PromptLib Smart Match

Also filed under Research & data

1. 0546

   Jev-guided sparse attention for MiniMax H3

   流行のJevをMiniMax H3に組み込んで、動画生成を高速化してみた！Attention処理のスパース化にJevを使用。 ・層ごとにJevが重要度を判定（4step 49層が対象） ・Jevがスパース率1%, 3%, 5%, 10%を選択 RTX4070で6分7秒→3分34秒で41.7%短縮！動画生成中にJevクラウドに問合せしているのに速い！

   @sep_is_heim · Research & data

   @sep_is_heim

   X post

   Research & data

   -

   -

2. 0538

   Made Jev talk (paper)

   I made Jev talk and wrote a paper on it. To publish it on arXiv, I need an endorser for csCL fom someone who has 3+ arXiv papers in any cs category, submitted between 3 months and 5 years ago. It's one click after I DM you the code and the paper. Or maybe someone you know. A

   @xucian_ · Research & data

   

   @xucian_

   X post

   Research & data

   -

   -

3. 0530

   Jev reads its own comment section

   I asked Jev to predict its own future. My last post (below) got 300k+ impressions, 400+ comments, 101 reposts. I used Jev to categorize every comment and quote to capture public X opinion on Jev’s future. Here’s results: ———— *Note: I created five prediction buckets,

   @JoshKuechly · Research & data

   

   @JoshKuechly

   X post

   Research & data

   -

   -

4. 0522

   Ultra-fast medical simulation

   I built an ultra-fast medical simulation with Jev and Grok 4.7 Grok 4.7 and I co-doctored a cancer patient across 20+ possible futures in just minutes. Grok proposed the moves. Jev ran the high-speed state decisions < 0.3 secs Patientic visualized the branched outcomes. 🧵👇

   @chris_not_busy · Research & data

   @chris_not_busy

   X post

   Research & data

   -

   -