Searcharxiv⌕ Search

arXiv subjects

Feiran You

Publications and source records attributed to Feiran You.

11 recordsLinked to original sources

CommJEPA: When Predictive Representation Learning Meets Wireless Intelligence

Artificial intelligence (AI) is becoming an integral part of wireless systems, yet much of today's wireless AI remains task-specific and reactive, with models typically trained to map current observations to predefined outputs or reconstruct observed data. While effective for individual tasks, such approaches provide limited support for learning what is predictable, reusable, and transferable in dynamic wireless environments. Joint-Embedding Predictive Architecture (JEPA) offers a different perspective by learning predictive representations in latent space that capture informative structure in the observations. In this article, we introduce Communication JEPA (CommJEPA) as a communication-oriented framework for predictive representation learning. The central idea is bidirectional. JEPA can equip wireless systems with predictive representations for capturing latent channel and environmental dynamics, integrating heterogeneous observations, adapting to changing conditions, and supporting future decisions. Conversely, the physical structure, partial observability, multiple time scales, action-dependent evolution, and resource constraints of wireless systems motivate new communication-aware JEPA designs. We develop this mutual perspective, organize the resulting design space, and discuss representative JEPA-based wireless instantiations for prediction and control. We further highlight open challenges toward scalable, interactive, and predictive wireless intelligence.

cs.NI↗

CORMA: Constraint-Routed Decision Mamba for Generalizable Multi-Constraint Offline Safe Reinforcement Learning

Offline safe reinforcement learning (RL) learns safety-aware policies from static datasets while satisfying safety constraints during deployment. Motivated by the strong trajectorymodeling capabilities of Transformers, recent Decision Transformer (DT)-based methods formulate offline safe RL as conditional sequence modeling by conditioning action generation on return-to-go (RTG) and cost-to-go (CTG) tokens, thereby enabling adaptation to varying safety budgets. However, existing DT-based methods are developed for single-constraint tasks. For tasks with multiple constraints, generalizing learned policies to unseen combinations of safety budgets remains challenging due to the conflicting requirements imposed by heterogeneous constraints. Moreover, the quadratic complexity of Transformer architectures significantly increases the computational overhead in multi-constraint tasks, as representing additional constraints requires more CTG tokens. Recently, Mamba has emerged as an efficient sequence-modeling backbone, offering linear computational complexity and strong generalization capabilities. In this paper, we propose CORMA, a constraint-routed decision Mamba framework for generalizable multi-constraint offline safe RL. CORMA decomposes policy inference into constraint-aware RTG estimation and adaptive action generation, where constraint-specific experts model feasible RTG distributions and a router-guided product-of-experts mechanism fuses these distributions to provide safety-aware guidance for a Mamba-based action decoder. A three-stage optimization strategy is designed to improve training stability. Extensive experiments on OSRL benchmarks demonstrate that CORMA achieves superior reward-safety trade-offs, reduces inference latency by 37% compared with DT-based methods, and exhibits stronger zero-shot generalization to unseen safety-budget combinations than offline safe RL baselines.

cs.LG↗

DT-JEPA: Learning to Predict Future Representations for Decision-Making

Decision Transformer (DT) has demonstrated strong performance in various offline reinforcement learning (RL) tasks by conditioning action generation on expected future returns and historical trajectories. However, treating expected future returns as the condition provides an incomplete description of the future, as trajectories with different state transitions and behaviors may share similar returns. Moreover, expected future returns inherently depend on task-specific reward functions, which makes policy learning reliant on reward-labeled datasets and restricts its scalability to tasks with similar but unseen rewards. Recently, Joint Embedding Predictive Architectures (JEPA) have emerged as a promising paradigm of self-supervised learning-based world models, which learn predictive representations of future dynamics in latent space rather than reconstructing future states in the original space. Inspired by JEPA, we propose DT-JEPA, an offline pretraining and online fine-tuning framework that learns general knowledge from reward-free offline trajectories and achieves excellent adaptation to unseen tasks. Instead of predicting a single deterministic future embedding, we design a novel probabilistic predictor to model the conditional distribution of future representations in the latent space, thereby capturing both predictive information and uncertainty about future dynamics. Theoretically, we show that 1) the JEPA objective seeks to maximize a variational lower bound on the mutual information between historical representations and future trajectories; and 2) predictive future-conditioned policy learning admits a finite-sample performance bound with an O(N-1/4) estimation term. Experiments on D4RL benchmarks demonstrate that DT-JEPA achieves efficient adaptation across varying offline RL tasks, outperforming traditional DT-based and other offline RL methods.

cs.LG↗

TwinJEPA: Action-Preferred Predictive Representations for Goal-Conditioned Control

