superior performance
Superior performance in AI indicates that a model exceeds the baseline or comparative standards established by prior research or established benchmarks. Achieving superior performance often entails innovations in model architecture, training methodologies, or data utilization.
- A Principled Path to Fitted Distributional Evaluation
- A Unified Framework for Fair Graph Generation: Theoretical Guarantees and Empirical Advances
- AF-UMC: An Alignment-Free Fusion Framework for Unaligned Multi-View Clustering
- Deep Tree Tensor Networks
- EditInfinity: Image Editing with Binary-Quantized Generative Models
- Environment Inference for Learning Generalizable Dynamical System
- Evolutionary Multi-View Classification via Eliminating Individual Fitness Bias
- Learning to Solve Complex Problems via Dataset Decomposition
- MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details
- Multi-Objective One-Shot Pruning for Large Language Models
- Put CASH on Bandits: A Max K-Armed Problem for Automated Machine Learning
- Sequential Multi-Agent Dynamic Algorithm Configuration
- Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought