Pith. sign in

REVIEW 5 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.13642 v2 pith:4KAVDJNR submitted 2025-06-16 cs.AI cs.CLcs.CVcs.SDeess.AS

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

classification cs.AI cs.CLcs.CVcs.SDeess.AS
keywords stream-omnispeechmodalitytextmodelalignmentsinteractionlarge
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original 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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models

    cs.CV 2025-12 unverdicted novelty 7.0

    AV-SpeakerBench is a new speaker-centered benchmark showing that top multimodal models still struggle with fine-grained audiovisual speech understanding, with Gemini 2.5 Pro leading but open models lagging on fusion.

  2. Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory

    cs.CV 2026-07 conditional novelty 6.5

    Dual global+latent states with hierarchical episodic merging enable reflexive, low-latency long-video agents that beat iterative reasoning baselines on accuracy and efficiency.

  3. Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning

    cs.CV 2026-07 unverdicted novelty 4.0

    TCA-Captioner introduces an Observer-Checker-Corrector refinement loop and TCA-Bench to address modality detachment and temporal incoherence in audiovisual video captioning.

  4. Watch, Remember, Reason: Human-View Video Understanding with MLLMs

    cs.CV 2026-06 unverdicted novelty 4.0

    This is a survey that frames video MLLM research via a human-view formulation of perceptual representations, memory states, reasoning traces, and predictions, then reviews methods, datasets, benchmarks, and open problems.

  5. PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory

    cs.AI 2026-04 unverdicted novelty 4.0

    PASK introduces the DD-MM-PAS paradigm for streaming proactive agents with intent-aware detection, hybrid memory modeling, and a new real-world benchmark where the IntentFlow model matches top LLMs on latency while fi...