paper-with-me

홈 › Papers

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

2025-12-22 · Yi Xin, Siqi Luo, Tianxiang Xu, 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 arxiv

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.

📄 PDF Abstract BibTeX arXiv:2512.19433

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models

2025-11-19 · Duo Li, Zuhao Yang, Xiaoqin Zhang, Ling Shao 외 arxiv

Discrete diffusion-based multimodal large language models (dMLLMs) have emerged as a promising alternative to autoregressive MLLMs thanks to their advantages in parallel decoding and bidirectional context modeling, but m…

Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models

2026-04-07 · Keuntae Kim, Mingyu Kang, Yong Suk Choi arxiv

Diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive (AR) LLMs. Recently, this paradigm has been extended to multimodal tasks, leading to the development of diffusion multimoda…

Answer GenerationVisual GroundingVisual Reasoning

Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models

2024-05-26 · Xijie Huang, Xinyuan Wang, Hantao Zhang, Yinghao Zhu 외

Security concerns related to Large Language Models (LLMs) have been extensively explored, yet the safety implications for Multimodal Large Language Models (MLLMs), particularly in medical contexts (MedMLLMs), remain insu…

Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models

2026-02-02 · Jinbin Bai, Yixuan Li, Yuchen Zhu, Yi Xin 외 arxiv

Inference-time compute has re-emerged as a practical way to improve LLM reasoning. Most test-time scaling (TTS) algorithms rely on autoregressive decoding, which is ill-suited to discrete diffusion language models (dLLMs…

Mathematical ReasoningCode Generation

Scaling Test-Time Compute for Agentic Coding

2026-04-16 · Joongwon Kim, Wannan Yang, Kelvin Niu, Hongming Zhang 외 arxiv

Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that can be directly compared, ranked or refined. Long-horizon coding agen…