visual generation

6 papers

• End-to-End Vision Tokenizer Tuning
• Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning
• OmniGen-AR: AutoRegressive Any-to-Image Generation
• Selftok-Zero: Reinforcement Learning for Visual Generation via Discrete and Autoregressive Visual Tokens
• VETA-DiT: Variance-Equalized and Temporally Adaptive Quantization for Efficient 4-bit Diffusion Transformers
• Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations