neural network optimization

Fast Training of Sinusoidal Neural Fields via Scaling Initialization ICLR 2025 Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State Tracking ACL 2025 Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond ICLR 2025 Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks ICLR 2025 Formation of Representations in Neural Networks ICLR 2025 FreqMoE: Dynamic Frequency Enhancement for Neural PDE Solvers IJCAI 2025 From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks ICLR 2025 From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers AAAI 2025 Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency ICLR 2025 GAP: a Global Adaptive Pruning Method for Large Language Models EMNLP 2025 Gated Delta Networks: Improving Mamba2 with Delta Rule ICLR 2025 Generalization Analysis for Deep Contrastive Representation Learning AAAI 2025 Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations ICCV 2025 GeneralizeFormer: Layer-Adaptive Model Generation across Test-Time Distribution Shifts WACV 2025 GenPTQ: Green Post-Training Quantization for Large-Scale ASR Models with Mixed-Precision Bit Allocation EMNLP 2025 GeoLoRA: Geometric integration for parameter efficient fine-tuning ICLR 2025 Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces ICLR 2025 GFPack++: Attention-Driven Gradient Fields for Optimizing 2D Irregular Packing ICCV 2025 GliaNet: Adaptive Neural Network Structure Learning with Glia-Driven CVPR 2025 GradQ-ViT: Robust and Efficient Gradient Quantization for Vision Transformers AAAI 2025 Grokking at the Edge of Numerical Stability ICLR 2025 HFT: Half Fine-Tuning for Large Language Models ACL 2025 Hierarchical Features Matter: A Deep Exploration of Progressive Parameterization Method for Dataset Distillation CVPR 2025 HIGGS: Pushing the Limits of Large Language Model Quantization via the Linearity Theorem NAACL 2025 HiRA: Parameter-Efficient Hadamard High-Rank Adaptation for Large Language Models ICLR 2025