arXiv subjects

Tao Deng

Publications and source records attributed to Tao Deng.

At least 19 recordsLinked to original sources

arXiv2026

Autonomous Optimization of Complex Oxides for Thermochemical Fuel Production

Two-step thermochemical fuel production, including H2O and CO2 splitting, offers a promising route to sustainable fuel manufacturing, with performance governed by redox-active oxides that enable cyclic reduction-oxidation reactions. Maximizing thermal-to-fuel conversion efficiency demands materials that simultaneously satisfy multiple stringent thermodynamic and kinetic targets. Addressing these requirements has increasingly driven materials design toward complex, multi-cation oxides, such as mixed-cation fluorites, perovskites, and high-entropy oxides, wherein composition, defect chemistry, phase stability, and morphology should be co-optimized. This creates a challenging materials optimization problem that is poorly suited to traditional trial-and-error approaches. In this review, we argue that thermochemical fuel production provides a compelling frontier for autonomous materials design and optimization. We first examine why redox-active complex oxides are difficult to develop, owing to multidimensional phase spaces, harsh operating conditions, and competing functional targets. We then discuss how high-throughput computation, automated synthesis, characterization and testing, and machine learning can be integrated into closed-loop workflows to address these challenges. Building on broader oxide materials research, we organize recent progress into a capability roadmap for complex-oxide optimization, spanning compositionally diverse synthesis, operando characterization, robotic testing, operation-condition computation, and multi-objective optimization. Finally, we outline key experimental, computational, and data challenges for building self-improving materials development platforms for materials development in thermochemical fuel production.

cond-mat.mtrl-sci↗

arXiv2026

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Pruning

Multimodal large language models (MLLMs) achieve strong performance across diverse vision-language tasks, but their efficiency is limited by the cost of processing numerous visual tokens. Visual token pruning can reduce this cost, but requires accurate token importance estimates. Recent studies have demonstrated that text-to-vision attention from middle language model layers can effectively guide visual token pruning, typically using attention from a predefined middle layer to select the visual tokens to retain. Two problems therefore remain. First, our analysis shows that the layer whose attention is most responsive to the question varies substantially across samples, making a fixed layer suboptimal. Second, obtaining attention from the appropriate middle layer requires processing numerous visual tokens through several language model layers, by which point considerable computation has already been spent. To address both problems, we propose Middle-layer Attention Prediction (MAP), which uses Question Contrastive Teacher Selection to identify a sample-specific teacher layer by contrasting attention under the original and reference questions, and distills attention from the selected layer into a lightweight predictor that estimates visual token importance from multi-modal input features. During inference, MAP combines the predicted importance scores with a diversity criterion to prune visual tokens before the first language model layer. Thus, MAP requires no attention maps for pruning and remains compatible with existing inference acceleration techniques. Across ten benchmarks on LLaVA-NeXT-7B, MAP retains 97.5% of the unpruned model performance with only 5.56% of the visual tokens, yielding a 3.09x end-to-end speedup.

cs.AI↗

arXiv2026

Mechanism-Dependent Descriptors Enable Predictive Design of Oxygen Capacity in Perovskite Oxides

Perovskite oxides can reversibly accommodate substantial changes in oxygen stoichiometry, making them attractive for clean-energy technologies including chemical looping and oxygen storage. Despite extensive efforts to optimize their redox properties, predictive descriptors capable of assessing oxygen capacity across diverse compositions remain under development. Here, we combine experiments and first-principles calculations to establish composition and oxygen-capacity relationships in the model perovskite series LnxSr1-xCoO3. We confirm that increasing Sr2+ content promotes the formation of high-valence Co4+, expanding the cationic redox reservoir available during oxygen release and thereby enhancing oxygen capacity. In this regime, oxygen-vacancy formation energy captures the observed trend because oxygen release is primarily compensated by Co4+/Co3+/Co2+ redox. Across the rare-earth series, however, oxygen capacity decreases from La to Lu despite progressively lower oxygen-vacancy formation energies. We reveal that this counterintuitive behavior originates from an alternative charge-compensation pathway, in which lattice oxygen is partially oxidized to O1- -like species during oxygen removal. Heavy rare-earth compositions (Tb-Lu) preferentially stabilize these oxygen-hole species through distinct local bonding environments, with charge compensation involving both oxidized lattice oxygen and reduced rare-earth and cobalt cations, thereby suppressing net oxygen release despite favorable vacancy thermodynamics. We further identify average metal-oxygen bond strength, quantified by integrated crystal orbital Hamilton population, as a physically meaningful descriptor for oxygen capacity when anionic redox becomes dominant.

cond-mat.mtrl-sci↗

arXiv2026

Optimal Routing for Federated Learning over Dynamic Satellite Networks: Tractable or Not?

