Introduces VIG metric to measure visual contribution via perplexity reduction and applies it for selective training of LVLMs on high-VIG samples and tokens to improve grounding with reduced supervision.
Minigpt-4: Enhancing vision-language understanding with advanced large language models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
LogicVista is a new benchmark dataset with 448 visual logic questions that evaluates multimodal LLMs on five reasoning tasks covering nine capabilities.
A 13B model called Orca learns detailed reasoning from GPT-4 explanation traces and reaches parity with ChatGPT on Big-Bench Hard while outperforming other 13B models.
citing papers explorer
-
Focusing Where Vision Matters: Selective Training for Large Vision Language Models via Visual Information Gain
Introduces VIG metric to measure visual contribution via perplexity reduction and applies it for selective training of LVLMs on high-VIG samples and tokens to improve grounding with reduced supervision.
-
LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts
LogicVista is a new benchmark dataset with 448 visual logic questions that evaluates multimodal LLMs on five reasoning tasks covering nine capabilities.
-
Orca: Progressive Learning from Complex Explanation Traces of GPT-4
A 13B model called Orca learns detailed reasoning from GPT-4 explanation traces and reaches parity with ChatGPT on Big-Bench Hard while outperforming other 13B models.