Optimization

SuBiTO: Synopsis-based Training Optimization for Continuous Real-Time Neural Learning over Big Streaming Data AAAI 2025 Subnet-Aware Dynamic Supernet Training for Neural Architecture Search CVPR 2025 Suboptimal Search with Dynamic Distribution of Suboptimality AAAI 2025 Sub-Sequential Physics-Informed Learning with State Space Model ICML 2025 Subspace Optimization for Large Language Models with Convergence Guarantees ICML 2025 Sufficient Invariant Learning for Distribution Shift CVPR 2025 Superfluous Instruction: Vulnerabilities Stemming from Task-Specific Superficial Expressions in Instruction Templates ACL 2025 Super Resolved Imaging with Adaptive Optics ICCV 2025 SuperServe: Fine-Grained Inference Serving for Unpredictable Workloads NSDI 2025 Supervised Optimism Correction: Be Confident When LLMs Are Sure ACL 2025 SurveyPilot: an Agentic Framework for Automated Human Opinion Collection from Social Media ACL 2025 SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression NAACL 2025 SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models ICLR 2025 SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training ICML 2025 SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligence EMNLP 2025 Swift Cross-Dataset Pruning: Enhancing Fine-Tuning Efficiency in Natural Language Understanding COLING 2025 Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories EMNLP 2025 SymmetricDiffusers: Learning Discrete Diffusion on Finite Symmetric Groups ICLR 2025 Symmetry-Aware GFlowNets ICML 2025 Synonym-unaware Fast Adversarial Training against Textual Adversarial Attacks NAACL 2025 Syntax-Aware Retrieval Augmentation for Neural Symbolic Regression EMNLP 2025 Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search ICLR 2025 Synthetic Text Generation for Training Large Language Models via Gradient Matching ICML 2025 SynthRL: Cross-domain Synthesizer Sound Matching via Reinforcement Learning IJCAI 2025 SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement ACL 2025