Neural Network Optimization

Not All Parameters Matter: Masking Diffusion Models for Enhancing Generation Ability CVPR 2025 NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent Kernel ICML 2025 Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm NAACL 2025 Offloaded Reasoning: Efficient Inference for Large Language Models via Modular Reasoning and Refinement EMNLP 2025 OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration ICCV 2025 One Last Attention for Your Vision-Language Model ICCV 2025 One-Pass to Reason: Token Duplication and Block-Sparse Mask for Efficient Fine-Tuning on Multi-Turn Reasoning IJCNLP 2025 On Generalization Bounds for Neural Networks with Low Rank Layers ALT 2025 On Global and Local Convergence of Iterative Linear Quadratic Optimization Algorithms for Discrete Time Nonlinear Control JMLR 2025 Online Curvature-Aware Replay: Leveraging $\mathbf2^nd$ Order Information for Online Continual Learning ICML 2025 On Local Overfitting and Forgetting in Deep Neural Networks AAAI 2025 On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning ICML 2025 On the Crucial Role of Initialization for Matrix Factorization ICLR 2025 On the Effects of Fine-tuning Language Models for Text-Based Reinforcement Learning COLING 2025 On the Natural Gradient of the Evidence Lower Bound JMLR 2025 On the Performance Analysis of Momentum Method: A Frequency Domain Perspective ICLR 2025 Optimal Brain Apoptosis ICLR 2025 Optimization for Neural Operators can Benefit from Width ICML 2025 Optimized Gradient Clipping for Noisy Label Learning AAAI 2025 Optimized Random Features for the Neural Tangent Kernel (Student Abstract) AAAI 2025 Optimizing Neural Network Effectiveness via Non-Monotonicity Refinement WACV 2025 Optimizing RLHF Training for Large Language Models with Stage Fusion NSDI 2025 Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models ACL 2025 Overcoming Lower-Level Constraints in Bilevel Optimization: A Novel Approach with Regularized Gap Functions ICLR 2025 Overcoming Spurious Solutions in Semi-Dual Neural Optimal Transport: A Smoothing Approach for Learning the Optimal Transport Plan ICML 2025