Optimization

Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences ICML 2025 SMT: Fine-Tuning Large Language Models with Sparse Matrices ICLR 2025 SODA: Spectral Orthogonal Decomposition Adaptation for Diffusion Models WACV 2025 SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs ACL 2025 Soft Local Completeness: Rethinking Completeness in XAI ICCV 2025 SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression AAAI 2025 Solving Convex-Concave Problems with O(ε^-4/7) Second-Order Oracle Complexity COLT 2025 Solving Differential Equations with Constrained Learning ICLR 2025 Solving hidden monotone variational inequalities with surrogate losses ICLR 2025 Solving Robust Markov Decision Processes: Generic, Reliable, Efficient AAAI 2025 Solving Video Inverse Problems Using Image Diffusion Models ICLR 2025 SOO-Bench: Benchmarks for Evaluating the Stability of Offline Black-Box Optimization ICLR 2025 SOPL: A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models EMNLP 2025 SOREL: A Stochastic Algorithm for Spectral Risks Minimization ICLR 2025 Sort-free Gaussian Splatting via Weighted Sum Rendering ICLR 2025 SOTA: Spike-Navigated Optimal TrAnsport Saliency Region Detection in Composite-bias Videos IJCAI 2025 Söze: One Network Telemetry Is All You Need for Per-flow Weighted Bandwidth Allocation at Scale OSDI 2025 Span-Agnostic Optimal Sample Complexity and Oracle Inequalities for Average-Reward RL COLT 2025 Sparse-Dense Side-Tuner for efficient Video Temporal Grounding ICCV 2025 SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity ICML 2025 SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks EMNLP 2025 Sparse SVM with Hard-Margin Loss: a Newton-Augmented Lagrangian Method in Reduced Dimensions JMLR 2025 Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs ACL 2025 Sparse Transfer Learning Accelerates and Enhances Certified Robustness: A Comprehensive Study AAAI 2025 Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering CVPR 2025