pith. sign in
Pith Number

pith:34ARD4PW

pith:2026:34ARD4PWGBFKI67Z7WST6QFWAE
not attested not anchored not stored refs resolved

DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation

Brandon Cui, David Acuna, Hyunwoo Kim, Jaehun Jung, Prithviraj Ammanabrolu, Ximing Lu, Yejin Choi

High answer divergence between teacher and student makes prompts far more effective for distilling reasoning into smaller vision-language models.

arxiv:2605.15532 v1 · 2026-05-15 · cs.LG · cs.AI · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{34ARD4PWGBFKI67Z7WST6QFWAE}

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

DeltaPrompts drives substantial gains, yielding up to 15% relative improvement even on top of a highly-optimized reasoning model (e.g., Qwen3-VL-8B-Thinking) -- averaged over 10 benchmarks spanning chart, document and perception-centric reasoning.

C2weakest assumption

That actively targeting student failure modes via the staged synthesis pipeline produces prompts whose divergence directly translates to improved learning signal without introducing new biases or distribution shifts that could harm generalization.

C3one line summary

DeltaPrompts generates 200k high-divergence reasoning prompts via staged synthesis to escape zero-delta traps in multimodal distillation, yielding up to 15% relative gains on chart, document, and perception benchmarks.

References

78 extracted · 78 resolved · 1 Pith anchors

[1] D. Acuna, C.-H. H. Yang, Y . Deng, J. Jung, X. Lu, P. Ammanabrolu, H. Kim, Y .-H. Liao, and Y . Choi. Long grounded thoughts: Synthesizing visual problems and reasoning chains at scale, 2026 2026
[2] R. Agarwal, N. Vieillard, Y . Zhou, P. Stanczyk, S. Ramos, M. Geist, and O. Bachem. On-policy distillation of language models: Learning from self-generated mistakes, 2024 2024
[3] E. Agustsson and R. Timofte. Ntire 2017 challenge on single image super-resolution: Dataset and study. InThe IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, July 2017 2017
[4] S. Bai, Y . Cai, R. Chen, K. Chen, X. Chen, Z. Cheng, L. Deng, W. Ding, C. Gao, C. Ge, W. Ge, Z. Guo, Q. Huang, J. Huang, F. Huang, B. Hui, S. Jiang, Z. Li, M. Li, M. Li, K. Li, Z. Lin, J. Lin, X. Liu 2025
[5] E. Borisova, N. Rauscher, and G. Rehm. SciVQA 2025: Overview of the first scientific visual question answering shared task. In T. Ghosal, P. Mayr, A. Singh, A. Naik, G. Rehm, D. Freitag, D. Li, S. Sch 2025

Formal links

2 machine-checked theorem links

Receipt and verification
First computed 2026-05-20T00:01:03.759525Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

df0111f1f6304aa47bf9fda53f40b6011f2f9be2ff2b28c78881d1e4945a2ff0

Aliases

arxiv: 2605.15532 · arxiv_version: 2605.15532v1 · doi: 10.48550/arxiv.2605.15532 · pith_short_12: 34ARD4PWGBFK · pith_short_16: 34ARD4PWGBFKI67Z · pith_short_8: 34ARD4PW
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/34ARD4PWGBFKI67Z7WST6QFWAE \
  | 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: df0111f1f6304aa47bf9fda53f40b6011f2f9be2ff2b28c78881d1e4945a2ff0
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "883bae94ff2fc62e21fb5ee30815f5c9ef232e4908e27f5ccf176f7fa4d411df",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-15T02:04:12Z",
    "title_canon_sha256": "205a12a65d62f544b2982b6c8f2121ea2c905435acae6af428c50bf3c8c6dfe0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15532",
    "kind": "arxiv",
    "version": 1
  }
}