Recent papers
A pin may embed a video, an official figure, or only the paper. Learned systems stay off hardware tables. GroceryVLA is a product model with no public arXiv. The catalog lists every homepage paper.
Humanoid-GPT
Zero-shot humanoid motion tracking with a GPT-style causal Transformer trained on a 2B-frame motion corpus.
Real-robot experiments use a 29-DoF Unitree G1 — not Galbot G1 and not Galbot ET1. Nearest open paper to the AstraBrain-WBC 0.5 announcement; not a proven one-to-one checkpoint identity.
LATENT
Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data. Whole-body returns on a racket-mounted humanoid.
Deployed body is a 29-DoF Unitree G1 — not Galbot G1 and not Galbot ET1. Quantitative table and extra project clips below.
TrackVLA
Embodied visual tracking in the wild: language-guided follow with a vision-language-action model. 1.7 million is the paper’s training mixture; EVT-Bench episode counts live on the Benchmarks atlas.
GroceryVLA
Retail, supermarket, and pharmacy shelf pick. End-to-end embodied VLA product model on Galbot G1. Not a reviewed paper; no arXiv id is assigned.
UniPart
Zero-shot language-grounded 3D part segmentation for embodied interaction. Not the CVPR 2026 UniPart generation paper by Xufan He.
Paper → body map
A paper proves only the robot it evaluates. A homepage “product model” is not a checkpoint identity. Galbot G1 and Unitree G1 stay in separate tables. Launch architecture names without a public checkpoint card sit outside tables.
Evaluated or listed on Galbot G1
| System | arXiv | Weights / code | Eval body in the source | End-effector in the source | Claim grade |
|---|---|---|---|---|---|
| GraspVLA# | arXiv:2505.03233 [R17] | HF shengliangd/GraspVLA [R17] | real-robot evals; robot not named in the paper [R17] | — | homepage product — homepage and founder profile call it the generalist grasp stack on Galbot G1 [R21] [P3] |
| GroceryVLA# | no public arXiv [R21] | — | Galbot G1 [R21] | — | homepage product — retail / pharmacy shelf-pick product model [P3] |
| TrackVLA / TrackVLA++# | arXiv:2505.23189; arXiv:2510.07134 [R19] [R25] | — | embodied visual tracking; Galbot G1 not named in the papers [R19] | — | homepage product — profile lists product-level tracking for unmanned retail [P3] |
| NavFoM# | arXiv:2509.12129 [R15] | — | cross-embodiment: quadruped, drone, vehicle, wheeled platforms [R15] | — | not claimed — no named Galbot G1 SKU [R21] |
| LDA-1B# | arXiv:2602.12215 [R9] | — | Galbot G1 [R9] | parallel-jaw gripper; Sharpa 22-DoF hand [R9] | paper eval — real-world figures in the paper, not a store SKU [R9] |
| WAM-TTT# | arXiv:2607.06988 [R5] | — | frozen world-action model (LDA line); robot not named in the source [R5] | — | not claimed — no public proof of a named Galbot G1 product checkpoint [R5] |
| StereoVLA# | arXiv:2512.21970 [R11] | HF shengliangd/StereoVLA [R11] | manipulation VLA; robot not named in the paper [R11] | — | not claimed — weights public; not listed as a Galbot G1 SKU [R11] |
Evaluated on Unitree G1
| System | arXiv | Weights / code | Eval body in the source | End-effector in the source | Claim grade |
|---|---|---|---|---|---|
| Humanoid-GPT# | arXiv:2606.03985 [R7] | GalaxyGeneralRobotics code [R7] | 29-DoF Unitree G1 [R7] | — | paper eval — nearest open paper to AstraBrain-WBC 0.5, not a proven one-to-one product checkpoint [P4] |
| LATENT# | arXiv:2603.12686 [R1] | official code on Galbot GitHub [R1] | 29-DoF Unitree G1 [R1] | — | paper eval — tennis whole-body control; the announced Galbot biped’s tennis mention is not this paper’s eval [R1] |
| LDA-1B (BrainCo variant)# | arXiv:2602.12215 [R9] | — | Unitree G1 [R9] | BrainCo 10-DoF hand [R9] | paper eval — not a BrainCo Revo 2 product column [R9] |
Lab pins for named suites
Lab-owned datasets and special-env suites. Scale, medium, and embodiment live on the Benchmarks atlas. A pin is not a robot SKU. Permalink ids stay stable.
HumanTracker
August 2026 motion-tracking benchmark. HumanScore is preference-aligned so eval can match contact, skating, and unstable support rather than only per-frame pose error. Scale is on the Benchmarks atlas. Not HumanoidBench.
OmniSpatial
Spatial-reasoning benchmark for VLMs, not motor control. Published scale is on the Benchmarks atlas.
Open6DOR
Open-instruction 6-DoF rearrangement. Language-specified placement pose, not pick-only grasping. Identity sheet: Benchmarks atlas. Unpublished scale stays empty there.
DexGraspNet
Dexterous grasp-synthesis dataset. Multifinger contact, not a parallel-jaw SKU. Grasp counts are on the Benchmarks atlas.
