Pith Number

pith:C5WEWKNE

pith:2026:C5WEWKNEC5LUFPWMHOWJIXE6AK

not attested not anchored not stored refs pending

E-VLA: Event-Augmented Vision-Language-Action Model for Dark and Blurred Scenes

Hao Shi, Jiajun Zhai, Kailun Yang, Kaiwei Wang, Shangwei Guo

Event-augmented VLA models restore robotic manipulation success in dark and blurred scenes via direct event fusion.

arxiv:2604.04834 v2 · 2026-04-06 · cs.CV · cs.MM · cs.RO · eess.IV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{C5WEWKNEC5LUFPWMHOWJIXE6AK}

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

even a simple parameter-free fusion, i.e., overlaying accumulated event maps onto RGB images, could substantially improve robustness in dark and blur-heavy scenes: on Pick-Place at 20 lux, success increases from 0% (image-only) to 60% with overlay fusion and to 90% with our event adapter; under severe motion blur (1000 ms exposure), Pick-Place improves from 0% to 20-25%, and Sorting from 5% to 32.5%.

C2weakest assumption

That the collected real-world RGB-event-action dataset and the chosen tasks/illumination settings are representative enough for the reported robustness gains to generalize to other robots, tasks, and VLA backbones without substantial retraining or hyperparameter retuning.

C3one line summary

E-VLA integrates event streams directly into VLA models via lightweight fusion, raising Pick-Place success from 0% to 60-90% at 20 lux and from 0% to 20-25% under severe motion blur.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performance

Receipt and verification

First computed	2026-07-01T01:17:50.121388Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

176c4b29a4175742becc3bac945c9e02b60fc220bdbece9c53ac9c8be0c1bf93

Aliases

arxiv: 2604.04834 · arxiv_version: 2604.04834v2 · doi: 10.48550/arxiv.2604.04834 · pith_short_12: C5WEWKNEC5LU · pith_short_16: C5WEWKNEC5LUFPWM · pith_short_8: C5WEWKNE

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/C5WEWKNEC5LUFPWMHOWJIXE6AK \
  | 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: 176c4b29a4175742becc3bac945c9e02b60fc220bdbece9c53ac9c8be0c1bf93

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "913b2537ba2df974ab24be41387af13d9e3b8e67b330c85ee562f53db9522bdc",
    "cross_cats_sorted": [
      "cs.MM",
      "cs.RO",
      "eess.IV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-06T16:35:57Z",
    "title_canon_sha256": "a172fe623d8b02d0cc8ebec9ee457523924914d082a250c7350a660b243af532"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.04834",
    "kind": "arxiv",
    "version": 2
  }
}