5 citations · 20 across the 30 of their papers we have counts for
30 papers
TASTE2: Text-Aligned Speech Modeling and Deployment toward Full-Duplex Voice Interaction
Yi-Chang Chen, Chun Wei Chen, Dien-Ruei Wu +7
Full-duplex voice interaction requires more than utterance-level conversion. It must process streaming speech, manage turn-taking and interruptions, while preserving pretrained lin…
Revisiting the Shape Convention of Transformer Language Models
Feng-Ting Liao, Guan-Ting Yi, Tzu-Quan Lin +2
The architectural shape of dense Transformers has remained remarkably stable: narrow-wide-narrow feed-forward networks (FFNs) consume most non-embedding parameters. Motivated by th…
Rethinking the shape convention of an MLP
Meng-Hsi Chen, Yu-Ang Lee, Feng-Ting Liao +1
Multi-layer perceptrons (MLPs) conventionally follow a narrow-wide-narrow design where skip connections operate at the input/output dimensions while processing occurs in expanded h…
Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds
Aya Kayal, Sattar Vakili, Laura Toni +2
Bayesian optimization (BO) with preference-based feedback has recently garnered significant attention due to its emerging applications. We refer to this problem as Bayesian Optimiz…
Towards a Foundation Model for Communication Systems
Davide Buffelli, Sowmen Das, Yu-Wei Lin +5
Artificial Intelligence (AI) has demonstrated unprecedented performance across various domains, and its application to communication systems is an active area of research. While cu…
Latent Flow Transformer
Yen-Chen Wu, Feng-Ting Liao, Meng-Hsi Chen +3
Transformers, the standard implementation for large language models (LLMs), typically consist of tens to hundreds of discrete layers. While more layers can lead to better performan…
Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity
Chan-Jan Hsu, Davide Buffelli, Jamie McGowan +4
Recent advances in large language models (LLMs) have demonstrated the power of reasoning through self-generated chains of thought. Multiple reasoning agents can collaborate to rais…
TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
Liang-Hsuan Tseng, Yi-Chang Chen, Kuan-Yi Lee +2
Recent efforts target spoken language models (SLMs) that not only listen but also speak for more natural human-LLM interaction. Joint speech-text modeling is a promising direction…
The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on Llama with Vision-Aware and Function-Calling Capabilities
MediaTek Research, :, Chan-Jan Hsu +6
Llama-Breeze2 (hereinafter referred to as Breeze2) is a suite of advanced multi-modal language models, available in 3B and 8B parameter configurations, specifically designed to enh…
BreezyVoice: Adapting TTS for Taiwanese Mandarin with Enhanced Polyphone Disambiguation -- Challenges and Insights
Chan-Jan Hsu, Yi-Cheng Lin, Chia-Chun Lin +10
We present BreezyVoice, a Text-to-Speech (TTS) system specifically adapted for Taiwanese Mandarin, highlighting phonetic control abilities to address the unique challenges of polyp…
Enhancing Function-Calling Capabilities in LLMs: Strategies for Prompt Formats, Data Integration, and Multilingual Translation
Yi-Chang Chen, Po-Chun Hsu, Chan-Jan Hsu +1
Large language models (LLMs) have significantly advanced autonomous agents, particularly in zero-shot tool usage, also known as function calling. This research delves into enhancin…
FineWeb-zhtw: Scalable Curation of Traditional Chinese Text Data from the Web
Cheng-Wei Lin, Wan-Hsuan Hsieh, Kai-Xin Guan +6
The quality and size of a pretraining dataset significantly influence the performance of large language models (LLMs). While there have been numerous efforts in the curation of suc…
Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization
Davide Buffelli, Jamie McGowan, Wangkun Xu +4
Second-order optimization has been shown to accelerate the training of deep neural networks in many applications, often yielding faster progress per iteration on the training loss…
RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented Dialogues
Tzu-Lin Kuo, Feng-Ting Liao, Mu-Wei Hsieh +3
In real-world applications with Large Language Models (LLMs), external retrieval mechanisms - such as Search-Augmented Generation (SAG), tool utilization, and Retrieval-Augmented G…
Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCR
Chan-Jan Hsu, Yi-Chang Chen, Feng-Ting Liao +4
We propose "Generative Fusion Decoding" (GFD), a novel shallow fusion framework designed to integrate large language models (LLMs) into cross-modal text recognition systems for aut…
Breeze-7B Technical Report
Chan-Jan Hsu, Chang-Le Liu, Feng-Ting Liao +3
Breeze-7B is an open-source language model based on Mistral-7B, designed to address the need for improved language comprehension and chatbot-oriented capabilities in Traditional Ch…
Advancing the Evaluation of Traditional Chinese Language Models: Towards a Comprehensive Benchmark Suite
Chan-Jan Hsu, Chang-Le Liu, Feng-Ting Liao +3
The evaluation of large language models is an essential task in the field of language understanding and generation. As language models continue to advance, the need for effective b…
Generative Diffusion Models for Radio Wireless Channel Modelling and Sampling
Ushnish Sengupta, Chinkuo Jao, Alberto Bernacchia +2
Channel modelling is essential to designing modern wireless communication systems. The increasing complexity of channel modelling and the cost of collecting high-quality wireless c…
Zero-shot Domain-sensitive Speech Recognition with Prompt-conditioning Fine-tuning
Feng-Ting Liao, Yung-Chieh Chan, Yi-Chang Chen +2
In this work, we propose a method to create domain-sensitive speech recognition models that utilize textual domain information by conditioning its generation on a given text prompt…
Image generation with shortest path diffusion
Ayan Das, Stathi Fotiadis, Anil Batra +5
The field of image generation has made significant progress thanks to the introduction of Diffusion Models, which learn to progressively reverse a given image corruption. Recently,…
Extending the Pre-Training of BLOOM for Improved Support of Traditional Chinese: Models, Methods and Results
Philipp Ennen, Po-Chun Hsu, Chan-Jan Hsu +6
In this paper we present the multilingual language model BLOOM-zh that features enhanced support for Traditional Chinese. BLOOM-zh has its origins in the open-source BLOOM models p…
Flexible Multiple-Objective Reinforcement Learning for Chip Placement
Fu-Chieh Chang, Yu-Wei Tseng, Ya-Wen Yu +11
Recently, successful applications of reinforcement learning to chip placement have emerged. Pretrained models are necessary to improve efficiency and effectiveness. Currently, the…
Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learning
Sattar Vakili, Jonathan Scarlett, Da-shan Shiu +1
Kernel-based models such as kernel ridge regression and Gaussian processes are ubiquitous in machine learning applications for regression and optimization. It is well known that a…
Uniform Generalization Bounds for Overparameterized Neural Networks
Sattar Vakili, Michael Bromberg, Jezabel Garcia +2
An interesting observation in artificial neural networks is their favorable generalization error despite typically being extremely overparameterized. It is well known that the clas…