Stream-Omni: Simultaneous Multimodal Interactions with Large Language-Vision-Speech Model

• URL: http://arxiv.org/abs/2506.13642v2
• Date: Sun, 22 Jun 2025 07:56:58 GMT
• Title: Stream-Omni: Simultaneous Multimodal Interactions with Large Language-Vision-Speech Model
• Authors: Shaolei Zhang, Shoutao Guo, Qingkai Fang, Yan Zhou, Yang Feng,
• Abstract summary: Stream- Omni is a large language-vision-speech model with efficient modality alignments.<n>It can simultaneously support interactions under various modality combinations.<n>It achieves strong performance on visual understanding, speech interaction, and vision-grounded speech interaction tasks.
• Score: 43.533849239738394
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The emergence of GPT-4o-like large multimodal models (LMMs) has raised the exploration of integrating text, vision, and speech modalities to support more flexible multimodal interaction. Existing LMMs typically concatenate representation of modalities along the sequence dimension and feed them into a large language model (LLM) backbone. While sequence-dimension concatenation is straightforward for modality integration, it often relies heavily on large-scale data to learn modality alignments. In this paper, we aim to model the relationships between modalities more purposefully, thereby achieving more efficient and flexible modality alignments. To this end, we propose Stream-Omni, a large language-vision-speech model with efficient modality alignments, which can simultaneously support interactions under various modality combinations. Stream-Omni employs LLM as the backbone and aligns the vision and speech to the text based on their relationships. For vision that is semantically complementary to text, Stream-Omni uses sequence-dimension concatenation to achieve vision-text alignment. For speech that is semantically consistent with text, Stream-Omni introduces a CTC-based layer-dimension mapping to achieve speech-text alignment. In this way, Stream-Omni can achieve modality alignments with less data (especially speech), enabling the transfer of text capabilities to other modalities. Experiments on various benchmarks demonstrate that Stream-Omni achieves strong performance on visual understanding, speech interaction, and vision-grounded speech interaction tasks. Owing to the layer-dimensional mapping, Stream-Omni can simultaneously provide intermediate text outputs (such as ASR transcriptions and model responses) during speech interaction, offering users a comprehensive multimodal experience.

Related papers

• GAID: Frame-Level Gated Audio-Visual Integration with Directional Perturbation for Text-Video Retrieval [12.483734449829235]
  GAID is a framework that integrates audio and visual features under textual guidance.<n>DASP injects structure-aware perturbations into text embeddings, enhancing robustness and discrimination without incurring multi-pass inference.<n>Experiments on MSR-VTT, DiDeMo, LSMDC, and VATEX show consistent state-of-the-art results with notable efficiency gains.
  arXiv  Detail & Related papers  (2025-08-03T10:44:24Z)
• Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations [33.11867433769496]
  This paper presents a framework that attempts to unify visual understanding and generation within a shared semantic representation.<n>At its core is the Text-Aligned Tokenizer (TA-Tok), which converts images into discrete tokens using a text-aligned codebook projected from a large language model's (LLM) vocabulary.<n> Experiments across benchmarks show that Tar matches or surpasses existing multimodal LLM methods, achieving faster convergence and greater training efficiency.
  arXiv  Detail & Related papers  (2025-06-23T17:59:14Z)
• Hierarchical Banzhaf Interaction for General Video-Language Representation Learning [60.44337740854767]
  Multimodal representation learning plays an important role in the artificial intelligence domain.<n>We introduce a new approach that models video-text as game players using multivariate cooperative game theory.<n>We extend our original structure into a flexible encoder-decoder framework, enabling the model to adapt to various downstream tasks.
  arXiv  Detail & Related papers  (2024-12-30T14:09:15Z)
• Masked Graph Learning with Recurrent Alignment for Multimodal Emotion Recognition in Conversation [12.455034591553506]
  Multimodal Emotion Recognition in Conversation (MERC) can be applied to public opinion monitoring, intelligent dialogue robots, and other fields. Previous work ignored the inter-modal alignment process and the intra-modal noise information before multimodal fusion. We have developed a novel approach called Masked Graph Learning with Recursive Alignment (MGLRA) to tackle this problem.
  arXiv  Detail & Related papers  (2024-07-23T02:23:51Z)
• Text-Video Retrieval with Global-Local Semantic Consistent Learning [122.15339128463715]
  We propose a simple yet effective method, Global-Local Semantic Consistent Learning (GLSCL) GLSCL capitalizes on latent shared semantics across modalities for text-video retrieval. Our method achieves comparable performance with SOTA as well as being nearly 220 times faster in terms of computational cost.
  arXiv  Detail & Related papers  (2024-05-21T11:59:36Z)
• ModaVerse: Efficiently Transforming Modalities with LLMs [25.49713745405194]
  We introduce ModaVerse, a Multi-modal Large Language Model capable of comprehending and transforming content across various modalities. We propose a novel Input/Output (I/O) alignment mechanism that operates directly at the level of natural language.
  arXiv  Detail & Related papers  (2024-01-12T06:28:54Z)
• Towards More Unified In-context Visual Understanding [74.55332581979292]
  We present a new ICL framework for visual understanding with multi-modal output enabled. First, we quantize and embed both text and visual prompt into a unified representational space. Then a decoder-only sparse transformer architecture is employed to perform generative modeling on them.
  arXiv  Detail & Related papers  (2023-12-05T06:02:21Z)
• TEAL: Tokenize and Embed ALL for Multi-modal Large Language Models [69.49978333446538]
  TEAL is an approach to treat the input from any modality as a token sequence. It embeds the token sequence into a joint embedding space with a learnable embedding matrix. Experiments show that TEAL achieves substantial improvements in multi-modal understanding.
  arXiv  Detail & Related papers  (2023-11-08T10:34:16Z)
• A Self-Adjusting Fusion Representation Learning Model for Unaligned Text-Audio Sequences [16.38826799727453]
  How to integrate relevant information of each modality to learn fusion representations has been one of the central challenges in multimodal learning. In this paper, a Self-Adjusting Fusion Representation Learning Model is proposed to learn robust crossmodal fusion representations directly from the unaligned text and audio sequences. Experiment results show that our model has significantly improved the performance of all the metrics on the unaligned text-audio sequences.
  arXiv  Detail & Related papers  (2022-11-12T13:05:28Z)
• mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections [104.14624185375897]
  mPLUG is a new vision-language foundation model for both cross-modal understanding and generation. It achieves state-of-the-art results on a wide range of vision-language downstream tasks, such as image captioning, image-text retrieval, visual grounding and visual question answering.
  arXiv  Detail & Related papers  (2022-05-24T11:52:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.