Follow
Kamyar Ghasemipour
Kamyar Ghasemipour
University of Toronto, Vector Institute
Verified email at cs.toronto.edu - Homepage
Title
Cited by
Cited by
Year
Photorealistic text-to-image diffusion models with deep language understanding
C Saharia, W Chan, S Saxena, L Li, J Whang, EL Denton, K Ghasemipour, ...
Advances in neural information processing systems 35, 36479-36494, 2022
45262022
A divergence minimization perspective on imitation learning methods
SKS Ghasemipour, R Zemel, S Gu
Conference on robot learning, 1259-1277, 2020
3012020
Acme: A research framework for distributed reinforcement learning
MW Hoffman, B Shahriari, J Aslanides, G Barth-Maron, N Momchev, ...
arXiv preprint arXiv:2006.00979, 2020
2512020
Emaq: Expected-max q-learning operator for simple yet effective offline and online rl
SKS Ghasemipour, D Schuurmans, SS Gu
International Conference on Machine Learning, 3682-3691, 2021
1222021
Why so pessimistic? estimating uncertainties for offline rl through ensembles, and why their independence matters
K Ghasemipour, SS Gu, O Nachum
Advances in Neural Information Processing Systems 35, 18267-18281, 2022
532022
Smile: Scalable meta inverse reinforcement learning through context-conditional policies
SK Seyed Ghasemipour, SS Gu, R Zemel
Advances in Neural Information Processing Systems 32, 2019
462019
Learning interactive real-world simulators
M Yang, Y Du, K Ghasemipour, J Tompson, D Schuurmans, P Abbeel
arXiv preprint arXiv:2310.06114, 2023
272023
Blocks assemble! learning to assemble with large-scale structured reinforcement learning
SKS Ghasemipour, S Kataoka, B David, D Freeman, SS Gu, I Mordatch
International Conference on Machine Learning, 7435-7469, 2022
262022
Gradient-based optimization of neural network architecture
W Grathwohl, E Creager, SKS Ghasemipour, R Zemel
152018
Bi-manual manipulation and attachment via sim-to-real reinforcement learning
S Kataoka, SKS Ghasemipour, D Freeman, I Mordatch
arXiv preprint arXiv:2203.08277, 2022
132022
Braxlines: Fast and interactive toolkit for rl-driven behavior engineering beyond reward maximization
SS Gu, M Diaz, DC Freeman, H Furuta, SKS Ghasemipour, A Raichuk, ...
arXiv preprint arXiv:2110.04686, 2021
132021
Photorealistic text-to-image diffusion models with deep language understanding. ArXiv abs/2205.11487 (2022)
C Saharia, W Chan, S Saxena, L Li, J Whang, EL Denton, ...
7
Photorealistic text-to-image diffusion models with deep language understanding. arXiv e-prints, pages arXiv–2205
C Saharia, W Chan, S Saxena, L Li, J Whang, E Denton, ...
62022
Bi-Manual Block Assembly via Sim-to-Real Reinforcement Learning
S Kataoka, Y Chung, SKS Ghasemipour, P Sanketi, SS Gu, I Mordatch
arXiv preprint arXiv:2303.14870, 2023
22023
others (2022). Photorealistic text-to-image diffusion models with deep language understanding
C Saharia, W Chan, S Saxena, L Li, J Whang, E Denton, ...
arXiv preprint arXiv:2205.11487, 0
2
ALOHA Unleashed: A Simple Recipe for Robot Dexterity
TZ Zhao, J Tompson, D Driess, P Florence, SKS Ghasemipour, C Finn, ...
8th Annual Conference on Robot Learning, 0
1
ABC PROBLEM: AN INVESTIGATION OF OFFLINE RL FOR VISION-BASED DYNAMIC MANIPULATION
SKS Ghasemipour, I Mordatch, SS Gu
CSC412 Project Report
SKS Ghasemipour
PolyRNN: Polygon-based Instance Segmentation with Recurrent Neural Networks
L Castrejon, K Ghasemipour
The system can't perform the operation now. Try again later.
Articles 1–19