Beyond task performance: evaluating and reducing the flaws of large multimodal models with in-context-learning.
Mustafa ShukorAlexandre RaméCorentin DancetteMatthieu CordPublished in: ICLR (2024)
Keyphrases
- prior knowledge
- learning models
- learning process
- learning systems
- accurate models
- reinforcement learning
- learning problems
- learning tasks
- learning contexts
- learned models
- structured prediction
- dynamic bayesian networks
- statistical models
- data sets
- unsupervised learning
- complex systems
- learning mechanism
- probabilistic model
- neural network
- machine learning
- genetic algorithm
- learning algorithm
- elementary school
- learning scheme
- hidden variables
- online learning
- learning analytics
- incremental learning
- computational models