neural network optimization

MDP: Multidimensional Vision Model Pruning with Latency Constraint CVPR 2025 MGDA Converges under Generalized Smoothness, Provably ICLR 2025 Mitigating Attention Localization in Small Scale: Self-Attention Refinement via One-step Belief Propagation EMNLP 2025 Mitigating Forgetting in Continual Learning with Selective Gradient Projection IJCNLP 2025 Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace ICLR 2025 MLAAN: Scaling Supervised Local Learning with Multilaminar Leap Augmented Auxiliary Network AAAI 2025 MLAS-LoRA: Language-Aware Parameters Detection and LoRA-Based Knowledge Transfer for Multilingual Machine Translation ACL 2025 MossNet: Mixture of State-Space Experts is a Multi-Head Attention IJCNLP 2025 MSQ: Memory-Efficient Bit Sparsification Quantization ICCV 2025 Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer ACL 2025 NLoRA: Nyström-Initiated Low-Rank Adaptation for Large Language Models EMNLP 2025 No More Tuning: Prioritized Multi-Task Learning with Lagrangian Differential Multiplier Methods AAAI 2025 Non-collective Calibrating Strategy for Time Series Forecasting IJCAI 2025 NormAL LoRA: What is the perfect size? EMNLP 2025 Not All Parameters Matter: Masking Diffusion Models for Enhancing Generation Ability CVPR 2025 OccLoff: Learning Optimized Feature Fusion for 3D Occupancy Prediction WACV 2025 One-for-All Pruning: A Universal Model for Customized Compression of Large Language Models ACL 2025 On the Effects of Fine-tuning Language Models for Text-Based Reinforcement Learning COLING 2025 On the Limit of Language Models as Planning Formalizers ACL 2025 On the Optimal Memorization Capacity of Transformers ICLR 2025 On the Performance Analysis of Momentum Method: A Frequency Domain Perspective ICLR 2025 Optimized Gradient Clipping for Noisy Label Learning AAAI 2025 Optimizing Neural Network Effectiveness via Non-Monotonicity Refinement WACV 2025 Optimizing Neural Network Representations of Boolean Networks ICLR 2025 PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer ICLR 2025