pith:3KECOAG2
See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Model
Differentiable grid sampling lets VLA models compress visual tokens to under 10 percent while keeping full manipulation success.
arxiv:2605.11817 v2 · 2026-05-12 · cs.RO · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{3KECOAG27EKT7EVDMBOTHH3LU3}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
validating the lowest feasible visual token count reported to date, GridS achieves a 76% reduction in FLOPs with no degradation in the success rate.
That adaptively predicting a minimal set of salient coordinates and extracting features via differentiable interpolation will always preserve the critical geometric details (contact points, spatial relations) required for manipulation success across tasks and environments.
GridS reduces visual tokens in VLA models to under 10% of the original count via task-aware differentiable resampling, delivering 76% lower FLOPs with no drop in task success rate on benchmarks and real robots.
Formal links
Receipt and verification
| First computed | 2026-05-20T00:04:36.178020Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
da882700daf9153f92a3605d339f6ba6ddbabefb3cda0ee048296a78b3bbf927
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/3KECOAG27EKT7EVDMBOTHH3LU3 \
| 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: da882700daf9153f92a3605d339f6ba6ddbabefb3cda0ee048296a78b3bbf927
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "10064b6bada4125ae37b0039636c0aaf75c085318aebb5df5037928af974560d",
"cross_cats_sorted": [
"cs.CV"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.RO",
"submitted_at": "2026-05-12T09:08:42Z",
"title_canon_sha256": "d890d3fb46f5b83e15da28afa517f3d7a715d5bb097cd3daccd743f67ac7048e"
},
"schema_version": "1.0",
"source": {
"id": "2605.11817",
"kind": "arxiv",
"version": 2
}
}