Pith Number

pith:26GH5WOR

pith:2026:26GH5WORHYUEK372LHSES7T333

not attested not anchored not stored refs resolved

DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding

Huawen Shen, Liu Yu, Shiyu Liu, Yichao Liu, Yu Zhou, Zeyu Chen

A training-free dynamic region search method improves GUI grounding performance by 14 percent in existing multimodal models.

arxiv:2605.15542 v1 · 2026-05-15 · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{26GH5WORHYUEK372LHSES7T333}

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

Experiments demonstrate that DRS-GUI yields a 14% improvement on ScreenSpot-Pro for general and GUI-specific MLLMs (Qwen2.5-VL-7B and UGround-V1-7B), significantly enhancing grounding performance and generalization.

C2weakest assumption

The three perceptual actions (Focus, Shift, and Scatter) performed by the lightweight UI Perceptor, when scheduled by the MCTS-based Action Planner, will reliably generate and select instruction-relevant region proposals from cluttered high-resolution screenshots without requiring any model training or fine-tuning.

C3one line summary

DRS-GUI introduces a dynamic region search method with Focus/Shift/Scatter actions and MCTS-based planning that improves GUI grounding accuracy by 14% on ScreenSpot-Pro for both general and GUI-specific MLLMs without any training.

References

54 extracted · 54 resolved · 17 Pith anchors

[1] GPT-4 Technical Report · arXiv:2303.08774

[2] Qwen Technical Report 2023 · arXiv:2309.16609

[3] Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond 2023 · arXiv:2308.12966

[4] Qwen2.5-VL Technical Report 2025 · arXiv:2502.13923

[5] Introducing our multimodal models, 2023 2023

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:01:04.400686Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d78c7ed9d13e28456ffa59e4497e7bdeeeaf92c0a6f92aebf01b29f637e2897c

Aliases

arxiv: 2605.15542 · arxiv_version: 2605.15542v1 · doi: 10.48550/arxiv.2605.15542 · pith_short_12: 26GH5WORHYUE · pith_short_16: 26GH5WORHYUEK372 · pith_short_8: 26GH5WOR

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/26GH5WORHYUEK372LHSES7T333 \
  | 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: d78c7ed9d13e28456ffa59e4497e7bdeeeaf92c0a6f92aebf01b29f637e2897c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1505f23c909af627f22c2459b06139f2a518910bb0d28529294ed56f6b4fb403",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-15T02:27:41Z",
    "title_canon_sha256": "72b5086792ce21d0a8928bc06558813c669fe1b879e949a1205315e775d4f736"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15542",
    "kind": "arxiv",
    "version": 1
  }
}