arXiv subjects

Xuyang Chen

Publications and source records attributed to Xuyang Chen.

At least 37 records · Page 2Linked to original sources

arXiv2026

VIPO: Value Function Inconsistency Penalized Offline Reinforcement Learning

Offline reinforcement learning (RL) learns effective policies from pre-collected datasets, offering a practical solution for applications where online interactions are risky or costly. Model-based approaches are particularly advantageous for offline RL, owing to their data efficiency and generalizability. However, due to inherent model errors, model-based methods often artificially introduce conservatism guided by heuristic uncertainty estimation, which can be unreliable. In this paper, we introduce VIPO, a novel model-based offline RL algorithm that incorporates self-supervised feedback from value estimation to enhance model training. Specifically, the model is learned by additionally minimizing the inconsistency between the value learned directly from the offline data and the value estimated from the model. We perform comprehensive evaluations from multiple perspectives to show that VIPO can learn a highly accurate model efficiently and consistently outperform existing methods. In particular, it achieves state-of-the-art performance on almost all tasks in both D4RL and NeoRL benchmarks. Overall, VIPO offers a general framework that can be readily integrated into existing model-based offline RL algorithms to systematically enhance model accuracy.

cs.LG↗

arXiv2026

OpenClaw-RL: Train Any Agent Simply by Talking

Every agent interaction generates a next-state signal, namely the user reply, tool output, terminal or GUI state change that follows each action, yet no existing agentic RL system recovers it as a live, online learning source. We present OpenClaw-RL, a framework that employs next-state signals to optimize personal agents online through infrastructure and methodology innovations. On the infrastructure side, we extend existing RL systems to a server-client architecture where the RL server hosts the policy behind an inference API and user terminals stream interaction data back over HTTP. From each observed next state, the system extracts two complementary training signals, evaluative and directive, via a separate asynchronous server so that neither signal extraction nor optimization blocks inference. On the methodology side, we introduce a hybrid RL objective that unifies both signal types in a single update: directive signals provide richer, token-level supervision but are sparser, while evaluative signals are more broadly available. To stabilize distillation under teacher-student mismatch, we propose overlap-guided hint selection, which picks the hint whose induced teacher distribution maximally overlaps with the student's top-$k$ tokens, together with a log-probability-difference clip that bounds per-token advantages. Applied to personal agents, OpenClaw-RL enables an agent to improve simply by being used, recovering conversational signals from user re-queries, corrections, and explicit feedback. Applied to general agents, OpenClaw-RL is the first RL framework to unify real-world agent settings spanning terminal, GUI, SWE, and tool-call environments, where we additionally demonstrate the utility of next-state signals in long-horizon settings.

cs.CL↗

arXiv2026

VTBench: A Multimodal Framework for Time-Series Classification with Chart-Based Representations

Time-series classification (TSC) has advanced significantly with deep learning, yet most models rely solely on raw numerical inputs, overlooking alternative representations. While texture-based encodings such as Gramian Angular Fields (GAF) and Recurrence Plots (RP) convert time series into 2D images, they often require heavy preprocessing and yield less intuitive representations. In contrast, chart-based visualizations offer more interpretable alternatives and show promise in specific domains; however, their effectiveness remains underexplored, with limited systematic evaluation across chart types, visual encoding choices, and datasets. In this work, we introduce VTBench, a systematic and extensible framework that re-examines TSC through multimodal fusion of raw sequences and chart-based visualizations. VTBench generates lightweight, human-interpretable plots -- line, area, bar, and scatter, providing complementary views of the same signal. We develop a modular architecture supporting multiple fusion strategies, including single-chart visual-numerical fusion, multi-chart visual fusion, and full multimodal fusion with raw inputs. Through experiments across 31 UCR datasets, we show that: (1) chart-only models are competitive in selected settings, particularly on smaller datasets; (2) combining multiple chart types can improve accuracy by capturing complementary visual cues; and (3) multimodal models improve or maintain performance when visual features provide non-redundant information, but may degrade accuracy when they introduce redundancy. We further distill practical guidelines for selecting chart types, fusion strategies, and configurations. VTBench establishes a unified foundation for interpretable and effective multimodal time-series classification.