Federated learning (FL) is a key paradigm for distributed model learning across decentralized data sources. Communication in each FL round typically consists of two phases: (i) distributing the global model from a server to clients, and (ii) collecting updated local models from clients to the server for aggregation. This paper focuses on a type of FL where communication between a client and the server is relay-based over dynamic networks, making routing optimization essential. A typical scenario is in-orbit FL, where satellites act as clients and communicate with a server (which can be a satellite, ground station, or aerial platform) via multi-hop inter-satellite links. This paper presents a comprehensive tractability analysis of routing optimization for in-orbit FL under different settings. For global model distribution, these include the number of models, the objective function, and routing schemes (unicast versus multicast, and splittable versus unsplittable flow). For local model collection, the settings consider the number of models, client selection, and flow splittability. For each case, we rigorously prove whether the global optimum is obtainable in polynomial time or the problem is NP-hard. Together, our analysis draws clear boundaries between tractable and intractable regimes for a broad spectrum of routing problems for in-orbit FL. For tractable cases, the derived efficient algorithms are directly applicable in practice. For intractable cases, we provide fundamental insights into their inherent complexity. These contributions fill a critical yet unexplored research gap, laying a foundation for principled routing design, evaluation, and deployment in satellite-based FL or similar distributed learning systems.

cs.LG↗

arXiv2026

RELATE: A Reinforcement Learning-Enhanced LLM Framework for Advertising Text Generation

In online advertising, advertising text plays a critical role in attracting user engagement and driving advertiser value. Existing industrial systems typically follow a two-stage paradigm, where candidate texts are first generated and subsequently aligned with online performance metrics such as click-through rate(CTR). This separation often leads to misaligned optimization objectives and low funnel efficiency, limiting global optimality. To address these limitations, we propose RELATE, a reinforcement learning-based end-to-end framework that unifies generation and objective alignment within a single model. Instead of decoupling text generation from downstream metric alignment, RELATE integrates performance and compliance objectives directly into the generation process via policy learning. To better capture ultimate advertiser value beyond click-level signals, We incorporate conversion-oriented metrics into the objective and jointly model them with compliance constraints as multi-dimensional rewards, enabling the model to generate high-quality ad texts that improve conversion performance under policy constraints. Extensive experiments on large-scale industrial datasets demonstrate that RELATE consistently outperforms baselines. Furthermore, online deployment on a production advertising platform yields statistically significant improvements in click-through conversion rate(CTCVR) under strict policy constraints, validating the robustness and real-world effectiveness of the proposed framework.

cs.AI↗

arXiv2025

Interpretable Nanoporous Materials Design with Symmetry-Aware Networks

Reticular frameworks hold promise for diverse sustainable applications, yet their immense chemical space limits efficient and systematic design. While machine learning provides a compelling pathway to accelerate exploration, existing approaches often lack either interpretability or fidelity in linking crystal geometry to emergent properties. Here, we introduce a site-resolved equivariant learning framework based on three-dimensional periodic space sampling, which decomposes reticular structures into local geometric environments for simultaneous property prediction and site-wise contribution analysis. Trained on a combination of constructed and retrieved datasets, the model achieves state-of-the-art accuracy and data efficiency across gas storage, gas separation, and electronic-property prediction tasks. Importantly, the framework reveals interpretable local structure-property relationships by identifying transferable high-contribution sites across diverse frameworks. Leveraging these learned motifs, we further demonstrate inverse design of new metal-organic frameworks exhibiting record-high N2 storage, strong CO2/N2 separation performance, and near-zero electronic band gaps, validated by physics-based simulations.

