Lijun Yu

8

Papers

884

Total Citations

1

Affiliations

Affiliations

Carnegie Mellon University

Papers (8)

Language Model Beats Diffusion - Tokenizer is key to visual generation

Photorealistic Video Generation with Diffusion Models

MaskBit: Embedding-free Image Generation via Bit Tokens

Language-Guided Image Tokenization for Generation

VideoPoet: A Large Language Model for Zero-Shot Video Generation

MAGVIT: Masked Generative Video Transformer

Rethinking Zero-Shot Action Recognition: Learning from Latent Atomic Actions

SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs