Neural Network Optimization

Learning Gaussian Multi-Index Models with Gradient Flow: Time Complexity and Directional Convergence AISTATS 2025 Learning High-Degree Parities: The Crucial Role of the Initialization ICLR 2025 Learning Instance-Specific Parameters of Black-Box Models using Differentiable Surrogates WACV 2025 Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics ICLR 2025 Learning Physics Informed Neural ODEs with Partial Measurements AAAI 2025 Learn Singularly Perturbed Solutions via Homotopy Dynamics ICML 2025 LESA: Learnable LLM Layer Scaling-Up ACL 2025 Let’s Focus on Neuron: Neuron-Level Supervised Fine-tuning for Large Language Model COLING 2025 Let’s Reason Formally: Natural-Formal Hybrid Reasoning Enhances LLM’s Math Capability EMNLP 2025 Let the Code LLM Edit Itself When You Edit the Code ICLR 2025 LEVIS: Large Exact Verifiable Input Spaces for Neural Networks ICML 2025 Lifelong Knowledge Editing requires Better Regularization EMNLP 2025 Linear Mode Connectivity between Multiple Models modulo Permutation Symmetries ICML 2025 Linear Recency Bias During Training Improves Transformers’ Fit to Reading Times COLING 2025 LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering ACL 2025 LLS: Local Learning Rule for Deep Neural Networks Inspired by Neural Activity Synchronization WACV 2025 Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation ICLR 2025 LOIRE: LifelOng learning on Incremental data via pre-trained language model gRowth Efficiently ICLR 2025 LongAttn: Selecting Long-context Training Data via Token-level Attention ACL 2025 Long Chain-of-Thought Fine-tuning via Understanding-to-Reasoning Transition EMNLP 2025 LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models ACL 2025 LoRA-MGPO: Mitigating Double Descent in Low-Rank Adaptation via Momentum-Guided Perturbation Optimization EMNLP 2025 LoRA-Pro: Are Low-Rank Adapters Properly Optimized? ICLR 2025 LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization EMNLP 2025 Losing Momentum in Continuous-time Stochastic Optimisation JMLR 2025