Negative prompting
Negative prompting is a technique used in artificial intelligence, particularly in generative models, to steer the output away from undesired features by specifying what should not be included in the generated content.
Technology & Innovation
Kaldi (speech recognition toolkit)
Kaldi is an open-source toolkit for speech recognition research. It provides a flexible and extensible framework for developing state-of-the-art speech recognition systems using various algorithms and models.
RoboCup
RoboCup is an international robotics competition with the goal of advancing artificial intelligence and robotics research through robot soccer matches and related challenges. It serves as a platform for innovation in autonomous robotics systems and multi-agent cooperation.
StarCoder
StarCoder is an open-source large language model designed to assist with programming tasks. Developed to provide code generation and understanding capabilities, it supports multiple programming languages and aims to facilitate software development processes.
Dropout as Bayesian approximation
Dropout as Bayesian approximation is a technique that interprets dropout in neural networks as a form of approximate Bayesian inference. This approach allows for uncertainty estimation in deep learning models by treating dropout as a variational approximation to a probabilistic model.
Task arithmetic for LLMs
Task arithmetic for LLMs refers to the method of combining multiple tasks to optimize the performance of large language models. It enhances task management and efficiency.
Randomized smoothing
Randomized smoothing is a technique in machine learning used to create robust classifiers by averaging predictions over noise-perturbed inputs. It provides certified robustness guarantees against adversarial attacks by transforming a base classifier into a smoothed classifier that is more resistant to input perturbations.
Physics-informed neural network (PINN)
Physics-informed neural networks (PINNs) are a class of deep learning models that incorporate physical laws, typically expressed as differential equations, into the training process. By embedding these constraints, PINNs can solve forward and inverse problems in scientific computing with improved accuracy and generalization.
System identification for sim-to-real
System identification for sim-to-real involves creating models that bridge the gap between simulated environments and real-world applications, enhancing the transferability of learned behaviors.
Large language model (LLM)
A large language model (LLM) is an advanced type of artificial intelligence designed to understand, generate, and interact using human language. These models are trained on vast amounts of text data and utilize deep learning techniques to perform a wide range of language-related tasks.