Optimization

Speculative Speech Recognition by Audio-Prefixed Low-Rank Adaptation of Language Models Interspeech 2024 SpeechAlign: Aligning Speech Generation to Human Preferences NeurIPS 2024 SpeedE: Euclidean Geometric Knowledge Graph Embedding Strikes Back NAACL 2024 SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits AISTATS 2024 SpeedLoader: An I/O efficient scheme for heterogeneous and distributed LLM operation NeurIPS 2024 Spiking Denoising Diffusion Probabilistic Models WACV 2024 Spiking Transformer with Experts Mixture NeurIPS 2024 SPO: Sequential Monte Carlo Policy Optimisation NeurIPS 2024 Sprout: Green Generative AI with Carbon-Efficient LLM Inference EMNLP 2024 SquirrelFS: using the Rust compiler to check file-system crash consistency OSDI 2024 S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training NeurIPS 2024 Stability Analysis of Switched Linear Systems with Neural Lyapunov Functions AAAI 2024 Stability and Generalization for Stochastic Recursive Momentum-based Algorithms for (Strongly-)Convex One to K-Level Stochastic Optimizations ICML 2024 Stability and Generalization of Adversarial Training for Shallow Neural Networks with Smooth Activation NeurIPS 2024 Stability-Informed Initialization of Neural Ordinary Differential Equations ICML 2024 Stabilized Proximal-Point Methods for Federated Optimization NeurIPS 2024 Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir Sampling NeurIPS 2024 Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Process ICML 2024 Stable Anisotropic Regularization ICLR 2024 Stable Language Model Pre-training by Reducing Embedding Variability EMNLP 2024 StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization ICML 2024 State-free Reinforcement Learning NeurIPS 2024 Statistical analysis for a penalized EM algorithm in high-dimensional mixture linear regression model JMLR 2024 Step-level Value Preference Optimization for Mathematical Reasoning EMNLP 2024 Stepping Forward on the Last Mile NeurIPS 2024