bubogpt
BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs
AI summary
Visual grounding framework
An open-source framework enabling multi-modal LLMs to jointly understand text, vision, and audio and ground knowledge into visual objects.
- stars
- 505
- forks
- 35
- watching
- 10
Similar projects
Found by comparing what the projects do, not just their names.
Object groundings model
An implementation of a computer vision model that grounds objects in images using natural language queries.
Deep learning framework bridge
An abstraction layer between various deep learning frameworks and your program.
Vision Reasoning Framework
A deep learning framework for iteratively decomposing vision and language reasoning via large language models.
lxtgh/omg-seg1.3K
Visual Model
Develops an end-to-end model for multiple visual perception and reasoning tasks using a single encoder, decoder, and large language model.
Multimodal conversational model
An end-to-end trained model capable of generating natural language responses integrated with object segmentation masks for interactive visual conversations
jy0205/lavit544
Visual understanding and generation framework
A unified framework for training large language models to understand and generate visual content
Benchmark
An image-context reasoning benchmark designed to challenge large vision-language models and help improve their accuracy
Image grounding model
An implementation of a deep learning model for grounding situation recognition in images
Visual search framework
PyTorch implementation of guided visual search mechanism for multimodal LLMs
LLM trainer
Transfers visual prompt generators across large language models to reduce training costs and enable customization of multimodal LLMs
Visual Reasoning Model
An open-source implementation of a deep learning model designed to improve the balance between performance and interpretability in visual reasoning tasks.
Research framework
An ML framework for accelerating research and its integration into production workflows
Visual Reasoning Benchmark
A benchmarking tool and software framework for evaluating few-shot visual reasoning capabilities in computer vision models.
Visual Model Benchmark
An open-source benchmarking framework for evaluating cross-style visual capability of large multimodal models
Visual concept detection framework
This codebase provides a framework for detecting visual concepts in images by leveraging image captions and pre-trained models.
