Skip to page content
SAVRN
Search Plan a project

Open-weight model · Robotics

executable-goals

by Tzu-Yu Chuang Claire0730/executable-goals

executable-goals is an open-weight model for robotics from Tzu-Yu Chuang, released under Apache License 2.0. Its published files total 1.0 GB.

Weights and frozen goal banks behind the paper. A 3D trace world model predicts one future per episode; the Entity-Level Goal Readout turns that prediction into a single executable goal in SE(3), and a shared Pose-Native Executor runs it closed loop at 20 Hz…

Parameters—
Context—
Weights1.0 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Model Card

By Tzu-Yu Chuang, published under apache-2.0, revision 0710d6eda61e.

Weights and frozen goal banks behind the paper. A 3D trace world model predicts one future per episode; the Entity-Level Goal Readout turns that prediction into a single executable goal in SE(3), and a shared Pose-Native Executor runs it closed loop at 20 Hz across five ManiSkill3 tasks. Reproducing the main table needs the executors and the banks only — no planner, no gated licence, one GPU: Everything else — the full install, the inference and training chains, which record backs which number — is in the code repository's README and docs/REPRODUCTION.md. Closed-loop success, %, PickCube / LiftPegUpright / PegInsertionSide / StackCube / PushCube. The readout rows share one set of executor…

Read Tzu-Yu Chuang's full model card

Predicted Futures Are Not Enough: Learning Executable Goals for Robot Manipulation

Code · Project page · Paper

Weights and frozen goal banks behind the paper. A 3D trace world model predicts one future per episode; the Entity-Level Goal Readout turns that prediction into a single executable goal in SE(3), and a shared Pose-Native Executor runs it closed loop at 20 Hz across five ManiSkill3 tasks.

What is here

Folder Contents Size
planner/ Three 3D Trace Planners fine-tuned from TraceGen: mix4_realcam_n2400 (Rigid Readout source), mix5_t2k_n3000 (entity branch), mix5_t2k_gmap (entity + map branch) 0.30–0.31 GB each
student/ The three Pose-Native Executors, 804,002 parameters each: mt5_rciid_gmpc_s0, mt5_rcfz_gmpc_s0, mt5_rcfz_t2k_s0 3.2 MB each
teacher/ Five privileged PPO teachers, one per task ~4 MB each
banks/ 49 frozen goal banks — one SE(3) goal per scene, for every reported row, task and evaluation seed 58 MB

Digests: SHA256SUMS (weights) and banks/SHA256SUMS.

Use

Reproducing the main table needs the executors and the banks only — no planner, no gated licence, one GPU:

git clone https://github.com/Claire0730/executable-goals && cd executable-goals
hf download Claire0730/executable-goals --local-dir checkpoints --include "student/*" --include "teacher/*" --include "SHA256SUMS"
hf download Claire0730/executable-goals --local-dir . --include "banks/*"
bash scripts/00_link_checkpoints.sh
ROW=final bash scripts/verify_main_table.sh 999

Everything else — the full install, the inference and training chains, which record backs which number — is in the code repository's README and docs/REPRODUCTION.md.

Results

Closed-loop success, %, PickCube / LiftPegUpright / PegInsertionSide / StackCube / PushCube. The readout rows share one set of executor weights; only the goal pipeline differs. "Recorded" pools evaluation seeds 999 / 997 / 998 (768 episodes per task).

Row Executor Printed Recorded
Rigid Readout K = 1 mt5_rcfz_gmpc_s0 29.80 / 70.18 / 20.05 / 52.47 / 99.74 (mean 54.45) 29.82 / 70.18 / 20.05 / 52.47 / 99.74
Rigid Readout K = 4 mt5_rcfz_gmpc_s0, PickCube cell mt5_rcfz_t2k_s0 46.48 / 76.95 / 21.88 / 54.82 / 99.22 (mean 59.87) 33.07 / 76.95 / 21.88 / 54.82 / 99.22 with one executor; the printed PickCube cell is the second, at seed 999
Entity-Level Goal Readout mt5_rciid_gmpc_s0 81.50 / 98.35 / 32.84 / 86.54 / 99.20 (mean 79.69) 81.51 / 98.31 / 32.81 / 86.46 / 99.22
Oracle Goal mt5_rcfz_gmpc_s0 94.66 / 97.27 / 36.72 / 87.11 / 99.74 identical

Terminal goal position error (mm, seed 999, PickCube / PegInsertionSide / StackCube): Rigid K = 1 41.1 / 42.6 / 28.9, Rigid K = 4 37.2 / 40.8 / 25.4, Entity-Level Goal Readout 31.5 / 29.4 / 12.8.

Before you rely on these

  • The planner files hold trained parameters only. Every frozen-encoder tensor was bitwise identical to the published Hub weights and was removed, along with the optimizer state. The encoders are re-created from the Hub when the planner is built, so DINOv3 is required and gated: accept its licence and run hf auth login once. verify_main_table.sh builds no planner and needs none of this.
  • Training paths inside the planner config are placeholders. dataset_dirs, cache_dir and checkpoint_dir read [path-to-the-repository-root-here]/.... They are metadata — inference and evaluation never read them — but set them to real directories before resuming training.
  • PegInsertionSide is not bitwise reproducible. Repeated evaluation of the same checkpoint moves by a couple of episodes in 256, which is why the verification script compares within ±0.04.
  • Simulation only, one training seed. The paper's real-robot results are not established for these checkpoints by this release, and the three evaluation seeds vary scenes, not training.
  • Nothing here is a third-party weight. CoTracker3 and SAM 2 are not redistributed; the code repository's README lists every external model, its licence and which stage needs it.

License and citation

Apache-2.0. The released weights contain only parameters trained by the authors; the upstream TraceGen Generalist checkpoint they are fine-tuned from is subject to its own terms.

@article{chuang2026executablegoals,
  title  = {Predicted Futures Are Not Enough: Learning Executable Goals for Robot Manipulation},
  author = {Chuang, Tzu-Yu and Chang, Ching-Hsiang and Lee, Yi-Hsiu and Chen, Yi-Ting and Sun, Min and Yang, YuanFu},
  year   = {2026}
}

Identity and Version

Repository
Claire0730/executable-goals
Publisher
Tzu-Yu Chuang
Task
Robotics
Modality
Control
Library
pytorch
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
0710d6eda61e9c24e4728173f7d2fce2e9d77599
First published
2026-09-23
Last updated
2026-10-08

Files and Weights

76 files, 1.0 GB in total. The weights are 60 files totalling 1.0 GB in npz, pt, pth.

