1 views collected around this technical thread.
This paper proposes CAIG, a novel method for generating high-CTR advertising images using multimodal large language models, combining reinforcement learning and preference optimization to align generated content with product features.
This article presents a comprehensive study of generative retrieval for large‑scale e‑commerce search, detailing background challenges, the advantages of generative methods, two concrete strategies—Lexical‑based and SemanticID‑based—along with task redesign, preference optimization, constrained beam search, extensive experiments, and future research directions.
Bilibili’s in‑house role‑playing large language model, built on the Index architecture and refined through pre‑training, supervised fine‑tuning, and preference optimization (PPO and DPO), achieved top scores on the Chinese CharacterEval benchmark, surpassing rivals while incorporating safety alignment and showcasing consistent, personality‑driven dialogue examples.