"Bienvenidos, nuestros duelistas"

From my Revolutionary Girl Utena-inspired Coco AU where Miguel ran away to an enchanted school and his cousins, Rosa & Abel had to get him home #pencodraws #cocopixar #pixarcoco #coco2017 #revolutionarygirlutena #coco_au

Tried using Emamori, a Glaze-like service based in Japan! Here's an older piece of Héctor that I made years ago. #pencodraws #coco #héctor #cocopixar #pixarcoco #coco2017

Perhaps the sweetest perversion to ever evade the Big D censors? <3 #Coco2017 #Watching #DiaDeLosMuertos #DayOfTheDead #Movies #GaelGarcíaBernalIsBoss

#FarCry6 #AntonCastillo #DiegoCastillo #Coco2017 #fanart

I wish you all Happy Halloween! Here are the arts for the flashmob in FC ASK! Once I found out that the actor who played Diego was the voice of Miguel from Coco, I just couldn't get this crossover out of my head!

#39for39 #foxandthehound #liloandstitch2002 #insideout2015 #coco2017 #encanto2021 #kpopdemonhunters2025 #39for39withbrandb #39for39withbrandb2026 #brandb39for39

on COCO2017, which enables MLLMs to focus more on understanding images in the objective world. To ensure data quality, we design a well-tailored annotation procedure, resulting in SpatialMQA consisting of 5,392 samples. Based on this benchmark, a [3/5 of https://arxiv.org/abs/2505.19015v1]

RefCOCO+, +17.9% on PixMo-Count, +4.2% on PageOCR, and notably, 31.9% AP on COCO2017 val for the first time, establishing a strong baseline for perception policy learning. [5/5 of https://arxiv.org/abs/2504.07954v1]

effectiveness. For instance, on COCO2017, ACAM-KD improves object detection performance by up to 1.4 mAP over the state-of-the-art when distilling a ResNet-50 student from a ResNet-101 teacher. For semantic segmentation on Cityscapes, it boosts mIoU [6/7 of https://arxiv.org/abs/2503.06307v1]

up to 15% overall speed-ups for image generation on COCO2017 and up to 20 times faster decoding in the sub-module, with additional gains on UCF-101 for video tasks. Memory requirements are moderately reduced, and while there is a small drop in [3/5 of https://arxiv.org/abs/2503.04871v1]

traditional codecs like H.264 by 12-15% in perceptual metrics while maintaining comparable PSNR/SSIM values, with 2.4x faster encoding and decoding speeds. On standard benchmarks including ImageNet-1k and COCO2017, GANCompress sets a new [6/8 of https://arxiv.org/abs/2505.13542v1]