Bio

I am a Postdoctoral Researcher at KTH Royal Institute of Technology in Stockholm, Sweden. My research lies at the intersection of artificial intelligence, machine learning, optimization, and wireless communication systems, with a focus on developing intelligent, autonomous, and energy-efficient networks. I work on learning and decision-making methods that enable communication systems to understand their environment, anticipate future network conditions, coordinate distributed actions, and allocate resources according to the value of the information being transmitted. My research spans reinforcement learning, self-supervised and predictive representation learning, multi-agent systems, explainable AI, forecasting, and data-driven optimization.

I received my Ph.D. in Information and Communication Technology from KTH in 2025. My doctoral thesis, AI-Assisted Mobility Management for Cellular-Connected UAVs, developed model-based and learning-based methods for reliable UAV connectivity, mobility management, and network optimization. From 2023 to 2024, I was a Visiting Student Research Collaborator at Princeton University, where I worked with Prof. H. Vincent Poor. I received my M.Sc. in Telecommunication Engineering from Politecnico di Milano, Italy, in 2019, and my B.Tech. in Electronics and Communication Engineering from the National Institute of Technology Srinagar, India, in 2014.

News

• July 2026: Submitted our paper JEPA for AI-Native 6G: Predictive Representations and Open Challenges to IEEE Communications Magazine.
• 2026: Our work on multi-connectivity for UAVs across cellular, aerial mesh, and LEO satellite networks was accepted at the EuCNC & 6G Summit 2026.

Research & Applied AI

My research investigates how artificial intelligence can transform future communication networks from systems that primarily transport data into systems that can predict, reason, coordinate, and act toward shared objectives.

• Reinforcement learning and multi-agent decision-making for mobility management, scheduling, clustering, power control, and dynamic resource allocation.
• Self-supervised and predictive representation learning for extracting useful network states from partial, noisy, and multimodal observations.
• Agentic AI and distributed intelligence for communication, coordination, and goal-oriented interaction among autonomous network agents.
• Forecasting and optimization for energy-aware radio access networks, battery scheduling, adaptive infrastructure operation, and sustainable network management.
• Value-aware and perception-aware communications in which network resources are allocated according to the relevance, urgency, and task-level utility of information.
• Explainable and trustworthy AI for operational, autonomous, and safety-critical communication systems.

Selected Projects

• RAI-6Green: Leading AI-related research activities at KTH in collaboration with Tele2, focusing on machine-learning and real-network-data-driven methods for energy-efficient radio access network operation.
• 3D-NET: Serving as a technical lead from the KTH side in research on integrated terrestrial, aerial, and satellite communication networks for 6G.
• SDLS: Developing machine-learning methods for RF spectrogram analysis, open-set recognition, continual learning, and drone-signal surveillance.
• 6G-SKY: Conducted research on AI-assisted mobility management, multi-link connectivity, and three-dimensional network design for integrated aerial, terrestrial, and satellite systems.