15 papers
SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation
Junsong Chen, Jincheng Yu, Yitong Li +11
We introduce SANA-Video 2.0, a hybrid video diffusion transformer instantiated at 5B and 14B scales under a unified architecture. Designed to generate high-quality video up to 720p…
Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling
Tianyu Xie, Shuchen Xue, Zijin Feng +4
Discrete diffusion models have recently shown great promise for modeling complex discrete data, with masked diffusion models (MDMs) offering a compelling trade-off between quality…
FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling
Yitong Li, Junsong Chen, Shuchen Xue +8
Reinforcement-Learning-based post-training has recently emerged as a promising paradigm for aligning text-to-image diffusion models with human preferences. In recent studies, incre…
Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing
Shilong Zhang, He Zhang, Zhifei Zhang +11
Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To uni…
Fast-dLLM v2: Efficient Block-Diffusion LLM
Chengyue Wu, Hao Zhang, Shuchen Xue +7
Autoregressive (AR) large language models (LLMs) have achieved remarkable performance across a wide range of natural language tasks, yet their inherent sequential decoding limits i…
Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models
Shuchen Xue, Chongjian Ge, Shilong Zhang +2
Reinforcement Learning (RL) has emerged as a central paradigm for advancing Large Language Models (LLMs), where pre-training and RL post-training share the same log-likelihood form…