(function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start': new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0], j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.data-privacy-src= 'https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f); })(window,document,'script','dataLayer','GTM-NMZN8BRP');

Search in SCBX

Featured on SCBX website

Mastering Agentic Workflows – 20 Principles to Build Smarter AI Systems

This SCBX Group framework outlines 20 key principles for building smarter agentic AI systems, focusing on evaluation, context engineering, prompt design, and tool integration to improve how AI thinks and acts.

By |2026-07-17T17:46:43+07:0022/06/2026|Optimal|0 Comments

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

SCB 10X introduces Typhoon OCR, an open vision-language model fine-tuned on a Thai-focused dataset using a multi-stage data construction pipeline. The model provides a unified framework capable of performing text translation, key-value extraction, and structured document parsing for both Thai and English.

By |2026-06-24T16:20:38+07:0022/06/2026|Human-Intelligence|0 Comments

Typhoon Isan: Open-Source ASR and a Language Technology Suite for Thailand’s Largest Dialect

SCB 10X develops Typhoon Isan. It is Thailand’s first open-source AI that understands the Isan language, combining useful datasets, clear transcription standards, and both real-time and accurate speech-to-text models.

By |2026-07-20T14:43:50+07:0022/06/2026|Exclusive, Human-Intelligence|0 Comments

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

This Research by SCBX Group and partners introduces Partial YaRN, a training-free position interpolation method that modifies only audio token positions while keeping text embeddings intact. The technique extends the context window, allowing processing of longer speech and audio tracks.

By |2026-06-24T16:18:50+07:0022/06/2026|Human-Intelligence|0 Comments

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

This Research by SCBX Group and Partners presents Typhoon-S, a framework for minimal open post-training designed to customize base models into highly capable regional assistants. It outlines requirements for general adoptability and sovereign capability to enable localized AI deployment with transparency.

By |2026-07-20T14:28:45+07:0019/06/2026|Optimal|0 Comments

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

This Research by SCBX Group and Partners introduces AudioJudge, a speech evaluation framework utilizing large audio models (LAMs) as judges. The system demonstrates a high correlation with human judgment across multiple audio attributes, offering a unified evaluation solution.

By |2026-06-24T16:06:28+07:0019/06/2026|Optimal|0 Comments

Towards Better Understanding of Program-of-Thought Reasoning

This Research by SCBX Group and Partners shows that Program-of-Thought (PoT) improves multilingual reasoning in LLMs by separating reasoning from execution. After fine-tuning, PoT outperforms Chain-of-Thought (CoT), and better reasoning leads to more accurate answers.

By |2026-06-24T16:04:25+07:0017/06/2026|Optimal|0 Comments
Go to Top