Nadav Timor(@NadavTimor):the gains come entirely from wrapping π0.5 in an agent that plans, verifies, and recovers. no new finetuning. @lianegalanti and team make the case that "agents for robots" can narrow capability gaps in off-the-shelf robot policies.

Nadav Timor

@NadavTimor

AI inference, speculative decoding, open source. Built novel decoding algorithms – default in Hugging Face Transformers (160+ ⭐). Making AI faster + cheaper

加入 December 2017

7.5K 正在關注 1.4K 粉絲

Nadav Timor@NadavTimor

2026.07.28 21:42

the gains come entirely from wrapping π0.5 in an agent that plans, verifies, and recovers. no new finetuning. @lianegalanti and team make the case that "agents for robots" can narrow capability gaps in off-the-shelf robot policies.