6g

论文提出一种6G无线接入网的隐私保护意图履约与验证架构，仅依赖声明的意图类别和标准O1小区级计数器进行资源分配与验证，并通过数据处理不等式给出隐私泄露上界，在四个运营商网络的生产数据上验证了检测性能与隐私权衡。

论文对比了 Jev-1.13.0 等决策模型与大型语言模型在 6G Open RAN RIC 中解释网络意图并生成 A1 策略的性能：LLM 因延迟过高（中位 0.286–2.35 秒）几乎无法满足 1 秒近实时预算，而 Jev 在 99.8% 的调用中达标，且未显示出优于 Jev 的 SLA 改善。

This paper explores the feasibility of a 7G mobile generation, arguing that it should only be justified if post-6G systems introduce unmet needs or coordination challenges beyond 6G and complementary technologies. It proposes a readiness framework to evaluate potential 7G discontinuities like agentic networks and quantum-enabled interworking.

ANP has been listed as a candidate protocol in 3GPP’s study of AI protocols for 6G, highlighting advancements in AI integration for future networks.

This paper presents a systematic machine learning study of 6G-IoT beamforming optimization, comparing network, environmental, device, and vision feature groups for predictive power, and applying clustering methods to enhance performance.

3GPP has completed Release 19, the second 5G-Advanced specification, setting the stage for future 6G studies in Release 20.

Proposes a VAE-based multi-task semantic communication framework for satellite-assisted autonomous driving, achieving significant bandwidth reduction while maintaining performance for traffic sign reconstruction and classification.

This paper presents a tutorial on using Joint-Embedding Predictive Architecture (JEPA) for self-supervised learning in 6G networks, along with a beam management case study and open challenges.

This survey classifies 78 joint OFDM-RIS optimization works into four paradigms, from convex relaxation to foundation models, and identifies open challenges for 6G networks.

This paper proposes a randomized anchoring strategy to mitigate anchoring bias in LLM-based agents for energy-efficient 6G autonomous networks, achieving up to 25% energy savings using a lightweight 1B-parameter model.

This paper presents an open-source NWDAF compatible with Free5GC that integrates an LLM interface for natural language interaction and intent-based network management, aiming toward AI-native 6G networks.

PilotWiMAE introduces a self-supervised framework that directly ingests noisy pilot observations for wireless channel representation learning, removing the unrealistic full-CSI assumption and enabling robust cross-frequency beam selection and channel estimation that beats supervised baselines.

This paper presents a visionary framework for AI-native 6G networks, proposing a unified foundation model and collaborative multi-agent systems to achieve autonomous, resilient network management beyond fragmented 5G approaches.