Downloads · 30 days
0
physrel-jepa
almogtavor/physrel-jepa
physrel-jepa is a machine learning model from almogtavor. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as mit.
Checkpoints for PhysRel-JEPA, an object-centric JEPA video world model that routes object interactions through a narrow gated edge bottleneck instead of the predictor's self-attention.
Access
Public
Updated Jul 10, 2026
Repo size
1.8 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pt1.8 GB · 100%
At a glance
- Library
- pytorch
- License
- mit
- Access
- Public
- Created
- Jul 10, 2026
- Updated
- Jul 10, 2026
- SHA
- 9adc598a
Model card
From the Hugging Face model README
PhysRel-JEPA checkpoints
Checkpoints for PhysRel-JEPA, an object-centric JEPA video world model that routes object interactions through a narrow gated edge bottleneck instead of the predictor's self-attention.
Files
| file | what | notes |
|---|---|---|
savi.pt | frozen SAVi encoder, 64x64, N=7 slots, dim 128 | trained 30 epochs on 5000 CLEVRER videos (8x H100, DDP) |
pred_ocjepa.pt | OC-JEPA predictor (no masking, no edges) | 5000-clip, 15-epoch run |
pred_cjepa.pt | C-JEPA predictor (object masking, no edges) | 5000-clip, 15-epoch run |
pred_physrel.pt | PhysRel-JEPA predictor (masking + edge bottleneck + property memory) | 5000-clip, 15-epoch run |
Each .pt is a torch.save dict with keys model (state_dict), opt (optimizer state),
and metadata. Predictor checkpoints include optimizer state, so they are resumable.
Loading
import torch
from physrel_jepa.config import load_config
from physrel_jepa.models.world_model import PhysRelJEPA
from physrel_jepa.models.encoder_savi import SAViEncoder
enc = SAViEncoder(num_slots=7, slot_dim=128, resolution=64)
enc.load_state_dict(torch.load("savi.pt", map_location="cpu")["model"])
cfg = load_config("configs/predictor_physrel.yaml")
pred = PhysRelJEPA(cfg.model)
pred.load_state_dict(torch.load("pred_physrel.pt", map_location="cpu")["model"])
Results (held-out future latent NMSE, lower is better)
5000 clips, 15 epochs, 5 seeds: OC-JEPA 0.00045, C-JEPA 0.00064, PhysRel-JEPA 0.00053. The edge bottleneck beats masking-only (PhysRel < C-JEPA) at this scale, while no-masking OC-JEPA is best under this budget. At 1500 clips / 200 epochs PhysRel-JEPA is best overall (0.00042, wins C-JEPA 5/5 seeds). See the repo for the full writeup and the gate-collapse ablation.
- Library
- pytorch
- License
- mit
- Created
- Jul 10, 2026
- Updated
- Jul 10, 2026