English
Related papers

Related papers: Dynamic Multi-Expert Projectors with Stabilized Ro…

200 papers

Audio-visual speech recognition (AVSR) has become critical for enhancing speech recognition in noisy environments by integrating both auditory and visual modalities. However, existing AVSR systems struggle to scale up without compromising…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-22 Sungnyun Kim , Kangwook Jang , Sangmin Bae , Sungwoo Cho , Se-Young Yun

Supervised fine-tuning (SFT) is a milestone in aligning large language models with human instructions and adapting them to downstream tasks. In particular, Low-Rank Adaptation (LoRA) has gained widespread attention due to its parameter…

Computation and Language · Computer Science 2025-11-05 Jia-Chen Zhang , Yu-Jie Xiong , Xi-He Qiu , Chun-Ming Xia , Fei Dai , Zheng Zhou

Mixture-of-Experts (MoE) based Large Language Models (LLMs) have achieved superior performance, yet the massive memory overhead caused by storing multiple expert networks severely hinders their practical deployment. Singular Value…

Machine Learning · Computer Science 2026-02-13 Zhendong Mi , Yixiao Chen , Pu Zhao , Xiaodong Yu , Hao Wang , Yanzhi Wang , Shaoyi Huang

Combining existing pre-trained expert LLMs is a promising avenue for scalably tackling large-scale and diverse tasks. However, selecting task-level experts is often too coarse-grained, as heterogeneous tasks may require different expertise…

Computation and Language · Computer Science 2025-07-22 Justin Chih-Yao Chen , Sukwon Yun , Elias Stengel-Eskin , Tianlong Chen , Mohit Bansal

Mixture-of-experts based models, which use language experts to extract language-specific representations effectively, have been well applied in code-switching automatic speech recognition. However, there is still substantial space to…

Sound · Computer Science 2023-10-10 Peikun Chen , Fan Yu , Yuhao Lian , Hongfei Xue , Xucheng Wan , Naijun Zheng , Huan Zhou , Lei Xie

We study training a single acoustic model for multiple languages with the aim of improving automatic speech recognition (ASR) performance on low-resource languages, and over-all simplifying deployment of ASR systems that support diverse…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-09 Vineel Pratap , Anuroop Sriram , Paden Tomasello , Awni Hannun , Vitaliy Liptchinsky , Gabriel Synnaeve , Ronan Collobert

Despite the rapid progress in automatic speech recognition (ASR) research, recognizing multilingual speech using a unified ASR system remains highly challenging. Previous works on multilingual speech recognition mainly focus on two…

Computation and Language · Computer Science 2022-06-07 Jinchuan Tian , Jianwei Yu , Chunlei Zhang , Chao Weng , Yuexian Zou , Dong Yu

Despite their impressive performance, self-supervised speech models often struggle to generalize to new languages and tend to forget previously acquired knowledge during continual training. To address this, we propose Lamer-SSL, a…

Computation and Language · Computer Science 2026-02-16 Jing Xu , Minglin Wu , Xueyuan Chen , Xixin Wu , Helen Meng

The rapid adoption of Mixture-of-Experts (MoE) architectures marks a major shift in the deployment of Large Language Models (LLMs). MoE LLMs improve scaling efficiency by activating only a small subset of parameters per token, but their…

Cryptography and Security · Computer Science 2026-02-10 Jona te Lintelo , Lichao Wu , Stjepan Picek

Large Vision-Language Models (LVLMs) have demonstrated impressive performance on multimodal tasks through scaled architectures and extensive training. However, existing Mixture of Experts (MoE) approaches face challenges due to the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Heng Zhang , Haichuan Hu , Yaomin Shen , Weihao Yu , Yilei Yuan , Haochen You , Guo Cheng , Zijian Zhang , Lubin Gan , Huihui Wei , Hao Zhang , Jin Huang

This paper describes SHNU multilingual conversational speech recognition system (SHNU-mASR, team name-"maybe"), submitted to Track 1 of the INTERSPEECH 2025 MLC-SLM Challenge. Our system integrates a parallel-speech-encoder architecture…

Computation and Language · Computer Science 2025-07-09 Yuxiang Mei , Yuang Zheng , Dongxing Xu , Yanhua Long

Mixture-of-Experts (MoE) models are a promising way to scale up model capacity without significantly increasing computational cost. A key component of MoEs is the router, which decides which subset of parameters (experts) process which…

Computer Vision and Pattern Recognition · Computer Science 2024-04-22 Tianlin Liu , Mathieu Blondel , Carlos Riquelme , Joan Puigcerver

The mixture-of-experts (MoE) architecture, which replaces dense networks with sparse ones, has attracted significant attention in large vision-language models (LVLMs) for achieving comparable performance while activating far fewer…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Chaoxiang Cai , Longrong Yang , Minghe Weng , Xuewei Li , Zequn Qin , Xi Li

Multi-speaker automatic speech recognition (ASR) is crucial for many real-world applications, but it requires dedicated modeling techniques. Existing approaches can be divided into modular and end-to-end methods. Modular approaches separate…

Computation and Language · Computer Science 2023-06-22 Simon Berger , Peter Vieting , Christoph Boeddeker , Ralf Schlüter , Reinhold Haeb-Umbach

Imitation learning enables robots to acquire manipulation skills from demonstrations, yet deploying a policy across tasks with heterogeneous dynamics remains challenging, as models tend to average over distinct behavioral modes present in…

Audio-Visual Speech Recognition (AVSR) achieves robust speech recognition in noisy environments by combining auditory and visual information. However, recent Large Language Model (LLM) based AVSR systems incur high computational costs due…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Jeong Hun Yeo , Hyeongseop Rha , Se Jin Park , Yong Man Ro

Mixture-of-Experts (MoE) architectures have emerged as a key strategy for scaling large language models (LLMs) efficiently. However, current MoE systems suffer from severe load imbalance, where only a small subset of experts is consistently…

Machine Learning · Computer Science 2025-06-27 Jiajie Yang

The Mixture of Experts (MoE) paradigm provides a powerful way to decompose dense layers into smaller, modular computations often more amenable to human interpretation, debugging, and editability. However, a major challenge lies in the…

Computer Vision and Pattern Recognition · Computer Science 2024-10-18 James Oldfield , Markos Georgopoulos , Grigorios G. Chrysos , Christos Tzelepis , Yannis Panagakis , Mihalis A. Nicolaou , Jiankang Deng , Ioannis Patras

In this paper, we introduce a speech-conditioned Large Language Model (LLM) integrated with a Mixture of Experts (MoE) based connector to address the challenge of Code-Switching (CS) in Automatic Speech Recognition (ASR). Specifically, we…

Sound · Computer Science 2024-11-01 Fengrun Zhang , Wang Geng , Hukai Huang , Yahui Shan , Cheng Yi , He Qu

Mixture-of-Experts (MoE) models enable efficient scaling of large language models (LLMs) by activating only a subset of experts per input. However, we observe that the commonly used auxiliary load balancing loss often leads to expert…

Computation and Language · Computer Science 2026-01-27 Hongcan Guo , Haolang Lu , Guoshun Nan , Bolun Chu , Jialin Zhuang , Yuan Yang , Wenhao Che , Xinye Cao , Sicong Leng , Qimei Cui , Xudong Jiang