Continual configuration tuning in cellular radio access networks (RANs) is critical for maintaining performance, reliability, energy efficiency, and user experience. However, this task remains largely manual in practice. Automating it needs to confront high-dimensional configuration spaces, sparse and biased exploration, strong parameter interactions, and substantial environmental confounding. Existing RAN configuration tuning approaches have limited effectiveness in addressing these challenges. In this paper, we present CausalTune, a novel causal learning framework for automated RAN configuration optimization based on observational telemetry. CausalTune disentangles configuration effects from environmental and operational confounders, generalizes to sparse and previously unseen parameter settings, and captures high-impact multi-parameter interactions. Our key insight is that effective causal inference in operational RANs requires reshaping raw telemetry to expose confounding and learning environment-invariant mechanisms. Guided by this insight, CausalTune employs a multistage pipeline that integrates distributional representation learning, causal modeling, and interaction-aware recommendation. We evaluate CausalTune using 10 months of RAN measurement data from 1M commercial cells of a major cellular operator. Our comparison to state-of-the-art baselines shows that CausalTune achieves up to 3X KPI improvement on the held-out dataset. In terms of causal modeling quality, CausalTune achieves up to 12X lower KPI reconstruction error; on recommended configuration safety, it achieves 4X higher agreement with expert engineers while significantly reducing off-target recommendations. These findings demonstrate the potential of causal learning to enable reliable, scalable, and interpretable RAN configuration tuning.

The forecasting of mobile data not only helps operators proactively perceive the network status, enabling them to arrange and schedule network resources in advance to improve user service quality, but also allows for the on-demand, flexible extrapolation of network changes under different strategies, effectively reducing the trial-and-error costs in the live network. Traditional prediction methods with tailored models for exclusive data types undoubtedly increase the design complexity and deployment costs. In this paper, we propose a Mobile Foundation Model (MobiFM) for data forecasting, which adopts a unified framework to forecast mobile data with diverse types (mobile traffic, users, and wireless channel), various time granularities (hourly and minute-level), and multiple spatial scales (cell-level and grid-level). MobiFM is a generative model built on diffusion and Transformer backbones. It incorporates a memory-network core that flexibly stores large amounts of contextual knowledge from urban environments, network configuration parameters, and spatio-temporal features. In parallel, MobiFM employs Mixture-of-Experts (MoE) networks to specialize and exploit the distinct characteristics of heterogeneous mobile data. We train the MobiFM using 10 real-world datasets with over 200,000 time-series points, totaling more than 1 billion tokens. The experimental results demonstrate that MobiFM achieves improvements of 20.24%, 10.92%, and 6.52% in the forecasting of mobile traffic, users, and wireless channel data, respectively, exhibiting good generalization performance compared to the baselines. Furthermore, based on MobiFM’s forecasting capability, we formulate an energy-saving optimization case, where the experimental results show the MobiFM-based scheme can improve energy efficiency up to 17.9%.

Recent advancements in Large Language Models (LLMs) have expanded their capabilities to multimodal contexts, including comprehensive video understanding.However, processing extensive videos such as 24-hour CCTV footage or full-length films presents significant challenges due to the vast data and processing demands.Traditional methods, like extracting key frames or converting frames to text, often result in substantial information loss.To address these shortcomings, we develop OmAgent, efficiently stores and retrieves relevant video frames for specific queries, preserving the detailed content of videos.Additionally, it features an Divide-and-Conquer Loop capable of autonomous reasoning, dynamically invoking APIs and tools to enhance query processing and accuracy.This approach ensures robust video understanding, significantly reducing information loss.Experimental results affirm OmAgent's efficacy in handling various types of videos and complex tasks.Moreover, we have endowed it with greater autonomy and a robust tool-calling system, enabling it to accomplish even more intricate tasks.Code:

Acquiring downlink channel state information (CSI) is crucial for optimizing performance in massive Multiple Input Multiple Output (MIMO) systems operating under Frequency Division Duplexing (FDD). Most cellular wireless communication systems employ codebook-based precoder designs, which offer advantages such as simpler, more efficient feedback mechanisms and reduced feedback overhead. Common codebook-based approaches include Type II and eType II precoding methods defined in the 3GPP standards. Feedback in these systems is typically standardized per subband (SB), allowing user equipment (UE) to select the optimal precoder from the codebook for each SB, thereby reducing feedback overhead. However, this subband-level feedback resolution may not suffice for frequency-selective channels. This paper addresses this issue by introducing an uplink CSI-assisted precoder upsampling module deployed at the gNodeB. This module upsamples SB-level precoders to resource block (RB)-level precoders, acting as a plug-in compatible with existing gNodeB or base stations.

The surge in popularity of 3D scene synthesis has driven the development of diverse methods for assessing the quality of synthesized scenes. While subjective assessment methods are widespread, their time-consuming and labor-intensive nature prompts exploration into more efficient objective alternatives. This paper introduces an objective approach to evaluating scene plausibility, aiming to overcome the limitations associated with subjective methods. To underpin our objective evaluation, we present the 3D-SPAD dataset, comprising plausibility scores for 3000 scenes across 46 object categories. Leveraging this dataset, we propose a graph attention-based network designed to accurately estimate scene plausibility. A comprehensive evaluation of our network is conducted through a series of experiments, showcasing its feasibility and reliability. For additional details and access to the code, please refer to our GitHub repository athttps://github.com/Mayibo-cuc/3D-SPAN.

5G networks, with their notable energy consumption, pose a significant challenge. Traditional energy-saving methods, effective for 4G, struggle in heterogeneous 4G and 5G networks. In this paper, we propose the pRoactivE Data-drivEn Energy Saving Method (REDEEM) to mitigate energy consumption in heterogeneous 4G and 5G mobile networks. REDEEM spatially divides the network into meshes based on cell overlaps, predicts cell traffic for proactive control, and selects active cells within each mesh. Our framework includes energy efficiency profiling for each mesh and offloads 5G traffic onto overlapping 4G cells to reduce 5G energy usage. Experiments based on the Nanchang mobile networks validate REDEEM’s effectiveness, yielding energy savings of 3442.72 MWh over a week. Notably, our approach achieves a 53.10% energy-saving rate, surpassing threshold-based methods by 38.85%, optimization-based methods by 18.15%, and fluid capacity engine by 14.79%. It minimally impacts service quality, with less than four parts per million traffic missed. Experimental results also demonstrate REDEEM’s robustness across various temporal, spatial, and traffic load scenarios.

Automated Machine Learning (AutoML) systems are emerging that automatically search for possible solutions from a large space of possible kinds of models. Although fully automated machine learning is appropriate for many applications, users often have knowledge that supplements and constraints the available data and solutions. This paper proposes human-guided machine learning (HGML) as a hybrid approach where a user interacts with an AutoML system and tasks it to explore different problem settings that reflect the user's knowledge about the data available. We present: 1) a task analysis of HGML that shows the tasks that a user would want to carry out, 2) a characterization of two scientific publications, one in neuroscience and one in political science, in terms of how the authors would search for solutions using an AutoML system, 3) requirements for HGML based on those characterizations, and 4) an assessment of existing AutoML systems in terms of those requirements.