Unverified50% confidenceFactExact time
HSTU was originally proposed by Meta in a 2024 paper titled "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations."
1
Sources
50%
Confidence
Long-term
Relevance
9/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMMLU于2021年由Hendrycks等人提出，题目来源于真实人类专业考试，覆盖57个学科领域56% similarVerifiedLLaMA was released by Meta in 2023 and is a landmark project in open-source large language models, demonstrating that smaller models trained on high-quality data can match closed-source models with far more parameters.56% similarUnverifiedTogetherAI 在 2024 年发表研究论文将 MoA 思路引入大语言模型领域，实验表明多个开源模型输出经聚合模型综合后可超越任何单一模型55% similarUnverified2023年CMU等机构发表的论文表明，通过对抗性后缀可以系统性绕过AI模型的对齐55% similarUnverifiedMeta在2023年曾公开部分推荐系统的工作原理，承认其使用了数千个信号来排序内容55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/963175API
curl https://kongchang.com/api/v1/knowledge/claims/963175MCP
get_claim(id=963175)