Researchers from Meta AI and collaborators have proposed Discriminator-Guided RL (DRL), a method to correct a structural flaw they identify in flow- and score-matching diffusion...
·
The Allen Institute for AI (AI2) has released MolmoMotion, a model that predicts future 3D point trajectories for objects in video given a frame, a set of query points, and a na...
·
A new research paper from Philippe Weier, Lukas Bode, Philipp Slusallek, Adrián Jarabo, and Sébastien Speierer introduces a compact five-dimensional neural encoding designed to ...
·
Object-WIPER, a training-free research method from Adobe Research and UT Dallas accepted to CVPR 2026, goes beyond simple mask-and-fill object removal by also erasing associated...
·
Researchers from the University of Maryland and Adobe have introduced SliderEdit, a framework that adds continuous, per-instruction intensity control to existing instruction-bas...
Researchers from UIUC, UMD, and collaborating institutions have introduced GenWildSplat, a feed-forward method for reconstructing 3D scenes from as few as two unconstrained, unp...
Researchers from Youku Moku-Lab and HUJING Digital Media & Entertainment Group have published MoVerse, a three-stage pipeline that converts a single narrow-field-of-view photogr...
Researchers from EPFL and Università della Svizzera italiana have introduced NASGabor (Normalized Anisotropic Spherical Gabor), a new spherical kernel function designed to repla...
·
Anthropic's Claude Fable 5 model was tasked with building LAAS — a fully procedural 4×4 km open world running in the browser via three.js WebGPURenderer and raw WGSL compute. Th...
·
INSID3 is a training-free in-context segmentation method that segments objects, parts, and personalized instances from a single annotated reference image using only frozen DINOv...
·
