residual connection

Adaptive Initial Residual Connections for GNNs with Theoretical Guarantees AAAI 2026 DiverseDiT: Towards Diverse Representation Learning in Diffusion Transformers CVPR 2026 Residual Connections Harm Generative Representation Learning CVPR 2026 Accelerated training through iterative gradient propagation along the residual path ICLR 2025 DeepCrossAttention: Supercharging Transformer Residual Connections ICML 2025 FreqMoE: Enhancing Time Series Forecasting through Frequency Decomposition Mixture of Experts AISTATS 2025 Hyper-Connections ICLR 2025 InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity ICCV 2025 Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking ACL 2025 LAuReL: Learned Augmented Residual Layer ICML 2025 Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs ICLR 2025 RiOT: Efficient Prompt Refinement with Residual Optimization Tree ACL 2025 RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation ACL 2025 SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connection EMNLP 2025 TSDT-Net: Ultra-Low-Complexity Two-Stage Model Combining Dual-Path-Transformer and Transform-Average-Concatenate Network for Speech Enhancement Interspeech 2025 Adaptive Rational Activations to Boost Deep Reinforcement Learning ICLR 2024 Curriculum-Enhanced Residual Soft An-Isotropic Normalization for Over-Smoothness in Deep GNNs AAAI 2024 Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning CVPR 2024 Exploiting Wavelet Scattering Transform for an Unsupervised Speaker Diarization in Deep Neural Network Framework Interspeech 2024 High-Performance Temporal Reversible Spiking Neural Networks with O(L) Training Memory and O(1) Inference Cost ICML 2024 PirateNets: Physics-informed Deep Learning with Residual Adaptive Networks JMLR 2024 Residual Hyperbolic Graph Convolution Networks AAAI 2024 RESPROMPT: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models NAACL 2024 Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs ICML 2024 The Orthogonality of Weight Vectors: The Key Characteristics of Normalization and Residual Connections IJCAI 2024