Vision-language models can produce fluent answers that are insufficiently grounded in the visual evidence: a single unsupported object, chart value, or intermediate inference can undermine an otherwise plausible response. We argue that this is a credit-assignment failure in multimodal post-training. Scalar outcome rewa...
Shu-Lin Tian, Ming-Lun Li, Yuhao Dong et al.· 0 citations
The Thinking Reward Model (TRM), a paradigm that explicitly determines what matters for each case before judging how well the candidate performs, is proposed, which formulates case-adaptive rubrics, performs rubric-guided assessment, and produces fine-grained pointwise rewards.
Xue-Yuan Bai, Zhen-Chen Tang, Yang Shi et al.· 0 citations
Improving text-to-image models has traditionally relied on increasing model size or the number of denoising steps. In this work, we explore an alternative way to scale computation by repeatedly running shared Transformer blocks within each denoising step, effectively increasing computational depth while keeping the par...
UMM-Reflection is introduced, which applies reinforcement learning (RL) to complete reflection trajectories inside one unified model: sibling trajectories share one initial image, so the group-relative advantage compares reflection strategies, and one trajectory-level advantage updates both the reflection tokens and th...
Yi-Jia Fan, Zi-Qi Huang, Zhongang Cai et al.· 0 citations
VA-Bench is introduced to evaluate the complete observe-reason-act-revise loop and tests whether general-purpose MLLMs can turn visual demonstrations and actively acquired evidence into successful embodied action.
Zhong-Bo Zhang, Jia-Yi Jin, Yi-Fan Wang et al.· 0 citations
Native unified modelling is position as a promising path towards systems that perceive, reason and create within a fully end-to-end framework through SenseNova-U1.5, an 8B-MoT native unified multimodal model that understands, reasons about, and generates visual content within an encoder-free and VAE-free architecture.
Hai-Wen Diao, Jia-Hao Wang, Chen-Jing Ding et al.· 3 citations
The results show that the value of UMMs extends beyond a unified interface: appropriate specialization, shared task knowledge, and end-to-end optimization can turn coexistence into synergy.
Peng-Hao Wu, Hai-Wen Diao, Wei-Chen Fan et al.· 2 citations
This work introduces VBVR-Pro, a closed-loop testbed that makes native visual reasoning through generation trainable, verifiable, optimizable, and experimentally controllable, and identifies recurring failure modes of the prevalent VLM-as-a-judge paradigm.
Junhua Xu, Rui-Si Wang, Fanyi Pu et al.· 5 citations
Experiments show that a single unified model can match leading task-specialized systems across structured visual understanding, dense geometric prediction, segmentation, and multi-view visual geometry.
Xiaoyang Han, Jianhua Li, Kewang Deng et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
