Optimization

DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation CVPR 2025 Democratic Training Against Universal Adversarial Perturbations ICLR 2025 Demonstration Selection for In-Context Learning via Reinforcement Learning ICML 2025 Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector ICML 2025 Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts ICLR 2025 Demystifying optimized prompts in language models EMNLP 2025 Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls EMNLP 2025 DenseSSM: State Space Models with Dense Hidden Connection for Efficient Large Language Models NAACL 2025 Density Ratio Estimation-based Bayesian Optimization with Semi-Supervised Learning ICML 2025 Dependent Randomized Rounding for Budget Constrained Experimental Design UAI 2025 depyf: Open the Opaque Box of PyTorch Compiler for Machine Learning Researchers JMLR 2025 DEQ-MPC : Deep Equilibrium Model Predictive Control CoRL 2025 Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning ACL 2025 (De)-regularized Maximum Mean Discrepancy Gradient Flow JMLR 2025 Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAI CVPR 2025 DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models CVPR 2025 Descent with Misaligned Gradients and Applications to Hidden Convexity ICLR 2025 De-singularity Subgradient for the q-th-Powered lₚ-Norm Weber Location Problem AAAI 2025 Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging AAAI 2025 Detecting Open World Objects via Partial Attribute Assignment CVPR 2025 Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective ICML 2025 Device-Cloud Collaborative Correction for On-Device Recommendation IJCAI 2025 DF$^2$: Distribution-Free Decision-Focused Learning UAI 2025 DFF: Decision-Focused Fine-Tuning for Smarter Predict-Then-Optimize with Limited Data AAAI 2025 DIDS: Domain Impact-aware Data Sampling for Large Language Model Training EMNLP 2025