Results for “linear-attention”
14 skills
dracounion lagging-area-focus
当感到生活失控、注意力分散，需要系统性重获专注力时
11 · bundle
omer-metin viral-hooks
Expert in creating opening lines, thumbnails, and hooks that stop the scroll. Covers curiosity gaps, pattern interrupts, emotional triggers, and platform-specific hooks. Knows how to earn attention in the first 3 seconds without resorting to clickbait. Use when "hook, opening line, scroll stopper, headline, first line, attention grab, thumbnail, clickable, " mentioned.
128 · bundle
dracounion attention-under-time
当规划内容创作策略或评估不同内容形式的长期价值时
11 · bundle
jiachen-t-wang scaling-instruction-finetuned-language-models-arxiv-2210-114
Scaling Instruction-Finetuned Language Models
6
jiachen-t-wang lora-low-rank-adaptation-of-large-language-models-arxiv-2106
LoRA: Low-Rank Adaptation of Large Language Models
6
dracounion life-cycle-awareness
当意识到自己处于迷茫、例行公事或心流等不同生活状态，并希望主动管理而非被动承受时
11 · bundle
dracounion cognitive-flip-pattern
当观察到或经历某种极端转化现象，或试图主动促成根本性观念转变时
11 · bundle
jiachen-t-wang lima-less-is-more-for-alignment-arxiv-2305-11206v1
LIMA: Less Is More for Alignment
6
jarbitechture learn
Recursive self-improving holon λ(ο,Κ,Σ).τ' for knowledge compounding and schema evolution. USE WHEN learning, improving, optimizing, assessing, reflecting, debugging, synthesizing, or refining—whether human, AI, or organizational. Triggers on /learn, /compound, /improve, /refine, /optimize, /assess, /reflect, "lessons learned", "best practices", "continuous improvement". Preserves Κ-monotonicity, η≥4, homoiconicity.
0 · bundle
curiositech alphago-deep-rl
Strategic patterns for solving intractable problems through cascading approximation, self-improvement, and heterogeneous evaluation from DeepMind's AlphaGo system
10 · bundle
jiachen-t-wang autoaugment-learning-augmentation-strategies-from-data-arxiv
AutoAugment: Learning Augmentation Strategies from Data
6
jiachen-t-wang mantis-interleaved-multi-image-instruction-tuning-arxiv-2405
Mantis: Interleaved Multi-Image Instruction Tuning
6
jiachen-t-wang llava-next-improved-reasoning-ocr-and-world-knowledge-arxiv-
LLaVA-NeXT: Improved Reasoning, OCR, and World Knowledge
6
dracounion pure-focus-state
当需要进入高效学习、创作或问题解决的心流状态时，调用此模型作为环境与心理准备框架
11 · bundle