Niels Rogge

Localized reading

Papers with Code MCP 서버를 소개합니다! 출시를 축하하기 위해 Claude Code에게 'search_papers' 도구를 사용하여 @typesafeai의 Jev 아키텍처를 조사해 달라고 요청했습니다. 그 결과는 다음과 같습니다. "만약...

Original post / EN

Introducing the Papers with Code MCP server! To celebrate its release, I've asked Claude Code to research the architecture of Jev by @typesafeai using the `search_papers` tool. Here's what it came up with: "If Jev is architecturally anything public, it's a large schema-conditioned bidirectional encoder with parallel label-query heads (GLiNER/ML-Decoder shape) trained with a proper-scoring-rule RL objective (RLCR shape), scaled far past the ~150M-param range those papers operate in — "neither small nor an LLM" fits that. The 40–200× speedup is consistent with removing autoregression, not with any exotic mechanism."