MIT (Lirui Wang, Kaiming He et al.)
HPT（Heterogeneous Pre-trained Transformers）
227M Commercial terms unverified 7/8 verified
1 of 8 required fields are unverified. They are shown as badges, not filled with defaults. Sources for verified fields are listed below.
Facts
- Released
- 2024-09 0 Source
- Parameters
- 0.227 B 1 Source
- Architecture
- Transformer policy 0 Source
- License
- MIT (code repository); model card has no licence tag 1 Source
- Commercial
- Commercial terms unverified 0 Source
- Weights
- huggingface.co ↗ 1 Source
- Code
- github.com ↗ 1 Source
- Paper
- arxiv.org ↗ 0 Source
- Input modalities
- rgb · state · language 0 Source
- Action space
- Separate action head per embodiment 0 Source
- Cross-embodiment
- Multi-embodiment mixed-data pretraining (README lists no specifics) 0 Source
- Pretraining data (hours)
- Unverified 0 Source
- Target forms
- Single arm · Dual arm 0 Source
Architecture · Transformer backbone aligning different embodiments into a shared latent space; XLarge 226.8M / Large 50.5M / Base 12.6M / Small 3.1M; NeurIPS 2024 Spotlight
Sources · 2 sources
params_b,license,arch_notes,code_url https://github.com/liruiw/HPT Official page · Fetched 2026-09-05 · No snapshot stored yet README：HPT-XLarge 226.8M / Large 50.5M / Base 12.6M / Small 3.1M；MIT license；NeurIPS 2024 Spotlight
weights_url https://huggingface.co/api/models/liruiw/hpt-xlarge Model hub page · Fetched 2026-09-05 · No snapshot stored yet Model card has no license field; createdAt 2024-05-15
Activity signals
Public counters fetched daily from GitHub, Hugging Face and ModelScope. Numbers only; no judgement. · fetched 2026-10-31
GitHub stars
546
-1 / 30 d
Commits · 90 d
0
last push 695 d ago
HF downloads · 30 d
30
all-time 318 · 0 likes
Weights last modified
2024-09-27
765 d ago
ModelScopeno same-name mirror found (searched by repo name)
Hugging Faceliruiw/hpt-xlarge
stars · last 30 d
Public benchmark scores
As printed in the source; protocols differ between papers. Full table with notes on the benchmarks page.
| Benchmark | Subset | Score | Source |
|---|---|---|---|
| Real-robot evaluation (self-reported)HPT-B Finetuned | Sweep Leftover | 70 | paper · Table 3 'Comparison on the Sweep Leftover', row 'HPT-B Finetuned' |
| Real-robot evaluation (self-reported)HPT-XL Finetuned | Sweep Leftover | 76.7 | paper · Table 3 'Comparison on the Sweep Leftover', row 'HPT-XL Finetuned' |
Deployment recipe
No recipe yet. We publish only steps that actually ran on a rented GPU with a measured latency; this model has not been through that yet.
Record history
2026-09-05
Sources fetched
params_b,license,arch_notes,code_url · weights_url
Latency & cost
cost = p50 ms ÷ 1000 × rental ÷ 3600 × 1000
| Hardware | p50 ms | p95 ms | Peak VRAM | Cost per 1k inferences ¥ | samples |
|---|---|---|---|---|---|
NVIDIA RTX 4090 ¥1.68/h · GongJi Compute (2026) | — | — | — | — no latency data | No data |
NVIDIA RTX 5090 ¥2.4/h · Runyun 2.4 / GongJi 2.5 / Paratera Cloud 2.98 (2026) | — | — | — | — no latency data | No data |
NVIDIA A100 80GB no rental price | — | — | — | — no latency data | No data |
NVIDIA Jetson AGX Thor no rental price | — | — | — | — no latency data | No data |
NVIDIA H100 80GB no rental price | — | — | — | — no latency data | No data |
NVIDIA A800 80GB no rental price | — | — | — | — no latency data | No data |
No latency measurements for this model yet · Data comes from literature, maintainer runs, or crowd CLI uploads. None exist so far.
Compatibility
Colored only where we hold evidence. An amber dot means the vendor declares this form as a target; that is a claim, not a verified compatibility.
| Unitree G1 | Unitree H1 | AgiBot Genie G1 | AgileX Piper arm | SO-101 | Franka FR3 / Panda | Fourier GR-2 | WidowX 250 S | Google Robot（Everyday Robots） | ALOHA 2 / Cobot Magic (dual-arm) | Galaxea R1 Pro | Franka Emika Panda | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| HPT（Heterogeneous Pre-trained Transformers） |
Legend Officially supportedCommunity reproducedFine-tunable in theoryUnsupportedUnknown Vendor-declared target form 2 / 12 cells with a definite status
Reproduction records
Did this model run on your robot? Report it with a link (log, video or repo). Records are reviewed by the maintainers; a verified “works” or “works after fine-tuning” upgrades the matrix cell to “community verified” with your link as evidence. Anonymous is fine; nothing but the fields below is stored.
No verified record yet for this model.
Clear direction, grounded judgement.