1.1CLJan 16
T*: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement LearningHanchen Xia, Baoyou Chen, Yutang Ge et al.
We present T*, a simple TraceRL-based training curriculum for progressive block-size scaling in masked diffusion language models (MDMs). Starting from an AR-initialized small-block MDM, T* transitions smoothly to larger blocks, enabling higher-parallelism decoding with minimal performance degradation on math reasoning benchmarks. Moreover, further analysis suggests that T* may actually converge to an alternative decoding schedule that achieves comparable performance.