Παρακολούθηση
Muhammed T Razzak
Muhammed T Razzak
University of Oxford
Η διεύθυνση ηλεκτρονικού ταχυδρομείου έχει επαληθευτεί στον τομέα cs.ox.ac.uk - Αρχική σελίδα
Τίτλος
Παρατίθεται από
Παρατίθεται από
Έτος
Prioritized training on points that are learnable, worth learning, and not yet learnt
S Mindermann*, MT Razzak*, W Xu*, A Kirsch, M Sharma, A Morisot, ...
International Conference on Machine Learning, 15630-15649, 2022
1492022
Multi-spectral multi-image super-resolution of Sentinel-2 with radiometric consistency losses and its effect on building delineation
MT Razzak, G Mateo-García, G Lecuyer, L Gómez-Chova, Y Gal, ...
ISPRS Journal of Photogrammetry and Remote Sensing 195, 1-13, 2023
482023
Semantic entropy probes: Robust and cheap hallucination detection in llms
J Kossen*, J Han*, M Razzak*, L Schut, S Malik, Y Gal
arXiv preprint arXiv:2406.15927, 2024
17*2024
Prioritized training on points that are learnable, worth learning, and not yet learned (workshop version)
S Mindermann, M Razzak, W Xu, A Kirsch, M Sharma, A Morisot, ...
arXiv preprint arXiv:2107.02565, 2021
22021
Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy
BA Tjandra*, M Razzak*, J Kossen*, K Handa, Y Gal
arXiv preprint arXiv:2410.17234, 2024
2024
The Benefits and Risks of Transductive Approaches for AI Fairness
M Razzak, A Kirsch, Y Gal
arXiv preprint arXiv:2406.12011, 2024
2024
Semantic Entropy Neurons: Encoding Semantic Uncertainty in the Latent Space of LLMs
J Han, J Kossen, M Razzak, Y Gal
2024
Efficient Experimentation for Estimation of Continuous and Discrete Conditional Treatment Effects
M Razzak*, P Tigas*, A Jesson, Y Gal, U Shalit
NeurIPS 2024 Workshop on Bayesian Decision-making and Uncertainty, 2024
2024
Interactive Segmentation for Disaster Relief Mapping
M Razzak, K Sankaran
AI for Social Good Workshop, IJCAI, 2019
2019
Δεν είναι δυνατή η εκτέλεση της ενέργειας από το σύστημα αυτή τη στιγμή. Προσπαθήστε ξανά αργότερα.
Άρθρα 1–9