RESEARCH AREAS

I work on Efficient and Explainable artificial intelligence (XAI), World Models (WM) for electromagnetics/wireless, and Learning-based Optimization (L2O) for real-world communication and network decisions. Our goal is interpretable, editable, and deployable methods that connect physics, data, and decision making.

Theoretical Part

Sparse and Efficient AI

Structured sparsity, low-rank, and tensorization across data, features, models, and gradients, with unified compression and distillation for edge–cloud collaboration and federated training. HW/SW co-acceleration (CPU, GPU, FPGA) enables reliable on-device deployment in wireless applications.

Structured sparsity and low-rank modeling

- Compression and distillation for models and gradients
- Communication-efficient training and adaptation
- Algorithm–system co-design for throughput and energy gains

Explainable AI (XAI)

Principled interpretability and reliability for models: from attribution and concept-based explanations to causal and statistical guarantees, ensuring trustworthy deployment.

Interpretable modeling and guarantees

- Attribution and concept-based explanations; counterfactual and causal probes; manifold learning
- Generalization and convergence bounds for nonconvex/structured models
- Risk control with conformal prediction; safety constraints and robust training

Application Part

World Models (WM) for Radio Environment

Physically grounded, data-driven models of radio EM environments that fuse geometry and materials (e.g., BIM, point clouds, maps), contextual signals (vision, language, IMU, GNSS), and RF measurements (sweeps arrays). We combine neural representations (3DGS and NeRF variants, diffusion and energy models, GNNs, neural operators such as FNO, DeepONet, and GNO) with PDE and boundary consistency, constitutive relations, and structured sparsity or low-rank priors. The models support editable inversion, uncertainty quantification, and active re-measurement for localized statistical channel modeling and environment-aware communication.

Localized statistical channel modeling

- Neural radio radiance fields; structured Bayesian inference on graphs /p>
- PDE and boundary consistency; material priors; calibrated uncertainty with multimodal fusion
- Geometry/materials plus RF arrays plus contextual signals

Learning-based Optimization (L2O)

Differentiable, learning-augmented solvers (RL, GNN, and neural combinatorial optimization) operating on WM for constrained decisions, with feasibility guarantees, learned warm-starts, and fast cross-scenario adaptation.

Communication and RAN optimization

- UAV sensing plan, site placement; beam, power, and spectrum allocation; routing and formation planning
- Relax–optimize–and–sample; neural projections; constraint satisfaction deployment
- Edge and federated execution for real-time, certifiable decisions

FieldMind: From Representation to Decisions

FieldMind is our instantiation of WM plus sparse and efficient AI plus L2O, coupled with algorithm–hardware co-design (C, CUDA, FPGA; edge and federated) for online decision making. It maps structure across data, algorithms, and architectures into solvers and hardware.