Adel Bibi

8

Papers

68

Total Citations

Papers (8)

When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations

Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models

SimCS: Simulation for Domain Incremental Online Continual Segmentation

Towards Certification of Uncertainty Calibration under Adversarial Attacks

Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation

Efficient Error Certification for Physics-Informed Neural Networks

Prompting a Pretrained Transformer Can Be a Universal Approximator

Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI