Tagged articles

MemSlides

3 articles · Page 1 of 1

Jul 22, 2026 · Artificial Intelligence

MemSlides Enables Precise Local Edits in AI‑Generated PPTs

MemSlides, a collaboration between Tsinghua, Shanghai Jiao Tong, and Beijing University of Posts and Telecommunications, introduces a hierarchical memory framework that lets a Slides Agent remember long‑term user preferences, temporary constraints, and tool experience, achieving accurate local PPT modifications and significantly improving personalization and edit efficiency.

AI PPTMemSlideshierarchical memory

0 likes · 13 min read

MemSlides Enables Precise Local Edits in AI‑Generated PPTs

Machine Learning Algorithms & Natural Language Processing

Jul 10, 2026 · Artificial Intelligence

MemSlides Agent Tops Hugging Face Leaderboard: A Powerful AI for Personalized PPT Creation

MemSlides, a memory‑driven Slides Agent, combines long‑term user‑profile memory, working memory for temporary constraints, and tool memory for operation experience to generate and iteratively edit PPTs, achieving a 96.3% closed‑loop completion rate, 53.4% strict validation pass, and cutting first‑edit time to 242.5 seconds.

AI PPTMemSlidesMemory Architecture

0 likes · 13 min read

MemSlides Agent Tops Hugging Face Leaderboard: A Powerful AI for Personalized PPT Creation

Machine Learning Algorithms & Natural Language Processing

Jul 3, 2026 · Artificial Intelligence

MemSlides: Memory‑Driven Slides Agent for Multi‑Round Precise PPT Edits (HuggingFace #1)

MemSlides introduces a hierarchical memory framework—persistent user profiles, active working memory, and tool experience—to turn AI slide generation into a stateful multi‑turn authoring process, improving persona alignment and local edit efficiency, with closed‑loop completion rising from 0.815 to 0.963 and edit time dropping from 609.5 s to 242.5 s.

AI PPT generationMemSlideslocal modification

0 likes · 13 min read

MemSlides: Memory‑Driven Slides Agent for Multi‑Round Precise PPT Edits (HuggingFace #1)