Joint-Embedding Predictive Architectures (JEPAs) are a promising paradigm for representation learning by predicting future latent states without reconstructing observations. Recent work has adapted JEPA-style latent prediction to offline zero-shot control through action-conditioned temporal prediction, enabling representations to capture long-horizon dynamics from fixed behavioral data. However, transition-level predictive objectives supervise actions in isolation and provide limited information about which actions are preferable when similar states admit different goal-conditioned outcomes. We introduce TwinJEPA, a framework for learning action-preferred predictive representations by augmenting JEPA-based control with offline-mined action-preference supervision. TwinJEPA identifies approximately matched states across offline trajectories and constructs preference pairs via goal-conditioned reward relabeling. It then learns two complementary objectives: reward-gap regression, which preserves the magnitude of outcome differences, and preference classification, which captures the relative ordering of alternative actions. Both objectives are used only during training and incur no additional inference-time cost. We evaluate TwinJEPA on long-horizon navigation and continuous-control benchmarks with state- and pixel-based observations. TwinJEPA yields positive benchmark-level mean differences across all matched state-based evaluations, while analyses across domains and observation modalities indicate that larger gains tend to arise when local action alternatives provide more informative outcome contrasts. The results suggest that local action-comparison supervision can complement temporal prediction by encouraging JEPA-based representations to retain both long-horizon temporal structure and fine-grained distinctions among locally observed actions for offline zero-shot control.

eess.SY↗

FARM: Fundamental Agentic Reward Model For Multi-task Wireless Network Optimization

Future wireless networks require learning agents to adapt across heterogeneous channel conditions, traffic patterns, quality-of-service (QoS) requirements, objectives, and operational constraints. Reusing decision knowledge across such tasks is challenging because conventional multi-task and transfer reinforcement learning methods primarily share or transfer policies, coupling transferable knowledge with task-dependent action mappings. This paper proposes FARM (Fundamental Agentic Reward Model for Multi-task Wireless Network Optimization), a reward-space transfer framework that shifts cross-task knowledge reuse from policy space to trajectory-level decision evaluation. FARM introduces an Agentic Reward Model (ARM) that learns a task-conditioned reward prior from heterogeneous source-task trajectories and provides auxiliary guidance for task-specific policy optimization. In Stage I, ARM jointly models task conditions, temporal trajectory dependencies, and objective-dependent reward structures while each source task retains its own controller. In Stage II, the learned reward prior is frozen and reused to guide the adaptation of a target-specific controller for previously unseen tasks, without transferring source-task policies. Experiments on heterogeneous multi-access edge computing (MEC) tasks show that FARM achieves a mean late-stage gain of 29.8% over Single-task SAC on unseen Rate-Latency targets, compared with 16.1% for CRA Transfer, and reaches a 46.2% gain on the moderate-OOD FAR-M case. Further analysis shows that both Mamba and Transformer trajectory encoders support Reward-Space Transfer, while Mamba provides improved robustness as longer history dependencies are introduced.

eess.SY↗

ReaCritic: Reasoning Transformer-based DRL Critic-model Scaling For Wireless Networks

Heterogeneous Networks (HetNets) pose critical challenges for intelligent management due to the diverse user requirements and time-varying wireless conditions. These factors introduce significant decision complexity, which limits the adaptability of existing Deep Reinforcement Learning (DRL) methods. In many DRL algorithms, especially those involving value-based or actor-critic structures, the critic component plays a key role in guiding policy learning by estimating value functions. However, conventional critic models often use shallow architectures that map observations directly to scalar estimates, limiting their ability to handle multi-task complexity. In contrast, recent progress in inference-time scaling of Large Language Models (LLMs) has shown that generating intermediate reasoning steps can significantly improve decision quality. Motivated by this, we propose ReaCritic, a reasoning transformer-based critic-model scaling scheme that brings reasoning-like ability into DRL. ReaCritic performs horizontal reasoning over parallel state-action inputs and vertical reasoning through deep transformer stacks. It is compatible with a broad range of value-based and actor-critic DRL algorithms and enhances generalization in dynamic wireless environments. Extensive experiments demonstrate that ReaCritic improves convergence speed and final performance across various HetNet settings and standard OpenAI Gym control tasks. The code of ReaCritic is available at https://github.com/NICE-HKU/ReaCritic.

