Kam-Woh Ng — accepted AI-conference papers

2026

Mixture of States: Routing Token-Level Dynamics for Multimodal Generation

Haozhe Liu, Ding Liu, Mingchen Zhuge, Zijian Zhou, Tian Xie, Sen He +13

CVPR 2026

We introduce MoS (Mixture of States), a novel fusion paradigm for multimodal diffusion models that merges modalities using flexible, state-based interactions. The core of MoS is a learnable, token-wise router that creates denoising timestep- and input-dependent interactions between modalities' hidde

Cited by 0 Source ↗code ↗Scholar ↗

2026

Scaling Zero-Shot Reference-to-Video Generation

Zijian Zhou, Shikun Liu, Haozhe Liu, Haonan Qiu, Zhaochong An, Weiming Ren +11

CVPR 2026

Reference-to-video (R2V) generation aims to synthesize videos that align with a text prompt while preserving the subject identity from reference images. However, current R2V methods are hindered by the reliance on explicit reference image-video-text triplets, whose construction is highly expensive a

Cited by 0 Source ↗code ↗Scholar ↗