Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration

• URL: http://arxiv.org/abs/2505.20256v1
• Date: Mon, 26 May 2025 17:34:06 GMT
• Title: Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
• Authors: Hao Zhong, Muzhi Zhu, Zongze Du, Zheng Huang, Canyu Zhao, Mingyu Liu, Wen Wang, Hao Chen, Chunhua Shen,
• Abstract summary: Long-grained video-audio reasoning and fine-grained pixel impose conflicting requirements on omnimodal models.<n>We tackle this trade-off with a two-system architecture: a Global Reasoning System selects informatives and rewrites the task at low spatial cost, while a Detail Understanding System performs pixel-level grounding.<n>Because optimalhorizon'' selection and reformulation are ambiguous and hard to supervise, we formulate them as a reinforcement learning (RL) problem and present Omni-R1, an end-to-end RL framework built on Group Relative Policy.
• Score: 50.38965090742822
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Long-horizon video-audio reasoning and fine-grained pixel understanding impose conflicting requirements on omnimodal models: dense temporal coverage demands many low-resolution frames, whereas precise grounding calls for high-resolution inputs. We tackle this trade-off with a two-system architecture: a Global Reasoning System selects informative keyframes and rewrites the task at low spatial cost, while a Detail Understanding System performs pixel-level grounding on the selected high-resolution snippets. Because ``optimal'' keyframe selection and reformulation are ambiguous and hard to supervise, we formulate them as a reinforcement learning (RL) problem and present Omni-R1, an end-to-end RL framework built on Group Relative Policy Optimization. Omni-R1 trains the Global Reasoning System through hierarchical rewards obtained via online collaboration with the Detail Understanding System, requiring only one epoch of RL on small task splits. Experiments on two challenging benchmarks, namely Referring Audio-Visual Segmentation (RefAVS) and Reasoning Video Object Segmentation (REVOS), show that Omni-R1 not only surpasses strong supervised baselines but also outperforms specialized state-of-the-art models, while substantially improving out-of-domain generalization and mitigating multimodal hallucination. Our results demonstrate the first successful application of RL to large-scale omnimodal reasoning and highlight a scalable path toward universally foundation models.

Related papers

• Team of One: Cracking Complex Video QA with Model Synergy [24.75732964829523]
  We propose a novel framework for open-ended video question answering that enhances reasoning depth and robustness in complex real-world scenarios.<n>Existing Video-Large Multimodal Models (Video-LMMs) often exhibit limited contextual understanding, weak temporal modeling, and poor generalization to ambiguous or compositional queries.
  arXiv  Detail & Related papers  (2025-07-18T11:12:44Z)
• SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-Resolution [55.14432034345353]
  We study key design principles for latter cascaded video super-resolution models, which are underexplored currently.<n>First, we propose two strategies to generate training pairs that better mimic the output characteristics of the base model, ensuring alignment between the VSR model and its upstream generator.<n>Second, we provide critical insights into VSR model behavior through systematic analysis of (1) timestep sampling strategies, (2) noise augmentation effects on low-resolution (LR) inputs.
  arXiv  Detail & Related papers  (2025-06-24T17:57:26Z)
• ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning [68.76048244253582]
  We introduce ViaRL, the first framework to leverage rule-based reinforcement learning (RL) for optimizing frame selection in video understanding.<n>ViaRL utilizes the answer accuracy of a downstream model as a reward signal to train a frame selector through trial-and-error.<n>ViaRL consistently delivers superior temporal grounding performance and robust generalization across diverse video understanding tasks.
  arXiv  Detail & Related papers  (2025-05-21T12:29:40Z)
• DSADF: Thinking Fast and Slow for Decision Making [9.84593001541736]
  We propose a Dual-System Adaptive Decision Framework (DSADF) to integrate two complementary modules: System 1, comprising an RL agent and a memory space for fast and intuitive decision making, and System 2, driven by a VLM for deep and analytical reasoning.
  arXiv  Detail & Related papers  (2025-05-13T02:58:04Z)
• Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1 [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark designed to evaluate post-training methods for MLLMs in video understanding.<n>It includes intricate real-world videos and complex everyday planning tasks in the format of multiple-choice questions.<n>Using Qwen2-VL-Instruct-7B as a base model, we compare RL with supervised fine-tuning (SFT)<n>Our detailed analysis reveals that RL enhances visual perception but often produces less coherent reasoning chains.
  arXiv  Detail & Related papers  (2025-03-31T17:55:23Z)
• Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation [58.799397354312596]
  Large language models (LLMs) have demonstrated remarkable capabilities in various domains, particularly in system 1 tasks.<n>Recent research on System2-to-System1 methods surge, exploring the System 2 reasoning knowledge via inference-time computation.<n>In this paper, we focus on code generation, which is a representative System 2 task, and identify two primary challenges.
  arXiv  Detail & Related papers  (2025-02-18T03:20:50Z)
• ModServe: Scalable and Resource-Efficient Large Multimodal Model Serving [19.388562622309838]
  Large multimodal models (LMMs) demonstrate impressive capabilities in understanding images, videos, and audio beyond text.<n>We present the first comprehensive systems analysis of two prominent LMM architectures, decoder-only and cross-attention, across six representative open-source models.<n>We propose ModServe, a modular LMM serving system that decouples stages for independent optimization and adaptive scaling.
  arXiv  Detail & Related papers  (2025-02-02T22:10:40Z)
• INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model [71.50973774576431]
  We propose a novel MLLM, INF-LLaVA, designed for effective high-resolution image perception. We introduce a Dual-perspective Cropping Module (DCM), which ensures that each sub-image contains continuous details from a local perspective. Second, we introduce Dual-perspective Enhancement Module (DEM) to enable the mutual enhancement of global and local features.
  arXiv  Detail & Related papers  (2024-07-23T06:02:30Z)
• Inter-slice Super-resolution of Magnetic Resonance Images by Pre-training and Self-supervised Fine-tuning [49.197385954021456]
  In clinical practice, 2D magnetic resonance (MR) sequences are widely adopted. While individual 2D slices can be stacked to form a 3D volume, the relatively large slice spacing can pose challenges for visualization and subsequent analysis tasks. To reduce slice spacing, deep-learning-based super-resolution techniques are widely investigated. Most current solutions require a substantial number of paired high-resolution and low-resolution images for supervised training, which are typically unavailable in real-world scenarios.
  arXiv  Detail & Related papers  (2024-06-10T02:20:26Z)
• Omni Aggregation Networks for Lightweight Image Super-Resolution [42.252518645833696]
  This work proposes two enhanced components under a new Omni-SR architecture. First, an Omni Self-Attention (OSA) block is proposed based on dense interaction principle. Second, a multi-scale interaction scheme is proposed to mitigate sub-optimal ERF.
  arXiv  Detail & Related papers  (2023-04-20T12:05:14Z)

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.