Weights60 files · 1.0 GB
Configuration12 files · 196.2 KB
Documentation1 file · 5.1 KB
Other2 files · 6.7 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
banks/liftpeg_goals_mix4_realcam_n2400_997_k1ransac.npzWeights1.2 MB 39ad581b108c
banks/liftpeg_goals_mix4_realcam_n2400_997_kmean_ransac.npzWeights1.3 MB 13e3cd56f47a
banks/liftpeg_goals_mix4_realcam_n2400_998_k1ransac.npzWeights1.2 MB 5fdad1567b00
banks/liftpeg_goals_mix4_realcam_n2400_998_kmean_ransac.npzWeights1.2 MB bc02cf9f8119
banks/liftpeg_goals_mix4_realcam_n2400_999_k1ransac.npzWeights1.2 MB c1fdd9a1591b
banks/liftpeg_goals_mix4_realcam_n2400_999_kmean_ransac.npzWeights1.3 MB 08aec1747f8e
banks/liftpeg_goals_mix5_t2k_n3000_997_t2kpos.npzWeights1.2 MB ca7c6da923fc
banks/liftpeg_goals_mix5_t2k_n3000_998_t2kpos.npzWeights1.2 MB ee0e8a4eacb6
banks/liftpeg_goals_mix5_t2k_n3000_999_t2kpos.npzWeights1.2 MB 411762f0b15a
banks/peginsert_goals_mix4_realcam_n2400_997_k1ransac.npzWeights1.2 MB 8a8d2c97e01d
banks/peginsert_goals_mix4_realcam_n2400_997_kmean_ransac.npzWeights1.3 MB df455f70f157
banks/peginsert_goals_mix4_realcam_n2400_998_k1ransac.npzWeights1.2 MB 55b89fc302e2
banks/peginsert_goals_mix4_realcam_n2400_998_kmean_ransac.npzWeights1.2 MB c605f677a437
banks/peginsert_goals_mix4_realcam_n2400_999_k1ransac.npzWeights1.2 MB 67ffc4f5a5e9
banks/peginsert_goals_mix4_realcam_n2400_999_kmean_ransac.npzWeights1.3 MB 93f77a966972
banks/peginsert_goals_mix5_t2k_n3000_997_t2kpos.npzWeights1.2 MB a9ee1f2386a8
banks/peginsert_goals_mix5_t2k_n3000_998_t2kpos.npzWeights1.2 MB 8e211e793943
banks/peginsert_goals_mix5_t2k_n3000_999_t2kpos.npzWeights1.2 MB e54d432ea3de
banks/pickcube_goals_mix4_realcam_n2400_997_k1ransac.npzWeights1.2 MB 411a1082a238
banks/pickcube_goals_mix4_realcam_n2400_997_kmean_ransac.npzWeights1.3 MB 751917aa35a3
banks/pickcube_goals_mix4_realcam_n2400_998_k1ransac.npzWeights1.2 MB a00b995ea94d
banks/pickcube_goals_mix4_realcam_n2400_998_kmean_ransac.npzWeights1.2 MB f279ac6ab1db
banks/pickcube_goals_mix4_realcam_n2400_999_k1ransac.npzWeights1.2 MB 3d4eafc68cff
banks/pickcube_goals_mix4_realcam_n2400_999_kmean_ransac.npzWeights1.3 MB 5859d4f88442
banks/pickcube_goals_mix5_t2k_gmap_997_gmappeakNC.npzWeights1.2 MB 58fe0ff29310
banks/pickcube_goals_mix5_t2k_gmap_997_sam2mk6.npzWeights1.2 MB 5c893341b7b1
banks/pickcube_goals_mix5_t2k_gmap_998_gmappeakNC.npzWeights1.2 MB 3e5f812e12a7
banks/pickcube_goals_mix5_t2k_gmap_998_sam2mk6.npzWeights1.2 MB bdbb676b2a5a
banks/pickcube_goals_mix5_t2k_gmap_999_gmappeakNC.npzWeights1.2 MB ce239da38fb8
banks/pickcube_goals_mix5_t2k_gmap_999_sam2mk6.npzWeights1.2 MB e722062c35a9
banks/pickcube_goals_mix5_t2k_n3000_999_k4ransac.npzWeights1.2 MB eb932a1d1c16
banks/pushcube_goals_mix5_t2k_n3000_997_k1ransac.npzWeights1.2 MB fea2de4b32b4
