§ research · storyline
Sparse-to-dense rewards improve language model post-training
Sparse-to-dense rewards improve language model post-training
This storyline groups 2 articles from 1 source. The originating feed didn’t ship an excerpt — open any link below to read the piece.
§ sources2 publications · timeline below
§ how this story moved
- primary — arXiv — cs.AI publishes the launch post.
- arXiv — cs.AI picks up coverage.