OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration

• URL: http://arxiv.org/abs/2605.28805v1
• Date: Wed, 27 May 2026 17:56:04 GMT
• Title: OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration
• Abstract summary: We investigate multimodal meta-verification, which leverages verifier-generated rationales rather than decision-only signals.<n>We train OmniVerifier-M1, a generalist visual verifier leveraging symbolic meta-verification and decoupled reinforcement learning.<n>This approach paves the way for more reliable, interpretable, and fine-grained multimodal verification, supporting safer and more controllable foundation model deployment.
• Score: 48.11927189422178
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual outcomes are increasingly central to multimodal large language models, making reliable and fine-grained verification essential for scaling generalist foundation models. In this work, we investigate multimodal meta-verification, which leverages verifier-generated rationales rather than decision-only signals, and explore how to effectively incorporate meta-verification feedback into multimodal verifier training. We identify two key findings. First, symbolic verifier outputs (e.g., bounding boxes) outperform textual explanations as meta-verification rationales, enabling efficient rule-based reinforcement learning rewards while avoiding reliance on model-based rewards from auxiliary judge models. Second, decoupling reinforcement learning objectives for binary judgment and meta-verification substantially outperforms joint reward optimization, due to intrinsic differences in output structure and learning dynamics. Based on these insights, we train OmniVerifier-M1, a generalist visual verifier leveraging symbolic meta-verification and decoupled reinforcement learning. OmniVerifier-M1 provides robust verification and fine-grained error localization, and further enables M1-TTS, a verifier-driven agentic generation system achieving dynamic region-level self-correction. This approach paves the way for more reliable, interpretable, and fine-grained multimodal verification, supporting safer and more controllable foundation model deployment.

Related papers

• Reasoning-Aware AIGC Detection via Alignment and Reinforcement [55.09684020007737]
  REVEAL is a framework that generates interpretable reasoning chains before classification.<n>It achieves state-of-the-art performance across multiple benchmarks.
  arXiv  Detail & Related papers  (2026-04-21T07:29:55Z)
• Endogenous Reprompting: Self-Evolving Cognitive Alignment for Unified Multimodal Models [23.128973540926552]
  Endogenous Reprompting transforms the model's understanding into an explicit generative reasoning step.<n>We show that SEER consistently outperforms state-of-the-art baselines in evaluation accuracy, reprompting efficiency, and generation quality.
  arXiv  Detail & Related papers  (2026-01-28T06:54:36Z)
• Generative Universal Verifier as Multimodal Meta-Reasoner [71.34250480838473]
  Generative Universal Verifier is a novel concept and plugin designed for next-generation multimodal reasoning in vision-language models and unified multimodal models.<n>We build ViVerBench, a benchmark spanning 16 categories of critical tasks for evaluating visual outcomes in multimodal reasoning.<n>We train OmniVerifier-7B, the first omni-capable generative verifier trained for universal visual verification.
  arXiv  Detail & Related papers  (2025-10-15T17:59:24Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding [54.49214267905562]
  We construct a transformer-based framework for multi-modal manipulation detection and grounding tasks. Our framework simultaneously explores modality-specific features while preserving the capability for multi-modal alignment. We propose an implicit manipulation query (IMQ) that adaptively aggregates global contextual cues within each modality.
  arXiv  Detail & Related papers  (2023-09-22T06:55:41Z)
• Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detection [33.210575826086654]
  We present a weakly-supervised RGB-D salient object detection model via supervision. We focus on effective multimodal representation learning via inter-modal mutual information regularization.
  arXiv  Detail & Related papers  (2023-06-06T12:36:57Z)
• USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval [115.28586222748478]
  Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality. Existing approaches typically suffer from two major limitations.
  arXiv  Detail & Related papers  (2023-01-17T12:42:58Z)

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.