Optimization

Composable Cross-prompt Essay Scoring by Merging Models EMNLP 2025 Consistency Trajectory Matching for One-Step Generative Super-Resolution ICCV 2025 Conversational SimulMT: Efficient Simultaneous Translation with Large Language Models ACL 2025 Cost-Optimal Grouped-Query Attention for Long-Context Modeling EMNLP 2025 Critical Influence of Overparameterization on Sharpness-aware Minimization UAI 2025 CTBench: A Library and Benchmark for Certified Training ICML 2025 DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models EMNLP 2025 Data-Free Group-Wise Fully Quantized Winograd Convolution via Learnable Scales CVPR 2025 Dataset Distillation via the Wasserstein Metric ICCV 2025 Dataset Distillation with Neural Characteristic Function: A Minmax Perspective CVPR 2025 DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space ICCV 2025 Decomposed Quadratization: Efficient QUBO Formulation for Learning Bayesian Network AAAI 2025 DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability EMNLP 2025 Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment CVPR 2025 Differentiable Adversarial Attacks for Marked Temporal Point Processes AAAI 2025 DiffIM: Differentiable Influence Minimization with Surrogate Modeling and Continuous Relaxation AAAI 2025 DiLQR: Differentiable Iterative Linear Quadratic Regulator via Implicit Differentiation ICML 2025 Distilling Parallel Gradients for Fast ODE Solvers of Diffusion Models ICCV 2025 DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models CVPR 2025 Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport ACL 2025 Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference EMNLP 2025 Do WGANs succeed because they minimize the Wasserstein Distance? Lessons from Discrete Generators ICLR 2025 Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation EMNLP 2025 Drop Dropout on Single Epoch Language Model Pretraining ACL 2025 DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization ACL 2025