cond-mat.mtrl-sci↗

arXiv2025

Data Skeleton Learning: Scalable Active Clustering with Sparse Graph Structures

In this work, we focus on the efficiency and scalability of pairwise constraint-based active clustering, crucial for processing large-scale data in applications such as data mining, knowledge annotation, and AI model pre-training. Our goals are threefold: (1) to reduce computational costs for iterative clustering updates; (2) to enhance the impact of user-provided constraints to minimize annotation requirements for precise clustering; and (3) to cut down memory usage in practical deployments. To achieve these aims, we propose a graph-based active clustering algorithm that utilizes two sparse graphs: one for representing relationships between data (our proposed data skeleton) and another for updating this data skeleton. These two graphs work in concert, enabling the refinement of connected subgraphs within the data skeleton to create nested clusters. Our empirical analysis confirms that the proposed algorithm consistently facilitates more accurate clustering with dramatically less input of user-provided constraints, and outperforms its counterparts in terms of computational performance and scalability, while maintaining robustness across various distance metrics.

cs.LG↗

arXiv2025

Probing Temperature at Nanoscale through Thermal Vibration Characterization using Scanning Precession Electron Diffraction

Accurate, non-contact temperature measurement with high spatial resolution is essential for understanding thermal behavior in integrated nanoscale devices and heterogeneous interfaces. However, existing techniques are often limited by the need for physical contact or insufficient spatial resolution for the measurement of local temperature and mapping its distribution. Here, we showcase the direct temperature measurement of graphene with nanometer spatial resolution in transmission electron microscopy. In experiments, combining a scanning nanobeam with precession electron diffraction offers the collection of kinemetic diffraction from a local area at the nanometer scale. In analysis, we use a pre-calculated, sample-specific structure-factor-based correction method to enable the linear fitting of the diffraction intensities, allowing the determination of the Debye-Waller factor as a function of temperature at the precision of 10-4{\AA}2/{\deg}C. With the high spatial resolution and measurement precision, the temperature and thermal vibration mapping further reveal the influence of graphene lattice parameters and thickness on the Debye-Waller factor, providing valuable insights into the vibrational properties impacted by temperature, lattice structure, and graphene layer thickness.

cond-mat.mtrl-sci↗

arXiv2025

Mobility-Aware Multi-Task Decentralized Federated Learning for Vehicular Networks: Modeling, Analysis, and Optimization

Federated learning (FL) is a promising paradigm that can enable collaborative model training between vehicles while protecting data privacy, thereby significantly improving the performance of intelligent transportation systems (ITSs). In vehicular networks, due to mobility, resource constraints, and the concurrent execution of multiple training tasks, how to allocate limited resources effectively to achieve optimal model training of multiple tasks is an extremely challenging issue. In this paper, we propose a mobility-aware multi-task decentralized federated learning (MMFL) framework for vehicular networks. By this framework, we address task scheduling, subcarrier allocation, and leader selection, as a joint optimization problem, termed as TSLP. For the case with a single FL task, we derive the convergence bound of model training. For general cases, we first model TSLP as a resource allocation game, and prove the existence of a Nash equilibrium (NE). Then, based on this proof, we reformulate the game as a decentralized partially observable Markov decision process (DEC-POMDP), and develop an algorithm based on heterogeneous-agent proximal policy optimization (HAPPO) to solve DEC-POMDP. Finally, numerical results are used to demonstrate the effectiveness of the proposed algorithm.

cs.NI↗

arXiv2025

WECAR: An End-Edge Collaborative Inference and Training Framework for WiFi-Based Continuous Human Activity Recognition

WiFi-based human activity recognition (HAR) holds significant promise for ubiquitous sensing in smart environments. A critical challenge lies in enabling systems to dynamically adapt to evolving scenarios, learning new activities without catastrophic forgetting of prior knowledge, while adhering to the stringent computational constraints of edge devices. Current approaches struggle to reconcile these requirements due to prohibitive storage demands for retaining historical data and inefficient parameter utilization. We propose WECAR, an end-edge collaborative inference and training framework for WiFi-based continuous HAR, which decouples computational workloads to overcome these limitations. In this framework, edge devices handle model training, lightweight optimization, and updates, while end devices perform efficient inference. WECAR introduces two key innovations, i.e., dynamic continual learning with parameter efficiency and hierarchical distillation for end deployment. For the former, we propose a transformer-based architecture enhanced by task-specific dynamic model expansion and stability-aware selective retraining. For the latter, we propose a dual-phase distillation mechanism that includes multi-head self-attention relation distillation and prefix relation distillation. We implement WECAR based on heterogeneous hardware using Jetson Nano as edge devices and the ESP32 as end devices, respectively. Our experiments across three public WiFi datasets reveal that WECAR not only outperforms several state-of-the-art methods in performance and parameter efficiency, but also achieves a substantial reduction in the model's parameter count post-optimization without sacrificing accuracy. This validates its practicality for resource-constrained environments.

