🏢 School of Artificial Intelligence, Jilin University
Sharpness-Aware Minimization Activates the Interactive Teaching's Understanding and Optimization
·1829 words·9 mins·
loading
·
loading
AI Theory
Optimization
🏢 School of Artificial Intelligence, Jilin University
Sharpness Reduction Interactive Teaching (SRIT) boosts interactive teaching’s performance by integrating SAM’s generalization capabilities, leading to improved model accuracy and generalization.
OT4P: Unlocking Effective Orthogonal Group Path for Permutation Relaxation
·2531 words·12 mins·
loading
·
loading
AI Generated
AI Theory
Optimization
🏢 School of Artificial Intelligence, Jilin University
OT4P: a novel temperature-controlled differentiable transformation efficiently relaxes permutation matrices onto the orthogonal group for gradient-based optimization.
Geometry Awakening: Cross-Geometry Learning Exhibits Superiority over Individual Structures
·2651 words·13 mins·
loading
·
loading
Machine Learning
Deep Learning
🏢 School of Artificial Intelligence, Jilin University
Cross-geometry learning using knowledge distillation significantly improves GNN performance by leveraging both Euclidean and hyperbolic geometric properties of graph data.
Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling
·1853 words·9 mins·
loading
·
loading
Machine Learning
Reinforcement Learning
🏢 School of Artificial Intelligence, Jilin University
Decision Mamba-Hybrid (DM-H) accelerates in-context RL for long-term tasks by cleverly combining the strengths of Mamba’s linear long-term memory processing and transformer’s high-quality predictions,…