Roger Grosse
University of Toronto
H-index: 44
North America-Canada
Top articles of Roger Grosse
Title | Journal | Author(s) | Publication Date |
---|---|---|---|
Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo | arXiv preprint arXiv:2404.17546 | Stephen Zhao Rob Brekelmans Alireza Makhzani Roger Grosse | 2024/4/26 |
REFACTOR: Learning to Extract Theorems from Proofs | arXiv preprint arXiv:2402.17032 | Jin Peng Zhou Yuhuai Wu Qiyang Li Roger Grosse | 2024/2/26 |
Similarity-based cooperative equilibrium | Advances in Neural Information Processing Systems | Caspar Oesterheld Johannes Treutlein Roger B Grosse Vincent Conitzer Jakob Foerster | 2024/2/13 |
Sleeper agents: Training deceptive llms that persist through safety training | arXiv preprint arXiv:2401.05566 | Evan Hubinger Carson Denison Jesse Mu Mike Lambert Meg Tong | 2024/1/10 |
Studying large language model generalization with influence functions | arXiv preprint arXiv:2308.03296 | Roger Grosse Juhan Bae Cem Anil Nelson Elhage Alex Tamkin | 2023/8/7 |
Statistics estimation in neural network training: a recursive identification approach | Ruth Crasto Xuchan Bao Roger Baker Grosse | 2023/7/9 | |
Efficient parametric approximations of neural network function space distance | Nikita Dhawan Sicong Huang Juhan Bae Roger Baker Grosse | 2023/7/3 | |
Calibrating language models via augmented prompt ensembles | Mingjian Jiang Yangjun Ruan Sicong Huang Saifei Liao Silviu Pitis | 2023/6/23 | |
Improving mutual information estimation with annealed and energy-based bounds | Rob Brekelmans Sicong Huang Marzyeh Ghassemi Greg Ver Steeg Roger Baker Grosse | 2022 | |
Discovering language model behaviors with model-written evaluations | arXiv preprint arXiv:2212.09251 | Ethan Perez Sam Ringer Kamilė Lukošiūtė Karina Nguyen Edwin Chen | 2022/12/19 |
Amortized proximal optimization | Advances in Neural Information Processing Systems | Juhan Bae Paul Vicol Jeff Z HaoChen Roger B Grosse | 2022/12/6 |
On implicit bias in overparameterized bilevel optimization | Paul Vicol Jonathan Lorraine Fabian Pedregosa David Duvenaud Roger B Grosse | 2022/6/28 | |
Multi-rate vae: Train once, get the full rate-distortion curve | Juhan Bae Michael R Zhang Michael Ruan Eric Wang So Hasegawa | 2022/12/7 | |
Similarity-based cooperation | arXiv preprint arXiv:2211.14468 | Caspar Oesterheld Johannes Treutlein Roger Grosse Vincent Conitzer Jakob Foerster | 2022/11 |
Near-optimal local convergence of alternating gradient descent-ascent for minimax optimization | Guodong Zhang Yuanhao Wang Laurent Lessard Roger Grosse | 2022 | |
Path independent equilibrium models can better exploit test-time computation | Advances in Neural Information Processing Systems | Cem Anil Ashwini Pokle Kaiqu Liang Johannes Treutlein Yuhuai Wu | 2022/12/6 |
Efficient parametric approximations of neural net function space distance | Nikita Dhawan Sicong Huang Juhan Bae Roger Baker Grosse | 2022/9/29 | |
Proximal learning with opponent-learning awareness | Advances in Neural Information Processing Systems | Stephen Zhao Chris Lu Roger B Grosse Jakob Foerster | 2022/12/6 |
Toy models of superposition | arXiv preprint arXiv:2209.10652 | Nelson Elhage Tristan Hume Catherine Olsson Nicholas Schiefer Tom Henighan | 2022/9/21 |
If influence functions are the answer, then what is the question? | Advances in Neural Information Processing Systems | Juhan Bae Nathan Ng Alston Lo Marzyeh Ghassemi Roger B Grosse | 2022/12/6 |