ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding

TL;DR

This work proposes ThinkOmni, a training-free and data-free framework that lifts textual reasoning to omni-modal scenarios and provides new insights into the generalization and application of reasoning capabilities.

Abstract

Omni-modal reasoning is essential for intelligent systems to understand and draw inferences from diverse data sources. While existing omni-modal large language models (OLLM) excel at perceiving diverse modalities, they lack the complex reasoning abilities of recent large reasoning models (LRM). However, enhancing the reasoning ability of OLLMs through additional training presents significant challenges, including the need for high-quality data, task-specific adaptation, and substantial computational costs. To address these limitations, we propose ThinkOmni, a training-free and data-free framework that lifts textual reasoning to omni-modal scenarios. ThinkOmni introduces two key components: 1) LRM-as-a-Guide, which leverages off-the-shelf LRMs to guide the OLLM decoding process; 2) Stepwise Contrastive Scaling, which adaptively balances perception and reasoning signals without manual hyperparameter tuning. Experiments on six multi-modal reasoning benchmarks demonstrate that ThinkOmni consistently delivers performance improvements, with main results achieving 70.2 on MathVista and 75.5 on MMAU. Overall, ThinkOmni offers a flexible and generalizable solution for omni-modal reasoning and provides new insights into the generalization and application of reasoning capabilities.

Figures (13)

• Figure 1: Comparison between existing methods and ThinkOmni. We integrate an OLLM with an LRM via guidance decoding, enabling advanced reasoning abilities with omni-modal input.
• Figure 2: Performance comparison.
• Figure 3: Guidance decoding methods. "Guid." denotes the guiding model, and "Amat." denotes the amateur model.
• Figure 4: Overview of ThinkOmni. The framework begins by separating input modalities of the OLLM and introducing the LRM as a guiding model. Stepwise Contrastive Scaling dynamically adjusts guidance parameters based on real-time prediction analysis, enabling adaptive and effective decoding across diverse tasks.
• Figure 5: Case studies from (a) MMAU and (b) MathVista.sakshi2024mmaulu2023mathvista Tasks require different levels of LRM involvement. Using a fixed $\alpha$ limits the ability of the model to optimally adapt to task-specific needs, highlighting the need for a more flexible approach.