paper-with-me

Papers

GenDistiller: Distilling Pre-trained Language Models based on an Autoregressive Generative Model

2024-06-12 · Yingying Gao, Shilei Zhang, Chao Deng, Junlan Feng

Pre-trained speech language models such as HuBERT and WavLM leverage unlabeled speech data for self-supervised learning and offer powerful representations for numerous downstream tasks. Despite the success of these models, their high requirements for memory and computing resource hinder their application on resource restricted devices. Therefore, this paper introduces GenDistiller, a novel knowledge distillation framework which generates the hidden representations of the pre-trained teacher model directly by a much smaller student network. The proposed method takes the previous hidden layer as history and implements a layer-by-layer prediction of the teacher model autoregressively. Experiments on SUPERB reveal the advantage of GenDistiller over the baseline distilling method without an autoregressive framework, with 33% fewer parameters, similar time consumption and better performance on most of the SUPERB tasks. Ultimately, the proposed GenDistiller reduces the size of WavLM by 82%.

📄 PDF Abstract BibTeX arXiv:2406.09444

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

GenDistiller: Distilling Pre-trained Language Models based on Generative Models

2023-10-20 · Yingying Gao, Shilei Zhang, Zihao Cui, Yanhan Xu 외

Self-supervised pre-trained models such as HuBERT and WavLM leverage unlabeled speech data for representation learning and offer significantly improve for numerous downstream tasks. Despite the success of these methods, …

Knowledge DistillationLanguage ModelingLanguage ModellingRepresentation Learning

WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation

2026-03-05 · Luca Della Libera, Cem Subakan, Mirco Ravanelli arxiv

Large language models show that simple autoregressive training can yield scalable and coherent generation, but extending this paradigm to speech remains challenging due to the entanglement of semantic and acoustic inform…

Learning to Watermark in the Latent Space of Generative Models

2026-01-22 · Sylvestre-Alvise Rebuffi, Tuan Tran, Valeriu Lacatusu, Pierre Fernandez 외 arxiv

Existing approaches for watermarking AI-generated images often rely on post-hoc methods applied in pixel space, introducing computational overhead and potential visual artifacts. In this work, we explore latent space wat…

Parallel Token Prediction for Language Models

2025-12-24 · Felix Draxler, Justus Will, Farrin Marouf Sofian, Theofanis Karaletsos 외 arxiv

Autoregressive decoding in language models is inherently slow, generating only one token per forward pass. We propose Parallel Token Prediction (PTP), a general-purpose framework for predicting multiple tokens in a singl…

MapDream: Task-Driven Map Learning for Vision-Language Navigation

2026-01-30 · Guoxin Lian, Shuo Wang, Yucheng Wang, Yongcai Wang 외 arxiv

Vision-Language Navigation (VLN) requires agents to follow natural language instructions in partially observed 3D environments, motivating map representations that aggregate spatial context beyond local perception. Howev…

Vision-Language Navigation