LLaVA-RLHF
Reward alignment system
Aligns large multimodal models with factually enhanced reward functions to improve performance and mitigate hacking in reinforcement learning
Aligning LMMs with Factually Augmented RLHF
319 stars
9 watching
25 forks
Language: Python
last commit: about 1 year ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 rlhf-v/rlhf-v | Aligns large language models' behavior through fine-grained correctional human feedback to improve trustworthiness and accuracy. | 233 |
 ethanyanjiali/minchatgpt | This project demonstrates the effectiveness of reinforcement learning from human feedback (RLHF) in improving small language models like GPT-2. | 213 |
 tristandeleu/pytorch-maml-rl | Replication of Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks in PyTorch for reinforcement learning tasks | 827 |
 wisconsinaivision/vip-llava | A system designed to enable large multimodal models to understand arbitrary visual prompts | 294 |
 sjtu-marl/malib | A framework for parallel population-based reinforcement learning | 497 |
 llava-vl/llava-interactive-demo | An all-in-one demo for interactive image processing and generation | 351 |
| llava-vl/llava-plus-codebase | A platform for training and deploying large language and vision models that can use tools to perform tasks | 704 |
 tatsu-lab/alpaca_farm | A framework for simulating and evaluating reinforcement learning from human feedback methods | 782 |
 matthiasplappert/keras-rl | A Python library implementing state-of-the-art deep reinforcement learning algorithms for Keras and OpenAI Gym environments. | 7 |
 kaixhin/rainbow | A Python implementation of a deep reinforcement learning algorithm combining multiple techniques for improved performance in Atari games | 1,585 |
 salt-nlp/llavar | An open-source project that enhances visual instruction tuning for text-rich image understanding by integrating GPT-4 models with multimodal datasets. | 258 |
 aidc-ai/ovis | An architecture designed to align visual and textual embeddings in multimodal learning | 517 |
 iffix/machin | An open-source reinforcement learning library for PyTorch, providing a simple and clear implementation of various algorithms. | 401 |
 yfzhang114/llava-align | Debiasing techniques to minimize hallucinations in large visual language models | 71 |
 lhfowl/robbing_the_fed | This implementation allows an attacker to directly obtain user data from federated learning gradient updates by modifying the shared model architecture. | 23 |