The Villain Made of Gas: Inside Netflix and Toho’s Ambitious Bet on ‘Human Vapor’

Toho cracks open its vault for the first time, teams with 'Train to Busan' writer Yeon Sang-ho and the Oscar-winning VFX crew ...
GitHub

SoulX-LiveAct: Towards Hour-Scale Real-Time Human Animation with Neighbor Forcing and ConvKV Memory

SoulX-LiveAct presents a novel framework that enables lifelike, multimodal-controlled, high-fidelity human animation video generation for real-time streaming interactions. (I) We identify ...
The Lancet

Human rights and the COVID-19 pandemic: a retrospective and prospective analysis

dDepartment of Global Health and Social Medicine, Harvard Medical School, Havard University, Boston, MA, USA eDivision of Global Health Equity, Department of Medicine, Brigham and Women's Hospital, ...
GitHub

Unleashing Guidance Without Classifiers for Human-Object Interaction Animation

[2026-03-27] Initial release of LIGHT. [2026-03-27] Release the inference pipeline. [2026-04-22] Release the training pipeline. [2026-04-22] Release the evaluation pipeline. [2026-04-22] Release the ...
IEEE

Free-viewpoint Human Animation with Pose-correlated Reference Selection

Abstract: Diffusion-based human animation aims to animate a human character based on a source human image as well as driving signals such as a sequence of poses. Leveraging the generative capacity of ...
Harvard Business Review

AI with a Human Face

The case for—and against—digital employees by Mike Seymour, Dan Lovallo, Kai Riemer, Alan R. Dennis and Lingyao (Ivy) Yuan All companies want to give their customers richer and more engaging ...
IEEE

MoAnimate: Bridging the Motion-Oriented Latent Representation Gaps in Human Video Animation

Abstract: Human animation strives to bring static characters to life. Existing methods produce high-quality outcomes for single-frame animation; however, they often fail to maintain satisfactory ...