SRUM：統一多模態模型的細粒度自我獎勵機制

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models

October 14, 2025

作者: Weiyang Jin, Yuwei Niu, Jiaqi Liao, Chengqi Duan, Aoxue Li, Shenghua Gao, Xihui Liu

cs.AI

摘要

近期，統一多模態模型（Unified Multimodal Models, UMMs）在整合視覺-語言生成與理解能力方面取得了顯著進展。然而，存在一個顯著的差距：模型強大的視覺理解能力往往無法有效轉移到其視覺生成上。模型可能基於用戶指令正確理解圖像，卻無法從文本提示生成忠實的圖像。這一現象直接引發了一個引人深思的問題：模型能否利用其理解模塊來獎勵其生成模塊，從而實現自我提升？為彌合這一差距並實現自我提升，我們引入了SRUM，這是一種自獎勵的後訓練框架，可直接應用於各種設計的現有UMMs。SRUM創建了一個反饋循環，其中模型自身的理解模塊充當內部「評估者」，提供糾正信號以改進其生成模塊，而無需額外的人類標註數據。為確保這一反饋的全面性，我們設計了一個全局-局部雙重獎勵系統。為應對圖像固有的結構複雜性，該系統提供多尺度指導：全局獎勵確保整體視覺語義和佈局的正確性，而局部獎勵則精細化對象層面的保真度。SRUM帶來了強大的能力並展現出良好的泛化性，在T2I-CompBench上的性能從82.18提升至88.37，在T2I-ReasonBench上從43.82提升至46.75。總體而言，我們的工作建立了一個強大的新範式，使UMMs的理解模塊能夠通過自獎勵來指導和增強其自身的生成能力。

English

Recently, remarkable progress has been made in Unified Multimodal Models (UMMs), which integrate vision-language generation and understanding capabilities within a single framework. However, a significant gap exists where a model's strong visual understanding often fails to transfer to its visual generation. A model might correctly understand an image based on user instructions, yet be unable to generate a faithful image from text prompts. This phenomenon directly raises a compelling question: Can a model achieve self-improvement by using its understanding module to reward its generation module? To bridge this gap and achieve self-improvement, we introduce SRUM, a self-rewarding post-training framework that can be directly applied to existing UMMs of various designs. SRUM creates a feedback loop where the model's own understanding module acts as an internal ``evaluator'', providing corrective signals to improve its generation module, without requiring additional human-labeled data. To ensure this feedback is comprehensive, we designed a global-local dual reward system. To tackle the inherent structural complexity of images, this system offers multi-scale guidance: a global reward ensures the correctness of the overall visual semantics and layout, while a local reward refines fine-grained, object-level fidelity. SRUM leads to powerful capabilities and shows strong generalization, boosting performance on T2I-CompBench from 82.18 to 88.37 and on T2I-ReasonBench from 43.82 to 46.75. Overall, our work establishes a powerful new paradigm for enabling a UMMs' understanding module to guide and enhance its own generation via self-rewarding.