The following papers were recommended by the Semantic Scholar API
\n- \n
- COOPER: A Unified Model for Cooperative Perception and Reasoning in Spatial Intelligence (2025) \n
- Interleaved Latent Visual Reasoning with Selective Perceptual Modeling (2025) \n
- Mull-Tokens: Modality-Agnostic Latent Thinking (2025) \n
- Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs (2025) \n
- ViRC: Enhancing Visual Interleaved Mathematical CoT with Reason Chunking (2025) \n
- Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning (2025) \n
- Rethinking Chain-of-Thought Reasoning for Videos (2025) \n
Please give a thumbs up to this comment if you found it helpful!
\nIf you want recommendations for any Paper on Hugging Face checkout this Space
\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
Omni-R1: Towards the Unified Generative Paradigm for Multimodal Reasoning
Abstract
Unified generative multimodal reasoning approach enables diverse reasoning skills through intermediate image generation, with a two-stage SFT+RL framework and a text-only bootstrapping variant.
Multimodal Large Language Models (MLLMs) are making significant progress in multimodal reasoning. Early approaches focus on pure text-based reasoning. More recent studies have incorporated multimodal information into the reasoning steps; however, they often follow a single task-specific reasoning pattern, which limits their generalizability across various multimodal tasks. In fact, there are numerous multimodal tasks requiring diverse reasoning skills, such as zooming in on a specific region or marking an object within an image. To address this, we propose unified generative multimodal reasoning, which unifies diverse multimodal reasoning skills by generating intermediate images during the reasoning process. We instantiate this paradigm with Omni-R1, a two-stage SFT+RL framework featuring perception alignment loss and perception reward, thereby enabling functional image generation. Additionally, we introduce Omni-R1-Zero, which eliminates the need for multimodal annotations by bootstrapping step-wise visualizations from text-only reasoning data. Empirical results show that Omni-R1 achieves unified generative reasoning across a wide range of multimodal tasks, and Omni-R1-Zero can match or even surpass Omni-R1 on average, suggesting a promising direction for generative multimodal reasoning.
Community
This paper proposes a unified generative multimodal reasoning paradigm, using a two-stage SFT+RL framework with perception alignment loss and perception reward, and explores bootstrapping step-wise visualizations from text-only reasoning data when multimodal annotation availability is extremely limited.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- COOPER: A Unified Model for Cooperative Perception and Reasoning in Spatial Intelligence (2025)
- Interleaved Latent Visual Reasoning with Selective Perceptual Modeling (2025)
- Mull-Tokens: Modality-Agnostic Latent Thinking (2025)
- Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs (2025)
- ViRC: Enhancing Visual Interleaved Mathematical CoT with Reason Chunking (2025)
- Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning (2025)
- Rethinking Chain-of-Thought Reasoning for Videos (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 2
Datasets citing this paper 1
Spaces citing this paper 0
No Space linking this paper