OmniEncoder: See, Hear, and Feel Continuous Motion Like Humans With One Encoder

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bai, Detao, Yao, Shimin, Chen, Weixuan, Lai, Chengen, Li, Yuanming, Ma, Zhiheng, Wei, Xihan
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911640552734720
author Bai, Detao
Yao, Shimin
Chen, Weixuan
Lai, Chengen
Li, Yuanming
Ma, Zhiheng
Wei, Xihan
author_facet Bai, Detao
Yao, Shimin
Chen, Weixuan
Lai, Chengen
Li, Yuanming
Ma, Zhiheng
Wei, Xihan
contents Recent advances in omni-modal large language models have enabled remarkable progress in joint vision-audio understanding. However, prevailing architectures rely on modality-specific encoders with a \emph{video-coarse, audio-dense} design -- sampling visual frames at 1--2 fps while processing audio waveforms at 25 fps -- resulting in systems that perceive video \emph{frame by frame, modality by modality} rather than holistically as humans do. Such a discrepancy leaves models with impoverished cross-modal interaction during encoding and an inability to capture fine-grained visual motion. To bridge this gap, we present \textbf{Omni-Encoder, a unified Transformer backbone designed to co-embed visual and audio signals at a symmetrical 25 fps} within a shared latent space. This architecture leverages three core innovations -- the Omni-Encoder Token Template, Omni-RoPE, and Temporal Window Shifting -- to effectively reconcile the dual challenges of modality disentanglement and computational efficiency. Experiments demonstrate that, compared to the modality-specific baseline Qwen2.5-Omni under the same input token budget to the LLM decoder, Omni-Encoder delivers substantial gains on visual continuous understanding tasks -- such as sign language recognition and fine-grained sports action analysis -- while maintaining competitive performance on established audio-visual benchmarks such as AVQA and Speaker Identification and Localization. These results suggest that unified omnivorous encoding offers a promising direction for building omni-modal models that more closely reflect the integrated nature of human perception.
format Preprint
id arxiv_https___arxiv_org_abs_2605_01506
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle OmniEncoder: See, Hear, and Feel Continuous Motion Like Humans With One Encoder
Bai, Detao
Yao, Shimin
Chen, Weixuan
Lai, Chengen
Li, Yuanming
Ma, Zhiheng
Wei, Xihan
Computer Vision and Pattern Recognition
Recent advances in omni-modal large language models have enabled remarkable progress in joint vision-audio understanding. However, prevailing architectures rely on modality-specific encoders with a \emph{video-coarse, audio-dense} design -- sampling visual frames at 1--2 fps while processing audio waveforms at 25 fps -- resulting in systems that perceive video \emph{frame by frame, modality by modality} rather than holistically as humans do. Such a discrepancy leaves models with impoverished cross-modal interaction during encoding and an inability to capture fine-grained visual motion. To bridge this gap, we present \textbf{Omni-Encoder, a unified Transformer backbone designed to co-embed visual and audio signals at a symmetrical 25 fps} within a shared latent space. This architecture leverages three core innovations -- the Omni-Encoder Token Template, Omni-RoPE, and Temporal Window Shifting -- to effectively reconcile the dual challenges of modality disentanglement and computational efficiency. Experiments demonstrate that, compared to the modality-specific baseline Qwen2.5-Omni under the same input token budget to the LLM decoder, Omni-Encoder delivers substantial gains on visual continuous understanding tasks -- such as sign language recognition and fine-grained sports action analysis -- while maintaining competitive performance on established audio-visual benchmarks such as AVQA and Speaker Identification and Localization. These results suggest that unified omnivorous encoding offers a promising direction for building omni-modal models that more closely reflect the integrated nature of human perception.
title OmniEncoder: See, Hear, and Feel Continuous Motion Like Humans With One Encoder
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.01506