AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition

Zhisheng Zhong, Chengyao Wang, Yuqi Liu, Senqiao Yang, Longxiang Tang, Yuechen Zhang, Jingyao Li, Tianyuan Qu, Yanwei Li, Yukang Chen, Shaozuo Yu, Sitong Wu and 3 more

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Unified any-modality language models · 22 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 latent cross-modality regularizer (LCMR) loss (ablation)Lyra · MM-Vet (speech+image)accuracy: 53.1 -> 58.1Improved
add LCMR loss (ablation)Lyra · TextVQA (speech+image)accuracy: 76.7 -> 77.8Improved
add LCMR loss (ablation)Lyra · LibriSpeechword error rate: 1.9 -> 2.0No clear effect
add LCMR loss (ablation)Lyra · MM-Vet (text+image)accuracy: 61.1 -> 62.6No clear effect
add latent multi-modality extractor LMME(4, 0.7) to long-context inference (ablation)Lyra baseline · prefill at 2^15 tokensprefill time: 2.99 -> 1.23Improved
add LMME so long inputs fit in memory (ablation)Lyra baseline · 2^16 tokensmemory: OOM -> 33GImproved
add LMME(4, 0.7) to training on Lyra-LongSpeech-12K (ablation)Lyra · training timehours: 9.6h -> 4.5hImproved
add LMME(4, 0.7) to training on Lyra-MM-1.5M (ablation)Lyra · training timehours: 66h -> 41hImproved
add extractor when training Vicuna-7B model from scratch (ablation)Vicuna-7B CLIP+Conv baseline · average of six benchmarksaverage rate: 100.0% -> 101.5%Improved
add extractor when training Qwen2-7B on LLaVA-665K (ablation)Qwen2-7B SigLIP baseline · average of six benchmarksaverage rate: 100.0% -> 99.6%No clear effect
add long speech capability integration to baseline (ablation)Baseline 7B · VideoMME overallaccuracy: 62.8 -> 66.2Improved
replace SFT with multi-modality LoRA when adding speech (ablation)Qwen2-VL · TextVQAaccuracy: 81.3 -> 82.6Improved

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