AI
๐—ฎ๐˜๐˜๐—ฒ๐—ป๐˜๐—ถ๐—ผ๐—ป ๐—ถ๐˜€ ๐—ฎ๐—น๐—น ๐˜†๐—ผ๐˜‚ ๐—ป๐—ฒ๐—ฒ๐—ฑ
Kazi  pfp
2 replies
1 recast
6 reactions

kevin j ๐Ÿ€™ pfp
0 reply
0 recast
8 reactions

Kazi  pfp
0 reply
1 recast
9 reactions

David  pfp
0 reply
0 recast
7 reactions

David  pfp
1 reply
0 recast
3 reactions

Kazi  pfp
0 reply
0 recast
7 reactions

Kuririn pfp
3 replies
0 recast
10 reactions

Claus Wilke pfp
1 reply
1 recast
15 reactions

๐š๐”ช๐Ÿพ๐šก๐šก๐Ÿพ pfp
The ฯ€โ‚€ release introduces a VLA generalist model for dexterous tasks like laundry folding and table bussing. ฯ€โ‚€ uses a transformer with flow matching, combining VLM pre-training benefits and continuous action chunks at 50Hz, and is pre-trained on a broad dataset. With distinct pre-training and post-training stages, it supports zero-shot and fine-tuned task adaptation, demonstrating robustness to external interventions, as seen in an uncut video of ฯ€โ‚€ folding laundry with a single model. ฯ€โ‚€ and its smaller, non-VLM version are evaluated against: - Octo and OpenVLA for zero-shot VLA tasks - ACT and Diffusion Policy for single tasks ฯ€โ‚€ surpasses in zero-shot accuracy, fine-tuning for new tasks, and language-following. Compute-parity ablations highlight trade-offs between VLA backbone gains and pre-training costs. Hierarchical methods like RT-H aid complex tasks needing low-level control and high-level planning, though Pi_0โ€™s robust architecture largely drives its performance. (link below)
2 replies
2 recasts
45 reactions

๐š๐”ช๐Ÿพ๐šก๐šก๐Ÿพ pfp
1 reply
0 recast
12 reactions

๐š๐”ช๐Ÿพ๐šก๐šก๐Ÿพ pfp
1 reply
2 recasts
8 reactions

๐š๐”ช๐Ÿพ๐šก๐šก๐Ÿพ pfp
0 reply
1 recast
5 reactions

๐š๐”ช๐Ÿพ๐šก๐šก๐Ÿพ pfp
0 reply
0 recast
8 reactions

๐š๐”ช๐Ÿพ๐šก๐šก๐Ÿพ pfp
OpenAIโ€™s London DevDayโ€”Romain Huet demonstrated a live drone setup in under 2 minutes using o1, along with a London Tube app built on stage. The audience gained full o1 access, including updated Realtime API pricing with caching: 50% off cached text inputs and 80% off cached audio. The Realtime API now offers five expressive voicesโ€”Coral, Verse, Ballad, Sage, and Ashโ€”supporting new speech-to-speech capabilities with steerable vocal tones. ๐Ÿ”—: https://platform.openai.com/docs/guides/realtime OpenAI launches SimpleQA, a factuality benchmark assessing language models accuracy on short, fact-seeking questions. ๐Ÿ”—: https://openai.com/index/introducing-simpleqa/ Alsoโ€”Advanced Voice is now available in macOS and Windows desktop apps. ๐Ÿ”—: https://openai.com/chatgpt/download/
1 reply
2 recasts
12 reactions

๐š๐”ช๐Ÿพ๐šก๐šก๐Ÿพ pfp
0 reply
0 recast
3 reactions