cs.CV↗

arXiv2026

Nonparametric Inference for Balance in Signed Networks

In many real-world networks, relationships often go beyond simple dyadic presence or absence; they can be positive, like friendship, alliance, and mutualism, or negative, characterized by enmity, disputes, and competition. To understand the formation mechanism of such signed networks, the social balance theory sheds light on the dynamics of positive and negative connections. In particular, it characterizes the proverbs, "a friend of my friend is my friend" and "an enemy of my enemy is my friend". In this work, we propose a nonparametric inference approach for assessing empirical evidence for the balance theory in real-world signed networks. We first characterize the generating process of signed networks with node exchangeability and propose a nonparametric sparse signed graphon model. Under this model, we construct confidence intervals for the population parameters associated with balance theory and establish their theoretical validity. Our inference procedure is as computationally efficient as a simple normal approximation but offers higher-order accuracy. By applying our method, we find strong real-world evidence for balance theory in signed networks across various domains, extending its applicability beyond social psychology.

stat.ME↗

arXiv2026

Semantic Transmission Framework in Direct Satellite Communications

Insufficient link budget has become a bottleneck problem for direct access in current satellite communications. In this paper, we develop a semantic transmission framework for direct satellite communications as an effective and viable solution to tackle this problem. To measure the tradeoffs between communication, computation, and generation quality, we introduce a semantic efficiency metric with optimized weights. The optimization aims to maximize the average semantic efficiency metric by jointly optimizing transmission mode selection, satellite-user association, ISL task migration, denoising steps, and adaptive weights, which is a complex nonlinear integer programming problem. To maximize the average semantic efficiency metric, we propose a decision-assisted REINFORCE++ algorithm that utilizes feasibility-aware action space and a critic-free stabilized policy update. Numerical results show that the proposed algorithm achieves higher semantic efficiency than baselines.

cs.IT↗

arXiv2026

QoE-Driven Multi-Task Offloading for Semantic-Aware Edge Computing Systems

Mobile edge computing (MEC) provides low-latency offloading solutions for computationally intensive tasks, effectively improving the computing efficiency and battery life of mobile devices. However, for data-intensive tasks or scenarios with limited uplink bandwidth, network congestion might occur due to massive simultaneous offloading nodes, increasing transmission latency and affecting task performance. In this paper, we propose a semantic-aware multi-modal task offloading framework to address the challenges posed by limited uplink bandwidth. By introducing a semantic extraction factor, we balance the relationship among transmission latency, computation energy consumption, and task performance. To measure the offloading performance of multi-modal tasks, we design a unified and fair quality of experience (QoE) metric that includes execution latency, energy consumption, and task performance. Lastly, we formulate the optimization problem as a Markov decision process (MDP) and exploit the multi-agent proximal policy optimization (MAPPO) reinforcement learning algorithm to jointly optimize the semantic extraction factor, communication resources, and computing resources to maximize overall QoE. Experimental results show that the proposed method achieves a reduction in execution latency and energy consumption of 18.1% and 12.9%, respectively compared with the semantic-unaware approach. Moreover, the proposed approach can be easily extended to models with different user preferences.

cs.NI↗

arXiv2025

Are Bus-Mounted Edge Servers Feasible?

Placement of edge servers is the prerequisite of provisioning edge computing services for Internet of Vehicles (IoV). Fixed-site edge servers at Road Side Units (RSUs) or base stations are able to offer basic service coverage for end users, i.e., vehicles on road. However, the server locations and capacity are fixed after deployment, rendering their inefficiency in handling spationtemporal user dynamics. Mobile servers such as buses, on the other hand, have the potential of adding computation elasticity to such system. To this end, this paper studies the feasibility of bus-mounted edge servers based on real traces. First, we investigate the coverage of the buses and base stations using the Shanghai bus/taxi/Telecom datasets, which shows a great potential of bus-based edge servers as they cover a great portion of geographic area and demand points. Next, we build a mathematical model and design a simple greedy heuristic algorithm to select a limited number of buses that maximizes the coverage of demand points, i.e., with a limited purchase budget. We perform trace-driven simulations to verify the performance of the proposed bus selection algorithm. The results show that our approach effectively handles the dynamic user demand under realistic constraints such as server capacity and purchase quantity. Thus, we claim: bus-mounted edge servers for vehicular networks in urban areas are feasible, beneficial, and valuable.

cs.DC↗

arXiv2025

Preference-Guided Reinforcement Learning for Efficient Exploration

In this paper, we investigate preference-based reinforcement learning (PbRL), which enables reinforcement learning (RL) agents to learn from human feedback. This is particularly valuable when defining a fine-grain reward function is not feasible. However, this approach is inefficient and impractical for promoting deep exploration in hard-exploration tasks with long horizons and sparse rewards. To tackle this issue, we introduce LOPE: \textbf{L}earning \textbf{O}nline with trajectory \textbf{P}reference guidanc\textbf{E}, an end-to-end preference-guided RL framework that enhances exploration efficiency in hard-exploration tasks. Our intuition is that LOPE directly adjusts the focus of online exploration by considering human feedback as guidance, thereby avoiding the need to learn a separate reward model from preferences. Specifically, LOPE includes a two-step sequential policy optimization technique consisting of trust-region-based policy improvement and preference guidance steps. We reformulate preference guidance as a trajectory-wise state marginal matching problem that minimizes the maximum mean discrepancy distance between the preferred trajectories and the learned policy. Furthermore, we provide a theoretical analysis to characterize the performance improvement bound and evaluate the effectiveness of the LOPE. When assessed in various challenging hard-exploration environments, LOPE outperforms several state-of-the-art methods in terms of convergence rate and overall performance.The code used in this study is available at https://github.com/buaawgj/LOPE.

cs.LG↗

arXiv2025

Taming OOD Actions for Offline Reinforcement Learning: An Advantage-Based Approach

Offline reinforcement learning (RL) learns policies from fixed datasets without online interactions, but suffers from distribution shift, causing inaccurate evaluation and overestimation of out-of-distribution (OOD) actions. Existing methods counter this by conservatively discouraging all OOD actions, which limits generalization. We propose Advantage-based Diffusion Actor-Critic (ADAC), which evaluates OOD actions via an advantage-like function and uses it to modulate the Q-function update discriminatively. Our key insight is that the (state) value function is generally learned more reliably than the action-value function; we thus use the next-state value to indirectly assess each action. We develop a PointMaze environment to clearly visualize that advantage modulation effectively selects superior OOD actions while discouraging inferior ones. Moreover, extensive experiments on the D4RL benchmark show that ADAC achieves state-of-the-art performance, with especially strong gains on challenging tasks.

cs.LG↗

arXiv2025

Box2Poly: Memory-Efficient Polygon Prediction of Arbitrarily Shaped and Rotated Text

Recently, Transformer-based text detection techniques have sought to predict polygons by encoding the coordinates of individual boundary vertices using distinct query features. However, this approach incurs a significant memory overhead and struggles to effectively capture the intricate relationships between vertices belonging to the same instance. Consequently, irregular text layouts often lead to the prediction of outlined vertices, diminishing the quality of results. To address these challenges, we present an innovative approach rooted in Sparse R-CNN: a cascade decoding pipeline for polygon prediction. Our method ensures precision by iteratively refining polygon predictions, considering both the scale and location of preceding results. Leveraging this stabilized regression pipeline, even employing just a single feature vector to guide polygon instance regression yields promising detection results. Simultaneously, the leverage of instance-level feature proposal substantially enhances memory efficiency (>50% less vs. the state-of-the-art method DPText-DETR) and reduces inference speed (>40% less vs. DPText-DETR) with minor performance drop on benchmarks.

cs.CV↗

arXiv2025

Watermark in the Classroom: A Conformal Framework for Adaptive AI Usage Detection

As artificial intelligence tools become ubiquitous in education, maintaining academic integrity while accommodating pedagogically beneficial AI assistance presents unprecedented challenges. Current AI detection systems fail to control false positive rates (FPR) and suffer from bias against minority student groups, prompting institutional suspensions of these technologies. Watermarking techniques offer statistical rigor through precise $p$-values but remain untested in educational contexts where students may use varying levels of permitted AI edits. We present the first adaptation of watermarking-based detection methods for classroom settings, introducing conformal methods that effectively control FPR across diverse classroom settings. Using essays from native and non-native English speakers, we simulate seven levels of AI editing interventions--from grammar correction to content expansion--across multiple language models and watermarking schemes, and evaluate our proposal under these different setups. Our findings provide educators with quantitative frameworks to enforce academic integrity standards while embracing AI integration in the classroom.

