Machine Learning

Democratizing LLM Efficiency: From Hyperscale Optimizations to Universal Deployability AAAI 2026 Demographic Parity in Regression and Classification Within the Unawareness Framework JMLR 2026 Demystifying Foreground-Background Memorization in Diffusion Models AAAI 2026 Demystifying GNN-to-MLP Knowledge Transfer: Theoretical Grounding and Dual-Stream Distillation Method AAAI 2026 Demystifying Mixed Outcomes of Self-Training: Pre-training Analyses on Non-Toy LLMs EACL 2026 Demystifying Uncertainty in LLMs: Active Calibration between Concepts and Human Evaluations ACL 2026 DeNAS-ViT: Data Efficient NAS-Optimized Vision Transformer for Ultrasound Image Segmentation AAAI 2026 Denoise, Divide, Distill, and Predict (D3P): Towards Forecasting Long-horizon Real-world Anomaly from Normalcy WACV 2026 Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering EACL 2026 Denoising Mixup for Regression AAAI 2026 De Novo Molecular Generation from Mass Spectra via Many-Body Enhanced Diffusion AAAI 2026 Dense Cross-Scale Image Alignment with Fully Spatial Correlation and Just Noticeable Difference Guidance AAAI 2026 DensiCrafter: Physically-Constrained Generation and Fabrication of Self-Supporting Hollow Structures AAAI 2026 Density estimation for Hellinger via minimum-distance estimators: mixtures of Gaussians, log-concave, and more COLT 2026 Departures: Distributional Transport for Single-Cell Perturbation Prediction with Neural Schrödinger Bridges AAAI 2026 Deploying Atmospheric and Oceanic AI Models on Chinese Hardware and Framework: Migration Strategies, Performance Optimization and Analysis AAAI 2026 Deploying Rapid Damage Assessments from sUAS Imagery for Disaster Response AAAI 2026 Dep-MAP: A Multi-level Alignment Framework with Semantic Prototypes for Video-based Automatic Depression Assessment AAAI 2026 DEPO: Dual-Efficiency Preference Optimization for LLM Agents AAAI 2026 Deriving Character Logic from Storyline as Codified Decision Trees ACL 2026 DermEVAL: A Dermatologist-Reviewed Benchmark for Multimodal Large Language Models WACV 2026 Describe Anything Anywhere At Any Moment CVPR 2026 Descrip3D: Enhancing Large Language Model-based 3D Scene Understanding with Object-Level Text Descriptions WACV 2026 Description Logics with Two Types of Definite Descriptions: Complexity, Expressiveness, and Automated Deduction AAAI 2026 Designed to Spread: A Generative Approach to Enhance Information Diffusion AAAI 2026