dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models

• URL: http://arxiv.org/abs/2512.19433v1
• Date: Mon, 22 Dec 2025 14:31:58 GMT
• Title: dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models
• Authors: Yi Xin, Siqi Luo, Qi Qin, Haoxing Chen, Kaiwen Zhu, Zhiwei Zhang, Yangfan He, Rongchao Zhang, Jinbin Bai, Shuo Cao, Bin Fu, Junjun He, Yihao Liu, Yuewen Cao, Xiaohong Liu,
• Abstract summary: 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.
• Score: 40.03969764207708
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion Multi-modal Large Language Models (dMLLMs) have recently emerged as a novel architecture unifying image generation and understanding. However, developing effective and efficient Test-Time Scaling (TTS) methods to unlock their full generative potential remains an underexplored challenge. To address this, we propose dMLLM-TTS, a novel framework operating on two complementary scaling axes: (1) trajectory exploration scaling to enhance the diversity of generated hypotheses, and (2) iterative refinement scaling for stable generation. Conventional TTS approaches typically perform linear search across these two dimensions, incurring substantial computational costs of O(NT) and requiring an external verifier for best-of-N selection. To overcome these limitations, we propose two innovations. First, we design an efficient hierarchical search algorithm with O(N+T) complexity that adaptively expands and prunes sampling trajectories. Second, we introduce a self-verified feedback mechanism that leverages the dMLLMs' intrinsic image understanding capabilities to assess text-image alignment, eliminating the need for external verifier. Extensive experiments on the GenEval benchmark across three representative dMLLMs (e.g., Lumina-DiMOO, MMaDA, Muddit) show that our framework substantially improves generation quality while achieving up to 6x greater efficiency than linear search. Project page: https://github.com/Alpha-VLLM/Lumina-DiMOO.

Related papers

• UniT: Unified Multimodal Chain-of-Thought Test-time Scaling [85.590774707406]
  Unified models can handle both multimodal understanding and generation within a single architecture, yet they typically operate in a single pass without iteratively refining their outputs.<n>We introduce UniT, a framework for multimodal test-time scaling that enables a single unified model to reason, verify, and refine across multiple rounds.
  arXiv  Detail & Related papers  (2026-02-12T18:59:49Z)
• Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models [96.0074341403456]
  Inference-time compute has re-emerged as a practical way to improve LLM reasoning.<n>Most test-time scaling (TTS) algorithms rely on autoregressive decoding.<n>We propose Prism, an efficient TTS framework for dLLMs.
  arXiv  Detail & Related papers  (2026-02-02T09:14:51Z)
• URaG: Unified Retrieval and Generation in Multimodal LLMs for Efficient Long Document Understanding [55.45331924836242]
  We present URaG, a framework that Unifies Retrieval and Generation within a single MLLM.<n>We show that URaG achieves state-of-the-art performance while reducing computational overhead by 44-56%.
  arXiv  Detail & Related papers  (2025-11-13T17:54:09Z)
• VeriMoA: A Mixture-of-Agents Framework for Spec-to-HDL Generation [22.276878955961504]
  Large Language Models (LLMs) show promise for Hardware Description Language (HDL) generation, but face challenges due to limited parametric knowledge and domain-specific constraints.<n>We propose VeriMoA, a training-free mixture-of-agents framework with two synergistic innovations.
  arXiv  Detail & Related papers  (2025-10-31T16:40:58Z)
• RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling [59.088798018184235]
  textbfRAPO++ is a cross-stage prompt optimization framework.<n>It unifies training-data-aligned refinement, test-time iterative scaling, and large language model fine-tuning.<n> RAPO++ achieves significant gains in semantic alignment, compositional reasoning, temporal stability, and physical plausibility.
  arXiv  Detail & Related papers  (2025-10-23T04:45:09Z)
• OmniBridge: Unified Multimodal Understanding, Generation, and Retrieval via Latent Space Alignment [79.98946571424607]
  We present OmniBridge, a unified framework that supports vision-language understanding, generation, and retrieval within a unified architecture.<n>To address the challenge of task interference, we propose a two-stage decoupled training strategy.<n>Experiments demonstrate that OmniBridge achieves competitive or state-of-the-art performance in all three tasks.
  arXiv  Detail & Related papers  (2025-09-23T13:57:55Z)
• Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers [16.135928990655422]
  This paper introduces textttBFS-Prover-V2, a system designed to address the dual scaling problem.<n>The first is a novel multi-turn off-policy RL framework for continually improving the performance of LLM step-prover at training time.<n>The second innovation is a planner-enhanced multi-agent search architecture that scales reasoning capabilities at inference time.
  arXiv  Detail & Related papers  (2025-09-08T09:54:18Z)
• Scale, Don't Fine-tune: Guiding Multimodal LLMs for Efficient Visual Place Recognition at Test-Time [12.659582318581606]
  Current approaches, including Vision Foundation Models (VFMs) and Multimodal Large Language Models (MLLMs), enhance semantic understanding but suffer from high computational overhead and limited cross-domain transferability when fine-tuned.<n>We propose a novel framework employing Test-Time Scaling (TTS) that leverages vision-language alignment capabilities through Guidance-based methods for direct similarity scoring.<n>Our approach eliminates two-stage processing by employing structured prompts that generate length-controllable scoring outputs.
  arXiv  Detail & Related papers  (2025-09-02T09:25:13Z)
• SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards [55.99492656542475]
  We propose textbfSUDER (textbfSelf-improving textbfUnified LMMs with textbfDual stextbfElf-textbfRewards), a framework reinforcing the understanding and generation capabilities of LMMs.
  arXiv  Detail & Related papers  (2025-06-09T17:38:45Z)

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.