Papers

Filtered to sequence-level learning · clear filter

Browse by term

continual learning 10large language models 6reinforcement learning 6policy optimization 2video generation 2

Matching papers

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift

5 upvotes · 20 JUL 2026 · Zitong Huang, Gustavo Lucas Carvalho, Deqing Fu et al.

This paper proposes a new method for training language models to generate coherent and faithful responses, even when the input data has changed significantly. Practitioners might care about this research because it could lead to more robust and adaptable language models that can handle real-world scenarios where data distributions shift.