PulseAugur
EN
LIVE 19:18:37
ENTITY Q/K/V projection weights

Q/K/V projection weights

PulseAugur coverage of Q/K/V projection weights — every cluster mentioning Q/K/V projection weights across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
0
1 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
0
1 over 90d
TIER MIX · 90D
TOPICS
RECENT · PAGE 1/1 · 1 TOTAL
  1. TOOL · CL_254391 ·

    New method probes VLM vision encoders for optimal PEFT layer selection

    Researchers have developed a new method for selecting optimal layers in vision encoders for vision-language models (VLMs) during parameter-efficient fine-tuning (PEFT). This approach analyzes the statistical properties …