Generative Flow Networks (GFlowNets)
Avyav Singh presented the collection of papers that elucidate Generative Flow Networks (Hu et al., 2023) (Bengio et al., 2023), (Madan et al., 2023) and (Malkin et al., 2022).
Abstract
This talk explored the development of Generative Flow Networks (GFlowNets). We dissucssed how the use of amortized Bayesian inference to sample intractable posteriors, achieved through LLMs fine-tuning and diversity prioritised reinforcement learning algorithms enables data-efficient adaptation of LLMs.
References
- Amortizing intractable inference in large language modelsarXiv preprint arXiv:2310.04363, 2023
- Gflownet foundationsJournal of Machine Learning Research, 2023
- Learning gflownets from partial episodes for improved convergence and stabilityIn International Conference on Machine Learning, 2023
- Trajectory balance: Improved credit assignment in gflownetsAdvances in Neural Information Processing Systems, 2022
Enjoy Reading This Article?
Here are some more articles you might like to read next: