Evaluating large language models (LLMs) on AMLworld's smallest test splits is costly because each of over a million targets requires a separate graph prompt. Sampling reduces this cost, but small balanced subsets change unweighted precision and F1. We introduce AMLworld-Compact, an evaluation set that retains every ill...
Natapong Nitarach, Phume Ngampornsukswadi, Pittawat Taveekitworachai et al.· 0 citations
Injection is proposed, an inference-time intervention that combines explicit, role-specific capability guidelines with a guiding prefilled response prefix that improves role-capability alignment across models, reducing above-role accuracy by up to 0.562 while preserving in-role accuracy with a marginal drop of less tha...
Pakhapoom Sarapat, Saksorn Ruangtanusak, Kunat Pipatanakul et al.· 0 citations
A deployable system for streaming Thai ASR that lets a user steer its vocabulary at decode time, without retraining is presented, which lifts keyword recall from 16.6% to 20.7% at no accuracy cost and negligible overhead.
Warit Sirichotedumrong, Tanawin Samutsin, Shahira Wani et al.· 0 citations
It is found that synthetic-only training can be competitive, and the 0.9B-parameter PaddleOCR-VL-1.6 is adapted into Wayu-Paxa-OCR-Zero, a Thai OCR model adapted without OCR labels from real Thai document pages, showing that synthetic-only training can be competitive.
The resulting 82M-parameter model, Wayu-Paxa-TTS-Edge, enables on-device Thai TTS without reference audio and achieves the lowest pause-placement error and intra-word pause rates among the three systems.
Kunat Pipatanakul, Potsawee Manakul, Warit Sirichotedumrong et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
