Despite significant advancements in Large Vision-Language Models (LVLMs), existing pixel-grounding models operate on single-image settings, limiting their ability to perform detailed, fine-grained comparisons across multiple images. Conversely, current multi-image understanding models lack pixel-level grounding. Our work addresses this gap by introducing the task of multi-image pixel-grounded reasoning segmentation, and PRIMA, a novel LVLM that integrates pixel-level grounding with robust multi-image reasoning capabilities to produce contextually rich, pixel-grounded explanations. Central to PRIMA is an efficient vision module that queries fine-grained visual representations across multiple images, reducing TFLOPs by $25.3\%$. To support training and evaluation, we curate $M^4Seg$, a new reasoning segmentation benchmark consisting of $\sim$224K question-answer pairs that require fine-grained visual understanding across multiple images. Experimental results demonstrate PRIMA outperforms state-of-the-art baselines.

The computational generation of poems is a complex task, which involves several sound, prosodic and rhythmic resources. In this work we present PROPOE 2, with the extension of structural and rhythmic possibilities compared to the original system, generating poems from metered sentences extracted from the prose of Brazilian literature, with multiple rhythmic assembly criteria. These advances allow for a more coherent exploration of rhythms and sound effects for the poem. Results of poems generated by the system are demonstrated, with variations in parameters to exemplify generation and evaluation using various criteria.

Azaz, Syria – With her smile as bright as ever, 15-year-old Rima Haj Hussein nervously walks into the Ataa Rehabilitation and Prosthetic Limb Centre for earthquake and war victims in Azaz, a town in northern Syria's Aleppo governorate. She recently celebrated passing her preparatory level exams, and her pride in pushing through after losing her leg in the massive earthquakes that hit southern Turkey and northern Syria six months ago is apparent. "When the exam results were announced, I was especially happy that I fulfilled a part of my father's wish for me. He always encouraged me to continue my education," she said. Rima had spent two months in a hospital near the Turkish border, asking her surviving family where her father was.

The first musical instrument I played was the harmonica. I hated it because I did not get a good grade from my music teacher and besides, I got a mouthful of blisters from practicing. Then I tried to learn guitar because I told myself it would improve my concentration and it would be pretty cool to be able to play an instrument in college. Of course, I failed again and consoled myself with the fact that not everyone has the talent to play an instrument, even though some people like me really like music. I still think it was the right decision to give up learning an instrument, although I feel envious every time I see someone playing an instrument right in front of me.