VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation Paper • 2601.02256 • Published Jan 5 • 33
NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation Paper • 2601.02204 • Published Jan 5 • 63
XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation Paper • 2506.21416 • Published Jun 26, 2025 • 28
DetailFlow: 1D Coarse-to-Fine Autoregressive Image Generation via Next-Detail Prediction Paper • 2505.21473 • Published May 27, 2025 • 16
TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation Paper • 2412.03069 • Published Dec 4, 2024 • 34
AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose Paper • 2308.03610 • Published Aug 7, 2023 • 25
