AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech

Chengyao Wang, Zhisheng Zhong, Bohao PENG, Senqiao Yang, Yuqi Liu, Haokun GUI, Bin Xia, Jingyao Li, Bei Yu, Jiaya Jia

ECCV 2026 · Large language models › Language, safety and interpretability · approach: Speech and audio language models · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add chunk-based decoding to SpeechLM for long-form speech (ablation)MGM-Omni SpeechLM · Long-TTS-Eval ENWER: 31.84 -> 4.98Improved
add chunk-based decoding to SpeechLM for long-form speech (ablation)MGM-Omni SpeechLM · Long-TTS-Eval ZHCER: 8.97 -> 5.64Improved
fuse Qwen2-Audio and Belle-Whisper encoders via information mining instead of Qwen2-Audio only (ablation)MGM-Omni audio encoder · CommonVoice ENWER: 13.0 -> 9.1Improved
fuse encoders via information mining instead of Belle-Whisper only (ablation)MGM-Omni audio encoder · CommonVoice ENWER: 21.7 -> 9.1Improved
fuse encoders via information mining instead of Qwen2-Audio only (ablation)MGM-Omni audio encoder · CommonVoice ZHCER: 3.9 -> 3.5Improved
increase parallel decoding size from 1 to 4 (ablation)MGM-Omni SpeechLM · Seed-TTS-Eval ENWER: 1.86 -> 2.28Hurt
increase parallel decoding size from 1 to 4 (ablation)MGM-Omni SpeechLM · Long-TTS-Eval samplesRTF: 0.57 -> 0.19Improved
increase parallel decoding size from 1 to 2 (ablation)MGM-Omni SpeechLM · Seed-TTS-Eval ENWER: 1.86 -> 2.02Hurt
scale SpeechLM from 0.6B to 4B parametersMGM-Omni-TTS · Seed-TTS-Eval ENWER: 2.48 -> 2.22Improved
scale MLLM from 7B to 32BMGM-Omni · LibriSpeech test-otherWER: 3.6 -> 3.2Improved
scale MLLM from 7B to 32BMGM-Omni · TextVQA-Speechaccuracy: 81.7 -> 78.2Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy