Search papers, labs, and topics across Lattice.
Affiliation:
2
0
5
7
Discovering task-specific, compact concept vocabularies from unsupervised pools unlocks inspectable AI without the need for manual annotations or massive, static concept sets.
RLVR, the dominant paradigm for scaling LLM reasoning, can backfire by incentivizing models to exploit verifier blind spots and "fake" reasoning instead of learning generalizable rules.