cs.LG↗

StarSD: One-for-Many Speculative Decoding

Speculative decoding accelerates autoregressive generation by separating token proposal from verification, but most existing approaches are designed for single-node execution and do not scale well to multi-accelerator clusters used for serving modern Large Language Models (LLMs). We present StarSD, a one-for-many speculative decoding framework that uses a single draft model to serve multiple target models across distributed nodes via a star topology. StarSD decouples drafting and verification, enabling effective sharing of draft computation, and preventing distributed accelerators from remaining idle under bursty workloads. We provide a system-level analysis that characterizes when and why a single draft model can remain fully utilized by multiple verifiers, yielding predictable latency and utilization gains. Extensive experiments in real-world distributed inference settings demonstrate that StarSD simplifies deployment and supports flexible resource allocation across heterogeneous accelerators, while maintaining output quality. These results indicate that StarSD is a practical and scalable framework for bringing speculative decoding to modern cloud and edge inference infrastructures.

eess.SY↗

Ubiquitous Intelligence Via Wireless Network-Driven LLMs Evolution

We introduce ubiquitous intelligence as a paradigm where Large Language Models (LLMs) evolve within wireless network-driven ecosystems. Unlike static model deployments, this approach enables scalable and continuous intelligence ascension through coordination between networks and LLMs. Wireless networks support system-orchestrated lifelong learning, while LLMs drive the next-generation network development that is more adaptive and responsive. This co-evolution highlights a shift toward self-improving systems, sustaining capability growth across diverse and resource-constrained environments.

cs.NI↗

JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services

Large Language Models (LLMs) are increasingly integrated into mobile services over wireless networks to support complex user requests. This trend has led to longer prompts, which improve LLMs' performance but increase data transmission costs and require more processing time, thereby reducing overall system efficiency and negatively impacting user experience. To address these challenges, we propose Joint Prompt and Power Optimization (JPPO), a framework that jointly optimizes prompt compression and wireless transmission power for mobile LLM services. JPPO leverages a Small Language Model (SLM) deployed at edge devices to perform lightweight prompt compression, reducing communication load before transmission to the cloud-based LLM. A Deep Reinforcement Learning (DRL) agent dynamically adjusts both the compression ratio and transmission power based on network conditions and service constraints, aiming to minimize service time while preserving response fidelity. We further extend the framework to JPPO++, which introduces a denoising-inspired compression scheme. This design performs iterative prompt refinement by progressively removing less informative tokens, allowing for more aggressive yet controlled compression. Experimental results show that JPPO++ reduces service time by 17% compared to the no-compression baseline while maintaining output quality. Under compression-prioritized settings, a reduction of up to 16x in prompt length can be achieved with an acceptable loss in accuracy. Specifically, JPPO with a 16x ratio reduces total service time by approximately 42.3%, and JPPO++ further improves this reduction to 46.5%.

cs.NI↗

DRESS: Diffusion Reasoning-based Reward Shaping Scheme For Intelligent Networks

Network optimization remains fundamental in wireless communications, with Artificial Intelligence (AI)-based solutions gaining widespread adoption. As Sixth-Generation (6G) communication networks pursue full-scenario coverage, optimization in complex extreme environments presents unprecedented challenges. The dynamic nature of these environments, combined with physical constraints, makes it difficult for AI solutions such as Deep Reinforcement Learning (DRL) to obtain effective reward feedback for the training process. However, many existing DRL-based network optimization studies overlook this challenge through idealized environment settings. Inspired by the powerful capabilities of Generative AI (GenAI), especially diffusion models, in capturing complex latent distributions, we introduce a novel Diffusion Reasoning-based Reward Shaping Scheme (DRESS) to achieve robust network optimization. By conditioning on observed environmental states and executed actions, DRESS leverages diffusion models' multi-step denoising process as a form of deep reasoning, progressively refining latent representations to generate meaningful auxiliary reward signals that capture patterns of network systems. Moreover, DRESS is designed for seamless integration with any DRL framework, allowing DRESS-aided DRL (DRESSed-DRL) to enable stable and efficient DRL training even under extreme network environments. Experimental results demonstrate that DRESSed-DRL achieves about 1.5x times faster convergence than its original version in sparse-reward wireless environments and significant performance improvements in multiple general DRL benchmark environments compared to baseline methods. The code of DRESS is available at https://github.com/NICE-HKU/DRESS.

cs.NI↗

JPPO: Joint Power and Prompt Optimization for Accelerated Large Language Model Services

Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, leading to their increasing deployment in wireless networks for a wide variety of user services. However, the growing longer prompt setting highlights the crucial issue of computational resource demands and huge communication load. To address this challenge, we propose Joint Power and Prompt Optimization (JPPO), a framework that combines Small Language Model (SLM)-based prompt compression with wireless power allocation optimization. By deploying SLM at user devices for prompt compression and employing Deep Reinforcement Learning for joint optimization of compression ratio and transmission power, JPPO effectively balances service quality with resource efficiency. Experimental results demonstrate that our framework achieves high service fidelity and low bit error rates while optimizing power usage in wireless LLM services. The system reduces response time by about 17%, with the improvement varying based on the length of the original prompt.

eess.AS↗