arXiv:2604.16993v2 Announce Type: replace Abstract: As embodied AI transitions to real-world deployment, the success of the Vision-and-Language Navigation (VLN) task tends to evolve from mere reachability to social compliance. However, current agents suffer from a "goal-driven tr…
A unified framework named Perceive-to-Reason (P2R) is introduced that separates visual perception from reasoning in vision-language models through a two-stage process, improving fine-grained visual reasoning performance on high-resolution images.
Multi-turn visual reasoning agents suffer from entangled reasoning and perception that cause redundant trajectories; PixelEyes addresses this by decoupling these processes through mask-guided search and semantic-region breadth-first search, demonstrated on a new benchmark with ex…
arXiv cs.CV
TIER_1English(EN)·Dengxian Gong, Yuanzheng Wu, Haobo Yuan, Zhengdong Hu, Tao Zhang, Yikang Zhou, Shihao Chen, Quanzhu Niu, Kai Wang, Jason Li, Haochen Wang, Lu Qi, Shunping Ji, Ming-Hsuan Yang·
arXiv:2607.00115v1 Announce Type: new Abstract: This paper explores multi-turn visual reasoning and observes that MLLMs repeatedly fail to localize the target, leading to long, redundant trajectories. We attribute this failure to the entanglement of reasoning and perception withi…
arXiv:2607.01191v1 Announce Type: new Abstract: Fine-grained visual reasoning remains challenging for vision-language models, especially when small but critical visual cues are buried in high-resolution images. Existing approaches rely on repeated cropping or test-time visual sea…
Fine-grained visual reasoning remains challenging for vision-language models, especially when small but critical visual cues are buried in high-resolution images. Existing approaches rely on repeated cropping or test-time visual search to introduce local evidence, but they typica…
