AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

ChronusOmni: Improving Time Awareness of Omni-Modal Large Language Models

Yijing Chen, Yihan Wu, Kaisi Guan, Wenhui Tan, Yuchen Ren, Yuyue Wang, Ruihua Song, Liyun Ru

ECCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual speech separation · 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 temporal interleaved tokenization (text timestamps interleaved with video and audio) (ablation)ChronusOmni · ChronusAV V2TR@0.7: 6.80 -> 45.95Improved
add temporal interleaved tokenization (ablation)ChronusOmni · ChronusAV A2TR@0.7: 13.00 -> 79.85Improved
add SFT stage before GRPO (ablation)ChronusOmni · ChronusAV T2ACIDEr: 6.91 -> 34.30Improved
add GRPO stage after SFT (ablation)ChronusOmni · ChronusAV V2TR@0.7: 15.45 -> 45.95Improved
add GRPO stage (ablation)ChronusOmni · ChronusAV V2A/A2VCIDEr: V2A 1.24 -> 13.60Improved
add SFT stage (ablation)ChronusOmni · ChronusAV V2TR@0.7: 37.20 -> 45.95Improved
use 128 inference frames instead of 64 (ablation)ChronusOmni · ChronusAV V2TR@0.7: 45.95 -> 43.85Hurt
use 32 inference frames instead of 64 (ablation)ChronusOmni · ChronusAV V2TR@0.7: 45.95 -> 32.95Hurt
apply ChronusOmni to Qwen3-Omni comparisonChronusOmni · ChronusAV V2TR@0.5: 37.85 -> 63.15Improved
add temporal training to OlaChronusOmni · VisSpeechWER: 12.3 -> 9.1Improved
add temporal training to OlaChronusOmni · LibriSpeech and Video-MMEWER / accuracyNo clear effect
evaluate vs LongVALE-LLM trained on LongVALE (zero-shot ChronusOmni)ChronusOmni · LongVALE Omni-DVCCIDEr: 7.9 -> 5.6Hurt

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