📡 Signal & Communications

🧪 ICML2026 · 1 paper notes

📌 Same area in other venues: 📷 CVPR2026 (5) · 🔬 ICLR2026 (8) · 🤖 AAAI2026 (3) · 🧠 NeurIPS2025 (12) · 📹 ICCV2025 (3)

Meta-learning Structure-Preserving Dynamics

Systematically introduces modulation-based meta-learning (hyper-network maps latent code \(\bm{z}^{(k)}\) to hierarchical modulation parameters) into Hamiltonian / GENERIC neural networks, proposing two novel modulations—latent multi-rank (MR) and latent SVD-like modulation—enabling a shared network to few-shot adapt to a family of new parameter instances without knowing system parameters \(\bm{\mu}\), while strictly preserving energy conservation/dissipative structure.