experimental evaluation
Experimental evaluation involves rigorously testing AI models or frameworks under controlled conditions to assess their performance, robustness, and effectiveness against predefined metrics.
- 3D Visual Illusion Depth Estimation
- Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation
- Differentially Private Quantiles with Smaller Error
- Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data
- FuXi-Ocean: A Global Ocean Forecasting System with Sub-Daily Resolution
- FuXi-Ocean: A Global Ocean Forecasting System with Sub-Daily Resolution
- Geometric Imbalance in Semi-Supervised Node Classification
- Improving planning and MBRL with temporally-extended actions
- K-DeCore: Facilitating Knowledge Transfer in Continual Structured Knowledge Reasoning via Knowledge Decoupling
- KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment
- MiniMax-Remover: Taming Bad Noise Helps Video Object Removal
- Monotone and Separable Set Functions: Characterizations and Neural Models
- OVS Meets Continual Learning: Towards Sustainable Open-Vocabulary Segmentation
- On Evaluating Policies for Robust POMDPs
- Pro3D-Editor: A Progressive Framework for Consistent and Precise 3D Editing
- Robust Satisficing Gaussian Process Bandits Under Adversarial Attacks
- Validating LLM-as-a-Judge Systems under Rating Indeterminacy