neural network optimization

Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters CVPR 2025 Towards Equilibrium: An Instantaneous Probe-and-Rebalance Multimodal Learning Approach IJCAI 2025 Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory CVPR 2025 Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It ICLR 2025 Transformers Provably Solve Parity Efficiently with Chain of Thought ICLR 2025 Transformers Struggle to Learn to Search ICLR 2025 Transformers without Normalization CVPR 2025 TRIAL: Token Relations and Importance Aware Late-interaction for Accurate Text Retrieval EMNLP 2025 Tuning the Frequencies: Robust Training for Sinusoidal Neural Networks CVPR 2025 u-μP: The Unit-Scaled Maximal Update Parametrization ICLR 2025 ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning ICCV 2025 Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing ICLR 2025 Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos ICLR 2025 UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter Efficient Fine-Tuning of Large Models ACL 2025 Using Powerful Prior Knowledge of Diffusion Model in Deep Unfolding Networks for Image Compressive Sensing CVPR 2025 Variable Layerwise Quantization: A Simple and Effective Approach to Quantize LLMs ACL 2025 Video Depth Anything: Consistent Depth Estimation for Super-Long Videos CVPR 2025 WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models CVPR 2025 What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis ICLR 2025 WINS: Winograd Structured Pruning for Fast Winograd Convolution ICCV 2025 $\boldsymbol{\mu}\mathbf{P^2}$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling NeurIPS 2024 1-Lipschitz Layers Compared: Memory Speed and Certifiable Robustness CVPR 2024 Abrupt Learning in Transformers: A Case Study on Matrix Completion NeurIPS 2024 Accurate and Steady Inertial Pose Estimation through Sequence Structure Learning and Modulation NeurIPS 2024 Adam-family Methods for Nonsmooth Optimization with Convergence Guarantees JMLR 2024