Research map / Large language models / AI and society
torchgfn: A PyTorch GFlowNet Library
Joseph D. Viviano, Omar G. Younis, Sanghyeok Choi, Victor Schmidt, Yoshua Bengio, Salem Lahlou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use torchgfn instead of gflownet | GFlowNet library · HyperGrid Small | per-iteration time (ms): 141.4 -> 30.8 | Improved |
| use torchgfn instead of gflownet | GFlowNet library · HyperGrid Medium | per-iteration time (ms): 223.0 -> 77.8 | Improved |
| use torchgfn instead of gflownet | GFlowNet library · HyperGrid Large | per-iteration time (ms): 364.7 -> 113.3 | Improved |
| use gfnx (JAX) instead of torchgfn | GFlowNet library · HyperGrid Small | per-iteration time (ms): 30.8 -> 2.5 | Improved |
| use gfnx (JAX) instead of torchgfn | GFlowNet library · HyperGrid Large | per-iteration time (ms): 113.3 -> 10.8 | Improved |
| use gfnx (JAX) instead of torchgfn | GFlowNet library · HyperGrid Large | memory (MB): 55 -> 361 | Hurt |
Closest papers by meaning
- gfnx: Fast and Scalable Library for Generative Flow Networks in JAX (NeurIPS 2026 · similarity 0.88)
- Revisiting Non-Acyclic GFlowNets in Discrete Environments (ICML 2025 · similarity 0.88)
- Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks (ICLR 2025 · similarity 0.88)
- Pessimistic Backward Policy for GFlowNets (NeurIPS 2024 · similarity 0.87)
- Pre-Training and Fine-Tuning Generative Flow Networks (ICLR 2024 · similarity 0.87)
- Flow Factorization for Efficient Generative Flow Networks (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
