arXiv AI By Lei Jiang

Do Recipes Have Personas? Characterizing and Generating Creator Style in Attributed Procedural Graphs

Read the original on arXiv AI →

The paper introduces ViralRecipesTrans, a dataset of execution flow graphs from culinary videos linked to specific creators, and proposes a graph learning framework to discover procedural personas. It shows that discrete topological metrics better capture a creator’s workflow than lexical classifiers, and presents a two‑stage generative model that predicts a creator’s exact execution graph for new dishes. The study finds that few‑shot LLMs excel at semantic assignment but lack macro‑planning, while the structured model offers superior topological control, and an ensemble approach combines both strengths for personalized workflow generation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers
Jul 15

ThinkBLOX: 3D Indoor Scene Generation with Progressive Reasoning

While traditional graphics methods often synthesize 3D indoor scenes autoregressively or hierarchically, recent vision-language model (VLM)-based generators predominantly adopt a one-shot paradigm where the full layout is planned at once. This one-shot approach often requires global re-optimization or complete reconstruction during interactive editing (e.

arXiv AI
Jul 20

Human-Aligned Procedural Level Generation Reinforcement Learning via Text-Level-Sketch Shared Representation

arXiv:2508. 09860v2 Announce Type: replace Abstract: Human-aligned AI is a critical component of co-creativity, as it enables models to accurately interpret human intent and generate controllable outputs that align with design goals in collaborative content creation.

By In-Chang Baek, Seoyoung Lee, Sung-Hyun Kim, Geumhwan Hwang, KyungJoong Kim