cs.LG↗

arXiv2025

Mobility-Aware Decentralized Federated Learning with Joint Optimization of Local Iteration and Leader Selection for Vehicular Networks

Federated learning (FL) emerges as a promising approach to empower vehicular networks, composed by intelligent connected vehicles equipped with advanced sensing, computing, and communication capabilities. While previous studies have explored the application of FL in vehicular networks, they have largely overlooked the intricate challenges arising from the mobility of vehicles and resource constraints. In this paper, we propose a framework of mobility-aware decentralized federated learning (MDFL) for vehicular networks. In this framework, nearby vehicles train an FL model collaboratively, yet in a decentralized manner. We formulate a local iteration and leader selection joint optimization problem (LSOP) to improve the training efficiency of MDFL. For problem solving, we first reformulate LSOP as a decentralized partially observable Markov decision process (Dec-POMDP), and then develop an effective optimization algorithm based on multi-agent proximal policy optimization (MAPPO) to solve Dec-POMDP. Finally, we verify the performance of the proposed algorithm by comparing it with other algorithms.

cs.NI↗

arXiv2025

SalM$^{2}$: An Extremely Lightweight Saliency Mamba Model for Real-Time Cognitive Awareness of Driver Attention

Driver attention recognition in driving scenarios is a popular direction in traffic scene perception technology. It aims to understand human driver attention to focus on specific targets/objects in the driving scene. However, traffic scenes contain not only a large amount of visual information but also semantic information related to driving tasks. Existing methods lack attention to the actual semantic information present in driving scenes. Additionally, the traffic scene is a complex and dynamic process that requires constant attention to objects related to the current driving task. Existing models, influenced by their foundational frameworks, tend to have large parameter counts and complex structures. Therefore, this paper proposes a real-time saliency Mamba network based on the latest Mamba framework. As shown in Figure 1, our model uses very few parameters (0.08M, only 0.09~11.16% of other models), while maintaining SOTA performance or achieving over 98% of the SOTA model's performance.

cs.CV↗

arXiv2025

ConSense: Continually Sensing Human Activity with WiFi via Growing and Picking

WiFi-based human activity recognition (HAR) holds significant application potential across various fields. To handle dynamic environments where new activities are continuously introduced, WiFi-based HAR systems must adapt by learning new concepts without forgetting previously learned ones. Furthermore, retaining knowledge from old activities by storing historical exemplar is impractical for WiFi-based HAR due to privacy concerns and limited storage capacity of edge devices. In this work, we propose ConSense, a lightweight and fast-adapted exemplar-free class incremental learning framework for WiFi-based HAR. The framework leverages the transformer architecture and involves dynamic model expansion and selective retraining to preserve previously learned knowledge while integrating new information. Specifically, during incremental sessions, small-scale trainable parameters that are trained specifically on the data of each task are added in the multi-head self-attention layer. In addition, a selective retraining strategy that dynamically adjusts the weights in multilayer perceptron based on the performance stability of neurons across tasks is used. Rather than training the entire model, the proposed strategies of dynamic model expansion and selective retraining reduce the overall computational load while balancing stability on previous tasks and plasticity on new tasks. Evaluation results on three public WiFi datasets demonstrate that ConSense not only outperforms several competitive approaches but also requires fewer parameters, highlighting its practical utility in class-incremental scenarios for HAR.

eess.SP↗

arXiv2024

AIM 2024 Challenge on Video Saliency Prediction: Methods and Results

This paper reviews the Challenge on Video Saliency Prediction at AIM 2024. The goal of the participants was to develop a method for predicting accurate saliency maps for the provided set of video sequences. Saliency maps are widely exploited in various applications, including video compression, quality assessment, visual perception studies, the advertising industry, etc. For this competition, a previously unused large-scale audio-visual mouse saliency (AViMoS) dataset of 1500 videos with more than 70 observers per video was collected using crowdsourced mouse tracking. The dataset collection methodology has been validated using conventional eye-tracking data and has shown high consistency. Over 30 teams registered in the challenge, and there are 7 teams that submitted the results in the final phase. The final phase solutions were tested and ranked by commonly used quality metrics on a private test subset. The results of this evaluation and the descriptions of the solutions are presented in this report. All data, including the private test subset, is made publicly available on the challenge homepage - https://challenges.videoprocessing.ai/challenges/video-saliency-prediction.html.

