design choices
Design choices in AI research encompass decisions regarding model architecture, data processing, and algorithm selection that can significantly affect the performance and efficiency of AI systems.
- Anytime-valid, Bayes-assisted, Prediction-Powered Inference
- GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights
- Generalizable Insights for Graph Transformers in Theory and Practice
- Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better
- Overcoming Challenges of Long-Horizon Prediction in Driving World Models
- SMRS: advocating a unified reporting standard for surrogate models in the artificial intelligence era.
- Towards a Golden Classifier-Free Guidance Path via Foresight Fixed Point Iterations
- UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?