Loading activity…
@xiye_nlp
I study language models. Assistant professor @UAlberta. Postdoc fellow @PrincetonPLI. CS PhD @UTAustin.
AI
The original post describes LongHarness as a challenging evaluation for systems such as RLMs and coding agents.
AI
A researcher announcing a new paper says the OPD→RL sequence outperformed pure OPD, pure RLVR and many joint OPD+RL methods across reasoning tasks.