DexGraspNet 2.0
Generative dexterous grasping in synthetic clutter. Grasp counts are on the Benchmarks atlas. The paper’s LEAP hand is not a robot payload cell.
GAPartNet
Part-centric articulated objects: drawers, doors, lids — not rigid free objects. GAPartManip (ICRA 2025) extends the manipulation set. Part counts are on the Benchmarks atlas.
Paper · Project · GAPartManip [R41]
EVT-Bench
Named evaluation suite in TrackVLA. 1.7 million is TrackVLA’s training mixture, not the suite size. Episode counts live on the Benchmarks atlas. Special env: occlusion, night, distractors, long-horizon follow.
EI-30k
Mixed-quality human and robot pretraining corpus used with LDA-1B. Hours are on the Benchmarks corpora sheet. Not a clean single-task demo set and not EVT-Bench.
Paper catalog
Homepage papers 2026–2023 plus selected earlier lineage. Pins above are a subset. Refresh from hughw19.github.io. GroceryVLA is a product model, not a paper.
2026
- WAM-TTT — preprint · arXiv:2607.06988 · pin · paper
- HumanTracker — ECCV 2026 · arXiv:2608.13555 · pin · paper
- UniPart — ECCV 2026 · no arXiv on homepage · pin
- MM-Nav — ECCV 2026 · arXiv:2510.03142 · pin · paper
- GraspADMM — IROS 2026 · arXiv:2603.13832 · pin · paper
- LATENT — IROS 2026 · arXiv:2603.12686 · pin · paper
- HDFlow — ICML 2026 spotlight · arXiv:2605.04525 · pin · paper
- LIMMT — ICML 2026 · arXiv:2606.06953 · pin · paper
- LDA-1B — RSS 2026 · arXiv:2602.12215 · pin · paper
- DAPL — RSS 2026 Best Paper Finalist · arXiv:2603.09882 · pin · paper
- StereoVLA — RSS 2026 · arXiv:2512.21970 · pin · paper
- Humanoid-GPT — CVPR 2026 · arXiv:2606.03985 · pin · paper
- Layered 4D-Rotor Gaussian Splatting — CVPR 2026 · no arXiv on homepage · project
- CL3R — ICRA 2026 · arXiv:2507.08262 · pin · paper
- NavGSim — ICRA 2026 · arXiv:2603.15186 · paper
- Robust Differentiable Collision Detection — ICRA 2026 · arXiv:2511.06267 · paper
- UrbanVLA — ICRA 2026 · arXiv:2510.23576 · pin · paper
- TrackVLA++ — ICRA 2026 · arXiv:2510.07134 · pin · paper
- OmniSpatial — ICLR 2026 · arXiv:2506.03135 · pin · paper
- NavFoM — ICLR 2026 · arXiv:2509.12129 · pin · paper
- FoldNet — RA-L & IROS 2026 · arXiv:2505.09109 · pin · paper
- DexNDM — ICLR 2026 · arXiv:2510.08556 · pin · paper
2025
- SoFar — NeurIPS 2025 spotlight · arXiv:2502.13143 · pin · paper
- TrackVLA / EVT-Bench — CoRL 2025 · arXiv:2505.23189 · pin · paper
- FetchBot — CoRL 2025 Oral · arXiv:2502.17894 · pin · paper
- GraspVLA — CoRL 2025 · arXiv:2505.03233 · pin · paper
- DexVLG — ICCV 2025 highlight · arXiv:2507.02747 · pin · paper
- DyWA — ICCV 2025 · arXiv:2503.16806 · pin · paper
- RoboHanger — RA-L · arXiv:2412.01083 · pin · paper
- Dexonomy — RSS 2025 · arXiv:2504.18829 · pin · paper
- Uni-NaVid — RSS 2025 · arXiv:2412.06224 · pin · paper
- Code-as-Monitor — CVPR 2025 · arXiv:2412.04455 · paper
- GAPartManip — ICRA 2025 · arXiv:2411.18276 · GAPartNet pin · paper
- BODex — ICRA 2025 · arXiv:2412.16490 · pin · paper
- NaVid-4D — ICRA 2025 · pin · project
- QuadWBG — ICRA 2025 · arXiv:2411.06782 · paper
- Watch Less, Feel More — ICRA 2025 · arXiv:2502.14457 · paper
- GroceryVLA — product model · no arXiv · pin
2024
- D3RoMa — CoRL 2024 · arXiv:2409.14365 · pin · paper
- DexGraspNet 2.0 — CoRL 2024 · arXiv:2410.23004 · pin · paper
- ScissorBot — CoRL 2024 · arXiv:2409.13966 · pin · paper
- Task-Oriented Dexterous Grasp — IROS 2024 · arXiv:2309.13586 · paper
- Open6DOR — IROS 2024 Oral · pin · project
- NaVid — RSS 2024 · arXiv:2402.15852 · paper
- SAGE — RSS 2024 · arXiv:2312.01307 · paper
- MaskClustering — CVPR 2024 · arXiv:2401.07745 · paper
- STOPNet — ICRA 2024 · arXiv:2310.05717 · pin · paper
- GAMMA — ICRA 2024 · arXiv:2309.15459 · paper
- ASGrasp — ICRA 2024 · arXiv:2405.05648 · pin · paper
2023 and selected earlier lineage
- UniDexGrasp++ — ICCV 2023 Oral & Best Paper Finalist · arXiv:2304.00464 · pin · paper
- GAPartNet — CVPR 2023 Highlight · arXiv:2211.05272 · pin · paper
