empirical study
A robust investigation that involves the collection and analysis of data based on observation or experience rather than theory alone. In AI, this often validates models and algorithms through experiments in real-world scenarios.
- Better Estimation of the Kullback--Leibler Divergence Between Language Models
- Does Thinking More Always Help? Mirage of Test-Time Scaling in Reasoning Models
- Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
- FreeInv: Free Lunch for Improving DDIM Inversion
- GIST: Greedy Independent Set Thresholding for Max-Min Diversification with Submodular Utility
- Graphs Help Graphs: Multi-Agent Graph Socialized Learning
- Homogeneous Algorithms Can Reduce Competition in Personalized Pricing
- In Search of Adam’s Secret Sauce
- In Search of Adam’s Secret Sauce
- Knee-Deep in C-RASP: A Transformer Depth Hierarchy
- Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning
- Nonparametric Quantile Regression with ReLU-Activated Recurrent Neural Networks
- Probing Equivariance and Symmetry Breaking in Convolutional Networks
- Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining
- Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study
- Why Playing Against Diverse and Challenging Opponents Speeds Up Coevolution: A Theoretical Analysis on Combinatorial Games
- You Only Communicate Once: One-shot Federated Low-Rank Adaptation of MLLM