Cross-Tokenizer LLM Distillation through a Byte-Level Interface Paper • 2604.07466 • Published 6 days ago • 4
Traditional Chinese Synthetic Datasets Verified with Labeled Data for Scene Text Recognition Paper • 2111.13327 • Published Nov 26, 2021
Breeze Taigi: Benchmarks and Models for Taiwanese Hokkien Speech Recognition and Synthesis Paper • 2603.19259 • Published Feb 26 • 2
MediaTek-Research/Breeze-ASR-26 Automatic Speech Recognition • 2B • Updated Nov 28, 2025 • 1.12k • 17
BreezeASR Collection Automatic Speech Recognition models of the Breeze family • 3 items • Updated 3 days ago • 1
MediaTek-Research/Breeze-ASR-26 Automatic Speech Recognition • 2B • Updated Nov 28, 2025 • 1.12k • 17
MediaTek-Research/Breeze-ASR-26 Automatic Speech Recognition • 2B • Updated Nov 28, 2025 • 1.12k • 17
MediaTek-Research/Breeze-ASR-26 Automatic Speech Recognition • 2B • Updated Nov 28, 2025 • 1.12k • 17
Revisiting the Shape Convention of Transformer Language Models Paper • 2602.06471 • Published Feb 6 • 4
Revisiting the Shape Convention of Transformer Language Models Paper • 2602.06471 • Published Feb 6 • 4
Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Multi-modal Text Recognition Paper • 2405.14259 • Published May 23, 2024 • 2
RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented Dialogues Paper • 2409.12558 • Published Sep 19, 2024