Optimization

Improved Sparse Upcycling for Instruction Tuning COLING 2025 Improved Theoretically-Grounded Evolutionary Algorithms for Subset Selection with a Linear Cost Constraint ICML 2025 Improvements to the Generate-and-Complete Approach to Conformant Planning IJCAI 2025 Improving Accuracy of Low-resource ASR using Rule-Based Character Constituency Loss (RBCCL) COLING 2025 Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization ACL 2025 Improving Continual Pre-training Through Seamless Data Packing ACL 2025 Improving Convergence Guarantees of Random Subspace Second-order Algorithm for Nonconvex Optimization ICLR 2025 Improving Deep Detector Robustness via Detection-Related Discriminant Maximization and Reorganization WACV 2025 Improving Deep Learning Speed and Performance Through Synaptic Neural Balance AAAI 2025 Improving Efficiency of Sampling-based Motion Planning via Message-Passing Monte Carlo CoRL 2025 Improving Flow Matching by Aligning Flow Divergence ICML 2025 Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging ICML 2025 Improving Generalization of Deep Neural Networks by Optimum Shifting AAAI 2025 Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization AAAI 2025 Improving LLM Safety Alignment with Dual-Objective Optimization ICML 2025 Improving Model Probability Calibration by Integration of Large Data Sources with Biased Labels AAAI 2025 Improving Multimodal Learning via Imbalanced Learning ICCV 2025 Improving Neutral Point-of-View Generation with Data- and Parameter-Efficient RL EMNLP 2025 Improving NMT Models by Retrofitting Quality Estimators into Trainable Energy Loss COLING 2025 Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces ICML 2025 Improving Pareto Set Learning for Expensive Multi-objective Optimization via Stein Variational Hypernetworks AAAI 2025 Improving Prediction Certainty Estimation for Reliable Early Exiting via Null Space Projection IJCAI 2025 Improving Preference Alignment of LLM with Inference-Free Self-Refinement EMNLP 2025 Improving Probabilistic Diffusion Models With Optimal Diagonal Covariance Matching ICLR 2025 Improving Rectified Flow with Boundary Conditions ICCV 2025