paper-with-me

Papers

Lamer-SSL: Layer-aware Mixture of LoRA Experts for Continual Multilingual Expansion of Self-supervised Models without Forgetting

2026-02-13 · Jing Xu, Minglin Wu, Xueyuan Chen, Xixin Wu, Helen Meng arxiv

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 parameter-efficient framework that integrates a Layer-Aware MixturE of LoRA Experts (Lamer) module with a replay strategy. The Lamer module enables flexible balancing between shared and language-specific representations, while layer-aware expert allocation assigns more experts to deeper layers where semantic information is richer. Meanwhile, the replay strategy retains prior knowledge using minimal data, mitigating forgetting during continual training. Experiments on automatic speech recognition (ASR) and language identification (LID) demonstrate that Lamer-SSL extends self-supervised models to new languages effectively while maintaining strong performance on previously learned languages with only 2.14% parameters being trainable.

📄 PDF Abstract BibTeX arXiv:2602.12746

Code (0)

등록된 구현이 없습니다.

Tasks

Language IdentificationSpeech Recognition

Similar Papers 제목 키워드 기반

Meta-RL Induces Exploration in Language Agents

2025-12-18 · Yulun Jiang, Liangze Jiang, Damien Teney, Michael Moor 외 arxiv

Reinforcement learning (RL) has enabled the training of large language model (LLM) agents to interact with the environment and to solve multi-turn long-horizon tasks. However, the RL-trained agents often struggle in task…

Reinforcement Learning

HELLoRA: Hot Experts Layer-Level Low-Rank Adaptation for Mixture-of-Experts Models

2026-05-11 · Jia Wei, Zhonghao Zhang, Ping Chen, Qianyang li 외 arxiv

Low-Rank Adaptation (LoRA) dominates parameter-efficient fine-tuning of large language models, yet most variants target dense architectures. Mixture-of-Experts (MoE) models scale parameters at near-constant per-token com…

parameter-efficient fine-tuningMathematical ReasoningCode Generation

Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learning

2025-06-05 · Ziqi Jia, Anmin Wang, Xiaoyang Qu, Xiaowen Yang 외

Previous continual learning setups for embodied intelligence focused on executing low-level actions based on human commands, neglecting the ability to learn high-level planning and multi-level knowledge. To address these…

Continual Learning

MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning

2024-10-23 · Jingfan Zhang, Yi Zhao, Dan Chen, Xing Tian 외

Low-rank adaptation (LoRA) and its mixture-of-experts (MOE) variants are highly effective parameter-efficient fine-tuning (PEFT) methods. However, they introduce significant latency in multi-tenant settings due to the Lo…

MathMixture-of-Expertsparameter-efficient fine-tuning

FRAME: Learning the Adaptation Domain with a Mixture of Fractional-Fourier Experts

2026-06-30 · Tom Saliencro, Maya Lindqvist, Rohan Desai, Priya Nair 외 arxiv

Parameter-efficient fine-tuning (PEFT) reparameterizes weight updates in a fixed basis: low-rank adapters operate in the spatial domain, while a recent line of spectral methods operates in a fixed Fourier domain. We argu…

parameter-efficient fine-tuning