公开(公告)号：US20250131027A1

公开(公告)日：2025-04-24

申请号：US18924763

申请日：2024-10-23

Applicant: SRI International

Inventor： Yangyi Chen ,  Karan Sikka ,  Michael A. Cogswell ,  Ajay Divakaran

IPC: G06F16/338 ,  G06F16/33 ,  G06F16/532

Abstract: In an example, a method for fine-tuning a Large Visual Language Model (LVLM) includes providing visual queries, each of the visual queries comprises at least an image and a textual query related to the image; processing, by the LVLM, the visual queries to extract visual embeddings from the visual queries, wherein the LVLM comprises a Visual Language Model (VLM), a first Large Language Model (LLM), and a linear projection layer interconnecting the VLM and the LLM; for visual queries: i) generating, by the LVLM, a response to the corresponding visual query based on the corresponding visual embedding; ii) evaluating, by a second LLM, the generated response to verify that the generated response satisfies predefined criteria; and iii) providing, by the second LLM, a feedback to the LVLM, in response to the evaluating the generated response; and fine-tuning the LVLM using aggregated feedback provided by the second LLM for the visual queries.