neural network optimization

Selective Task Group Updates for Multi-Task Optimization ICLR 2025 Self-Adjust Softmax EMNLP 2025 Self-Aligning Depth-Regularized Radiance Fields for Asynchronous RGB-D Sequences WACV 2025 Self-Normalized Resets for Plasticity in Continual Learning ICLR 2025 Sensitivity-Aware Efficient Fine-Tuning via Compact Dynamic-Rank Adaptation CVPR 2025 Sensitivity-Constrained Fourier Neural Operators for Forward and Inverse Problems in Parametric Differential Equations ICLR 2025 Sharpness-Aware Minimization: General Analysis and Improved Rates ICLR 2025 Sharpness-aware Zeroth-order Optimization for Graph Transformers IJCAI 2025 ShortGPT: Layers in Large Language Models are More Redundant Than You Expect ACL 2025 Simulating Training Dynamics to Reconstruct Training Data from Deep Neural Networks ICLR 2025 Spectral Scaling Laws in Language Models: emphHow Effectively Do Feed-Forward Networks Use Their Latent Space? EMNLP 2025 Stability and Generalization for Stochastic (Compositional) Optimizations IJCAI 2025 Stabilizing Sharpness-Aware Minimization Through A Simple Renormalization Strategy JMLR 2025 Stable learning using spiking neural networks equipped with affine encoders and decoders JMLR 2025 StitchLLM: Serving LLMs, One Block at a Time ACL 2025 Strong Model Collapse ICLR 2025 Structured IB: Improving Information Bottleneck with Structured Feature Learning AAAI 2025 STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning ACL 2025 SuBiTO: Synopsis-based Training Optimization for Continuous Real-Time Neural Learning over Big Streaming Data AAAI 2025 Swing-by Dynamics in Concept Learning and Compositional Generalization ICLR 2025 The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning JMLR 2025 The Optimization Landscape of SGD Across the Feature Learning Strength ICLR 2025 The Role of Outgoing Connection Heterogeneity in Feedforward Layers of Large Language Models EMNLP 2025 Three Mechanisms of Feature Learning in a Linear Network ICLR 2025 TopoNets: High performing vision and language models with brain-like topography ICLR 2025