HypoLoop / README.md
nielsr's picture
nielsr HF Staff
Add link to paper page
2df5234 verified
|
Raw History Blame
2.24 kB
metadata
library_name: pytorch
license: other
license_name: per-asset-terms
tags:
  - scientific-machine-learning
  - model-editing
  - safetensors
  - depth-estimation

HypoLoop

Native model weights and registered feedback data from HypoLoop: Revising Weight-Editing Plans from Scientific Feedback. The implementation, preprint, and loading instructions are available on GitHub. HypoLoop repository 路 Loading guide

Paper task Data Model weights
PHY01 路 Burgers Registered field histories, spatial grid, feedback and held-out targets FNO1d base and final fixed- and dynamic-location checkpoints for both services
MATH01 路 Constrained QP Registered right-hand sides, objective and constraint matrices, feedback and held-out solutions DC3 base and final fixed- and dynamic-location checkpoints for both services
DEP02 路 DIODE 24 registered RGB images, scene IDs, sampled depth targets and grid coordinates Fixed-plan and revised-plan Claude head replacements for Depth Anything V2 Metric VKITTI ViT-S
DEP01 路 Make3D Original Make3D dataset DeepSeek HL-Global head replacements for the same Depth Anything V2 base

manifest.json lists every checkpoint, its architecture, and the corresponding data files. checksums.sha256 records the upload contents. LICENSES.md lists source attribution and terms by asset.

The registered order is initial feedback F0, subsequent feedback B1 and B2, then held-out evaluation E. Use E for evaluation. Each target archive aligns ids with y. DIODE uses the 41脳61 sampled grid in grid.json, with NaN for invalid depth. The 12 reference images are from the original Make3D training collection.

The two depth cases use named-tensor replacements. Load the original VKITTI ViT-S metric checkpoint before applying a replacement. Depth Anything V2 upstream model