structural diversity

4 papers

• AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs
• ChA-MAEViT: Unifying Channel-Aware Masked Autoencoders and Multi-Channel Vision Transformers for Improved Cross-Channel Learning
• Geometry-Aware Edge Pooling for Graph Neural Networks
• Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning