Flow network based generative models for non-iterative diverse candidate generation. Emmanuel Bengio, Moksh Jain, Maksym Korablyov, Doina Precup, Yoshua Bengio. Neural Information Processing Systems (NeurIPS). 2021. paper core theory loss
Probabilistic inference with GFlowNets - Bibliography
Bibliography
This page is designed to contain a bibliography collection of scientific literature related to GFlowNets. The page is still work in progress though, so the current content is likely to miss important references and is not well organised yet. If you have suggestions to add to the list, please do get in touch.
Trajectory balance: Improved credit assignment in GFlowNets. Nikolay Malkin, Moksh Jain, Emmanuel Bengio, Chen Sun, Yoshua Bengio. Neural Information Processing Systems (NeurIPS). 2022. paper core theory methods loss
GFlowNet Foundations. Yoshua Bengio, Salem Lahlou, Tristan Deleu, Edward J. Hu, Mo Tiwari, Emmanuel Bengio. Journal of Machine Learning Research (JMLR). 2023. paper core theory loss
Learning GFlowNets from partial episodes for improved convergence and stability. Kanika Madan, Jarrid Rector-Brooks, Maksym Korablyov, Emmanuel Bengio, Moksh Jain, Andrei Nica, Tom Bosc, Yoshua Bengio, Nikolay Malkin. International Conference on Machine Learning (ICML). 2023. paper core theory loss
Better training of GFlowNets with local credit and incomplete trajectories. Ling Pan, Nikolay Malkin, Dinghuai Zhang, Yoshua Bengio. International Conference on Machine Learning (ICML). 2023. paper theory methods loss
Learning energy decompositions for partial inference of GFlowNets. Hyosoon Jang, Minsu Kim, Sungsoo Ahn. arXiv:2310.03301. 2023. paper theory methods loss
Crystal-GFN: sampling crystals with desirable properties and constraints. Mila AI4Science, Alex Hernandez-Garcia, Alexandre Duval, Alexandra Volokhova, Yoshua Bengio, Divya Sharma, Pierre Luc Carrier, Yasmine Benabed, Michał Koziarski, Victor Schmidt. Neural Information Processing Systems (NeurIPS), Workshop on Accelerated Materials Design (AI4Mat). 2023. paper applications
Towards equilibrium molecular conformation generation with GFlowNets. Alexandra Volokhova, Michał Koziarski, Alex Hernandez-Garcia, Cheng-Hao Liu, Santiago Miret, Pablo Lemos, Luca Thiede, Zichao Yan, Alán Aspuru-Guzik, Yoshua Bengio. Digital Discovery, Royal Society of Chemistry. 2023. paper applications
GFlowNets for AI-driven scientific discovery. Moksh Jain, Tristan Deleu, Jason Hartford, Cheng-Hao Liu, Alex Hernandez-Garcia, Yoshua Bengio. Digital Discovery, Royal Society of Chemistry. 2023. paper review
A theory of continuous generative flow networks. Salem Lahlou, Tristan Deleu, Pablo Lemos, Dinghuai Zhang, Alexandra Volokhova, Alex Hernandez-Garcia, Léna Néhale Ezzine, Yoshua Bengio, Nikolay Malkin. International Conference on Machine Learning (ICML). 2023. paper theory methods
Multi-Objective GFlowNets. Moksh Jain, Sharath Chandra Raparthy, Alex Hernandez-Garcia, Jarrid Rector-Brooks, Yoshua Bengio, Santiago Miret, Emmanuel Bengio. International Conference on Machine Learning (ICML). 2023. paper theory methods applications
Biological sequence design with GFlowNets. Moksh Jain, Emmanuel Bengio, Alex Hernandez-Garcia, Jarrid Rector-Brooks, Bonaventure F. P. Dossou, Chanakya Ekbote, Jie Fu, Tianyu Zhang, Micheal Kilgour, Dinghuai Zhang, Lena Simine, Payel Das, Yoshua Bengio. International Conference on Machine Learning (ICML). 2023. paper methods applications activelearning
Robust Scheduling with GFlowNets. David W. Zhang, Corrado Rainone, Markus Peschl, Roberto Bondesan. International Conference on Learning Representations (ICLR). 2023. paper loss applications
GFlowNets with human feedback. Yinchuan Li, Shuang Luo, Yunfeng Shao, Jianye Hao. International Conference on Learning Representations (ICLR). 2023. paper applications LLMs
Better training of GFlowNets with local credit and incomplete trajectories. Ling Pan, Nikolay Malkin, Dinghuai Zhang, Yoshua Bengio. International Conference on Machine Learning (ICML). 2023. paper theory methods loss
Learning energy decompositions for partial inference of GFlowNets. Hyosoon Jang, Minsu Kim, Sungsoo Ahn. arXiv:2310.03301. 2023. paper theory methods loss
Crystal-GFN: sampling crystals with desirable properties and constraints. Mila AI4Science, Alex Hernandez-Garcia, Alexandre Duval, Alexandra Volokhova, Yoshua Bengio, Divya Sharma, Pierre Luc Carrier, Yasmine Benabed, Michał Koziarski, Victor Schmidt. Neural Information Processing Systems (NeurIPS), Workshop on Accelerated Materials Design (AI4Mat). 2023. paper applications
Towards equilibrium molecular conformation generation with GFlowNets. Alexandra Volokhova, Michał Koziarski, Alex Hernandez-Garcia, Cheng-Hao Liu, Santiago Miret, Pablo Lemos, Luca Thiede, Zichao Yan, Alán Aspuru-Guzik, Yoshua Bengio. Digital Discovery, Royal Society of Chemistry. 2023. paper applications
GFlowNets for AI-driven scientific discovery. Moksh Jain, Tristan Deleu, Jason Hartford, Cheng-Hao Liu, Alex Hernandez-Garcia, Yoshua Bengio. Digital Discovery, Royal Society of Chemistry. 2023. paper review
A theory of continuous generative flow networks. Salem Lahlou, Tristan Deleu, Pablo Lemos, Dinghuai Zhang, Alexandra Volokhova, Alex Hernandez-Garcia, Léna Néhale Ezzine, Yoshua Bengio, Nikolay Malkin. International Conference on Machine Learning (ICML). 2023. paper theory methods
Multi-Objective GFlowNets. Moksh Jain, Sharath Chandra Raparthy, Alex Hernandez-Garcia, Jarrid Rector-Brooks, Yoshua Bengio, Santiago Miret, Emmanuel Bengio. International Conference on Machine Learning (ICML). 2023. paper theory methods applications
Biological sequence design with GFlowNets. Moksh Jain, Emmanuel Bengio, Alex Hernandez-Garcia, Jarrid Rector-Brooks, Bonaventure F. P. Dossou, Chanakya Ekbote, Jie Fu, Tianyu Zhang, Micheal Kilgour, Dinghuai Zhang, Lena Simine, Payel Das, Yoshua Bengio. International Conference on Machine Learning (ICML). 2023. paper methods applications activelearning
Robust Scheduling with GFlowNets. David W. Zhang, Corrado Rainone, Markus Peschl, Roberto Bondesan. International Conference on Learning Representations (ICLR). 2023. paper loss applications
GFlowNets with human feedback. Yinchuan Li, Shuang Luo, Yunfeng Shao, Jianye Hao. International Conference on Learning Representations (ICLR). 2023. paper applications LLMs
Improved off-policy reinforcement learning in biological sequence design. Hyeonah Kim, Minsu Kim, Taeyoung Yun, Sanghyeok Choi, Emmanuel Bengio, Alex Hernandez-Garcia, Jinkyoo Park. arXiv:2410.04461. 2024. paper methods
Multi-Fidelity Active Learning with GFlowNets. Alex Hernandez-Garcia, Nikita Saxena, Moksh Jain, Cheng-Hao Liu, Yoshua Bengio. Transactions on Machine Learning Research (TMLR). 2024. paper activelearning applications
GDPO: learning to directly align language models with diversity using GFlowNets. Oh Joon Kwon, Daiki E. Matsunaga, Kee-Eung Kim. arXiv:2410.15096. 2024. paper applications LLMs
GFlowNet fine-tuning for diverse correct solutions in mathematical reasoning tasks. Ryoichi Takase, Masaya Tsunokake, Yuta Tsuchiya, Shota Inuzuka. arXiv:2410.20147. 2024. paper applications LLMs
Amortizing intractable inference in large language models. Edward J. Hu, Moksh Jain, Eric Elmoznino, Younesse Kaddar, Guillaume Lajoie, Yoshua Bengio, Nikolay Malkin. International Conference on Learning Representations (ICLR). 2024. paper applications LLMs
Latent logic tree extraction for event sequence explanation from LLMs. Zitao Song, Chao Yang, Chaojie Wang, Bo An, Shuang Li. International Conference on Machine Learning (ICML). 2024. paper applications LLMs
Preference alignment with flow matching. Minu Kim, Yongsik Lee, Sehyeok Kang, Jihwan Oh, Song Chong, Se-Young Yun. Neural Information Processing Systems (NeurIPS). 2024. paper applications LLMs
GFlowNet training by policy gradients. Puhua Niu, Shili Wu, Mingzhou Fan, Xiaoning Qian. nternational Conference on Machine Learning. 2024. paper core theory loss
Improved off-policy reinforcement learning in biological sequence design. Hyeonah Kim, Minsu Kim, Taeyoung Yun, Sanghyeok Choi, Emmanuel Bengio, Alex Hernandez-Garcia, Jinkyoo Park. arXiv:2410.04461. 2024. paper methods
Multi-Fidelity Active Learning with GFlowNets. Alex Hernandez-Garcia, Nikita Saxena, Moksh Jain, Cheng-Hao Liu, Yoshua Bengio. Transactions on Machine Learning Research (TMLR). 2024. paper activelearning applications
GDPO: learning to directly align language models with diversity using GFlowNets. Oh Joon Kwon, Daiki E. Matsunaga, Kee-Eung Kim. arXiv:2410.15096. 2024. paper applications LLMs
GFlowNet fine-tuning for diverse correct solutions in mathematical reasoning tasks. Ryoichi Takase, Masaya Tsunokake, Yuta Tsuchiya, Shota Inuzuka. arXiv:2410.20147. 2024. paper applications LLMs
Amortizing intractable inference in large language models. Edward J. Hu, Moksh Jain, Eric Elmoznino, Younesse Kaddar, Guillaume Lajoie, Yoshua Bengio, Nikolay Malkin. International Conference on Learning Representations (ICLR). 2024. paper applications LLMs
Latent logic tree extraction for event sequence explanation from LLMs. Zitao Song, Chao Yang, Chaojie Wang, Bo An, Shuang Li. International Conference on Machine Learning (ICML). 2024. paper applications LLMs
Preference alignment with flow matching. Minu Kim, Yongsik Lee, Sehyeok Kang, Jihwan Oh, Song Chong, Se-Young Yun. Neural Information Processing Systems (NeurIPS). 2024. paper applications LLMs
GFlowNet training by policy gradients. Puhua Niu, Shili Wu, Mingzhou Fan, Xiaoning Qian. International Conference on Machine Learning (ICML). 2024. paper methods
Generative flow networks: theory and applications to structure learning. Tristan Deleu. PhD thesis. 2025. paper theory applications
Action abstractions for amortized sampling. Oussama Boussif, Léna Néhale Ezzine, Joseph D Viviano, Michał Koziarski, Moksh Jain, Nikolay Malkin, Emmanuel Bengio, Rim Assouel, Yoshua Bengio. International Conference on Learning Representations (ICLR). 2025. paper methods
Learning decision trees as amortized structure inference. Mohammed Mahfoud, Ghait Boukachab, Michał Koziarski, Alex Hernandez-Garcia, Stefan Bauer, Yoshua Bengio, Nikolay Malkin. arXiv:2503.06985. 2025. paper applications theory
Flow of reasoning: Training LLMs for divergent reasoning with minimal examples. Fangxu Yu, Lai Jiang, Haoqiang Kang, Shibo Hao, Lianhui Qin. International Conference on Machine Learning (ICML). 2025. paper applications LLMs
Reinforced sequential Monte Carlo for amortised sampling. Sanghyeok Choi, Sarthak Mittal, Víctor Elvira, Jinkyoo Park, Nikolay Malkin. arXiv:2510.11711. 2025. paper methods theory
Generative flow networks: theory and applications to structure learning. Tristan Deleu. PhD thesis. 2025. paper theory applications
Action abstractions for amortized sampling. Oussama Boussif, Léna Néhale Ezzine, Joseph D Viviano, Michał Koziarski, Moksh Jain, Nikolay Malkin, Emmanuel Bengio, Rim Assouel, Yoshua Bengio. International Conference on Learning Representations (ICLR). 2025. paper methods
Learning decision trees as amortized structure inference. Mohammed Mahfoud, Ghait Boukachab, Michał Koziarski, Alex Hernandez-Garcia, Stefan Bauer, Yoshua Bengio, Nikolay Malkin. arXiv:2503.06985. 2025. paper applications theory
Flow of reasoning: Training LLMs for divergent reasoning with minimal examples. Fangxu Yu, Lai Jiang, Haoqiang Kang, Shibo Hao, Lianhui Qin. International Conference on Machine Learning (ICML). 2025. paper applications LLMs
Reinforced sequential Monte Carlo for amortised sampling. Sanghyeok Choi, Sarthak Mittal, Víctor Elvira, Jinkyoo Park, Nikolay Malkin. arXiv:2510.11711. 2025. paper methods theory