Follow
Francesco Faccio
Francesco Faccio
Senior Research Scientist, Google DeepMind
Verified email at google.com - Homepage
Title
Cited by
Cited by
Year
Policy optimization via importance sampling
AM Metelli, M Papini, F Faccio, M Restelli
NeurIPS 2018 (oral), 2018
1142018
Mindstorms in Natural Language-Based Societies of Mind
M Zhuge*, H Liu*, F Faccio*, DR Ashley*, R Csordás, A Gopalakrishnan, ...
NeurIPSW (Best Paper Award), 2023
752023
GPTSwarm: Language Agents as Optimizable Graphs
M Zhuge, W Wang, L Kirsch, F Faccio, D Khizbullin, J Schmidhuber
ICML 2024 (oral), 2024
56*2024
Cross-attention makes inference cumbersome in text-to-image diffusion models
W Zhang, H Liu, J Xie, F Faccio, MZ Shou, J Schmidhuber
arXiv e-prints, arXiv: 2404.02747, 2024
272024
Parameter-based value functions
F Faccio, L Kirsch, J Schmidhuber
ICLR 2021, 2020
262020
Goal-conditioned generators of deep policies
F Faccio*, V Herrmann*, A Ramesh, L Kirsch, J Schmidhuber
AAAI 2023 (oral), 2023
142023
Neural differential equations for learning to program neural nets through continuous learning rules
K Irie, F Faccio, J Schmidhuber
NeurIPS 2022, 2022
142022
General Policy Evaluation and Improvement by Learning to Identify Few But Crucial States
F Faccio, A Ramesh, V Herrmann, J Harb, J Schmidhuber
Decision Awareness in Reinforcement Learning Workshop at ICML 2022, 2022
122022
Bayesian brains and the Rényi divergence
N Sajid*, F Faccio*, L Da Costa, T Parr, J Schmidhuber, K Friston
Neural Computation 34 (4), 829-855, 2022
122022
Learning to identify critical states for reinforcement learning from videos
H Liu, M Zhuge, B Li, Y Wang, F Faccio, B Ghanem, J Schmidhuber
ICCV 2023, 2023
112023
Upside-down reinforcement learning can diverge in stochastic environments with episodic resets
M Štrupl, F Faccio, DR Ashley, J Schmidhuber, RK Srivastava
arXiv preprint arXiv:2205.06595, 2022
112022
The languini kitchen: Enabling language modelling research at different scales of compute
A Stanić, D Ashley, O Serikov, L Kirsch, F Faccio, J Schmidhuber, ...
arXiv preprint arXiv:2309.11197, 2023
92023
Learning useful representations of recurrent neural network weight matrices
V Herrmann, F Faccio, J Schmidhuber
ICML 2024 (oral), 2024
82024
Language agents as optimizable graphs, 2024
M Zhuge, W Wang, L Kirsch, F Faccio, D Khizbullin, J Schmidhuber
URL https://arxiv. org/abs/2402.16823, 0
5
Reward-Weighted Regression Converges to a Global Optimum
M Štrupl*, F Faccio*, DR Ashley, RK Srivastava, J Schmidhuber
AAAI 2022, 2022
42022
How to correctly do semantic backpropagation on language-based agentic systems
W Wang, HA Alyahya, DR Ashley, O Serikov, D Khizbullin, F Faccio, ...
arXiv preprint arXiv:2412.03624, 2024
32024
Highway reinforcement learning
Y Wang, M Strupl, F Faccio, Q Wu, H Liu, M Grudzień, X Tan, ...
arXiv preprint arXiv:2405.18289, 2024
32024
Highway Value Iteration Networks
Y Wang, W Li, F Faccio, Q Wu, J Schmidhuber
ICML 2024, 2024
22024
Faster Diffusion via Temporal Attention Decomposition
H Liu, W Zhang, J Xie, F Faccio, M Xu, T Xiang, MZ Shou, JM Perez-Rua, ...
arXiv preprint arXiv:2404.02747, 2024
22024
Faster Diffusion via Temporal Attention Decomposition
H Liu, W Zhang, J Xie, F Faccio, M Xu, T Xiang, MZ Shou, JM Perez-Rua, ...
Transactions on Machine Learning Research, 2025
12025
The system can't perform the operation now. Try again later.
Articles 1–20