Diffusion VLMs

VLM: Vision-Language Model

Latest papers

13 papers2 papers in the last four weeks, down 50% on the four weeks before. 0.0% of all new papers.

Before the Token Commits: Trajectory-Level Benchmarking of Visual Hallucinations in Diffusion VLMs
Sep 28, 2026Yadong Wang, Siping Yue, Yu Tian +2VLM Evaluation Vision-Language Models
Nanjing University of Aeronautics and Astronautics · State Key Laboratory of Ocean Sensing, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou, 311215, China · Security Capability Center
CT-OPD: Counterfactual Trace On-Policy Distillation for Diffusion Vision-Language Models
Sep 26, 2026Long Qian, Bingke Zhu, Jiaqi Wei +3Diffusion VLMs Vision-Language Models
Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences · School of Future Technology, University of Chinese Academy of Sciences · School of Engineering, Cardiff University +2
Routing by Reasoning Need: Trajectory-Aware Decoding Control for Diffusion Vision-Language Models
Sep 10, 2026Yixiang Liu, Zhongxing Xu, Zhonghua Wang +1Diffusion Language Model Inference VLM Reasoning
Southern University of Science and Technology · Monash University
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes
Sep 3, 2026Chuyan Chen, Haoxing Chen, Kun Chen +27Diffusion Transformer T2I Diffusion Models
AGI Research Center, Inclusion AI
DIVA: Exploiting Cross-Step Conditional Propagation for Visual Jailbreaks in Discrete Diffusion Vision-Language Models
Sep 1, 2026Guorui Song, Runqing Tang, Jingye Zhang +11Diffusion VLMs Adversarial Attacks on VLMs
Tsinghua University · Beijing University of Posts and Telecommunications
Reliability Challenges in Diffusion Vision-Language Models
Sep 1, 2026Md. Atabuzzaman, Chris ThomasVLM Evaluation VLM Robustness
Department of Computer Science Virginia Tech
DAVET: Denoising-Aware Visual Evidence Trajectory Allocation for Diffusion Vision-Language Models
Aug 3, 2026Yongkang Zhou, Xiang Xia, Cheng Yan +2Vision-Language Models Diffusion VLMs
University of Science and Technology of China Hefei, China
ST-Veto: Spatio-Temporal Token Veto for Diffusion MLLMs via Taylor Prediction and Visual Grounding
Jul 20, 2026Keuntae Kim, Beomseok Lee, Hyunwoo Kim +1VLM Reasoning Diffusion Language Model Decoding
Hanyang University · LG Electronics · KT Corporation
Mitigating Mask Prior Drift and Positional Attention Collapse in Large Diffusion Vision-Language Models
May 14, 2026Sujung Hong, Chanyong Yoon, Seong Jae HwangVision-Language Models Diffusion VLMs
Department of Artificial Intelligence, Yonsei University, Seoul, Republic of Korea.
BARD: Bridging AutoRegressive and Diffusion Vision-Language Models Via Highly Efficient Progressive Block Merging and Stage-Wise Distillation
Apr 15, 2026Baoyou Chen, Hanchen Xia, Peng Tu +5Vision-Language Models Diffusion VLMs
Shanghai Academy of AI for Science · Fudan University · Shanghai Innovation Institute +1
Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM
Apr 8, 2026Chengyue Wu, Shiyi Lan, Yonggan Fu +9Vision-Language Models Diffusion VLMs
The University of Hong Kong · NVIDIA · MBZUAI +1
Towards GUI Agents: Vision-Language Diffusion Models for GUI Grounding
Mar 27, 2026Shrinidhi Kumbhar, Haofu Liao, Srikar Appalaraju +1Diffusion VLMs GUI Grounding
Arizona State University · AWS Agentic AI
LaViDa: A Large Diffusion Language Model for Multimodal Understanding
May 22, 2025Shufan Li, Konstantinos Kallidromitis, Hritik Bansal +7Multimodal Understanding Vision-Language Models
1UCLA · 2Panasonic AI Research · 4Salesforce Research +1

Sep 28, 2026J/K move · Enter open · S save

Before the Token Commits: Trajectory-Level Benchmarking of Visual Hallucinations in Diffusion VLMs

Yadong Wang, Siping Yue, Yu Tian, Chuanxing Geng+1

Nanjing University of Aeronautics and Astronautics · State Key Laboratory of Ocean Sensing, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou, 311215, China · Security Capability Center

VLM Evaluation Vision-Language Models Diffusion VLMs VLM Hallucination VLM Hallucination Mitigation

Open paper AskPDF arXiv

Multimodal diffusion language models generate responses by iteratively unmasking tokens, making each answer the endpoint of a multi-step trajectory rather than an immediate commitment. Hallucination benchmarks built for autoregressive models evaluate only the final output, and therefore cannot determine whether an unsupported claim in diffusion VLMs appears late or has already stabilized before any answer token is revealed. We introduce DynaHall, a trajectory-level benchmark of annotation-backed binary visual propositions covering object existence, counting, attributes, and relations, with controlled hard negatives graded by visual prior. DynaHall is paired with a commitment-aware protocol that records the intermediate answer tendency at every unmasking step alongside the committed output. Across five diffusion VLMs from three architecture families, visual hallucination is settled before commitment: an unsupported answer is already the preferred state while the answer position is still masked, and later unmasking steps rarely reverse it, so the failure is not introduced at the write step. This holds across decoding schedules, answer formats, and open-ended generation. DynaHall also exposes failures hidden by final-output metrics, including counting and relation collapse, prior-driven false positives, and attribute errors whose direction changes by type. Guided by this diagnosis, PGS (Pre-commitment Gradient Steering) edits still-masked answer states to reduce false positives, bringing the affirmation rate close to balance, and transfers to another architecture without degrading general ability. DynaHall and PGS suggest that hallucination should be measured and mitigated along the generation trajectory of diffusion VLMs, not only at the final answer.