Neural Network Optimization

DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration ACL 2025 Debiasing 6-DOF IMU via Hierarchical Learning of Continuous Bias Dynamics RSS 2025 Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation COLING 2025 Deconstructing Attention: Investigating Design Principles for Effective Language Modeling IJCNLP 2025 Deconstructing What Makes a Good Optimizer for Autoregressive Language Models ICLR 2025 Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer ICML 2025 DeepTAGE: Deep Temporal-Aligned Gradient Enhancement for Optimizing Spiking Neural Networks ICLR 2025 DEIM: DETR with Improved Matching for Fast Convergence CVPR 2025 Delta-NAS: Difference of Architecture Encoding for Predictor-Based Evolutionary Neural Architecture Search WACV 2025 Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models ACL 2025 Demystifying the Token Dynamics of Deep Selective State Space Models ICLR 2025 Dendritic Localized Learning: Toward Biologically Plausible Algorithm ICML 2025 depyf: Open the Opaque Box of PyTorch Compiler for Machine Learning Researchers JMLR 2025 Design and Analysis of few Million Parameter Transformer-based Language Models trained over a few Million Tokens Dataset EMNLP 2025 Design Choices for Extending the Context Length of Visual Language Models ACL 2025 D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement ICLR 2025 Differential Mamba IJCNLP 2025 DiffSkip: Differential Layer Skipping in Large Language Models ACL 2025 DiLQR: Differentiable Iterative Linear Quadratic Regulator via Implicit Differentiation ICML 2025 DINT Transformer EMNLP 2025 DIRAS: Efficient LLM Annotation of Document Relevance for Retrieval Augmented Generation NAACL 2025 Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values EMNLP 2025 Disentangle to Decay: Linear Attention with Trainable Decay Factor COLING 2025 Disentangling Mathematical Reasoning in LLMs: A Methodological Investigation of Internal Mechanisms EMNLP 2025 Divergence of Neural Tangent Kernel in Classification Problems ICLR 2025