8 citations · 18 across the 12 of their papers we have counts for
15 papers
Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models
Francisco Eiras, Aleksandar Petrov, Philip H. S. Torr +2
Recent research shows that fine-tuning on benign instruction-following data can inadvertently undo the safety alignment process and increase a model's propensity to comply with har…
Risks and Opportunities of Open-Source Generative AI
Francisco Eiras, Aleksandar Petrov, Bertie Vidgen +22
Applications of Generative AI (Gen AI) are expected to revolutionize a number of different areas, ranging from science & medicine to education. The potential for these seismic chan…
Near to Mid-term Risks and Opportunities of Open-Source Generative AI
Francisco Eiras, Aleksandar Petrov, Bertie Vidgen +21
In the next few years, applications of Generative AI are expected to revolutionize a number of different areas, ranging from science & medicine to education. The potential for thes…
Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation
Francisco Eiras, Kemal Oksuz, Adel Bibi +2
Referring Image Segmentation (RIS) - the problem of identifying objects in images through natural language sentences - is a challenging task currently mostly solved through supervi…
Faithful Knowledge Distillation
Tom A. Lamb, Rudy Brunel, Krishnamurthy DJ Dvijotham +3
Knowledge distillation (KD) has received much attention due to its success in compressing networks to allow for their deployment in resource-constrained systems. While the problem…
Efficient Error Certification for Physics-Informed Neural Networks
Francisco Eiras, Adel Bibi, Rudy Bunel +3
Recent work provides promising evidence that Physics-Informed Neural Networks (PINN) can efficiently solve partial differential equations (PDE). However, previous works have failed…
Certifying Ensembles: A General Certification Theory with S-Lipschitzness
Aleksandar Petrov, Francisco Eiras, Amartya Sanyal +2
Improving and guaranteeing the robustness of deep learning models has been a topic of intense research. Ensembling, which combines several classifiers to provide a better model, ha…
Interpretable Goal Recognition in the Presence of Occluded Factors for Autonomous Vehicles
Josiah P. Hanna, Arrasy Rahman, Elliot Fosong +5
Recognising the goals or intentions of observed vehicles is a key step towards predicting the long-term future behaviour of other agents in an autonomous driving scenario. When the…
ANCER: Anisotropic Certification via Sample-wise Volume Maximization
Francisco Eiras, Motasem Alfarra, M. Pawan Kumar +4
Randomized smoothing has recently emerged as an effective tool that enables certification of deep neural network classifiers at scale. All prior art on randomized smoothing has foc…
PILOT: Efficient Planning by Imitation Learning and Optimisation for Safe Autonomous Driving
Henry Pulver, Francisco Eiras, Ludovico Carozza +3
Achieving a proper balance between planning quality, safety and efficiency is a major challenge for autonomous driving. Optimisation-based motion planners are capable of producing…
Interpretable Goal-based Prediction and Planning for Autonomous Driving
Stefano V. Albrecht, Cillian Brewitt, John Wilhelm +4
We propose an integrated prediction and planning system for autonomous driving which uses rational inverse planning to recognise the goals of other vehicles. Goal recognition infor…
A Two-Stage Optimization-based Motion Planner for Safe Urban Driving
Francisco Eiras, Majd Hawasly, Stefano V. Albrecht +1
Recent road trials have shown that guaranteeing the safety of driving decisions is essential for the wider adoption of autonomous vehicle technology. One promising direction is to…
PaRoT: A Practical Framework for Robust Deep Neural Network Training
Edward Ayers, Francisco Eiras, Majd Hawasly +1
Deep Neural Networks (DNNs) are finding important applications in safety-critical systems such as Autonomous Vehicles (AVs), where perceiving the environment correctly and robustly…
Correct-by-Construction Advanced Driver Assistance Systems based on a Cognitive Architecture
Francisco Eiras, Morteza Lahijanian, Marta Kwiatkowska
Research into safety in autonomous and semi-autonomous vehicles has, so far, largely been focused on testing and validation through simulation. Due to the fact that failure of thes…
Analytical Modeling of Vanishing Points and Curves in Catadioptric Cameras
Pedro Miraldo, Francisco Eiras, Srikumar Ramalingam
Vanishing points and vanishing lines are classical geometrical concepts in perspective cameras that have a lineage dating back to 3 centuries. A vanishing point is a point on the i…