DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding

• URL: http://arxiv.org/abs/2601.23161v1
• Date: Fri, 30 Jan 2026 16:44:23 GMT
• Title: DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding
• Authors: Jiaming Zhou, Xuxin Cheng, Shiwan Zhao, Yuhang Jia, Cao Liu, Ke Zeng, Xunliang Cai, Yong Qin,
• Abstract summary: We introduce DIFFA-2, a practical diffusion-based LALM for general audio understanding.<n>DIFFA-2 upgrades the speech encoder, employs dual semantic and acoustic adapters, and is trained with a four-stage curriculum.<n>Experiments on MMSU, MMAU, and MMAR show that DIFFA-2 consistently improves over DIFFA.
• Score: 58.29124051111574
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autoregressive (AR) large audio language models (LALMs) such as Qwen-2.5-Omni have achieved strong performance on audio understanding and interaction, but scaling them remains costly in data and computation, and strictly sequential decoding limits inference efficiency. Diffusion large language models (dLLMs) have recently been shown to make effective use of limited training data, and prior work on DIFFA indicates that replacing an AR backbone with a diffusion counterpart can substantially improve audio understanding under matched settings, albeit at a proof-of-concept scale without large-scale instruction tuning, preference alignment, or practical decoding schemes. We introduce DIFFA-2, a practical diffusion-based LALM for general audio understanding. DIFFA-2 upgrades the speech encoder, employs dual semantic and acoustic adapters, and is trained with a four-stage curriculum that combines semantic and acoustic alignment, large-scale supervised fine-tuning, and variance-reduced preference optimization, using only fully open-source corpora. Experiments on MMSU, MMAU, and MMAR show that DIFFA-2 consistently improves over DIFFA and is competitive to strong AR LALMs under practical training budgets, supporting diffusion-based modeling is a viable backbone for large-scale audio understanding. Our code is available at https://github.com/NKU-HLT/DIFFA.git.

Related papers

• Representation-Regularized Convolutional Audio Transformer for Audio Understanding [53.092757178419355]
  bootstrapping representations from scratch is computationally expensive, often requiring extensive training to converge.<n>We propose the Convolutional Audio Transformer (CAT), a unified framework designed to address these challenges.
  arXiv  Detail & Related papers  (2026-01-29T12:16:19Z)
• Codec2Vec: Self-Supervised Speech Representation Learning Using Neural Speech Codecs [29.817724789807457]
  We introduce Codec2Vec, the first speech representation learning framework that relies exclusively on discrete audio units.<n>This approach offers several advantages, including improved data storage and transmission efficiency, faster training, and enhanced data privacy.
  arXiv  Detail & Related papers  (2025-11-20T18:46:15Z)
• Diffusion-Link: Diffusion Probabilistic Model for Bridging the Audio-Text Modality Gap [36.21722709167031]
  Diffusion-Link is a diffusion-based modality-bridging module.<n>It maps audio embeddings into the text-embedding distribution.<n>This is the first application of diffusion-based modality bridging to Automatic Audio Captioning.
  arXiv  Detail & Related papers  (2025-10-13T12:25:33Z)
• Fork-Merge Decoding: Enhancing Multimodal Understanding in Audio-Visual Large Language Models [35.86252379746625]
  The goal of this work is to enhance balanced multimodal understanding in audio-visual large language models (AV-LLMs)<n>In current AV-LLMs, audio and video features are typically processed jointly in the decoder.<n>We propose Fork-Merge Decoding (FMD), a simple yet effective inference-time strategy that requires no additional training or architectural modifications.
  arXiv  Detail & Related papers  (2025-05-27T08:22:56Z)
• From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data [55.2480439325792]
  Audio-aware large language models (ALLMs) have recently made great strides in understanding and processing audio inputs.<n>These models are typically adapted from text-based large language models (LLMs) through additional training on audio-related tasks.<n>We propose a data generation framework that produces contrastive-like training data, designed to enhance ALLMs' ability to differentiate between present and absent sounds.
  arXiv  Detail & Related papers  (2025-05-26T16:08:41Z)
• Mutual Learning for Acoustic Matching and Dereverberation via Visual Scene-driven Diffusion [93.32354378820648]
  We introduce MVSD, a mutual learning framework based on diffusion models. MVSD considers the two tasks symmetrically, exploiting the reciprocal relationship to facilitate learning from inverse tasks. Our framework can improve the performance of the reverberator and dereverberator.
  arXiv  Detail & Related papers  (2024-07-15T00:47:56Z)
• Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation [72.7915031238824]
  Large diffusion models have been successful in text-to-audio (T2A) synthesis tasks. They often suffer from common issues such as semantic misalignment and poor temporal consistency. We propose Make-an-Audio 2, a latent diffusion-based T2A method that builds on the success of Make-an-Audio.
  arXiv  Detail & Related papers  (2023-05-29T10:41:28Z)
• Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation [76.13334392868208]
  Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues. In this work, we explore self-supervised pre-training with unlabeled speech data and data augmentation to tackle this issue.
  arXiv  Detail & Related papers  (2022-04-06T17:59:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.