods, SDM not only exhibits stronger attack performance but also achieves higher attack cost-effectiveness. Additionally, SDM can be combined with adversarial training methods to enhance their defensive effects. The code is available at https://github.com/X-L-Liu/SDM.

At the intersection of the cutting-edge technologies and privacy concerns, Federated Learning (FL) with its distributed architecture, stands at the forefront in a bid to facilitate collaborative model training across multiple clients while preserving data privacy. However, the applicability of FL systems is hindered by fairness concerns arising from numerous sources of heterogeneity that can result in biases and undermine a system's effectiveness, with skewed predictions, reduced accuracy, and inefficient model convergence. This survey thus explores the diverse sources of bias, including but not limited to, data, client, and model biases, and thoroughly discusses the strengths and limitations inherited within the array of the state-of-the-art techniques utilized in the literature to mitigate such disparities in the FL training process. We delineate a comprehensive overview of the several notions, theoretical underpinnings, and technical aspects associated with fairness and their adoption in FL-based multidisciplinary environments. Furthermore, we examine salient evaluation metrics leveraged to measure fairness quantitatively. Finally, we envisage exciting open research directions that have the potential to drive future advancements in achieving fairer FL frameworks, in turn, offering a strong foundation for future research in this pivotal area.

In this paper, we propose an evolutionary Multi-objective Optimization for Replica-Exchange-based Physics-informed Operator learning Network, which is a novel operator learning network to efficiently solve parametric partial differential equations. In forward and inverse settings, this operator learning network only admits minimum requirement of noisy observational data. While physics-informed neural networks and operator learning approaches such as Deep Operator Networks and Fourier Neural Operators offer promising alternatives to traditional numerical solvers, they struggle with balancing operator and physics losses, maintaining robustness under noisy or sparse data, and providing uncertainty quantification. The proposed framework addresses these limitations by integrating: (i) evolutionary multi-objective optimization to adaptively balance operator and physics-based losses in the Pareto front; (ii) replica exchange stochastic gradient Langevin dynamics to improve global parameter-space exploration and accelerate convergence; and (iii) built-in Bayesian uncertainty quantification from stochastic sampling. The proposed operator learning method is tested numerically on several different problems including one-dimensional Burgers equation and the time-fractional mixed diffusion-wave equation. The results indicate that our framework consistently outperforms the general operator learning methods in accuracy, noise robustness, and the ability to quantify uncertainty.