SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.18814 · 2024

Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
dvlab-research/minigemini canonical 7 of 8
FunctionStatusWhere it lives
create_one_query Ran dvlab-research/minigemini/mgm/eval/model_math_vista.py
code served (permissive licence) · get_code("269bb26a4378dd51")
expand2square Ran dvlab-research/minigemini/mgm/mm_utils.py
code served (permissive licence) · get_code("592b3c1a88f93d7c")
get_chunk Ran dvlab-research/minigemini/mgm/eval/model_math_vista.py
code served (permissive licence) · get_code("42a46570620cd9fa")
is_none Ran dvlab-research/minigemini/mgm/eval/model_vqa_mmbench.py
code served (permissive licence) · get_code("bae18947b56f2be1")
load_image Ran dvlab-research/minigemini/predict.py
code served (permissive licence) · get_code("9b3c1cb391672ccb")
load_image_from_base64 Ran dvlab-research/minigemini/mgm/mm_utils.py
code served (permissive licence) · get_code("c3ee9d07c900dd55")
split_list Ran dvlab-research/minigemini/mgm/eval/model_math_vista.py
code served (permissive licence) · get_code("076c252c52cbb161")
process_images Not yet run dvlab-research/minigemini/mgm/mm_utils.py
code served (permissive licence) · get_code("d6153bc4456b4b0c")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this work, we introduce Mini-Gemini, a simple and effective framework enhancing multi-modality Vision Language Models (VLMs). Despite the advancements in VLMs facilitating basic visual dialog and reasoning, a performance gap persists compared to advanced models like GPT-4 and Gemini. We try to narrow the gap by mining the potential of VLMs for better performance and any-to-any workflow from three aspects, i.e., high-resolution visual tokens, high-quality data, and VLM-guided generation. To enhance visual tokens, we propose to utilize an additional visual encoder for high-resolution refinement without increasing the visual token count. We further construct a high-quality dataset that promotes precise image comprehension and reasoning-based generation, expanding the operational scope of current VLMs. In general, Mini-Gemini further mines the potential of VLMs and empowers current frameworks with image understanding, reasoning, and generation simultaneously. Mini-Gemini supports a series of dense and MoE Large Language Models (LLMs) from 2B to 34B. It is demonstrated to achieve leading performance in several zero-shot benchmarks and even surpasses the developed private models. Code and models are available at https://github.com/dvlab-research/MiniGemini.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.18814")
get_code_for_paper("2403.18814")
have("2403.18814")

Connect an agent — have() is free.