6 papers
Retrievable Gradients: Continual Post-Training Without Cumulative Weight Drift
Weihang Su, Jiacheng Kang, Jingyan Xu +7
Continual post-training enables models to absorb emerging knowledge after deployment, but repeatedly updating shared parameters can accumulate weight drift, potentially causing cat…
TrustMargin: Training-Free Arbitration between Parametric Memory and Retrieved Evidence in Large Language Models
Jingyan Xu, Hong Shi, Yi Shan +4
Large language models answer knowledge-intensive questions using both parametric memory and retrieved evidence, but neither source is uniformly reliable. Retrieval can fill knowled…
Lamer-SSL: Layer-aware Mixture of LoRA Experts for Continual Multilingual Expansion of Self-supervised Models without Forgetting
Jing Xu, Minglin Wu, Xueyuan Chen +2
Despite their impressive performance, self-supervised speech models often struggle to generalize to new languages and tend to forget previously acquired knowledge during continual…
MiLorE-SSL: Scaling Multilingual Capabilities in Self-Supervised Models without Forgetting
Jing Xu, Minglin Wu, Xueyuan Chen +2
Self-supervised learning (SSL) has greatly advanced speech representation learning, but multilingual SSL models remain constrained to languages encountered during pretraining. Retr…
Seamless Language Expansion: Enhancing Multilingual Mastery in Self-Supervised Models
Jing Xu, Minglin Wu, Xixin Wu +1
Self-supervised (SSL) models have shown great performance in various downstream tasks. However, they are typically developed for limited languages, and may encounter new languages…
DiffDSR: Dysarthric Speech Reconstruction Using Latent Diffusion Model
Xueyuan Chen, Dongchao Yang, Wenxuan Wu +5
Dysarthric speech reconstruction (DSR) aims to convert dysarthric speech into comprehensible speech while maintaining the speaker's identity. Despite significant advancements, exis…