# Is DreamFAR SOTA?

Pending benchmarks. Announced Oct 29, 2026; no independent results yet.

As of Nov 3, 2026, DreamFAR is pending benchmarks on isitsota: announced Oct 29, 2026, with no independent results on the boards we track yet.

Amazon FAR's action-conditioned world model for bimanual robot manipulation. It predicts the next camera frames from robot actions, so a person, a recorded episode or a policy can drive a simulated robot in real time. Its dynamics model is trained from scratch on robot teleoperation data with no internet-video pretraining. A live web demo is public; code and weights are announced but not yet released.

Canonical: https://isitsota.com/m/dreamfar
Last updated: 2026-10-30
Tracking since: 2026-10-30

## Announced facts

| Fact | Value |
| --- | --- |
| Lab | Amazon |
| Announced | Oct 29, 2026 |
| API | Not yet |
| Open weights | Announced, not yet published · Code and model weights announced as coming soon; none published yet |
| Parameters | 1.9B dynamics transformer plus a 46M encoder and 50M decoder tokenizer (paper figures; weights not yet released) (unsure) |
| Type | Action-conditioned robot world model (latent flow matching) for bimanual manipulation |
| Architecture | Causal transformer with 28 blocks of hidden size 2048 that predicts the next latent frame from the action, recent frames and contact-based memory keyframes retrieved by end-effector pose |
| Tokenizer | Unit-sphere tokenizer fine-tuned from a pretrained SSDD-M checkpoint; each 256 x 256 camera view becomes a 16 x 16 grid of 16-dimensional latents |
| Training data | Internal bimanual teleoperation dataset on YAM robots (two 6-DoF arms with parallel grippers, three camera views, 14-D actions at 10 Hz); dynamics trained from scratch, no internet-video pretraining |
| Training compute | 256 H200 GPUs for six days |
| Context | 5-second window of 50 frames plus eight memory slots and one learned sink frame |
| Control inputs | Recorded actions, a policy, or a person via mouse, keyboard, webcam hand tracking or GELLO leader arms |
| Live demo | Public web demo on the project page; one driver at a time in 4-minute sessions |
| Paper | 14-page PDF on the project page; no arXiv listing |
| Authors | Amazon FAR, with co-authors from Cornell University, University of Maryland and University of Pennsylvania |
| Release | Project page and X announcement Oct 29, 2026 |

Tags marked unsure are not stated on the lab's own pages.

## What would let us call it

Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.

- [x] Publicly announced with a source
- [ ] Usable by the public (API or weights)
- [ ] Listed on an independent board we track
- [ ] Enough results for a rank in a category
- [ ] Holds across two snapshots (crowns only)

## What the lab claims

Self-reported. Shown for context; not used in any verdict.

- Lab claim: real-time interaction at 10 Hz (10+ FPS on a commercial GPU), 5+ minutes of autoregressive rollout, and generalization across 1,000+ tasks.
- Lab claim: with every model trained on the public ABC dataset, DreamFAR averages 16.4 dB PSNR over 60-second rollouts on 1,000 held-out episodes, versus 15.8 for Cosmos-Predict 2.5, 14.5 for WEAVER and 11.0 for IWS, with the lowest LPIPS in every 10-second bin.
- Lab claim: policy task progress inside DreamFAR correlates with the real robot at Pearson r = 0.71 across two policy checkpoints and three tasks; it is optimistic in absolute terms.
- Lab claim: fine-tuning pi0 on 75 real plus 75 DreamFAR-teleoperated demonstrations of placing chip bags in a basket nearly doubles real-only task progress, to 63%.

## Sources

- LAB: [DreamFAR: Real-Time and Long-Horizon Interaction with Diverse Objects (project page)](https://www.yimingdou.com/DreamFAR/) (2026-10-29)
- PAPER: [DreamFAR paper (PDF)](https://www.yimingdou.com/DreamFAR/assets/paper/DreamFAR.pdf)
- LAB: [Yiming Dou (Amazon FAR) on X](https://x.com/_YimingDou/status/2115842800407466466) (2026-10-29)

Tracking ends Jan 28, 2027 unless the API or weights become available.

## Related

- Lab: [Amazon](https://isitsota.com/labs/amazon.md)
- All pending releases: https://isitsota.com/releases.md
- JSON: https://api.isitsota.com/v1/models/dreamfar