Παρακολούθηση
Francois Charton
Francois Charton
Research engineer, FAIR, Meta
Η διεύθυνση ηλεκτρονικού ταχυδρομείου έχει επαληθευτεί στον τομέα fb.com
Τίτλος
Παρατίθεται από
Παρατίθεται από
Έτος
Deep learning for symbolic mathematics
G Lample, F Charton
International Conference on Learning Representations (ICLR) 2020, 2019
5612019
End-to-end symbolic regression with transformers
PA Kamienny, S d'Ascoli, G Lample, F Charton
Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS) 2022, 2022
1842022
Leveraging automated unit tests for unsupervised code translation
B Roziere, JM Zhang, F Charton, M Harman, G Synnaeve, G Lample
International Conference on Learning Representations (ICLR) 2022, 2021
1252021
Deep symbolic regression for recurrence prediction
S d’Ascoli, PA Kamienny, G Lample, F Charton
International Conference on Machine Learning, ICML, 2022, 4520-4536, 2022
79*2022
Code translation with compiler representations
M Szafraniec, B Roziere, HLF Charton, P Labatut, G Synnaeve
International conference on learning representations (ICLR) 2023, 2022
762022
Linear algebra with transformers
F Charton
Transactions on Machine Learning Research (TMLR) October 2022, 2021
672021
A tale of tails: Model collapse as a change of scaling laws
E Dohmatob, Y Feng, P Yang, F Charton, J Kempe
arXiv preprint arXiv:2402.07043, 2024
522024
Learning advanced mathematical computations from examples
F Charton, A Hayat, G Lample
International Conference on Learning Representations (ICLR) 2021, 2020
42*2020
SALSA: Attacking Lattice Cryptography with Transformers
E Wenger, M Chen, F Charton, K Lauter
Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS) 2022, 2022
392022
Length generalization in arithmetic transformers
S Jelassi, S d'Ascoli, C Domingo-Enrich, Y Wu, Y Li, F Charton
arXiv preprint arXiv:2306.15400, 2023
352023
Learning the greatest common divisor: explaining transformer predictions
F Charton
arXiv preprint arXiv:2308.15594, 2023
23*2023
Back-to-back regression: Disentangling the influence of correlated factors from multivariate observations
JR King, F Charton, D Lopez-Paz, M Oquab
NeuroImage 220, 117028, 2020
22*2020
Transforming the bootstrap: using transformers to compute scattering amplitudes in planar super Yang–Mills theory
T Cai, GW Merz, F Charton, N Nolte, M Wilhelm, K Cranmer, LJ Dixon
Machine Learning: Science and Technology 5 (3), 035073, 2024
172024
What is my math transformer doing?--Three results on interpretability and generalization
F Charton
The 2nd Workshop on Mathematical Reasoning and AI at NeurIPS'22, 2022
172022
Beyond model collapse: Scaling up with synthesized data requires reinforcement
Y Feng, E Dohmatob, P Yang, F Charton, J Kempe
ICML 2024 Workshop on Theoretical Foundations of Foundation Models, 2024
162024
SALSA VERDE: a machine learning attack on LWE with sparse small secrets
CY Li, E Wenger, Z Allen-Zhu, F Charton, KE Lauter
Thirty-seventh Conference on Neural Information Processing Systems, 2024, 2023
142023
SALSA PICANTE: a machine learning attack on LWE with binary secrets
C Li, J Sotáková, E Wenger, M Malhou, E Garcelon, F Charton, K Lauter
The thirtieth ACM Conference on Computer and Communications Security (CCS) 2023, 2023
122023
Global Lyapunov functions: a long-standing open problem in mathematics, with symbolic transformers
A Alfarano, F Charton, A Hayat
Advances in Neural Information Processing Systems 37, 93643-93670, 2025
102025
Iteration head: A mechanistic study of chain-of-thought
V Cabannes, C Arnal, W Bouaziz, X Yang, F Charton, J Kempe
Advances in Neural Information Processing Systems 37, 109101-109122, 2025
62025
PatternBoost: Constructions in mathematics with a little help from AI
F Charton, JS Ellenberg, AZ Wagner, G Williamson
arXiv preprint arXiv:2411.00566, 2024
52024
Δεν είναι δυνατή η εκτέλεση της ενέργειας από το σύστημα αυτή τη στιγμή. Προσπαθήστε ξανά αργότερα.
Άρθρα 1–20