@inproceedings{kumar-etal-2026-cps,
title = "{CPS} Lab 1@{MML}ow 2026: Hierarchical Multimodal Classification of {T}amil Political Memes via Logit-Conditioned Stance-Target Prediction",
author = "Kumar, Vishal and
Srivastava, Anika and
Sharma, Harshita and
Aggarwal, Nitisha and
Jain Saxena, Geetika and
Pundir, Amit and
Singh, Sanjeev",
editor = "Ponnusamy, Rahul and
Kumaresan, Prasanna Kumar and
Rajiakodi, Saranya and
B, Premjith and
MC, Shunmuga Priya and
Murugappan, Abirami and
G, Jyothish Lal and
V, Sowmya and
Chakravarthi, Bharathi Raja",
booktitle = "Proceedings of the Fifth Workshop on Multimodal Machine Learning in Low-resource Languages",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mmlow-main.11/",
pages = "97--102",
ISBN = "979-8-89176-445-3",
abstract = "Political memes have become an effective tool for online political communication and engagement. Their interpretation is particularly challenging in low-resource and code-mixed languages such as Tamil, where memes often include Tamil-English, use culturally relevant lexicon, incorporate political entities, and utilize references to prominent personalities and parties. This paper presents our submission to the MMLow shared task at AACL-IJCNLP 2026 on multi-level classification of Tamil political memes, which requires jointly predicting (i) a coarse-grained stance label (Support vs. Troll) and (ii) a fine-grained target label identifying whether the meme concerns a political party or a person. We proposed a lightweight hierarchical classifier built on frozen, pretrained multimodal encoders: images are represented using CLIP (ViT-B/32) and text using the multilingual BGE-M3 embedding model, with the two modalities combined via early, non-parametric concatenation fusion. A shared encoder feeds two prediction heads, where the target-identification head is explicitly conditioned on the stance head{'}s output logits via a gradient-detachment mechanism, allowing the model to respect the task{'}s label hierarchy without corrupting the coarse-level classifier{'}s gradients. To address pronounced class imbalance in both label levels, we applied balanced loss weighting at each level. On the test set of unlabeled data, our system achieved 3rd place, with macro-F1 scores of 0.856 for stance classification and 0.532 for target identification, yielding a final score of 0.694, indicating promising performance on the Tamil political meme classification problem."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-etal-2026-cps">
<titleInfo>
<title>CPS Lab 1@MMLow 2026: Hierarchical Multimodal Classification of Tamil Political Memes via Logit-Conditioned Stance-Target Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vishal</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anika</namePart>
<namePart type="family">Srivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harshita</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitisha</namePart>
<namePart type="family">Aggarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geetika</namePart>
<namePart type="family">Jain Saxena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amit</namePart>
<namePart type="family">Pundir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjeev</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Multimodal Machine Learning in Low-resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Ponnusamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prasanna</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Kumaresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saranya</namePart>
<namePart type="family">Rajiakodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Premjith</namePart>
<namePart type="family">B</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shunmuga</namePart>
<namePart type="given">Priya</namePart>
<namePart type="family">MC</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abirami</namePart>
<namePart type="family">Murugappan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jyothish</namePart>
<namePart type="given">Lal</namePart>
<namePart type="family">G</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sowmya</namePart>
<namePart type="family">V</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-445-3</identifier>
</relatedItem>
<abstract>Political memes have become an effective tool for online political communication and engagement. Their interpretation is particularly challenging in low-resource and code-mixed languages such as Tamil, where memes often include Tamil-English, use culturally relevant lexicon, incorporate political entities, and utilize references to prominent personalities and parties. This paper presents our submission to the MMLow shared task at AACL-IJCNLP 2026 on multi-level classification of Tamil political memes, which requires jointly predicting (i) a coarse-grained stance label (Support vs. Troll) and (ii) a fine-grained target label identifying whether the meme concerns a political party or a person. We proposed a lightweight hierarchical classifier built on frozen, pretrained multimodal encoders: images are represented using CLIP (ViT-B/32) and text using the multilingual BGE-M3 embedding model, with the two modalities combined via early, non-parametric concatenation fusion. A shared encoder feeds two prediction heads, where the target-identification head is explicitly conditioned on the stance head’s output logits via a gradient-detachment mechanism, allowing the model to respect the task’s label hierarchy without corrupting the coarse-level classifier’s gradients. To address pronounced class imbalance in both label levels, we applied balanced loss weighting at each level. On the test set of unlabeled data, our system achieved 3rd place, with macro-F1 scores of 0.856 for stance classification and 0.532 for target identification, yielding a final score of 0.694, indicating promising performance on the Tamil political meme classification problem.</abstract>
<identifier type="citekey">kumar-etal-2026-cps</identifier>
<location>
<url>https://aclanthology.org/2026.mmlow-main.11/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>97</start>
<end>102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CPS Lab 1@MMLow 2026: Hierarchical Multimodal Classification of Tamil Political Memes via Logit-Conditioned Stance-Target Prediction
%A Kumar, Vishal
%A Srivastava, Anika
%A Sharma, Harshita
%A Aggarwal, Nitisha
%A Jain Saxena, Geetika
%A Pundir, Amit
%A Singh, Sanjeev
%Y Ponnusamy, Rahul
%Y Kumaresan, Prasanna Kumar
%Y Rajiakodi, Saranya
%Y B, Premjith
%Y MC, Shunmuga Priya
%Y Murugappan, Abirami
%Y G, Jyothish Lal
%Y V, Sowmya
%Y Chakravarthi, Bharathi Raja
%S Proceedings of the Fifth Workshop on Multimodal Machine Learning in Low-resource Languages
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-445-3
%F kumar-etal-2026-cps
%X Political memes have become an effective tool for online political communication and engagement. Their interpretation is particularly challenging in low-resource and code-mixed languages such as Tamil, where memes often include Tamil-English, use culturally relevant lexicon, incorporate political entities, and utilize references to prominent personalities and parties. This paper presents our submission to the MMLow shared task at AACL-IJCNLP 2026 on multi-level classification of Tamil political memes, which requires jointly predicting (i) a coarse-grained stance label (Support vs. Troll) and (ii) a fine-grained target label identifying whether the meme concerns a political party or a person. We proposed a lightweight hierarchical classifier built on frozen, pretrained multimodal encoders: images are represented using CLIP (ViT-B/32) and text using the multilingual BGE-M3 embedding model, with the two modalities combined via early, non-parametric concatenation fusion. A shared encoder feeds two prediction heads, where the target-identification head is explicitly conditioned on the stance head’s output logits via a gradient-detachment mechanism, allowing the model to respect the task’s label hierarchy without corrupting the coarse-level classifier’s gradients. To address pronounced class imbalance in both label levels, we applied balanced loss weighting at each level. On the test set of unlabeled data, our system achieved 3rd place, with macro-F1 scores of 0.856 for stance classification and 0.532 for target identification, yielding a final score of 0.694, indicating promising performance on the Tamil political meme classification problem.
%U https://aclanthology.org/2026.mmlow-main.11/
%P 97-102
Markdown (Informal)
[CPS Lab 1@MMLow 2026: Hierarchical Multimodal Classification of Tamil Political Memes via Logit-Conditioned Stance-Target Prediction](https://aclanthology.org/2026.mmlow-main.11/) (Kumar et al., MMLow 2026)
ACL