Reinforcing Multimodal Understanding and Generation with Dual Self-rewards

• URL: http://arxiv.org/abs/2506.07963v2
• Date: Thu, 12 Jun 2025 10:19:29 GMT
• Title: Reinforcing Multimodal Understanding and Generation with Dual Self-rewards
• Authors: Jixiang Hong, Yiran Zhang, Guanzhong Wang, Yi Liu, Ji-Rong Wen, Rui Yan,
• Abstract summary: Large language models (LLMs) unify cross-model understanding and generation into a single framework.<n>Current solutions require external supervision (e.g., human feedback or reward models) and only address unidirectional tasks.<n>We introduce a self-supervised dual reward mechanism to reinforce the understanding and generation capabilities of LMMs.
• Score: 56.08202047680044
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Building upon large language models (LLMs), recent large multimodal models (LMMs) unify cross-model understanding and generation into a single framework. However, LMMs still struggle to achieve accurate image-text alignment, prone to generating text responses contradicting the visual input or failing to follow the text-to-image prompts. Current solutions require external supervision (e.g., human feedback or reward models) and only address unidirectional tasks-either understanding or generation. In this work, based on the observation that understanding and generation are inverse dual tasks, we introduce a self-supervised dual reward mechanism to reinforce the understanding and generation capabilities of LMMs. Specifically, we sample multiple outputs for a given input in one task domain, then reverse the input-output pairs to compute the dual likelihood of the model as self-rewards for optimization. Extensive experimental results on visual understanding and generation benchmarks demonstrate that our method can effectively enhance the performance of the model without any external supervision, especially achieving remarkable improvements in text-to-image tasks.

