pith. sign in

Title resolution pending

**Identify the degree of each vertex**:

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Beyond Mode Collapse: Distribution Matching for Diverse Reasoning

cs.AI · 2026-05-19 · unverdicted · novelty 6.0

DMPO approximates forward KL minimization in on-policy RL by aligning the policy to a group-level reward-proportional target distribution, yielding 9-12% relative gains over GRPO on NP-Bench and smaller gains on math reasoning.

citing papers explorer

Showing 1 of 1 citing paper.

  • Beyond Mode Collapse: Distribution Matching for Diverse Reasoning cs.AI · 2026-05-19 · unverdicted · none · ref 56

    DMPO approximates forward KL minimization in on-policy RL by aligning the policy to a group-level reward-proportional target distribution, yielding 9-12% relative gains over GRPO on NP-Bench and smaller gains on math reasoning.