Pith Number

pith:SKPLKAAG

pith:2026:SKPLKAAGTU2O524V5X5GEY3WS2

not attested not anchored not stored refs pending

AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models

Guangrui Ren, Hao Dong, Hongwei Fan, Jiadong Xu, Juan Zhu, Muhe Cai, Xiaoqi Li, Yan Shen

AT-VLA adds tactile signals to vision-language-action models only when they significantly aid action generation, paired with dual streams for fast responses.

arxiv:2605.07308 v2 · 2026-05-08 · cs.RO

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{SKPLKAAGTU2O524V5X5GEY3WS2}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

AT-VLA introduces a novel Adaptive Tactile Injection mechanism... dynamically determines the appropriate timing and locations for tactile injection... Furthermore, to enable rapid and accurate tactile responses, we propose a Tactile Reaction Dual-Stream mechanism... achieving real-time close-loop responses within 0.04 s. Real-world experiments thoroughly validate the effectiveness of AT-VLA in contact-rich manipulation tasks.

C2weakest assumption

That dynamically injecting tactile signals only when they 'significantly contribute' will avoid disrupting pretrained VLA capabilities and that the dual-stream split preserves necessary integration between vision-language reasoning and tactile control without loss of performance.

C3one line summary

AT-VLA introduces adaptive tactile injection and a dual-stream tactile reaction mechanism to integrate real-time tactile feedback into pretrained VLA models for contact-rich robotic manipulation.

Receipt and verification

First computed	2026-05-20T00:04:34.625108Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

929eb500069d34eeeb95edfa626376969faeec916fa347c1c49f666036c943b5

Aliases

arxiv: 2605.07308 · arxiv_version: 2605.07308v2 · doi: 10.48550/arxiv.2605.07308 · pith_short_12: SKPLKAAGTU2O · pith_short_16: SKPLKAAGTU2O524V · pith_short_8: SKPLKAAG

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/SKPLKAAGTU2O524V5X5GEY3WS2 \
  | 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: 929eb500069d34eeeb95edfa626376969faeec916fa347c1c49f666036c943b5

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e084975e0f6cd50fb850c2353143d5b9ff2efb8ebac8c52aa9d7f84e06de943b",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2026-05-08T06:17:08Z",
    "title_canon_sha256": "4c0a7af4a6b801e899dc73f734099c2c5795ca0e0cc3833d736bd5c098af3882"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.07308",
    "kind": "arxiv",
    "version": 2
  }
}