InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing

• URL: http://arxiv.org/abs/2603.09877v1
• Date: Tue, 10 Mar 2026 16:38:33 GMT
• Title: InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing
• Abstract summary: InternVL-U is a lightweight 4B- parameter UMM that democratizes multimodal understanding and reasoning capabilities.<n>It integrates a state-of-the-art Multimodal Large Language Model (MLLM) with a specialized MMDiT-based visual generation head.<n>It consistently outperforms unified baseline models with over 3x larger scales such as BAGEL (14B) on various generation and editing tasks.
• Score: 87.5130783098133
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Unified multimodal models (UMMs) that integrate understanding, reasoning, generation, and editing face inherent trade-offs between maintaining strong semantic comprehension and acquiring powerful generation capabilities. In this report, we present InternVL-U, a lightweight 4B-parameter UMM that democratizes these capabilities within a unified framework. Guided by the principles of unified contextual modeling and modality-specific modular design with decoupled visual representations, InternVL-U integrates a state-of-the-art Multimodal Large Language Model (MLLM) with a specialized MMDiT-based visual generation head. To further bridge the gap between aesthetic generation and high-level intelligence, we construct a comprehensive data synthesis pipeline targeting high-semantic-density tasks, such as text rendering and scientific reasoning, under a reasoning-centric paradigm that leverages Chain-of-Thought (CoT) to better align abstract user intent with fine-grained visual generation details. Extensive experiments demonstrate that InternVL-U achieves a superior performance - efficiency balance. Despite using only 4B parameters, it consistently outperforms unified baseline models with over 3x larger scales such as BAGEL (14B) on various generation and editing tasks, while retaining strong multimodal understanding and reasoning capabilities.

Related papers

• TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training [25.562880121429966]
  We present TorchUMM, the first unified framework for comprehensive evaluation, analysis, and post-training of unified multimodal models.<n>Our benchmark encompasses multimodal understanding, generation, and editing, and integrates both established and novel datasets.
  arXiv  Detail & Related papers  (2026-04-12T19:19:04Z)
• Beyond Language Modeling: An Exploration of Multimodal Pretraining [125.34714978184638]
  We provide empirical clarity through controlled, from-scratch pretraining experiments.<n>We adopt the Transfusion framework, using next-token prediction for language and diffusion for vision.<n>We demonstrate that the MoE architecture harmonizes this scaling asymmetry by providing the high model capacity required by language.
  arXiv  Detail & Related papers  (2026-03-03T18:58:00Z)
• UniG2U-Bench: Do Unified Models Advance Multimodal Understanding? [50.92401586025528]
  Unified multimodal models have recently demonstrated strong generative capabilities, yet whether and when generation improves understanding remains unclear.<n>We introduce UniG2U-Bench, a comprehensive benchmark categorizing generation-to-understanding (G2U) evaluation into 7 regimes and 30 subtasks.
  arXiv  Detail & Related papers  (2026-03-03T18:36:16Z)
• MindGPT-4ov: An Enhanced MLLM via a Multi-Stage Post-Training Paradigm [25.7631608456086]
  MindGPT-4ov is a general post-training paradigm spanning data production, model training, and efficient deployment.<n>It achieves state-of-the-art performance across multiple benchmarks at low cost.<n>MindGPT-4ov also demonstrates superior user experience in vertical domain tasks.
  arXiv  Detail & Related papers  (2025-12-02T16:04:11Z)
• Query-Kontext: An Unified Multimodal Model for Image Generation and Editing [53.765351127477224]
  Unified Multimodal Models (UMMs) have demonstrated remarkable performance in text-to-image generation (T2I) and editing (TI2I)<n>We introduce Query-Kontext, a novel approach that bridges the VLM and diffusion model via a multimodal kontext'' composed of semantic cues and coarse-grained image conditions encoded from multimodal inputs.<n> Experiments show that our approach matches strong unified baselines and even outperforms task-specific state-of-the-art methods in several cases.
  arXiv  Detail & Related papers  (2025-09-30T17:59:46Z)
• UniAlignment: Semantic Alignment for Unified Image Generation, Understanding, Manipulation and Perception [54.53657134205492]
  UniAlignment is a unified multimodal generation framework within a single diffusion transformer.<n>It incorporates both intrinsic-modal semantic alignment and cross-modal semantic alignment, thereby enhancing the model's cross-modal consistency and instruction-following robustness.<n>We present SemGen-Bench, a new benchmark specifically designed to evaluate multimodal semantic consistency under complex textual instructions.
  arXiv  Detail & Related papers  (2025-09-28T09:11:30Z)
• All in One: Exploring Unified Vision-Language Tracking with Multi-Modal Alignment [39.54689489555342]
  Current vision-injected (VL) tracking framework consists of three parts, ie a visual feature extractor, a language feature extractor, and a fusion model.<n>We propose an All-in-One framework, which learns joint feature extraction and interaction by adopting a unified transformer backbone.
  arXiv  Detail & Related papers  (2023-07-07T03:51:21Z)
• UniDiff: Advancing Vision-Language Models with Generative and Discriminative Learning [86.91893533388628]
  This paper presents UniDiff, a unified multi-modal model that integrates image-text contrastive learning (ITC), text-conditioned image synthesis learning (IS), and reciprocal semantic consistency modeling (RSC) UniDiff demonstrates versatility in both multi-modal understanding and generative tasks.
  arXiv  Detail & Related papers  (2023-06-01T15:39:38Z)

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.