# MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free

arXiv: https://arxiv.org/abs/2601.02967 · HTML: https://mlsanity.com/paper/2601.02967/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts.
- Builds on 42 of its 52 references that are in the map.
- First posted on arXiv 6 Jan 2026.

## Placed in

- Mixture-of-experts / [Multimodal MoE models](https://mlsanity.com/moe/multimodal-moe-models/)

## Builds on (most cited first, 30 of 42)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Conflict-Averse Gradient Descent for Multi-task Learning](https://mlsanity.com/paper/2110.14048/) (2021)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark](https://mlsanity.com/paper/2410.19168/) (2024)
- [AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head](https://mlsanity.com/paper/2304.12995/) (2023)
- [GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot](https://mlsanity.com/paper/2412.02612/) (2024)
- [Kimi-Audio Technical Report](https://mlsanity.com/paper/2504.18425/) (2025)
- [Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models](https://mlsanity.com/paper/2507.08128/) (2025)
- [Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming](https://mlsanity.com/paper/2408.16725/) (2024)
- [Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts](https://mlsanity.com/paper/2206.02770/) (2022)
- [VoiceBench: Benchmarking LLM-Based Voice Assistants](https://mlsanity.com/paper/2410.17196/) (2024)
- [LLaMA-Omni: Seamless Speech Interaction with Large Language Models](https://mlsanity.com/paper/2409.06666/) (2024)
- [Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts](https://mlsanity.com/paper/2405.11273/) (2024)
- [Step-Audio 2 Technical Report](https://mlsanity.com/paper/2507.16632/) (2025)
- [WavChat: A Survey of Spoken Dialogue Models](https://mlsanity.com/paper/2411.13577/) (2024)

## Built on by (most cited first, 5 of 5)

- [Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs](https://mlsanity.com/paper/2607.06540/) (2026)
- [Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging](https://mlsanity.com/paper/2606.01717/) (2026)
- [Entropy-Aware Domain-Routed Mixture-of-Experts Speech-LLM Framework: A Case Study of Multi-Domain Child-Adult ASR](https://mlsanity.com/paper/2606.10454/) (2026)
- [UniAE-MoE: A Unified Audio Encoder via Mixture of Experts](https://mlsanity.com/paper/2609.39199/) (2026)
- [LLM-HB: Language-Aware LLM-Guided Hotword Biasing for Code-Switching ASR](https://mlsanity.com/paper/2610.16579/) (2026)

## Abstract (arXiv)

Extending the input modality of Large Language Models~(LLMs) to the audio domain is essential for achieving comprehensive multimodal perception. However, it is well-known that acoustic information is intrinsically textitheterogeneous, entangling attributes such as speech, music, and environmental context. Existing research is limited to a dense, parameter-shared adapter to model these diverse patterns, which induces textitgradient conflict during optimization, as parameter updates required for distinct attributes contradict each other. To address this limitation, we introduce the textitMoE-Adapter, a sparse Mixture-of-Experts~(MoE) architecture designed to decouple acoustic information. Specifically, it employs a dynamic gating mechanism that routes audio tokens to specialized experts capturing complementary feature subspaces while retaining shared experts for global context, thereby mitigating gradient conflicts and enabling fine-grained feature learning. Comprehensive experiments show that the MoE-Adapter achieves superior performance on both audio semantic and paralinguistic tasks, consistently outperforming dense linear baselines with comparable computational costs. Furthermore, we will release the related code and models to facilitate future research.