discrete tokens
- BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning
- BitMark: Watermarking Bitwise Autoregressive Image Generative Models
- Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better
- OmniSVG: A Unified Scalable Vector Graphics Generation Model
- Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought
- Selftok-Zero: Reinforcement Learning for Visual Generation via Discrete and Autoregressive Visual Tokens
- Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations