Skip to content
ENTITY PROFILE / KNOWLEDGE GRAPH

LoRA GRPO

RSS

LoRA GRPO, an LoRA reinforcement‐learning from human feedback method using VERL, was evaluated with AIME‑2024, boosting mean@8 from 0.56 to 0.85, with training–rollout KL ≈2×10⁻⁴. Funders VC backed Berachain NGRAVE followed a similar phishing campaign that targeted SecuX users on Oct. 16.· Entity summary generated by Graphiti

RELATIONS
2Relations
CURRENT
2Current
EVENTS
2Events
REPORTS
2Source reports
KNOWLEDGE ATLAS0 entities · 0 relations
No public neighbors yet
Explore all published links of a node; previously discovered relations remain visible.

Relation timeline

BY VALID-FROM DATE
  1. NGRAVEFOLLOWED SIMILAR PHISHING CAMPAIGN AGAINSTLoRA GRPO

    NGRAVE followed a similar phishing campaign that targeted SecuX users on Oct. 16.

    Current1 sourceNGRAVE
  2. JSCBACKEDLoRA GRPO

    Funders VC backed Berachain

    Current1 sourceJSC

Relations are facts Graphiti extracted from reports, not verbatim quotes. An end date means later reporting showed the relation no longer holds.

Events 2

Source reports 2