How does the cross-modal alignment quality (measured by zero-shot accuracy on VQA and TextVQA) of Uni-MoE-2.0-

Abstract

Abstract: We present Uni-MoE 2.0 from the Lychee family. As a fully open-source omnimodal large model (OLM), it substantially advances Lychee's Uni-MoE series in language-centric multimodal understanding, reasoning, and generating. Based on the dense LLM, we build Uni-MoE-2.0-Omni from scratch through three core contributions: dynamic-capacity Mixture-of-Experts (MoE) design, a progressive training strategy enhanced with an iterative reinforcement strategy, and a carefully curated multimodal data matching technique. It is capable of omnimodal understanding, as well as generating images, text, and speech

Research Question

How does the cross-modal alignment quality (measured by zero-shot accuracy on VQA and TextVQA) of Uni-MoE-2.0-Omni degrade when the input modality composition shifts from single-image to multi-image and video frames, relative to a dense multimodal LLM baseline of equivalent total parameter count?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance