Optimization

R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference ICLR 2025 RTE-GMoE: A Model-agnostic Approach for Relation Triplet Extraction via Graph-based Mixture-of-Expert Mutual Learning EMNLP 2025 R-TOFU: Unlearning in Large Reasoning Models EMNLP 2025 RTop-K: Ultra-Fast Row-Wise Top-K Selection for Neural Network Acceleration on GPUs ICLR 2025 RTTC: Reward-Guided Collaborative Test-Time Compute EMNLP 2025 Runtime Analysis for Multi-Objective Evolutionary Algorithms in Unbounded Integer Spaces AAAI 2025 Runtime Analysis of Evolutionary NAS for Multiclass Classification ICML 2025 RZ-NAS: Enhancing LLM-guided Neural Architecture Search via Reflective Zero-Cost Strategy ICML 2025 s1: Simple test-time scaling EMNLP 2025 S2LPP: Small-to-Large Prompt Prediction across LLMs EMNLP 2025 S2WTM: Spherical Sliced-Wasserstein Autoencoder for Topic Modeling ACL 2025 SAC-GNC: SAmple Consensus for adaptive Graduated Non-Convexity ICCV 2025 Safe Beyond the Horizon: Efficient Sampling-based MPC with Neural Control Barrier Functions RSS 2025 Safe-EF: Error Feedback for Non-smooth Constrained Optimization ICML 2025 SAFE: Finding Sparse and Flat Minima to Improve Pruning ICML 2025 Safe Online Convex Optimization with Heavy-Tailed Observation Noises AAAI 2025 SAFER: Sharpness Aware layer-selective Finetuning for Enhanced Robustness in vision transformers ICCV 2025 Safety Alignment Should be Made More Than Just a Few Tokens Deep ICLR 2025 Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking ICLR 2025 SAIL: Sample-Centric In-Context Learning for Document Information Extraction AAAI 2025 SAKE: Steering Activations for Knowledge Editing ACL 2025 SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation ICCV 2025 Sample and Oracle Efficient Reinforcement Learning for MDPs with Linearly-Realizable Value Functions COLT 2025 Sample Complexity of Branch-length Estimation by Maximum Likelihood ICML 2025 Sample Efficient Demonstration Selection for In-Context Learning ICML 2025