Papers4

All Beginner Intermediate Advanced

All Sources arXiv

#KV caching

World Action Models are Zero-shot Policies

Intermediate

Seonghyeon Ye, Yunhao Ge et al.Feb 17arXiv

DreamZero is a robot brain that learns actions by predicting short videos of the future and the matching moves at the same time.

#World Action Models#DreamZero#video diffusion

Advancing Open-source World Models

Intermediate

Robbyant Team, Zelin Gao et al.Jan 28arXiv

LingBot-World is an open-source world model that turns video generation into an interactive, real-time simulator.

#world model#video diffusion#causal attention

Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation

Intermediate

Taekyung Ki, Sangwon Jang et al.Jan 2arXiv

This paper builds a real-time talking-listening head avatar that reacts naturally to your words, tone, nods, and smiles in about half a second.

#interactive avatar#talking head generation#causal diffusion forcing

Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed

Intermediate

Yonggan Fu, Lexington Whalen et al.Dec 16arXiv

Autoregressive (AR) models write one word at a time, which is accurate but slow, especially when your computer or GPU can’t keep many tasks in memory at once.

#diffusion language models#autoregressive models#AR-to-dLM conversion