stat.AP↗

arXiv2025

Exploration and Comparison: Development and Implementation of Multiple Ultrasound Imaging Modalities

Ultrasound imaging, as a noninvasive, real-time, and low-cost modality, plays a vital role in clinical diagnosis, catheterization intervention, and portable devices. With the development of transducer hardware and the continuous progress of imaging algorithms, how to realize high-quality image reconstruction in different application scenarios has become a research focus.This project focuses on the systematic research and implementation of three typical ultrasound imaging modalities - line array imaging, endoscopic imaging and plane wave imaging, covering simulation data processing, imaging algorithm implementation and real data validation, etc., aiming to deepen the understanding of the principles and processes of various types of imaging.

physics.med-ph↗

arXiv2025

QoE Optimization for Semantic Self-Correcting Video Transmission in Multi-UAV Networks

Real-time unmanned aerial vehicle (UAV) video streaming is essential for time-sensitive applications, including remote surveillance, emergency response, and environmental monitoring. However, it faces challenges such as limited bandwidth, latency fluctuations, and high packet loss. To address these issues, we propose a novel semantic self-correcting video transmission framework with ultra-fine bitrate granularity (SSCV-G). In SSCV-G, video frames are encoded into a compact semantic codebook space, and the transmitter adaptively sends a subset of semantic indices based on bandwidth availability, enabling fine-grained bitrate control for improved bandwidth efficiency. At the receiver, a spatio-temporal vision transformer (ST-ViT) performs multi-frame joint decoding to reconstruct dropped semantic indices by modeling intra- and inter-frame dependencies. To further improve performance under dynamic network conditions, we integrate a multi-user proximal policy optimization (MUPPO) reinforcement learning scheme that jointly optimizes communication resource allocation and semantic bitrate selection to maximize user Quality of Experience (QoE). Extensive experiments demonstrate that the proposed SSCV-G significantly outperforms state-of-the-art video codecs in coding efficiency, bandwidth adaptability, and packet loss robustness. Moreover, the proposed MUPPO-based QoE optimization consistently surpasses existing benchmarks.

eess.IV↗

arXiv2025

Deep Reinforcement Learning-Based Resource Allocation for Hybrid Bit and Generative Semantic Communications in Space-Air-Ground Integrated Networks

In this paper, we introduce a novel framework consisting of hybrid bit-level and generative semantic communications for efficient downlink image transmission within space-air-ground integrated networks (SAGINs). The proposed model comprises multiple low Earth orbit (LEO) satellites, unmanned aerial vehicles (UAVs), and ground users. Considering the limitations in signal coverage and receiver antennas that make the direct communication between satellites and ground users unfeasible in many scenarios, thus UAVs serve as relays and forward images from satellites to the ground users. Our hybrid communication framework effectively combines bit-level transmission with several semantic-level image generation modes, optimizing bandwidth usage to meet stringent satellite link budget constraints and ensure communication reliability and low latency under low signal-to-noise ratio (SNR) conditions. To reduce the transmission delay while ensuring reconstruction quality for the ground user, we propose a novel metric to measure delay and reconstruction quality in the proposed system, and employ a deep reinforcement learning (DRL)-based strategy to optimize resource allocation in the proposed network. Simulation results demonstrate the superiority of the proposed framework in terms of communication resource conservation, reduced latency, and maintaining high image quality, significantly outperforming traditional solutions. Therefore, the proposed framework can ensure that real-time image transmission requirements in SAGINs, even under dynamic network conditions and user demand.

cs.IT↗

arXiv2025

The Communication and Computation Trade-off in Wireless Semantic Communications

Semantic communications have emerged as a crucial research direction for future wireless communication networks. However, as wireless systems become increasingly complex, the demands for computation and communication resources in semantic communications continue to grow rapidly. This paper investigates the trade-off between computation and communication in wireless semantic communications, taking into consideration transmission task delay and performance constraints within the semantic communication framework. We propose a novel tradeoff metric to analyze the balance between computation and communication in semantic transmissions and employ the deep reinforcement learning (DRL) algorithm to minimize this metric, thereby reducing the cost associated with balancing computation and communication. Through simulations, we analyze the tradeoff between computation and communication and demonstrate the effectiveness of optimizing this trade-off metric.

eess.SP↗

arXiv2025

Global Optimality of Single-Timescale Actor-Critic under Continuous State-Action Space: A Study on Linear Quadratic Regulator

