mlsanityData to 7 Oct 2026

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

arXiv 2412.13702 ↗First posted 18 Dec 2024cs.CL cs.AIcited by 12

On the map: Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning

Abstract (arXiv)

This paper introduces Typhoon 2, a series of text and multimodal large language models optimized for the Thai language. The series includes models for text, vision, and audio. Typhoon2-Text builds on state-of-the-art open models, such as Llama 3 and Qwen2, and we perform continual pre-training on a mixture of English and Thai data. We employ post-training techniques to enhance Thai language performance while preserving the base models' original capabilities. We release text models across a range of sizes, from 1 to 70 billion parameters, available in both base and instruction-tuned variants. To guardrail text generation, we release Typhoon2-Safety, a classifier enhanced for Thai cultures and language. Typhoon2-Vision improves Thai document understanding while retaining general visual capabilities, such as image captioning. Typhoon2-Audio introduces an end-to-end speech-to-speech model architecture capable of processing audio, speech, and text inputs and generating both text and speech outputs.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 65 of its 129 references that are in the map. First posted on arXiv 18 Dec 2024.

Builds on

65 of 129 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution18 Sep
  2. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs24 Jun
  3. 2023MMBench: Is Your Multi-modal Model an All-around Player?12 Jul
  4. 2023SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities18 May

Other references · 61

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  6. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  7. 2023Visual Instruction Tuningcited by 7,792
  8. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  9. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  10. 2021Program Synthesis with Large Language Modelscited by 3,509
  11. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  12. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
38 more
  1. 2024Qwen2 Technical Reportcited by 2,076
  2. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,883
  3. 2019Towards VQA Models That Can Readcited by 1,696
  4. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,449
  5. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,330
  6. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  7. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,288
  8. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
  9. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,143
  10. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,124
  11. 2024The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scalecited by 1,104
  12. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,057
  13. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Trainingcited by 988
  14. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 828
  15. 2023Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunchcited by 679
  16. 2023Safe RLHF: Safe Reinforcement Learning from Human Feedbackcited by 630
  17. 2023Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelscited by 591
  18. 2023Textbooks Are All You Needcited by 561
  19. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 466
  20. 2024WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMscited by 460
  21. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 458
  22. 2023Scaling Speech Technology to 1,000+ Languagescited by 401
  23. 2024Automated Design of Agentic Systemscited by 360
  24. 2023Magicoder: Empowering Code Generation with OSS-Instructcited by 251
  25. 2024Evolutionary Optimization of Model Merging Recipescited by 204
  26. 2024ToolACE: Winning the Points of LLM Function Callingcited by 204
  27. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasetscited by 188
  28. 2024LLaMA-Omni: Seamless Speech Interaction with Large Language Modelscited by 169
  29. 2024OpenCoder: The Open Cookbook for Top-Tier Code Large Language Modelscited by 127
  30. 2024Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinementcited by 111
  31. 2023M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Modelscited by 109
  32. 2024LLaMA Beyond English: An Empirical Study on Language Capability Transfercited by 94
  33. 2024MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answeringcited by 93
  34. 2024Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Modelscited by 91
  35. 2024LLM Pruning and Distillation in Practice: The Minitron Approachcited by 82
  36. 2019GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answeringcited by 77
  37. 2024Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Modelscited by 73
  38. 2023SlimPajama-DC: Understanding Data Combinations for LLM Trainingcited by 72

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 3.

12 papers.

  1. 2025A Survey of Token Compression for Efficient Multimodal Large Language Modelscited by 22
  2. 2025Typhoon T1: An Open Thai Reasoning Modelcited by 3
  3. 2025OpenThaiGPT 1.6 and R1: Thai-Centric Open Source and Reasoning Large Language Modelscited by 2
  4. 2025Thai Semantic End-of-Turn Detection for Real-Time Voice Agentscited by 2
  5. 2025Towards culturally-appropriate conversational AI for health in the majority world: An exploratory study with citizens and professionals in Latin Americacited by 1
  6. 2025Empowering Global Voices: A Data-Efficient, Phoneme-Tone Adaptive Approach to High-Fidelity Speech Synthesiscited by 0
  7. 2025OpenJAI-v1.0: An Open Thai Large Language Modelcited by 0
  8. 2025JAI-1: A Thai-Centric Large Language Modelcited by 0
  9. 2025SiamGPT: Quality-First Fine-Tuning for Stable Thai Text Generationcited by 0
  10. 2026Hello-Chat: Towards Realistic Social Audio Interactionscited by 0
  11. 2026Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Modelscited by 0
  12. 2026TSWAP: A Multilingual Retrieval-Augmented Thai Wellness Advisorcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025ThaiOCRBench: A Task-Diverse Benchmark for Vision-Language Understanding in Thai
  2. 2026Typhoon OCR: Open Vision-Language Model For Thai Document Extraction
  3. 2026BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models
  4. 2024A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision-Language Tasks
  5. 2024The Revolution of Multimodal Large Language Models: A Survey
  6. 2023SEED-Bench-2: Benchmarking Multimodal Large Language Models
  7. 2024SUTRA: Scalable Multilingual Language Model Architecture
  8. 2024A Survey of Multimodal Large Language Model from A Data-centric Perspective