Artificial Intelligence for Robust and Scalable Wireless Communication
Bibliographic record
Abstract
Artificial Intelligence (AI) has emerged as a key enabler of next-generation wireless communication, particularly in optimizing resource allocation, user localization, and beamforming in millimeter-wave (mmWave) and multiple-input multiple-output (MIMO) systems. These high-frequency networks face inherent challenges such as severe path loss, sensitivity to user mobility, and the need for precise beam alignment. Traditional signal processing techniques often struggle to maintain performance under such dynamic and uncertain conditions, motivating the integration of machine learning to achieve more adaptive and intelligent wireless systems.In this work, we investigated multiple AI-driven approaches for enhancing wireless communication. First, we studied user localization in mmWave systems equipped with MIMO antennas and reflective intelligent surfaces. Using MATLAB-based equation modeling, we validated localization strategies and subsequently developed a Python interface to visualize real-time beam directions and user positions. Building on this, we explored computer vision techniques to further improve user localization and dynamically adjust beam steering in response to user mobility.Beyond system-level implementations, we also explored the role of foundation models in wireless applications, focusing on their ability to generalize from limited data and remain robust to imperfect or noisy inputs. To achieve this, we optimized a transformer-based architecture through masking-based self-supervision and evaluated its performance across downstream communication tasks. Our results suggest that integrating foundation models with traditional wireless architectures can significantly enhance both adaptability and reliability, paving the way for AI-augmented communication systems that are scalable and resilient to real-world challenges.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".