@inproceedings{te-etal-2026-ssr,
title = "{SSR}-A: Spatial- and Semantic-Aware Instructions and Curriculum Reinforcement for Advertisement Compliant Rectification",
author = "Te, Cao and
Xue, Mengge and
Hu, Zhenyu and
Chen, Yuan and
Liu, Liqun and
Shu, Peng and
Yu, Huan and
Jiang, Jie",
editor = "Li, Yunyao and
Rehm, Georg and
Tu, Mei",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 6: Industry Track)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-industry.23/",
doi = "10.18653/v1/2026.acl-industry.23",
pages = "346--357",
ISBN = "979-8-89176-394-4",
abstract = "While advertising is a cornerstone of commercial growth, it is constrained by online violation detection systems that reject non-compliant content at a million-scale daily. Advertisers urgently require automated solutions to rectify these advertisements, especially visual ads, as manual fixing is unscalable. Although recent safety-driven methods can achieve compliance, they typically suffer from over-editing, destroying the original commercial intent and perceptual similarity.To address this, we present SSR-A, a framework tailored for the minimalist rectification of non-compliant image ads.Instead of fine-tuning image editing models directly, SSR-A focuses on translating violation policies into targeted editing instructions.We first introduce a Spatial- and Semantic-Aware Instruction Synthesis Pipeline, where MLLMs synthesize candidate instructions{---}incorporating spatial grounding and semantic guidance{---}and select the optimal instruction via multi-dimensional evaluation. Furthermore, we align the model using Curriculum Reinforcement Learning, employing GRPO with multi-faceted rewards to progressively navigate the trade-off between compliance and visual preservation. Extensive experiments and online A/B tests show that SSR-A significantly outperforms state-of-the-art baselines in both compliance and preservation of visual and commercial consistency."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="te-etal-2026-ssr">
<titleInfo>
<title>SSR-A: Spatial- and Semantic-Aware Instructions and Curriculum Reinforcement for Advertisement Compliant Rectification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cao</namePart>
<namePart type="family">Te</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengge</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenyu</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liqun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Shu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<abstract>While advertising is a cornerstone of commercial growth, it is constrained by online violation detection systems that reject non-compliant content at a million-scale daily. Advertisers urgently require automated solutions to rectify these advertisements, especially visual ads, as manual fixing is unscalable. Although recent safety-driven methods can achieve compliance, they typically suffer from over-editing, destroying the original commercial intent and perceptual similarity.To address this, we present SSR-A, a framework tailored for the minimalist rectification of non-compliant image ads.Instead of fine-tuning image editing models directly, SSR-A focuses on translating violation policies into targeted editing instructions.We first introduce a Spatial- and Semantic-Aware Instruction Synthesis Pipeline, where MLLMs synthesize candidate instructions—incorporating spatial grounding and semantic guidance—and select the optimal instruction via multi-dimensional evaluation. Furthermore, we align the model using Curriculum Reinforcement Learning, employing GRPO with multi-faceted rewards to progressively navigate the trade-off between compliance and visual preservation. Extensive experiments and online A/B tests show that SSR-A significantly outperforms state-of-the-art baselines in both compliance and preservation of visual and commercial consistency.</abstract>
<identifier type="citekey">te-etal-2026-ssr</identifier>
<identifier type="doi">10.18653/v1/2026.acl-industry.23</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.23/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>346</start>
<end>357</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SSR-A: Spatial- and Semantic-Aware Instructions and Curriculum Reinforcement for Advertisement Compliant Rectification
%A Te, Cao
%A Xue, Mengge
%A Hu, Zhenyu
%A Chen, Yuan
%A Liu, Liqun
%A Shu, Peng
%A Yu, Huan
%A Jiang, Jie
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F te-etal-2026-ssr
%X While advertising is a cornerstone of commercial growth, it is constrained by online violation detection systems that reject non-compliant content at a million-scale daily. Advertisers urgently require automated solutions to rectify these advertisements, especially visual ads, as manual fixing is unscalable. Although recent safety-driven methods can achieve compliance, they typically suffer from over-editing, destroying the original commercial intent and perceptual similarity.To address this, we present SSR-A, a framework tailored for the minimalist rectification of non-compliant image ads.Instead of fine-tuning image editing models directly, SSR-A focuses on translating violation policies into targeted editing instructions.We first introduce a Spatial- and Semantic-Aware Instruction Synthesis Pipeline, where MLLMs synthesize candidate instructions—incorporating spatial grounding and semantic guidance—and select the optimal instruction via multi-dimensional evaluation. Furthermore, we align the model using Curriculum Reinforcement Learning, employing GRPO with multi-faceted rewards to progressively navigate the trade-off between compliance and visual preservation. Extensive experiments and online A/B tests show that SSR-A significantly outperforms state-of-the-art baselines in both compliance and preservation of visual and commercial consistency.
%R 10.18653/v1/2026.acl-industry.23
%U https://aclanthology.org/2026.acl-industry.23/
%U https://doi.org/10.18653/v1/2026.acl-industry.23
%P 346-357
Markdown (Informal)
[SSR-A: Spatial- and Semantic-Aware Instructions and Curriculum Reinforcement for Advertisement Compliant Rectification](https://aclanthology.org/2026.acl-industry.23/) (Te et al., ACL 2026)
ACL
- Cao Te, Mengge Xue, Zhenyu Hu, Yuan Chen, Liqun Liu, Peng Shu, Huan Yu, and Jie Jiang. 2026. SSR-A: Spatial- and Semantic-Aware Instructions and Curriculum Reinforcement for Advertisement Compliant Rectification. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track), pages 346–357, San Diego, California, USA. Association for Computational Linguistics.