InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation Paper • 2605.14333 • Published May 14 • 35
Steering Visual Generation in Unified Multimodal Models with Understanding Supervision Paper • 2605.05781 • Published May 7 • 5
Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models Paper • 2604.25636 • Published Apr 28 • 25
The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models Paper • 2601.15165 • Published Jan 21 • 75
CODA: Repurposing Continuous VAEs for Discrete Tokenization Paper • 2503.17760 • Published Mar 22, 2025 • 4
