Efficient Computing

Parameter-Efficient Fine-Tuning of Large Language Models via Deconvolution in Subspace COLING 2025 Parameter-Efficient Fine-Tuning of State Space Models ICML 2025 Parameter-Efficient Fine-Tuning via Circular Convolution ACL 2025 Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation CVPR 2025 Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models ICML 2025 Partial Forward Blocking: A Novel Data Pruning Paradigm for Lossless Training Acceleration ICCV 2025 Patch Ranking: Token Pruning as Ranking Prediction for Efficient CLIP WACV 2025 Path-Adaptive Matting for Efficient Inference Under Various Computational Cost Constraints AAAI 2025 Patient-Centric Multilingual Question Answering and Summary Generation for Head and Neck Cancer and Blood Donation AACL 2025 PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language Models IJCAI 2025 PDE-Transformer: Efficient and Versatile Transformers for Physics Simulations ICML 2025 PDUDT: Provable Decentralized Unlearning under Dynamic Topologies ICML 2025 PEFTDiff: Diffusion-Guided Transferability Estimation for Parameter-Efficient Fine-Tuning ICCV 2025 Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios NAACL 2025 Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting ICML 2025 Perceptual Video Compression with Neural Wrapping CVPR 2025 PerfSeer: An Efficient and Accurate Deep Learning Models Performance Predictor IJCAI 2025 Permutation Equivariant Neural Networks for Symmetric Tensors ICML 2025 Permutation-Free High-Order Interaction Tests ICML 2025 Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs ICLR 2025 PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting for Novel View Synthesis ICML 2025 Pfeife: Automatic Pipeline Parallelism for PyTorch ICML 2025 PhenoRAG: Retrieval-Augmented Generation for Efficient Zero-Shot Phenotype Identification in Clinical Reports MLHC 2025 Physics-based Generative Models for Geometrically Consistent and Interpretable Wireless Channel Synthesis IJCAI 2025 PhysicsEval: Inference-Time Techniques to Improve the Reasoning Proficiency of Large Language Models on Physics Problems IJCNLP 2025