7 papers
Persistent Recursive Worlds Enable Autonomous Software Evolution
Beichen Huang, Zhenyu Liang, Bowen Zheng +1
Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve continuity through persistent sessi…
Autoregressive Visual Generation Needs a Prologue
Bowen Zheng, Weijian Luo, Guang Yang +2
In this work, we propose Prologue, an approach to bridging the reconstruction-generation gap in autoregressive (AR) image generation. Instead of modifying visual tokens to satisfy…
Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
Tao Liu, Hao Yan, Mengting Chen +8
Step distillation has become a leading technique for accelerating diffusion models, among which Distribution Matching Distillation (DMD) and Consistency Distillation are two repres…
Taming the Entropy Cliff: Variable Codebook Size Quantization for Autoregressive Visual Generation
Bowen Zheng, Weijian Luo, Guang Yang +2
Most discrete visual tokenizers rely on a default design: every position in the sequence shares the same codebook. Researchers try to scale the codebook size to get better reco…
Learning Discrete Autoregressive Priors with Wasserstein Gradient Flow
Bowen Zheng, Yihong Luo, Tianyang Hu
Discrete image tokenizers are commonly trained in two stages: first for reconstruction, and then with a prior model fitted to the frozen token sequences. This decoupling leaves the…
Rethinking Decoupled Knowledge Distillation: A Predictive Distribution Perspective
Bowen Zheng, Ran Cheng
In the history of knowledge distillation, the focus has once shifted over time from logit-based to feature-based approaches. However, this transition has been revisited with the ad…