Neural Network Optimization

OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels CVPR 2025 P3: Prompts Promote Prompting ACL 2025 PALM: Pushing Adaptive Learning Rate Mechanisms for Continual Test-Time Adaptation AAAI 2025 Parameter-free and Accessible Prompt Learning to Enhance Adversarial Robustness for Pre-trained Vision-Language Models NAACL 2025 Parameterized Blur Kernel Prior Learning for Local Motion Deblurring CVPR 2025 PARQ: Piecewise-Affine Regularized Quantization ICML 2025 PCAN: A Pandemic-Compatible Attentive Neural Network for Retail Sales Forecasting IJCAI 2025 PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QA ACL 2025 PeSANet: Physics-encoded Spectral Attention Network for Simulating PDE-Governed Complex Systems IJCAI 2025 PFDiff: Training-Free Acceleration of Diffusion Models Combining Past and Future Scores ICLR 2025 PIP: Perturbation-based Iterative Pruning for Large Language Models EMNLP 2025 Planning-Aware Code Infilling via Horizon-Length Prediction EMNLP 2025 Plastic Learning with Deep Fourier Features ICLR 2025 PLEX: Adaptive Parameter-Efficient Fine-Tuning for Code LLMs using Lottery-Tickets NAACL 2025 Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models ICLR 2025 Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network AAAI 2025 PoseMamba: Monocular 3D Human Pose Estimation with Bidirectional Global-Local Spatio-Temporal State Space Model AAAI 2025 Positional Overload: Positional Debiasing and Context Window Extension for Large Language Models using Set Encoding ACL 2025 PowerMLP: An Efficient Version of KAN AAAI 2025 PRDP: Progressively Refined Differentiable Physics ICLR 2025 Prediction-Feedback DETR for Temporal Action Detection AAAI 2025 Prejudge-Before-Think: Enhancing Large Language Models at Test-Time by Process Prejudge Reasoning EMNLP 2025 Principles of Visual Tokens for Efficient Video Understanding ICCV 2025 Probing Semantic Routing in Large Mixture-of-Expert Models EMNLP 2025 Progressive Focused Transformer for Single Image Super-Resolution CVPR 2025