# DATAFARM: robot AI research model

DATAFARM (Distribution-Aligned Task and Motion Planning for Fine-Tuning [Vision-Language-Action](/glossary/vision-language-action-model.md) Models) is a 2026 research method from [Stanford](/locations/stanford.md)/[Princeton](/locations/princeton-new-jersey.md) (Sahoo, Huang, Silver; under review) that aligns planner-generated TAMP trajectories with a VLA's pretraining distribution in joint space, motion style, and timing so synthetic demos help fine-tuning. Project page reports 56.7% average success vs 8.3% raw TAMP and 61.7% human teleop on three tabletop tasks.

- **Slug:** datafarm
- **Type:** Research model
- **Maturity (DEPLOY ladder):** Research
- **Open source:** no

## Architecture

TAMP trajectory generation guided by pretraining-distribution models: Gaussian mixture over joint configurations + trajectory encoder costs for endpoint selection, path optimization, and retiming; evaluated fine-tuning pi0.5-DROID-class VLAs.


## Key facts

- **Average success 56.7% vs raw TAMP 8.3% / human teleop ~61.7% (research-stated):** Research-stated (research-stated; also Robots Digest X): DATAFARM (Sahoo / Huang / Silver; [Stanford](/locations/stanford.md) + [Princeton](/locations/princeton-new-jersey.md); under review 2026) aligns TAMP synthetic trajectories to the [VLA](/glossary/vision-language-action-model.md) pretraining distribution (joint configs, motion style, timing). On three tabletop fine-tuning tasks, average success 56.7% vs 8.3% raw TAMP and 61.7% human [teleoperation](/glossary/teleoperation.md); approaches teleop without teleoperating. Cap: author project-page table; not an independent replication.
- **Timing alignment mattered most in ablations (research-stated):** Research-stated (research-stated): removing one alignment component at a time drops average success from 56.7% to 23.3% without joint space, 15.0% without style, and 0% without timing. Cap: author ablation table on the project page.
- **OOD cloth-folding retention ~85% after fine-tune (research-stated):** Research-stated (research-stated): on Deformable Object Manipulation (cloth folding; outside fine-tuning distribution / beyond TAMP), the fine-tuned model retains about 85% success vs ~90% for the pretrained pi0.5-DROID baseline. Cap: author OOD retention claim.


## Sources (2)

1. **DATAFARM: Distribution-Aligned Task and Motion Planning for Fine-Tuning Vision-Language-Action Models** · https://prpl-group.com/datafarm/ · 2026
2. **Robots Digest: DATAFARM summary** · https://x.com/robotsdigest/status/2106429690659631214 · 2026-10-03


## Common questions

### What is DATAFARM?

DATAFARM (Distribution-Aligned Task and Motion Planning for Fine-Tuning [Vision-Language-Action](/glossary/vision-language-action-model.md) Models) is a 2026 research method from [Stanford](/locations/stanford.md)/[Princeton](/locations/princeton-new-jersey.md) (Sahoo, Huang, Silver; under review) that aligns planner-generated TAMP trajectories with a VLA's pretraining distribution in joint space, motion style, and timing so synthetic demos help fine-tuning. Project page reports 56.7% average success vs 8.3% raw TAMP and 61.7% human teleop on three tabletop tasks.

### Is DATAFARM open source?

No. DATAFARM is recorded as proprietary on the DEPLOY registry. Model weights and source are not publicly available.

### What type of AI is DATAFARM?

DATAFARM is a research model, built on a TAMP trajectory generation guided by pretraining-distribution models: Gaussian mixture over joint configurations + trajectory encoder costs for endpoint selection, path optimization, and retiming; evaluated fine-tuning pi0.5-DROID-class VLAs. architecture on the DEPLOY registry.

### What is DATAFARM's maturity stage?

DATAFARM is at the research stage on the DEPLOY maturity ladder. Research stage means active development without commercial deployments on file.

### Which robots run on DATAFARM?

No robot models on the DEPLOY registry are recorded as running DATAFARM. DEPLOY wires brain-to-model connections only when the wiring is verifiable from primary sources; absence may reflect pre-deployment or unverified manufacturer claims.


_API: GET /v1/brains/d68b389d-026f-462b-8b74-3451fa337c67 · canonical URL: /brains/datafarm_