Neural Network Optimization

FESSNC: Fast Exponentially Stable and Safe Neural Controller ICML 2024 Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation EMNLP 2024 Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning CVPR 2024 FINER: Flexible Spectral-bias Tuning in Implicit NEural Representation by Variable-periodic Activation Functions CVPR 2024 Fine-tuning after Prompting: an Explainable Way for Classification ACL 2024 FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning ICLR 2024 FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision NeurIPS 2024 FLORA: Fine-Grained Low-Rank Architecture Search for Vision Transformer WACV 2024 Flora: Low-Rank Adapters Are Secretly Gradient Compressors ICML 2024 Focused Large Language Models are Stable Many-Shot Learners EMNLP 2024 Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics ICML 2024 Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning NeurIPS 2024 Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use ACL 2024 Forward Learning of Graph Neural Networks ICLR 2024 Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization ICLR 2024 Found in the middle: Calibrating Positional Attention Bias Improves Long Context Utilization ACL 2024 Friendly Sharpness-Aware Minimization CVPR 2024 From Activation to Initialization: Scaling Insights for Optimizing Neural Fields CVPR 2024 From Bottom to Top: Extending the Potential of Parameter Efficient Fine-Tuning EMNLP 2024 From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers CVPR 2024 Fundamental Convergence Analysis of Sharpness-Aware Minimization NeurIPS 2024 Generalizable Symbolic Optimizer Learning ECCV 2024 Generalization of Scaled Deep ResNets in the Mean-Field Regime ICLR 2024 Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning NeurIPS 2024 Global Convergence in Training Large-Scale Transformers NeurIPS 2024