4 papers · 1 filter
Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation
Jitesh Jain, Zhengyuan Yang, Humphrey Shi +2
In recent times, the standard practice for developing MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision. This approach often…
List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs
An Yan, Zhengyuan Yang, Junda Wu +8
Set-of-Mark (SoM) Prompting unleashes the visual grounding capability of GPT-4V, by enabling the model to associate visual objects with tags inserted on the image. These tags, mark…
ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding
Xingyu Fu, Minqian Liu, Zhengyuan Yang +6
Structured image understanding, such as interpreting tables and charts, requires strategically refocusing across various structures and texts within an image, forming a reasoning s…
Interfacing Foundation Models' Embeddings
Xueyan Zou, Linjie Li, Jianfeng Wang +10
Foundation models possess strong capabilities in reasoning and memorizing across modalities. To further unleash the power of foundation models, we present FIND, a generalized inter…