Neural Network Optimization

Efficient Model Editing with Task-Localized Sparse Fine-tuning ICLR 2025 Efficient stagewise pretraining via progressive subnetworks ICLR 2025 Efficient Test-time Adaptive Object Detection via Sensitivity-Guided Pruning CVPR 2025 Efficient Training of Neural Fractional-Order Differential Equation via Adjoint Backpropagation AAAI 2025 EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba AAAI 2025 Emergence in non-neural models: grokking modular arithmetic via average gradient outer product ICML 2025 Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning ACL 2025 Enhancing Language Model Hypernetworks with Restart: A Study on Optimization NAACL 2025 Enhancing Large Language Model Performance with Gradient-Based Parameter Selection AAAI 2025 Enhancing Logits Distillation with Plug&Play Kendall’s $τ$ Ranking Loss ICML 2025 Enhancing Talent Search Ranking with Role-Aware Expert Mixtures and LLM-based Fine-Grained Job Descriptions EMNLP 2025 Entropy-based Activation Function Optimization: A Method on Searching Better Activation Functions ICLR 2025 Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models COLING 2025 Equivariant Manifold Neural ODEs and Differential Invariants JMLR 2025 ESBN: Estimation Shift of Batch Normalization for Source-free Universal Domain Adaptation IJCAI 2025 EvoPress: Accurate Dynamic Model Compression via Evolutionary Search ICML 2025 Explicit and Implicit Graduated Optimization in Deep Neural Networks AAAI 2025 Exploiting Position Information in Convolutional Kernels for Structural Re-parameterization IJCAI 2025 Exploring and Controlling Diversity in LLM-Agent Conversation EMNLP 2025 Exploring smaller batch sizes for a high-performing BabyLM model architecture EMNLP 2025 Exploring the Limitations of Mamba in COPY and CoT Reasoning EMNLP 2025 Expressivity of Neural Networks with Random Weights and Learned Biases ICLR 2025 Faster Double Adaptive Gradient Methods AAAI 2025 FASTer: Focal token Acquiring-and-Scaling Transformer for Long-term 3D Objection Detection CVPR 2025 Faster Speculative Decoding via Effective Draft Decoder with Pruned Candidate Tree ACL 2025