banks/pushcube_goals_mix5_t2k_n3000_997_kmean_ransac.npzWeights1.2 MB 01cc9b0bc507
banks/pushcube_goals_mix5_t2k_n3000_997_t2kpos.npzWeights1.2 MB 7048dd9899fd
banks/pushcube_goals_mix5_t2k_n3000_998_k1ransac.npzWeights1.2 MB 58aae9b01c69
banks/pushcube_goals_mix5_t2k_n3000_998_kmean_ransac.npzWeights1.2 MB 891453f91e7b
banks/pushcube_goals_mix5_t2k_n3000_998_t2kpos.npzWeights1.2 MB 25e0ffb4fc87
banks/pushcube_goals_mix5_t2k_n3000_999_k1ransac.npzWeights1.2 MB 89f1cd951fff
banks/pushcube_goals_mix5_t2k_n3000_999_kmean_ransac.npzWeights1.2 MB 32691ffb642c
banks/pushcube_goals_mix5_t2k_n3000_999_t2kpos.npzWeights1.2 MB 79c121c506d2
banks/stack_goals_mix4_realcam_n2400_997_k1ransac.npzWeights1.2 MB a718e53198bc
banks/stack_goals_mix4_realcam_n2400_997_kmean_ransac.npzWeights1.3 MB 6c3b0a141c50
banks/stack_goals_mix4_realcam_n2400_998_k1ransac.npzWeights1.2 MB 9d500e186c5b
banks/stack_goals_mix4_realcam_n2400_998_kmean_ransac.npzWeights1.2 MB e6e31ee7c3cd
banks/stack_goals_mix4_realcam_n2400_999_k1ransac.npzWeights1.2 MB 27b422f1b666
banks/stack_goals_mix4_realcam_n2400_999_kmean_ransac.npzWeights1.3 MB 66da6cf61737
banks/stack_goals_mix5_t2k_gmap_997_gmapdcc.npzWeights1.2 MB 8627b111ef14
banks/stack_goals_mix5_t2k_gmap_998_gmapdcc.npzWeights1.2 MB 8e9935edec3a
banks/stack_goals_mix5_t2k_gmap_999_gmapdcc.npzWeights1.2 MB a23ac9091191
planner/mix4_realcam_n2400.pthWeights302.0 MB 81f25468df5d
planner/mix5_t2k_gmap.pthWeights314.2 MB 46643abdd974
planner/mix5_t2k_n3000.pthWeights314.2 MB 6b5b6544a0b7
student/mt5_rcfz_gmpc_s0/student.ptWeights3.2 MB 50467d34909e
student/mt5_rcfz_t2k_s0/student.ptWeights3.2 MB 99aaa1f6eb50
student/mt5_rciid_gmpc_s0/student.ptWeights3.2 MB 5ed8f4361eb6
teacher/lp_v9_nz_s0/agent.ptWeights4.0 MB b3449a618fdf
teacher/pc_v9_nz_s0/agent.ptWeights4.1 MB 702259e46a7c
teacher/pi_v9_frame4_s0/agent.ptWeights4.1 MB ef0559ebcfdc
teacher/push_v9_nz_s0/agent.ptWeights4.0 MB 34c0175e65cb
teacher/sc_v9_nz03b_s0/agent.ptWeights4.0 MB fd8ef9911d8e
student/mt5_rcfz_gmpc_s0/run.jsonConfiguration51.9 KB —
student/mt5_rcfz_t2k_s0/run.jsonConfiguration51.8 KB —
student/mt5_rciid_gmpc_s0/run.jsonConfiguration51.8 KB —
teacher/lp_v9_nz_s0/patches.jsonConfiguration285 B —
teacher/lp_v9_nz_s0/run.jsonConfiguration18.2 KB —
teacher/pc_v9_nz_s0/patches.jsonConfiguration320 B —
teacher/pc_v9_nz_s0/run.jsonConfiguration5.7 KB —
teacher/pi_v9_frame4_s0/patches.jsonConfiguration392 B —
teacher/pi_v9_frame4_s0/run.jsonConfiguration4.3 KB —
teacher/push_v9_nz_s0/run.jsonConfiguration5.5 KB —
teacher/sc_v9_nz03b_s0/patches.jsonConfiguration254 B —
teacher/sc_v9_nz03b_s0/run.jsonConfiguration5.8 KB —
README.mdDocumentation5.1 KB —
SHA256SUMSOther1.1 KB —
banks/SHA256SUMSOther5.6 KB —
.gitattributesRepository1.5 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
1.0 GB
Download from Tzu-Yu Chuang

