Skip to content

X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation

Sep 2026 · 0 citations · 25 references
Computer Science

TL;DR

X-AuT, a progressive framework that selects layer combinations through short behavioral probes and restores the pruned model through representation alignment, cross-scale distillation, scheduled student-policy supervision, and LoRA finetuning, is introduced.

Abstract

Reducing audio-encoder depth lowers the inference cost of speech large language models, but removing complete blocks perturbs the embeddings consumed by the decoder and can cause deletion and premature end-of-sequence errors. We introduce X-AuT, a progressive framework that selects layer combinations through short behavioral probes and restores the pruned model through representation alignment, cross-scale distillation, scheduled student-policy supervision, and LoRA finetuning. The language-model backbone remains frozen, while attention LoRA adapters and the tied output embedding adapt during distillation. Training uses the highest-agreement tier from a transcript-consistency pipeline, followed by source reweighting during finetuning. On ten public Chinese--English benchmarks, compressing Qwen3-ASR-0.6B from 18 to 16 audio-encoder layers reduces macro-average error from 5.61% to 5.27%. The 14-layer model reaches 5.75% with 20.7% fewer audio-tower parameters. Under the matched recipe, the 1.7B teacher yields 5.55% mean error, compared with 8.45% for self-distillation, and progressive 18$\rightarrow$14 pruning outperforms direct pruning (5.75% vs. 6.73%). These single-run results establish two practical operating points and show that the accuracy effects vary across benchmarks. Project website: https://xpeng-ai.github.io/x-aut

View source

Similar papers

#machine learning Preprint Sep 2026

AnchorPrompt: Self-Distilled Soft Prompts for Robust Audio-Language Models

Large audio-language models (LALMs) are sensitive to input perturbations, such as noise, waveform corruption, and adversarial injections. We propose AnchorPrompt, an efficient adaptation method that keeps the model frozen and learns a single block of prompt vectors inserted at the decoder input, between the audio and q...

Pooneh Mousavi, Amir Ivry, M. Ravanelli et al. · 0 citations
#small language model Preprint Sep 2026

Compressing Streaming Neural Audio Encoders via Latent-Space Distillation

This work studies how to compress a tokenizer by distillation, taking as the supervision target neither the discrete token nor the output distribution but the pre-quantizer latent the model actually consumes - the last representation the two token interfaces share.

Prasanth Yadla, Mohammad Samragh, Dongseong Hwang et al. · 0 citations

Mizar: A 159M-Parameter Audio-Language Model for Audio Understanding

Mizar, a 159.3M-parameter ALM, is introduced, a recipe that brings together architecture, data, and three-stage training to build Mizar, a 159.3M-parameter ALM that surpasses the previous best-performing ALM below 200M parameters on all three benchmarks.

Kai-Yang Li, Shaobo Han, Yue Tian et al. · 0 citations
#natural language process... Open access Sep 2026

SEAR: Segment-Evidence-Aware Routing for Weak-to-Strong Multilingual Speech MCQ

This paper describes the system for Task~2 of the second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge, which adapt Qwen3-Omni-30B-A3B-Instruct with a segment-evidence-aware data and post-training pipeline and obtains 90.92% accuracy on the final official evaluation set.

H. Le, L. Nguyen, Minh Tri Dao · 1 citation

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.