Papers6

#variational autoencoder

SARAH: Spatially Aware Real-time Agentic Humans

Evonne Ng, Siwei Zhang et al.Feb 20arXiv

SARAH is a real-time system that makes virtual characters move their whole bodies naturally during a conversation while knowing where the user is.

#spatially aware motion#real-time avatars#causal transformer

Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars

Beginner

Youliang Zhang, Zhengguang Zhou et al.Feb 2arXiv

This paper teaches talking avatars not just to speak, but to look around their scene and handle nearby objects exactly as a text instruction says.

#grounded human-object interaction#talking avatars#diffusion transformer

Beyond Imitation: Reinforcement Learning for Active Latent Planning

Intermediate

Zhi Zheng, Wee Sun LeeJan 29arXiv

The paper shows how to make AI think faster and smarter by planning in a hidden space instead of writing long step-by-step sentences.

#latent reasoning#chain-of-thought#variational autoencoder

LTX-2: Efficient Joint Audio-Visual Foundation Model

Intermediate

Yoav HaCohen, Benny Brazowski et al.Jan 6arXiv

LTX-2 is an open-source model that makes video and sound together from a text prompt, so the picture and audio match in time and meaning.

#text-to-video#text-to-audio#audiovisual generation

Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition

Intermediate

Shengming Yin, Zekai Zhang et al.Dec 17arXiv

The paper turns one flat picture into a neat stack of see‑through layers, so you can edit one thing without messing up the rest.

#image decomposition#RGBA layers#alpha blending

Scaling Zero-Shot Reference-to-Video Generation

Intermediate

Zijian Zhou, Shikun Liu et al.Dec 7arXiv

Saber is a new way to make videos that match a text description while keeping the look of people or objects from reference photos, without needing special triplet datasets.

#reference-to-video generation#zero-shot video synthesis#masked training