Actor-critic methods have achieved state-of-the-art performance in various challenging tasks. However, theoretical understandings of their performance remain elusive and challenging. Existing studies mostly focus on practically uncommon variants such as double-loop or two-timescale stepsize actor-critic algorithms for simplicity. These results certify local convergence on finite state- or action-space only. We push the boundary to investigate the classic single-sample single-timescale actor-critic on continuous (infinite) state-action space, where we employ the canonical linear quadratic regulator (LQR) problem as a case study. We show that the popular single-timescale actor-critic can attain an epsilon-optimal solution with an order of epsilon to -2 sample complexity for solving LQR on the demanding continuous state-action space. Our work provides new insights into the performance of single-timescale actor-critic, which further bridges the gap between theory and practice.

cs.LG↗

arXiv2024

Strong local variational approach for superconductivity theory, and the principles of coherent interaction and action-counteraction

For the two-mode electron pairing, we propose a local stacking force pairing mechanism driven by strong local fluctuations, with two straight pairing orbits where the tying Cooper pairing $C_{-k\downarrow}C_{k\uparrow}e^{ik\cdot r}$ replaces the itinerant pairing. Based on coherent interaction and action-counteraction principles, the strong local variational theory is constructed, with the energy extremum and gap equations forming self-consistent pairs, involving the local variational parameter $λ$, energy gap $Δ$, and the energy cut-off $\hbar ω_0$. As $\hbar ω_0(j)$ approaches its cut-off, $λ$ and $Δ$ converge to fixed values. The theory predicts that the coupling strength $Vg(0)$ reduces to $\tilde{V}g(0)=e^{-\left(1-α_{1}\right)^{2} k^{2} / 4 λ^{2}} Vg(0)$, and the Cooper pair reduces similarly. For weak coupling, $α_1=1$, and when $Vg(0)=0.1$, $Δ_{\mathrm{A \cdot C}}=108 Δ_{\text{BCS}}$, but $Δ_{\mathrm{A \cdot C}}$ decreases to $28 Δ_{\text{BCS}}$ at $Vg(0)=0.2$. For strong coupling, $α_1=0$, if $Vg(0)=1.4$, $\tilde{V} g(0)$ reduces to 0.2, and the smaller Cooper pair $\widetilde{C_{k \uparrow} C_{-k \downarrow}}$ reduces to $0.14 C_{k \uparrow} C_{-k \downarrow}$. Additionally, $Δ_{\mathrm{A \cdot C}} = 0.5676~\text{eV} \gg \hbar ω_{\text{D}}$, and the local stacking force is $\widetilde{V}_{\text{st}}=0.264 ~\text{eV}$. With $k^2/λ^2 =$ const, the local strength increases, causing the stacking force to grow significantly. Thus, $\hbar ω_0$ and $Δ$ yield a unique solution.

cond-mat.supr-con↗

arXiv2024

Contrastive Learning of Shared Spatiotemporal EEG Representations Across Individuals for Naturalistic Neuroscience

Neural representations induced by naturalistic stimuli offer insights into how humans respond to stimuli in daily life. Understanding neural mechanisms underlying naturalistic stimuli processing hinges on the precise identification and extraction of the shared neural patterns that are consistently present across individuals. Targeting the Electroencephalogram (EEG) technique, known for its rich spatial and temporal information, this study presents a framework for Contrastive Learning of Shared SpatioTemporal EEG Representations across individuals (CL-SSTER). CL-SSTER utilizes contrastive learning to maximize the similarity of EEG representations across individuals for identical stimuli, contrasting with those for varied stimuli. The network employed spatial and temporal convolutions to simultaneously learn the spatial and temporal patterns inherent in EEG. The versatility of CL-SSTER was demonstrated on three EEG datasets, including a synthetic dataset, a natural speech comprehension EEG dataset, and an emotional video watching EEG dataset. CL-SSTER attained the highest inter-subject correlation (ISC) values compared to the state-of-the-art ISC methods. The latent representations generated by CL-SSTER exhibited reliable spatiotemporal EEG patterns, which can be explained by properties of the naturalistic stimuli. CL-SSTER serves as an interpretable and scalable framework for the identification of inter-subject shared neural representations in naturalistic neuroscience.

q-bio.NC↗