Related papers

• Synergizing Understanding and Generation with Interleaved Analyzing-Drafting Thinking [154.2388970262703]
  Unified Vision-Language Models (UVLMs) aim to advance multimodal learning by supporting both understanding and generation within a single framework.<n>We introduce the interleaved Analyzing-Drafting problem-solving loop (AD-Loop), a new think paradigm that alternates between analytic and drafting operations.<n>By interleaving textual thoughts with visual thoughts, AD-Loop enables models to iteratively refine both comprehension and outputs, fostering genuine synergy.
  arXiv  Detail & Related papers  (2026-02-24T23:26:09Z)
• 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)
• dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models [40.03969764207708]
  Diffusion Multi-modal Large Language Models (dMLLMs) have recently emerged as a novel architecture unifying image generation and understanding.<n>We propose dMLLM-TTS, a novel framework operating on two complementary scaling axes to unlock their full generative potential.<n>Our framework substantially improves generation quality while achieving up to 6x greater efficiency than linear search.
  arXiv  Detail & Related papers  (2025-12-22T14:31:58Z)
• UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings [70.60608084375691]
  We pioneer the exploration of generative embeddings, unifying embedding tasks within a generative paradigm.<n>We propose UME-R1, a universal multimodal embedding framework consisting of a two-stage training strategy.<n> evaluated on the MMEB-V2 benchmark across 78 tasks spanning video, image, and visual documents.
  arXiv  Detail & Related papers  (2025-11-01T05:04:23Z)
• Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark [69.8473923357969]
  Unified multimodal models aim to jointly enable visual understanding and generation, yet current benchmarks rarely examine their true integration.<n>We present Uni-MMMU, a comprehensive benchmark that unfolds the bidirectional synergy between generation and understanding across eight reasoning-centric domains.
  arXiv  Detail & Related papers  (2025-10-15T17:10:35Z)
• SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models [44.79249920949795]
  Unified Multimodal Models (UMMs) integrate vision-language generation and understanding capabilities within a single framework.<n>A model might correctly understand an image based on user instructions, yet be unable to generate a faithful image from text prompts.<n>We introduce SRUM, a self-rewarding post-training framework that can be directly applied to existing UMMs of various designs.
  arXiv  Detail & Related papers  (2025-10-14T17:56:11Z)
• Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Models [28.82265769298008]
  We introduce a simple but efficient learning mechanism for improving the robust alignment between visual and textual modalities.<n>The proposed approach consistently achieves state-of-the-art (SoTA) performance compared with prior LMMs.
  arXiv  Detail & Related papers  (2025-08-19T20:53:24Z)
• Harmonizing Visual Representations for Unified Multimodal Understanding and Generation [53.01486796503091]
  We present emphHarmon, a unified autoregressive framework that harmonizes understanding and generation tasks with a shared MAR encoder.<n>Harmon achieves state-of-the-art image generation results on the GenEval, MJHQ30K and WISE benchmarks.
  arXiv  Detail & Related papers  (2025-03-27T20:50:38Z)
• CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning [24.981279071712173]
  We introduce CAFe, a contrastive-autoregressive fine-tuning framework that enhances LVLMs for both representation and generative tasks.<n>Our approach unifies these traditionally separate tasks, achieving state-of-the-art results in both multimodal retrieval and multimodal generative benchmarks.
  arXiv  Detail & Related papers  (2025-03-25T17:57:17Z)
• HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding [67.24430397016275]
  We propose a new early-fusion LMM that can fuse multi-modal inputs in the early stage and respond to visual instructions in an auto-regressive manner.<n>The proposed model demonstrates superior performance compared to other LMMs using one transformer and significantly narrows the performance gap with compositional LMMs.
  arXiv  Detail & Related papers  (2025-03-12T06:01:05Z)
• ARMOR: Empowering Multimodal Understanding Model with Interleaved Multimodal Generation Capability [14.703591553247948]
  ARMOR is a resource-efficient and pure autoregressive framework for multimodal large language models.<n>It achieves both understanding and generation by fine-tuning existing MLLMs.<n>We show that ARMOR upgrades existing MLLMs to UniMs with promising image generation capabilities, using limited training resources.
  arXiv  Detail & Related papers  (2025-03-09T10:15:39Z)
• VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model [38.61292051733335]
  We present VARGPT, a novel multimodal large language model (MLLM) that unifies visual understanding and generation within a single autoregressive framework.<n>VarGPT employs a next-token prediction paradigm for visual understanding and a next-scale prediction paradigm for visual autoregressive generation.<n> Notably, VARGPT naturally supports capabilities in autoregressive visual generation and instruction-to-image synthesis, showcasing its versatility in both visual understanding and generation tasks.
  arXiv  Detail & Related papers  (2025-01-21T17:50:43Z)
• MetaMorph: Multimodal Understanding and Generation via Instruction Tuning [57.35160715164359]
  Visual-Predictive Instruction Tuning (VPiT) is a simple and effective extension to visual instruction tuning.<n>VPiT teaches an LLM to predict discrete text tokens and continuous visual tokens from any input sequence of image and text data.<n>We train our MetaMorph model and achieve competitive performance on both visual understanding and generation.
  arXiv  Detail & Related papers  (2024-12-18T18:58:50Z)
• SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation [92.73405185996315]
  Large Multimodal Models (LMMs) have demonstrated impressive capabilities in multimodal understanding and generation.<n>Existing approaches, such as layout planning for multi-step generation and learning from human feedback or AI feedback, depend heavily on prompt engineering.<n>We introduce a model-agnostic iterative self-feedback framework (SILMM) that can enable LMMs to provide helpful and scalable self-improvement and optimize text-image alignment.
  arXiv  Detail & Related papers  (2024-12-08T05:28:08Z)
• EMMA: Efficient Visual Alignment in Multi-Modal LLMs [56.03417732498859]
  EMMA is a lightweight cross-modality module designed to efficiently fuse visual and textual encodings. EMMA boosts performance across multiple tasks by up to 9.3% while significantly improving robustness against hallucinations.
  arXiv  Detail & Related papers  (2024-10-02T23:00:31Z)
• Exploring the Transferability of Visual Prompting for Multimodal Large Language Models [47.162575147632396]
  Transferable Visual Prompting (TVP) is a simple and effective approach to generate visual prompts that can transfer to different models and improve their performance on downstream tasks after trained on only one model. We introduce two strategies to address the issue of cross-model feature corruption of existing visual prompting methods and enhance the transferability of the learned prompts.
  arXiv  Detail & Related papers  (2024-04-17T09:39:07Z)

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.