arXiv:2603. 00171v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) are shifting towards "Thinking with Images" by actively exploring image details.
By Yuxiang Shen, Hailong Huang, Zhenkun Gao, Xueheng Li, Man Zhou, Chengjun Xie, Haoxuan Che, Xuanhua He, Jie Zhang
arXiv:2604. 01280v2 Announce Type: replace-cross Abstract: Knowledge-based Visual Question Answering (KB-VQA) requires Multimodal Large Language Models (MLLMs) to identify and combine fine-grained visual cues with retrieved textual evidence.
By Marco Morini, Sara Sarto, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
The paper introduces LIRSeg, a method that replaces explicit Chain-of-Thought reasoning in multimodal large language models with a compact set of learnable latent tokens for reasoning segmentation. LIRSeg is trained in two stages—spatial alignment and GRPO—while employing extreme-advantage sampling, decoupled exploration-stability updates, and latent diversity amplification to enhance token informativeness. Experiments show that LIRSeg improves segmentation accuracy and reasoning efficiency, achieving significant gIoU gains over the VisionReasoner baseline and reducing reasoning tokens by about 16×.
By Tianhang Guo, Yulin He, Wei Chen, Wenjuan Zhou, Yuhang Li, Xinbiao Gan
ARGenSeg introduces an autoregressive generation-based approach for image segmentation that integrates seamlessly with multimodal large language models (MLLMs). Unlike prior methods that use boundary points or dedicated segmentation heads, ARGenSeg generates dense masks directly through visual token output and detokenization via a universal VQ‑VAE, enabling fine‑grained pixel‑level perception. The framework employs a next‑scale‑prediction strategy to parallelize token generation, resulting in faster inference while outperforming state‑of‑the‑art segmentation models on multiple datasets.
By Xiaolong Wang, Lixiang Ru, Ziyuan Huang, Kaixiang Ji, Dandan Zheng, Jingdong Chen, Jun Zhou
Knowledge-Intensive Visual Question Answering (KI-VQA) benchmarks evaluate Vision-Language Models (VLMs) as multimodal knowledge assistants by requiring external information beyond a provided image to answer questions. KI-VQA involves multiple sub-problems -referring expression understanding, visual grounding, object recognition, knowledge retrieval, and reasoning-yet existing benchmarks typically report only end-task accuracy, obscuring where failures arise.
The paper introduces Selective Probability Mass Concentration (sPMC), a training framework that strengthens implicit visual grounding in multimodal large language models by selectively regularizing attention heads most responsive to visual evidence. sPMC treats attention over visual tokens as a spatial probability distribution and encourages mass to concentrate on semantically relevant regions using segmentation-derived priors, while leaving other heads unconstrained. Across six multimodal benchmarks, sPMC yields an average zero‑shot improvement of 3% and gains up to 11.3% for various models by regularizing only 3%–15% of their attention heads.
By Jiaqi Deng, Zonghan Wu, Zhan Heng, Xiaoshui Huang, Huan Huo, Guandong Xu