pith:TGEBEKQL
MidSteer: Optimal Affine Framework for Steering Generative Models
MidSteer is a general affine framework for concept steering in generative models that relaxes optimality assumptions of prior LEACE-based methods to enable directed minimal-disturbance transformations.
arxiv:2605.05220 v2 · 2026-04-17 · cs.LG · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{TGEBEKQL75JVKZB35A6ROC2Y2F}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
We introduce MidSteer (Minimal Disturbance concept Steering), a more general affine framework for concept manipulation that relaxes these assumptions and enables directed, minimal-disturbance transformations.
The assumptions under which LEACE-Switch provides an optimal affine solution hold for the specific concept manipulations considered; MidSteer relaxes them but still relies on affine transformations being sufficient for effective steering.
MidSteer is a general affine framework for concept steering in generative models that relaxes optimality assumptions of prior LEACE-based methods to enable directed minimal-disturbance transformations.
Receipt and verification
| First computed | 2026-06-02T01:03:16.237923Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
9988122a0bff5355643be83d170b58d174430e036159c4d29c3d88cc7629bc3a
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/TGEBEKQL75JVKZB35A6ROC2Y2F \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 9988122a0bff5355643be83d170b58d174430e036159c4d29c3d88cc7629bc3a
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "b33f659b4f8c5067b4ab1e7e1e3cd197418277740fab53d9af1d5651beb8df33",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-04-17T19:23:33Z",
"title_canon_sha256": "bdb1215781d2ae0a57a65fca1c703486ea46d7f45c68040d389c0cc665cb4bcb"
},
"schema_version": "1.0",
"source": {
"id": "2605.05220",
"kind": "arxiv",
"version": 2
}
}