arxiv
PublishedJune 5, 2026 at 4:00 AM
—neutral
GeoMin: Data-Efficient Semi-Supervised RLVR via Geometric Distribution Modeling
Publisher summary· verbatim
arXiv:2606.04516v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) significantly advances LLM reasoning, yet it faces a dilemma: standard supervised scaling is throttled by high annotation costs, while unsupervised alternatives suffer from severe model collapse.
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivSFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning51marxivOptical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning51marxivDynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models51marxivTemporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents51mThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