Released by Tzu-Yu Chuang through its official repository on Hugging Face. Read the license.

Built From

  • Derived from JayLee131/TraceGen
  • Described by arXiv:2610.09309

Memory Requirements

PrecisionWeights in memory
As published1.0 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About executable-goals

Can I use executable-goals commercially?

Yes. executable-goals is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

LIBERO 4in1（liberospatial / liberoobject / liberogoal / libero10）共 53.19 GB 的 Wan2.2-VAE 编码 latent 缓存： 训练 LIBERO policy（action head / VLA）时直接读取 latent 缓存，避免重复 VAE 编码。 - 窗口模式: windowed（--windowed） - 输出:.pt 文件，每 episode 一个 - dataset（推荐）: https://huggingface.co/datasets/MangoGoes/libero4in1wan2.2vaelatentdataset - model（本仓库）: https://huggingface.co/MangoGoes/libero4in1wan2.2vaelatentcosmosstyle

Open weights other cosmos
View model

Model · Robotics

wam_ctxpool_bmethod

Hyeonmo Kang

Wan2.2-TI2V-5B video DiT + 48-joint action head, trainingmode=joint. The base is suhyeok's finalized B-method recipe: a teacher-forced (sigma=0.25) self-EMA teacher plus an iBOT prototype loss at L18 L18, gamma=0.01, two-view. On top of it the 3 PAST cond latent frames are pooled into one motion frame before a chosen block. These are NOT the surrogate ctxpool runs. The surrogate line (older base, pd8 x GA1) lives in hmkang/wamctxpoolxattn and hmkang/wamctxpoolavg. Do not compare across the two sets. Geometry: 4-latin (numframesin=25, numframesout=41, fdf 2) = 4 cond + 2 future latent slots, 96 tokens per latent frame, 576 tokens per row. Effective batch 16 clips x GA 2 x 2 views = 64 rows…

Open weights apache-2.0 wan2.2
View model

weighted/imatrix quants of https://huggingface.co/DeepCybo/PhysBrain1.5-8B For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/PhysBrain1.5-8B-GGUF This is a vision model - mmproj files (if any) will be in the static repository. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter…

Open weights transformers
View model

static quants of https://huggingface.co/MirilAI/Miril-DroneVLM-2B-2 For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant…

Open weights apache-2.0 transformers
View model

Model · Robotics

microduck-bubu-sprint

Dadudu

Own lineage: PPO from scratch (nb1, commit 46c48b1) continued as nb2 and nb4 (commit fac88cc), checkpoint 850 (1.328 s); evolution strategies on the weights against the Arena sprint scorer (0.952 s); then the network frozen and wrapped in a step counter carried in the headroll action that adds joint-target and forward-command offsets from about 0.5 m to the line, found by CMA-ES on the event's official seeds: 0.940 s. No other entry's weights used. Simulation only. A perpetual policy for the microduck (61-D observation, 14 actions, 50 Hz). Runs until told otherwise — a gait, loaded into a policy slot. The observation normalizer is baked into policy.onnx; feed raw observations. manifest.json…

Open weights microduck
View model

Model · Robotics

EgoSteer-3B-RealMan

EgoSteer

EgoSteer-3B-RealMan is the generalist policy from EgoSteer: A Full-Stack System Towards Steerable Dexterous Manipulation from Egocentric Videos. It is a world-model-enhanced Vision-Language-Action (VLA) policy built on a Qwen3-VL backbone with a flow-matching action expert, post-trained from EgoSteer-3B-Base on real-world demonstrations collected on the RealMan robot. This is a robot-ready dual-camera (head + chest) checkpoint, corresponding to EgoSteer-9.6K-DG in the paper. For the base model to fine-tune on your own data, see EgoSteer-3B-Base. Our full-stack system integrates EgoSmith (data pipeline), Robot Stack (deployment), and EgoSteer (policy) to learn from 9.6k hours of large-scale…

Open weights apache-2.0
View model