ReOPD released: Offline path planning variant offers 4x speedup
kastnerkyle · x · 2026-08-15
ReOPD code, models, and data are now available. As an offline variant of OPD, ReOPD achieves a 4x speedup without requiring an online environment and suffers no performance degradation. The project optimizes path planning algorithms, with the preprint, code, and model weights released.
More from Research
- Faraday 27B Launch: Outperforms Claude and GPT-4.5 in Replicating Papers — jzl86 · 2026-08-15
- Kaggle study reveals 3D U-Nets beat Vision Transformers in Cryo-ET challenge — bravo_abad · 2026-08-15
- Study Finds Repeated Sampling Beats Self-Reflection for LLMs at Equal Token Cost — rohanpaul_ai · 2026-08-15
- Editing one fact in an LLM can break the reasoning around it — bravo_abad · 2026-08-15
- Reflection: The golden decade of Deep Learning (2012-2022) — jzl86 · 2026-08-15
- IJCAI 2026 tutorial: building unified multimodal models from tokenizers to training — jindong_wang92 · 2026-08-15