Image de couverture de livre

Distilling Multilingual Vision-Language Models: When Smaller Models Stay Multilingual

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sriratanawilai, Sukrit, Thongwat, Jhayahgrit, Chumpu, Romrawin, Payoungkhamdee, Patomporn, Nutanong, Sarana, Limkonchotiwat, Peerat
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

When Better Teachers Don't Make Better Students: Revisiting Knowledge Distillation for CLIP Models in VQA
par: Tuchinda, Pume, et autres
Publié: (2025)

Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environments
par: Payoungkhamdee, Patomporn, et autres
Publié: (2025)

Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning
par: Udsa, Tinnakit, et autres
Publié: (2025)

WangchanLion and WangchanX MRC Eval
par: Phatthiyaphaibun, Wannaphong, et autres
Publié: (2024)

Space Decomposition for Sentence Embedding
par: Ponwitayarat, Wuttikorn, et autres
Publié: (2024)

Mangosteen: An Open Thai Corpus for Language Model Pretraining
par: Phatthiyaphaibun, Wannaphong, et autres
Publié: (2025)

Assessing Thai Dialect Performance in LLMs with Automatic Benchmarks and Human Evaluation
par: Limkonchotiwat, Peerat, et autres
Publié: (2025)

WangchanThaiInstruct: An instruction-following Dataset for Culture-Aware, Multitask, and Multi-domain Evaluation in Thai
par: Limkonchotiwat, Peerat, et autres
Publié: (2025)

Language Surgery in Multilingual Large Language Models
par: Lopo, Joanito Agili, et autres
Publié: (2025)

SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia
par: Tasawong, Panuthep, et autres
Publié: (2026)

MultiLexNorm++: A Unified Benchmark and a Generative Model for Lexical Normalization for Asian Languages
par: Buaphet, Weerayut, et autres
Publié: (2026)

SEA-BED: How Do Embedding Models Represent Southeast Asian Languages?
par: Ponwitayarat, Wuttikorn, et autres
Publié: (2025)

Addressing Topic Leakage in Cross-Topic Evaluation for Authorship Verification
par: Sawatphol, Jitkapat, et autres
Publié: (2024)

BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models
par: Aung, Thura, et autres
Publié: (2026)

A Two-Phase Stability Study of LLM Judges and Bar Council Examiners on Thai Bar-Exam Free-Form Essays
par: Akarajaradwong, Pawitsapak, et autres
Publié: (2026)

Seed-Free Synthetic Data Generation Framework for Instruction-Tuning LLMs: A Case Study in Thai
par: Pengpun, Parinthapat, et autres
Publié: (2024)

SEADialogues: A Multilingual Culturally Grounded Multi-turn Dialogue Dataset on Southeast Asian Languages
par: Kautsar, Muhammad Dehan Al, et autres
Publié: (2025)

Prior Prompt Engineering for Reinforcement Fine-Tuning
par: Taveekitworachai, Pittawat, et autres
Publié: (2025)

Multilingual Vision-Language Models, A Survey
par: Manea, Andrei-Alexandru, et autres
Publié: (2025)

Multilingual Large Language Models and Curse of Multilinguality
par: Gurgurov, Daniil, et autres
Publié: (2024)

SEA-SafeguardBench: Evaluating AI Safety in SEA Languages and Cultures
par: Tasawong, Panuthep, et autres
Publié: (2025)

Pruning Multilingual Large Language Models for Multilingual Inference
par: Kim, Hwichan, et autres
Publié: (2024)

Constructing Multilingual Visual-Text Datasets Revealing Visual Multilingual Ability of Vision Language Models
par: Atuhurra, Jesse, et autres
Publié: (2024)

Multilingual Training and Evaluation Resources for Vision-Language Models
par: Baiamonte, Daniela, et autres
Publié: (2026)

Multi-Hypothesis Distillation of Multilingual Neural Translation Models for Low-Resource Languages
par: Galiano-Jiménez, Aarón, et autres
Publié: (2025)

Efficient Multilingual Dialogue Processing via Translation Pipelines and Distilled Language Models
par: Novoa, Santiago Martínez, et autres
Publié: (2026)

BPE Stays on SCRIPT: Structured Encoding for Robust Multilingual Pretokenization
par: Land, Sander, et autres
Publié: (2025)

Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Models
par: Lu, Hongyuan, et autres
Publié: (2024)

Mitigating Multilingual Hallucination in Large Vision-Language Models
par: Qu, Xiaoye, et autres
Publié: (2024)

Behind Maya: Building a Multilingual Vision Language Model
par: Alam, Nahid, et autres
Publié: (2025)

Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model
par: Geigle, Gregor, et autres
Publié: (2025)

Exploring Vision Language Models for Multimodal and Multilingual Stance Detection
par: Vasilakes, Jake, et autres
Publié: (2025)

AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment
par: Bu, Mengyu, et autres
Publié: (2025)

When Alignment Hurts: Decoupling Representational Spaces in Multilingual Models
par: Elshabrawy, Ahmed, et autres
Publié: (2025)

When Abundance Conceals Weakness: Knowledge Conflict in Multilingual Models
par: Zhao, Jiaqi, et autres
Publié: (2026)

Mixed Distillation Helps Smaller Language Model Better Reasoning
par: Li, Chenglin, et autres
Publié: (2023)

Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models
par: Fan, Yuchun, et autres
Publié: (2025)

Once Correct, Still Wrong: Counterfactual Hallucination in Multilingual Vision-Language Models
par: Mousi, Basel, et autres
Publié: (2026)

Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages
par: Zhang, Yuanchi, et autres
Publié: (2024)

Can Group Relative Policy Optimization Improve Thai Legal Reasoning and Question Answering?
par: Akarajaradwong, Pawitsapak, et autres
Publié: (2025)