Optimization

Periodical Moving Average Accelerates Gradient Accumulation for Post-Training UAI 2025 PMPO: Probabilistic Metric Prompt Optimization for Small and Large Language Models EMNLP 2025 PoseAnchor: Robust Root Position Estimation for 3D Human Pose Estimation ICCV 2025 Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models EMNLP 2025 Position Really Matters: Towards a Holistic Approach for Prompt Tuning NAACL 2025 Principles of Visual Tokens for Efficient Video Understanding ICCV 2025 ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformations ACL 2025 ProCut: LLM Prompt Compression via Attribution Estimation EMNLP 2025 Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble ICML 2025 ProReflow: Progressive Reflow with Decomposed Velocity CVPR 2025 Prototype-based Optimal Transport for Out-of-Distribution Detection IJCAI 2025 PURA: Parameter Update-Recovery Test-Time Adaption for RGB-T Tracking CVPR 2025 Q-Mamba: Towards more efficient Mamba models via post-training quantization ACL 2025 Qua2SeDiMo: Quantifiable Quantization Sensitivity of Diffusion Models AAAI 2025 Quantization without Tears CVPR 2025 QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models EMNLP 2025 RaSS: Improving Denoising Diffusion Samplers with Reinforced Active Sampling Scheduler CVPR 2025 RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectories CVPR 2025 Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models CVPR 2025 Rectified Diffusion Guidance for Conditional Generation CVPR 2025 Redundancy, Isotropy, and Intrinsic Dimensionality of Prompt-based Text Embeddings ACL 2025 Refined Analysis of Constant Step Size Federated Averaging and Federated Richardson-Romberg Extrapolation AISTATS 2025 Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory ACL 2025 Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration JMLR 2025 Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation ACL 2025