Author

Kunat Pipatanakul

Observed name: Pipatanakul, Kunat

Institution: AI Singapore

Observed institution: AI Singapore

OpenAlex ID: A5021237405

Typhoon: Thai Large Language Models

2023 · Pipatanakul, Kunat, Jirabovonvisut, Phatrasek, et al. · arXiv (Cornell University) · 9

PDF

Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models

2025 · Potsawee Manakul, Guangzhi Sun, et al. · Interspeech (USB) · 3

PDF

ThaiOCRBench: A Task-Diverse Benchmark for Vision-Language Understanding in Thai

2025 · Surapon Nonesung, Teetouch Jaknamon, et al. · International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL) · 2

PDF

Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs

2025 · Dou, Longxu, Liu, Qian, et al. · arXiv (Cornell University) · 1

PDF

Prior Prompt Engineering for Reinforcement Fine-Tuning

2025 · Pittawat Taveekitworachai, Potsawee Manakul, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 1

PDF

Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models

2024 · Pipatanakul, Kunat, Manakul, Potsawee, et al. · arXiv (Cornell University) · 1

PDF

CrossCheckGPT: Universal Hallucination Ranking for Multimodal Foundation Models

2024 · Sun, Guangzhi, Manakul, Potsawee, et al. · arXiv (Cornell University) · 1

PDF

SEA-HELM Audio: Evaluating Multilingual ASR-LLM Pipeline Performance Across SEA-HELM Subsets

2026 · Adila, Aulia, Tan, Yixian, et al. · arXiv (Cornell University)

PDF

AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis

2026 · Nitarach, Natapong, Ngampornsukswadi, Phume, et al. · arXiv (Cornell University)

PDF

When a Kindergartener Solves Calculus: Measuring Capability Leakage in Role-Prompted Reasoning Models

2026 · Sarapat, Pakhapoom, Ruangtanusak, Saksorn, et al. · arXiv (Cornell University)

PDF

Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow Fusion

2026 · Sirichotedumrong, Warit, Samutsin, Tanawin, et al. · arXiv (Cornell University)

PDF

Pushing CPU Speech Synthesis to the Wall: Extreme Inference Tuning under Serverless Architecture and Billing

2026 · Nathong, Pakorn, Pipatanakul, Kunat · arXiv (Cornell University)

PDF

How Far Can Synthetic Data Take Thai OCR?

2026 · Pipatanakul, Kunat · arXiv (Cornell University)

PDF

Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech

2026 · Pipatanakul, Kunat, Manakul, Potsawee, et al. · arXiv (Cornell University)

PDF

Extending Audio Context for Long-Form Understanding in Large Audio-Language Models

2026 · Association for Computational Linguistics 2026, Chaichana, Yuatyong, et al. · Underline Science Inc.

AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation

2026 · Association for Computational Linguistics 2026, Gan, Haosheng, et al. · Underline Science Inc.

ThaiSafetyBench: Assessing Language Model Safety in Thai Cultural Contexts

2026 · Ukarapol, Trapoom, Chukamphaeng, Nut, et al. · arXiv (Cornell University)

PDF

Formula-One Prompting: A Composable Equation-First Prefix for Applied Mathematics

2026 · Nitarach, Natapong, Taveekitworachai, Pittawat, et al. · arXiv (Cornell University)

PDF

Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models

2026 · Pipatanakul, Kunat, Taveekitworachai, Pittawat · arXiv (Cornell University)

PDF

Typhoon OCR: Open Vision-Language Model For Thai Document Extraction

2026 · Nonesung, Surapon, Nitarach, Natapong, et al. · arXiv (Cornell University)

PDF

Typhoon ASR Real-time: FastConformer-Transducer for Thai Automatic Speech Recognition

2026 · Sirichotedumrong, Warit, Na-Thalang, Adisai, et al. · arXiv (Cornell University)

PDF

AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation

2026 · Potsawee Manakul, Woody Haosheng Gan, et al. · Conference of the European Chapter of the Association for Computational Linguistics

PDF

Extending Audio Context for Long-Form Understanding in Large Audio-Language Models

2026 · Yuatyong Chaichana, Pittawat Taveekitworachai, et al. · Conference of the European Chapter of the Association for Computational Linguistics

PDF

ThaiOCRBench: A Task-Diverse Benchmark for Vision-Language Understanding in Thai

2025 · Association for Computational Linguistics 2025, Chaiophat, Sirinya, et al. · Underline Science Inc.

ThaiOCRBench: A Task-Diverse Benchmark for Vision-Language Understanding in Thai

2025 · Nonesung, Surapon, Jaknamon, Teetouch, et al. · arXiv (Cornell University)

PDF

Works count: 38

Citation count: 18

H-index: 2

I10-index: