RT @andrewliao11: 🎉 Great news! "LongPerceptualThoughts" accepted at @COLMConf! . #montreal #COLM2025.

RT @_akhaliq: Nvidia just announced Align Your Flow. Scaling Continuous-Time Flow Map Distillation

RT @AljosaOsep: We are presenting the next work in the SALverse this morning: Zero-Shot 4D Lidar Panoptic Segmentation! we also have a demo….

Looking for 3D reconstruction from images in seconds?. We are presenting Light3R-SfM at 5pm today (in 1.5 hours) at Poster #91! . Come by and have a chat! . Paper: Project page:

RT @zianwang97: 🚀 We just open-sourced Cosmos DiffusionRenderer!. This major upgrade brings significantly improved video de-lighting and re….

RT @andrewliao11: 🚀 New work: LongPerceptualThoughts. We introduce a synthetic data pipeline to fine-tune VLMs with Long Chain-of-thoughts.….

RT @ZGojcic: 📣 We have released the source code of 3DGRT and 3DGUT in a common 3DGRUT repo under the Apache license! . Go try it out and pl….

RT @xuanchi13: 📢🚗✨ Excited to announce InfiniCube, our scalable generative model for dynamic 3D driving scene generation with high fidelity….

RT @ylecun: The heretofore silent majority of AI scientists and engineers who.- do not believe in AI extinction scenarios or.- believe we h….

Paper: Code: Project page: x.

@PatrickDendorf1 @lealtaixe TL;DR: We observe that single generator methods transform a continuous latent space with a continuous function which causes out-of-distribution samples. We tackle this problem by introducing discontinuity into our model using multiple generators.

#ICCV2021 Paper: MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction. Joint work with awesome @PatrickDendorf1 and @lealtaixe. Join us for poster session 10, today at today 5PM and Friday 10PM (EDT)!

RT @lealtaixe: MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction. Paper: https://t….