Neural Network Optimization

Learning Kolmogorov-Arnold Neural Activation Functions by Infinite-Dimensional Optimization L4DC 2025 LightThinker: Thinking Step-by-Step Compression EMNLP 2025 LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation EMNLP 2025 Locally Optimal Descent for Dynamic Stepsize Scheduling AISTATS 2025 Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query EMNLP 2025 LoRA-MGPO: Mitigating Double Descent in Low-Rank Adaptation via Momentum-Guided Perturbation Optimization EMNLP 2025 LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty CVPR 2025 Low-Rank Interconnected Adaptation across Layers ACL 2025 MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection ACL 2025 Memory-Efficient Backpropagation for Fine-Tuning LLMs on Resource-Constrained Mobile Devices EMNLP 2025 Memory-Efficient Optimization with Factorized Hamiltonian Descent AISTATS 2025 Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning ICLR 2025 MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices EMNLP 2025 Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer ACL 2025 NeuroAda: Activating Each Neuron’s Potential for Parameter-Efficient Fine-Tuning EMNLP 2025 Not All Parameters Matter: Masking Diffusion Models for Enhancing Generation Ability CVPR 2025 On Relation-Specific Neurons in Large Language Models EMNLP 2025 On the Geometry and Optimization of Polynomial Convolutional Networks AISTATS 2025 On the O(sqrt(d)/T^(1/4)) Convergence Rate of RMSProp and Its Momentum Extension Measured by l_1 Norm JMLR 2025 Optimized Gradient Clipping for Noisy Label Learning AAAI 2025 Optimizing Neural Network Training and Quantization with Rooted Logistic Objectives AISTATS 2025 Orthogonal projection-based regularization for efficient model augmentation L4DC 2025 Parameter-Efficient Fine-Tuning via Circular Convolution ACL 2025 ParZC: Parametric Zero-Cost Proxies for Efficient NAS AAAI 2025 Periodical Moving Average Accelerates Gradient Accumulation for Post-Training UAI 2025