Ovis
by AIDC-AI
A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.
AI summary
Multimodal aligner
An MLLM architecture designed to align visual and textual embeddings through structural alignment
- stars
- 575
- forks
- 33
- watching
- 7
Similar projects
Found by comparing what the projects do, not just their names.
Visual Instruction Toolkit
A method and toolkit for fine-tuning large language models to perform visual instruction tasks in multiple languages.
Behavior alignment tool
Aligns large language models' behavior through fine-grained correctional human feedback to improve trustworthiness and accuracy.
Multimodal LLM
An implementation of a multimodal language model with capabilities for comprehension and generation
Multimodal model trainer
An implementation of a multimodal LLM training paradigm to enhance truthfulness and ethics in language models
Model aligner
Aligns large multimodal models with human intentions and values using various algorithms and fine-tuning methods.
nvlabs/prismer1.3K
Vision-Language Model
A deep learning framework for training multi-modal models with vision and language capabilities.
Multimodal alignment model
Extending pretraining models to handle multiple modalities by aligning language and video representations
Visual Instruction Tuning
An open-source project that enhances visual instruction tuning for text-rich image understanding by integrating GPT-4 models with multimodal datasets.
Vision-Language Model
A multimodal AI model that enables real-world vision-language understanding applications
Multimodal benchmarking
Evaluates and benchmarks multimodal language models' ability to process visual, acoustic, and textual inputs simultaneously.
Text aligner
A plugin for aligning bilingual parallel texts by re-positioning text and applying highlighting.
Attention calibrator
This project proposes a novel method for calibrating attention distributions in multimodal models to improve contextualized representations of image-text pairs.
Visual Prompt Model
A system designed to enable large multimodal models to understand arbitrary visual prompts
Mixture of Experts Model
A large vision-language model using a mixture-of-experts architecture to improve performance on multi-modal learning tasks
Visual decoder
A large language model designed to process and generate visual information
