Showing 1–20 of 20 results
/ Date/ Name
Mar 7, 2026Taiwan Safety Benchmark and Breeze Guard: Toward Trustworthy AI for Taiwanese MandarinDec 5, 2025Spectrally-selective dynamic radiative thermoregulation via phase engineeringApr 8, 2025High-efficiency broadband active metasurfaces via reversible metal electrodepositionJan 23, 2025The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on Llama with Vision-Aware and Function-Calling CapabilitiesDec 2, 2024Enhancing Function-Calling Capabilities in LLMs: Strategies for Prompt Formats, Data Integration, and Multilingual TranslationNov 11, 2024Building a Taiwanese Mandarin Spoken Language Model: A First AttemptSep 19, 2024RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented DialoguesMay 23, 2024Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCRMar 5, 2024Breeze-7B Technical ReportSep 29, 2023Low-Resource Self-Supervised Learning with SSL-Enhanced TTSApr 25, 2023Federated Deep Reinforcement Learning for THz-Beam Search with Limited CSIMar 8, 2023Extending the Pre-Training of BLOOM for Improved Support of Traditional Chinese: Models, Methods and ResultsMay 8, 2022Silence is Sweeter Than Speech: Self-Supervised Model Using Silence to Store Speaker InformationApr 25, 2022Parallel Synthesis for Autoregressive Speech GenerationApr 1, 2022Universal Adaptor: Converting Mel-Spectrograms Between Different Configurations for Speech SynthesisJul 29, 2021Bio-inspired vascularized electrodes for high-performance fast-charging batteries designed by deep learningMar 6, 2021Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-SpeechMay 15, 2020WG-WaveNet: Real-Time High-Fidelity Speech Synthesis without GPUDec 5, 2019Towards Robust Neural Vocoding for Speech Generation: A SurveyMay 28, 2019Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion