Cover Image

When Better Teachers Don't Make Better Students: Revisiting Knowledge Distillation for CLIP Models in VQA

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tuchinda, Pume, Pengpun, Parinthapat, Chumpu, Romrawin, Nutanong, Sarana, Limkonchotiwat, Peerat
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Distilling Multilingual Vision-Language Models: When Smaller Models Stay Multilingual
by: Sriratanawilai, Sukrit, et al.
Published: (2025)

Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environments
by: Payoungkhamdee, Patomporn, et al.
Published: (2025)

Seed-Free Synthetic Data Generation Framework for Instruction-Tuning LLMs: A Case Study in Thai
by: Pengpun, Parinthapat, et al.
Published: (2024)

WangchanThaiInstruct: An instruction-following Dataset for Culture-Aware, Multitask, and Multi-domain Evaluation in Thai
by: Limkonchotiwat, Peerat, et al.
Published: (2025)

Space Decomposition for Sentence Embedding
by: Ponwitayarat, Wuttikorn, et al.
Published: (2024)

Assessing Thai Dialect Performance in LLMs with Automatic Benchmarks and Human Evaluation
by: Limkonchotiwat, Peerat, et al.
Published: (2025)

Mangosteen: An Open Thai Corpus for Language Model Pretraining
by: Phatthiyaphaibun, Wannaphong, et al.
Published: (2025)

Don't Throw Away Data: Better Sequence Knowledge Distillation
by: Wang, Jun, et al.
Published: (2024)

Can General-Purpose Large Language Models Generalize to English-Thai Machine Translation ?
by: Chiaranaipanich, Jirat, et al.
Published: (2024)

WangchanLion and WangchanX MRC Eval
by: Phatthiyaphaibun, Wannaphong, et al.
Published: (2024)

The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models
by: Chen, Yanjun, et al.
Published: (2024)

Addressing Topic Leakage in Cross-Topic Evaluation for Authorship Verification
by: Sawatphol, Jitkapat, et al.
Published: (2024)

Data or Language Supervision: What Makes CLIP Better than DINO?
by: Liu, Yiming, et al.
Published: (2025)

CLIP-Adapter: Better Vision-Language Models with Feature Adapters
by: Gao, Peng, et al.
Published: (2021)

MultiLexNorm++: A Unified Benchmark and a Generative Model for Lexical Normalization for Asian Languages
by: Buaphet, Weerayut, et al.
Published: (2026)

A Two-Phase Stability Study of LLM Judges and Bar Council Examiners on Thai Bar-Exam Free-Form Essays
by: Akarajaradwong, Pawitsapak, et al.
Published: (2026)

Know "No" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP
by: Park, Junsung, et al.
Published: (2025)

SEA-BED: How Do Embedding Models Represent Southeast Asian Languages?
by: Ponwitayarat, Wuttikorn, et al.
Published: (2025)

Prior Prompt Engineering for Reinforcement Fine-Tuning
by: Taveekitworachai, Pittawat, et al.
Published: (2025)

On Creating an English-Thai Code-switched Machine Translation in Medical Domain
by: Pengpun, Parinthapat, et al.
Published: (2024)

EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs
by: Yeom, Jewon, et al.
Published: (2026)

Make LVLMs Focus: Context-Aware Attention Modulation for Better Multimodal In-Context Learning
by: Li, Yanshu, et al.
Published: (2025)

BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models
by: Aung, Thura, et al.
Published: (2026)

Enhancing CLIP Conceptual Embedding through Knowledge Distillation
by: Kao, Kuei-Chun
Published: (2024)

Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning
by: Udsa, Tinnakit, et al.
Published: (2025)

World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning
by: Wang, Siyin, et al.
Published: (2025)

Knowledge Generation for Zero-shot Knowledge-based VQA
by: Cao, Rui, et al.
Published: (2024)

MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings
by: Chen, Haonan, et al.
Published: (2025)

Making Large Language Models Perform Better in Knowledge Graph Completion
by: Zhang, Yichi, et al.
Published: (2023)

Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks
by: Chan, Brian J, et al.
Published: (2024)

Are Bigger Encoders Always Better in Vision Large Models?
by: Li, Bozhou, et al.
Published: (2024)

SEA-SafeguardBench: Evaluating AI Safety in SEA Languages and Cultures
by: Tasawong, Panuthep, et al.
Published: (2025)

SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia
by: Tasawong, Panuthep, et al.
Published: (2026)

Can Group Relative Policy Optimization Improve Thai Legal Reasoning and Question Answering?
by: Akarajaradwong, Pawitsapak, et al.
Published: (2025)

Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation
by: Csizmadia, Daniel, et al.
Published: (2025)

ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs
by: Li, Chaoyu, et al.
Published: (2025)

Language Models Meet Anomaly Detection for Better Interpretability and Generalizability
by: Li, Jun, et al.
Published: (2024)

Learn 3D VQA Better with Active Selection and Reannotation
by: Zhou, Shengli, et al.
Published: (2025)

NitiBench: A Comprehensive Study of LLM Framework Capabilities for Thai Legal Question Answering
by: Akarajaradwong, Pawitsapak, et al.
Published: (2025)

SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs
by: Su, Xin, et al.
Published: (2024)