- 3D-Aware Object Goal Navigation — CVPR 2023 · arXiv:2212.00338 · paper
- UniDexGrasp — CVPR 2023 · arXiv:2303.00938 · paper
- PartManip — CVPR 2023 · arXiv:2303.16958 · paper
- Discrete Normalizing Flows on SO(3) — CVPR 2023 · arXiv:2304.03937 · paper
- DiGA — CVPR 2023 · arXiv:2304.02222 · paper
- DexGraspNet — ICRA 2023 · arXiv:2210.02697 · pin · paper
- GraspNeRF — ICRA 2023 · arXiv:2210.06575 · paper
- DREDS — ECCV 2022 · arXiv:2208.03792 · pin · paper
- HOI4D — CVPR 2022 · arXiv:2203.01577 · paper
- CAPTRA — ICCV 2021 Oral · arXiv:2104.03437 · paper
- NOCS — CVPR 2019 Oral · arXiv:1901.02970 · paper
- EI-30k — dataset with LDA-1B · pin
LATENT — autonomous humanoid tennis research
Deployed body: 29-DoF Unitree G1 with the right hand replaced by a racket on a 3D-printed wrist connector. Not Galbot G1 or Galbot ET1.
| Metric | Published result | Evidence / condition |
|---|---|---|
| System# | LATENT — Learning Athletic Humanoid TEnnis skills from imperfect human motioN daTa [R1] | Paper §1 |
| Robot body# | 29-DoF Unitree G1; right hand replaced by a racket on a 3D-printed wrist connector [R1] | Paper §4.3 and §5 |
| Motion data# | 5 amateur players; 5 h of unedited, unannotated primitive-skill motion; 3 × 5 m capture area [R1] | Paper §3.1 |
| Control / simulation# | High-level planner and low-level controller at 50 Hz; training simulation at 2,000 Hz [R1] | Paper §3 |
| Training episode# | 8 incoming balls; one launch every 2 s [R1] | Training task, paper §3.3.1 |
| Real-world success# | Forehand 90.90%; backhand 77.78%; forecourt 88.89%; backcourt 81.82% [R1] | Paper Table 5; successful return lands inside the opponent's court |
| Real-world sensing# | External optical motion capture estimates robot 6D pose and ball state using reflective markers [R1] | Paper §4.3; not onboard-vision-only autonomy |
Official project videos
Berkeley Humanoid Lite — open research hardware
Paper system-design section. Total DoF stays — (no vendor-style total in the extract). Cost is “under $5,000 (U.S. market)”, not a later aggregator $15k. Not mixed into the Unitree family table.
| Metric | Berkeley Humanoid Lite |
|---|---|
| Height# | 800 mm [R52] |
| Mass# | 16 kg [R52] |
| Total DoF# | — |
| Stated hardware cost# | under $5,000 (U.S. market prices) [R52] |
| Compute# | Intel N95 mini PC [R52] |
| Battery# | 6S 4000 mAh LiPo [R52] |
| Stated operation time# | ~30 min [R52] |
| Actuator bus# | CAN 2.0 at 1 Mbps; 250 Hz to actuators and IMU [R52] |
| Code / asset licenses# | MIT code; CC BY-SA 4.0 assets (repository) [R54] |
| Sim assets# | URDF / MJCF / USD in the repository; no browser assembly on this site [R54] |
The paper demonstrates zero-shot RL locomotion transfer and teleoperated manipulation. Those are experiment results, not a product payload. A 3D card is omitted until a commit is pinned and a render is produced here.
Research asset
- LATENT racket MJCF — the racket-mounted Unitree G1 model used in the paper's MuJoCo experiments, linked from the official project. github.com/GalaxyGeneralRobotics/LATENT [R2]
ToddlerBot — open research hardware
CoRL 2025 system-design text. Height from 0.56 m. Active DoF excludes end-effectors. Payload and walking-endurance figures are experiment results, not a product rating. Project-page 2.0 extras unused. Not a Unitree family column.
| Metric | ToddlerBot |
|---|---|
| Height# | 560 mm [R55] |
| Mass# | 3.4 kg [R55] |
| Active DoF (excluding end-effectors)# | 30 — 7 per arm, 6 per leg, 2 neck, 2 waist [R55] |
| Stated hardware cost# | under $6,000 [R55] |
| Compute# | Jetson Orin NX 16GB [R55] |
| Experiment — lift# | 1484 g in the paper’s payload test [R55] |
| Experiment — walking endurance# | 19 min stepping in place on a walking RL policy [R55] |
| Code repository# | hshi74/toddlerbot [R57] |
“40% of body weight” is an experiment comment, not a second mass. No 3D card until a commit is pinned. Stanford-TML/toddlerbot returned HTTP 404 here.