I agree that this site is using cookies. You can find further informations here.
X
Uesato, Jonathan
28  results:
Search for persons X
?
1

Taxonomy of Risks posed by Language Models:

, In: 2022 ACM Conference on Fairness, Accountability, and Transparency,
Weidinger, Laura ; Uesato, Jonathan ; Rauh, Maribeth... - p. 214-229 , 2022
Link: https://dl.acm.org/doi/1..
 
?
2

Scalable Verified Training for Provably Robust Image Classi..:

, In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV),
Gowal, Sven ; Dvijotham, Krishnamurthy ; Stanforth, Robert... - p. 4841-4850 , 2019
Link: https://doi.org/10.1109/..
 
?
3

Robustness via Curvature Regularization, and Vice Versa:

, In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),
Moosavi-Dezfooli, Seyed-Mohsen ; Fawzi, Alhussein ; Uesato, Jonathan. - p. 9070-9078 , 2019
Link: https://doi.org/10.1109/..
 
?
4

Solving math word problems with process- and outcome-based ..:

Uesato, Jonathan ; Kushman, Nate ; Kumar, Ramana...
http://arxiv.org/abs/2211.14275.  , 2022
Link: http://arxiv.org/abs/221..
 
?
5

Characteristics of Harmful Text: Towards Rigorous Benchmark..:

Rauh, Maribeth ; Mellor, John ; Uesato, Jonathan...
http://arxiv.org/abs/2206.08325.  , 2022
Link: http://arxiv.org/abs/220..
 
?
6

Improving alignment of dialogue agents via targeted human j..:

Glaese, Amelia ; McAleese, Nat ; Trębacz, Maja...
http://arxiv.org/abs/2209.14375.  , 2022
Link: http://arxiv.org/abs/220..
 
?
7

Goal Misgeneralization: Why Correct Specifications Aren't E..:

Shah, Rohin ; Varma, Vikrant ; Kumar, Ramana...
http://arxiv.org/abs/2210.01790.  , 2022
Link: http://arxiv.org/abs/221..
 
?
8

Make Sure You're Unsure: A Framework for Verifying Probabil..:

Berrada, Leonard ; Dathathri, Sumanth ; Dvijotham, Krishnamurthy...
http://arxiv.org/abs/2102.09479.  , 2021
Link: http://arxiv.org/abs/210..
 
?
9

Scaling Language Models: Methods, Analysis & Insights from ..:

Rae, Jack W ; Borgeaud, Sebastian ; Cai, Trevor...
http://arxiv.org/abs/2112.11446.  , 2021
Link: http://arxiv.org/abs/211..
 
?
10

Challenges in Detoxifying Language Models:

Welbl, Johannes ; Glaese, Amelia ; Uesato, Jonathan...
http://arxiv.org/abs/2109.07445.  , 2021
Link: http://arxiv.org/abs/210..
 
?
11

An Empirical Investigation of Learning from Biased Toxicity..:

Nanda, Neel ; Uesato, Jonathan ; Gowal, Sven
http://arxiv.org/abs/2110.01577.  , 2021
Link: http://arxiv.org/abs/211..
 
?
12

Ethical and social risks of harm from Language Models:

Weidinger, Laura ; Mellor, John ; Rauh, Maribeth...
http://arxiv.org/abs/2112.04359.  , 2021
Link: http://arxiv.org/abs/211..
 
?
13

Uncovering the Limits of Adversarial Training against Norm-..:

Gowal, Sven ; Qin, Chongli ; Uesato, Jonathan..
http://arxiv.org/abs/2010.03593.  , 2020
Link: http://arxiv.org/abs/201..
 
?
14

Enabling certification of verification-agnostic networks vi..:

Dathathri, Sumanth ; Dvijotham, Krishnamurthy ; Kurakin, Alexey...
http://arxiv.org/abs/2010.11645.  , 2020
Link: http://arxiv.org/abs/201..
 
?
15

REALab: An Embedded Perspective on Tampering:

Kumar, Ramana ; Uesato, Jonathan ; Ngo, Richard...
http://arxiv.org/abs/2011.08820.  , 2020
Link: http://arxiv.org/abs/201..
 
1-15