Optimization

Sparsifying Mamba EMNLP 2025 Sparsity-Based Interpolation of External, Internal and Swap Regret COLT 2025 Sparsity May Be All You Need: Sparse Random Parameter Adaptation EMNLP 2025 Spatially-Adaptive Hash Encodings for Neural Surface Reconstruction WACV 2025 Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion ICLR 2025 Spatial Transport Optimization by Repositioning Attention Map for Training-Free Text-to-Image Synthesis CVPR 2025 Spatio-Spectral Pattern Illumination for Direct and Indirect Separation from a Single Hyperspectral Image ICCV 2025 SPECTRA: Faster Large Language Model Inference with Optimized Internal and External Speculation ACL 2025 Spectral-Refiner: Accurate Fine-Tuning of Spatiotemporal Fourier Neural Operator for Turbulent Flows ICLR 2025 Speculative Decoding for Multi-Sample Inference EMNLP 2025 Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion NAACL 2025 Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance EMNLP 2025 Speeding Up Hyper-Heuristics With Markov-Chain Operator Selection and the Only-Worsening Acceptance Operator IJCAI 2025 Speeding up Policy Simulation in Supply Chain RL ICML 2025 Speeding Up the NSGA-II with a Simple Tie-Breaking Rule AAAI 2025 Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives CVPR 2025 Spherical Tree-Sliced Wasserstein Distance ICLR 2025 SpikePack: Enhanced Information Flow in Spiking Neural Networks with High Hardware Compatibility ICCV 2025 SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers ACL 2025 SPO: Self Preference Optimization with Self Regularization EMNLP 2025 Square$χ$PO: Differentially Private and Robust $χ^2$-Preference Optimization in Offline Direct Alignment ICML 2025 SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget ICLR 2025 SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code Generation IJCAI 2025 SSHR: More Secure Generative Steganography with High-Quality Revealed Secret Images ICML 2025 SSH: Sparse Spectrum Adaptation via Discrete Hartley Transformation NAACL 2025