4 papers
Step-Level On-Policy Distillation: Interpolating Between On-Policy Distillation and Supervised Fine-Tuning
Changhui Sun, Lanbo Liu, Hang Lei +11
On-policy distillation (OPD) aligns a student model with a teacher's logit distribution on student-generated trajectories. This approach has achieved strong empirical gains and can…
MDLMPE: Distribution Aware Positional Encoding for Masked Diffusion Language Models
Tong Ling, Hang Lei, Feng Xiao +5
Masked diffusion language models (MDLMs) enable parallel generation and bidirectional context modeling, but their positional context differs fundamentally from that of autoregressi…
Rewarding Creativity: A Human-Aligned Generative Reward Model for Reinforcement Learning in Storytelling
Zhaoyan Li, Hang Lei, Yujia Wang +3
While Large Language Models (LLMs) can generate fluent text, producing high-quality creative stories remains challenging. Reinforcement Learning (RL) offers a promising solution bu…
Beyond Direct Generation: A Decomposed Approach to Well-Crafted Screenwriting with LLMs
Hang Lei, Shengyi Zong, Zhaoyan Li +3
The screenplay serves as the foundation for television production, defining narrative structure, character development, and dialogue. While Large Language Models (LLMs) show great…