cs.CV↗

arXiv2023

Task Offloading Optimization in Mobile Edge Computing under Uncertain Processing Cycles and Intermittent Communications

Mobile edge computing (MEC) has been regarded as a promising approach to deal with explosive computation requirements by enabling cloud computing capabilities at the edge of networks. Existing models of MEC impose some strong assumptions on the known processing cycles and unintermittent communications. However, practical MEC systems are constrained by various uncertainties and intermittent communications, rendering these assumptions impractical. In view of this, we investigate how to schedule task offloading in MEC systems with uncertainties. First, we derive a closed-form expression of the average offloading success probability in a device-to-device (D2D) assisted MEC system with uncertain computation processing cycles and intermittent communications. Then, we formulate a task offloading maximization problem (TOMP), and prove that the problem is NP-hard. For problem solving, if the problem instance exhibits a symmetric structure, we propose a task scheduling algorithm based on dynamic programming (TSDP). By solving this problem instance, we derive a bound to benchmark sub-optimal algorithm. For general scenarios, by reformulating the problem, we propose a repeated matching algorithm (RMA). Finally, in performance evaluations, we validate the accuracy of the closed-form expression of the average offloading success probability by Monte Carlo simulations, as well as the effectiveness of the proposed algorithms.

cs.NI↗

arXiv2023

Less Carbon Footprint in Edge Computing by Joint Task Offloading and Energy Sharing

In sprite the state-of-the-art, significantly reducing carbon footprint (CF) in communications systems remains urgent. We address this challenge in the context of edge computing. The carbon intensity of electricity supply largely varies spatially as well as temporally. This, together with energy sharing via a battery management system (BMS), justifies the potential of CF-oriented task offloading, by redistributing the computational tasks in time and space. In this paper, we consider optimal task scheduling and offloading, as well as battery charging to minimize the total CF. We formulate this CF minimization problem as an integer linear programming model. However, we demonstrate that, via a graph-based reformulation, the problem can be cast as a minimum-cost flow problem. This finding reveals that global optimum can be admitted in polynomial time. Numerical results using real-world data show that optimization can reduce up to 83.3% of the total CF.

cs.DC↗

arXiv2022

Rethinking the Detection Head Configuration for Traffic Object Detection

Multi-scale detection plays an important role in object detection models. However, researchers usually feel blank on how to reasonably configure detection heads combining multi-scale features at different input resolutions. We find that there are different matching relationships between the object distribution and the detection head at different input resolutions. Based on the instructive findings, we propose a lightweight traffic object detection network based on matching between detection head and object distribution, termed as MHD-Net. It consists of three main parts. The first is the detection head and object distribution matching strategy, which guides the rational configuration of detection head, so as to leverage multi-scale features to effectively detect objects at vastly different scales. The second is the cross-scale detection head configuration guideline, which instructs to replace multiple detection heads with only two detection heads possessing of rich feature representations to achieve an excellent balance between detection accuracy, model parameters, FLOPs and detection speed. The third is the receptive field enlargement method, which combines the dilated convolution module with shallow features of backbone to further improve the detection accuracy at the cost of increasing model parameters very slightly. The proposed model achieves more competitive performance than other models on BDD100K dataset and our proposed ETFOD-v2 dataset. The code will be available.

cs.CV↗

arXiv2022

Chiral Quantum Phases and Tricriticality in a Dicke Triangle

The existence of quantum tricriticality and exotic phases are found in a Dicke triangle (TDT) where three cavities, each one containing an ensemble of three-level atoms, are connected to each other through the action of an artificial magnetic field. The conventional superradiant phase (SR) is connected to the normal phase through first- and second-order boundaries, with tricritical points located at the intersection of such boundaries. Apart from the SR phase, a chiral superradiant (CSR) phase is found by tuning the artificial magnetic field. This phase is characterized by a nonzero photon current and its boundary presents chiral tricritical points (CTCPs). Through the study of different critical exponents, we are able to differentiate the universality class of the CTCP and TCP from that of second-order critical points, as well as find distinctive critical behavior among the two different superradiant phases. The TDT can be implemented in various systems, including atoms in optical cavities as well as the circuit QED system, allowing the exploration of a great variety of critical manifolds.

quant-ph↗