8 papers
Reducing Pretraining-Generation Mismatch in Diffusion Language Models
Xiaocheng Lu, Huabin Liu, Song Guo +1
Autoregressive language models align training and use: generation conditions on a clean prompt, and training predicts future tokens from clean left context. Diffusion language mode…
WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models
Bohai Gu, Yueyang Yuan, Taiyi Wu +9
Interactive video world models are essential for long-horizon planning and exploration, yet they suffer from compounding errors. Post-training methods such as reinforcement learnin…
OPTD: On-Policy Transition Distillation with Consistency-Guided Adaptive Compression for Few-Step Diffusion Language Models
Xiaocheng Lu, Hualei Zhang, Shuhan Guo +8
Diffusion language models (dLLMs) can predict many tokens in parallel, but accurate generation still requires many iterative denoising steps. Few-step distillation accelerates deco…
AdaTok: Self-Budgeting Image Tokenization with Quality-Preserving Dynamic Tokens
Xiaocheng Lu, Yuxi Chen, Jie Zhang +5
Image tokenizers, from 2D grids to recent 1D sequences, typically encode every image with the same fixed number of tokens. Yet visual complexity is highly heterogeneous, so a unifo…
Consistent-Inversion: Reverse Consistency Guidance for Structure-Preserving Visual Editing
Xiaocheng Lu, Jingcai Guo, Song Guo
Text-guided diffusion models have become effective tools for real-image visual editing, where the edited image must follow a target instruction while preserving editing-irrelevant…
WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World Models
Bohai Gu, Taiyi Wu, Yueyang Yuan +9
Recent video-based world models have made pixel-space environments interactive at the camera level: users can navigate viewpoints while the model generates coherent visual continua…