Video unavailable. Open the source below.
New1kPapers
This is a concrete batch classification example: Jev selects among a fixed set of 24 research topics after another model compresses each paper into a summary.
Added to Jevfast
How it uses Jev
Limited inference from the creator post and inspected demo: The pipeline summarizes each research paper with DeepSeek V4 Flash, then sends the paper title, summary, and 24 possible topics to Jev for classification. The post describes the task and input fields but does not specify the exact request format or Jev's output schema.
Why it is interesting
This is a concrete batch classification example: Jev selects among a fixed set of 24 research topics after another model compresses each paper into a summary. The author reports processing 1,018 papers; cost and latency figures are omitted here because they are unverified claims in the post.