The Secret Wasn't a Bigger Model: 500 Randomized Demos Lift Dream-1 Score 159%
paigeinsf · x · 2026-11-19
The gain came not from a bigger model but from 500 demonstrations, each starting from a randomly scrambled layout, lifting Dream-1's score 159% from 8.5 to 22.
Before fine-tuning, Dream-1 barely reached past the middle of the table — 4 of 16 toy peppers near the edges; after, 11 of 14. It even learned a rule it used to ignore: lining up cubes using only a ruler, going from a zero-shot score of 1 to 41 after fine-tuning.
More from Embodied
- SE3 Labs Releases A Wider Dream Eval, Opens 500-Episode Robot Demo Dataset on Hugging Face — paigeinsf · 2026-11-19
- LLMs zero-shot beat fine-tuned world action models on 7 of 10 robot tasks — paigeinsf · 2026-11-19
- Memory and Reasoning Remain LLM Territory: Fable Beats Dream-1 64 to 9 on Cup Task — paigeinsf · 2026-11-19
- Fine-tuned World Action Model Dream-1 Jumps 159%, Beats Frontier LLMs on Robot Tasks — paigeinsf · 2026-11-19
- Fine-tuned Dream-1 world action model jumps 159% on real-robot benchmark at 1/100th the cost — paigeinsf · 2026-11-19
- Robotics founder: "sim2real is BS" — labs buying data is a flash in the pan — Scobleizer · 2026-11-19