7 citations · 10 across the 23 of their papers we have counts for
27 papers
ANOVA approximation for high-dimensional control systems
Melanie Kircheis, Daniel Potts, Manuel Schaller +1
We study the data-driven approximation of control-affine systems, where the drift and each control vector field exhibit a low-dimensional structure. While the ANOVA (ANalysis Of VA…
When a Kindergartener Solves Calculus: Measuring Capability Leakage in Role-Prompted Reasoning Models
Pakhapoom Sarapat, Saksorn Ruangtanusak, Kunat Pipatanakul +1
We investigate the problem of role-capability leakage (RCL), in which a role-prompted reasoning model generates convincing in-role text while continuing to exhibit capabilities on…
Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow Fusion
Warit Sirichotedumrong, Tanawin Samutsin, Shah Faisal Wani +2
Open Thai automatic speech recognition (ASR) is dominated by offline, Whisper-based models that read the whole utterance before transcribing, ruling out low-latency uses such as li…
Pushing CPU Speech Synthesis to the Wall: Extreme Inference Tuning under Serverless Architecture and Billing
Pakorn Nathong, Kunat Pipatanakul
Instance-billed serverless platforms charge for CPU and memory over the lifetime of a warm instance, making idle inference state a direct serving cost. We present billing-aware neu…
How Far Can Synthetic Data Take Thai OCR?
Kunat Pipatanakul
We investigate what makes synthetic OCR supervision transfer to real Thai documents and use the resulting insights to build Wayu-Paxa-OCR-Zero, a Thai OCR model adapted without OCR…
Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech
Kunat Pipatanakul, Potsawee Manakul, Warit Sirichotedumrong +3
In low-resource settings, deploying TTS typically requires choosing between a large voice-cloning model with costly inference or a compact fixed-voice system that requires a speake…
ThaiSafetyBench: Assessing Language Model Safety in Thai Cultural Contexts
Trapoom Ukarapol, Nut Chukamphaeng, Kunat Pipatanakul +1
The safety evaluation of large language models (LLMs) remains largely centered on English, leaving non-English languages and culturally grounded risks underexplored. In this work,…
Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models
Kunat Pipatanakul, Pittawat Taveekitworachai
Large language models (LLMs) have progressed rapidly; however, most state-of-the-art models are trained and evaluated primarily in high-resource languages such as English and Chine…
Typhoon OCR: Open Vision-Language Model For Thai Document Extraction
Surapon Nonesung, Natapong Nitarach, Teetouch Jaknamon +2
Document extraction is a core component of digital workflows, yet existing vision-language models (VLMs) predominantly favor high-resource languages. Thai presents additional chall…
Typhoon ASR Real-time: FastConformer-Transducer for Thai Automatic Speech Recognition
Warit Sirichotedumrong, Adisai Na-Thalang, Potsawee Manakul +3
Large encoder-decoder models like Whisper achieve strong offline transcription but remain impractical for streaming applications due to high latency. However, due to the accessibil…
Formula-One Prompting: A Composable Equation-First Prefix for Applied Mathematics
Natapong Nitarach, Pittawat Taveekitworachai, Kunat Pipatanakul
This paper introduces Formula Prompting (FP) and Formula-One Prompting (F-1), two single-call methods that elicit governing equations before solving applied-math problems. Chain-of…
ThaiOCRBench: A Task-Diverse Benchmark for Vision-Language Understanding in Thai
Surapon Nonesung, Teetouch Jaknamon, Sirinya Chaiophat +5
We present ThaiOCRBench, the first comprehensive benchmark for evaluating vision-language models (VLMs) on Thai text-rich visual understanding tasks. Despite recent progress in mul…
Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting
Saksorn Ruangtanusak, Pittawat Taveekitworachai, Kunat Pipatanakul
This report investigates approaches for prompting a tool-augmented large language model (LLM) to act as a role-playing dialogue agent in the API track of the Commonsense Persona-gr…
Extending Audio Context for Long-Form Understanding in Large Audio-Language Models
Yuatyong Chaichana, Pittawat Taveekitworachai, Warit Sirichotedumrong +2
Large Audio-Language Models (LALMs) are often constrained by short audio context windows, even when their text backbones support long contexts, limiting long-form audio understandi…
On the Robustness of Answer Formats in Medical Reasoning Models
Pittawat Taveekitworachai, Natpatchara Pongjirapat, Krittaphas Chaisutyakorn +3
Medical reasoning models (MRMs) achieve superior performance on medical benchmarks compared to medical LLMs; however, high accuracy alone is insufficient for practical deployment.…
Mangosteen: An Open Thai Corpus for Language Model Pretraining
Wannaphong Phatthiyaphaibun, Can Udomcharoenchaikit, Pakpoom Singkorapoom +4
Pre-training data shapes a language model's quality, but raw web text is noisy and demands careful cleaning. Existing large-scale corpora rely on English-centric or language-agnost…
AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation
Potsawee Manakul, Woody Haosheng Gan, Michael J. Ryan +5
Current speech evaluation suffers from two critical limitations: the need and difficulty of designing specialized systems targeting individual audio characteristics, and poor corre…
FinCoT: Grounding Chain-of-Thought in Expert Financial Reasoning
Natapong Nitarach, Warit Sirichotedumrong, Panop Pitchayarthorn +3
This paper presents FinCoT, a structured chain-of-thought (CoT) prompting framework that embeds domain-specific expert financial reasoning blueprints to guide large language models…
Prior Prompt Engineering for Reinforcement Fine-Tuning
Pittawat Taveekitworachai, Potsawee Manakul, Sarana Nutanong +1
This paper investigates prior prompt engineering (pPE) in the context of reinforcement fine-tuning (RFT), where language models (LMs) are incentivized to exhibit behaviors that max…
Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe
Kunat Pipatanakul, Pittawat Taveekitworachai, Potsawee Manakul +1
This paper investigates data selection and model merging methodologies aimed at incorporating advanced reasoning capabilities such as those of DeepSeek R1 into language-specific la…
Typhoon T1: An Open Thai Reasoning Model
Pittawat Taveekitworachai, Potsawee Manakul, Kasima Tharnpipitchai +1
This paper introduces Typhoon T1, an open effort to develop an open Thai reasoning model. A reasoning model is a relatively new type of generative model built on top of large langu…
Mind the Gap! Static and Interactive Evaluations of Large Audio Models
Minzhi Li, William Barr Held, Michael J Ryan +4
As AI chatbots become ubiquitous, voice interaction presents a compelling way to enable rapid, high-bandwidth communication for both semantic and social signals. This has driven re…
Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs
Longxu Dou, Qian Liu, Fan Zhou +38
Sailor2 is a family of cutting-edge multilingual language models for South-East Asian (SEA) languages, available in 1B, 8B, and 20B sizes to suit diverse applications. Building on…
Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models
Kunat Pipatanakul, Potsawee Manakul, Natapong Nitarach +9
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. Typh…