Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning
Paper
•
2505.07538
•
Published
Yue Zhongqi
nickyue
AI & ML interests
post-training, multimodal large language models, generalization
Recent Activity
authored
a paper
about 2 months ago
Discrete Visual Tokens of Autoregression, by Diffusion, and for
Reasoning
authored
a paper
about 2 months ago
Generative Multimodal Pretraining with Discrete Diffusion Timestep
Tokens
authored
a paper
about 2 months ago
Expanding the Action Space of LLMs to Reason Beyond Language
Organizations
None yet
authored
3
papers
about 2 months ago