Terry Winograd
Terry Winograd is a prominent figure in the fields of artificial intelligence and human-computer interaction, known for his pioneering work in natural language processing.
Technology & Innovation
Point-E
Point-E is a machine learning model designed to generate three-dimensional point clouds from two-dimensional images or text prompts. It emphasizes fast and efficient 3D shape generation using neural networks, targeting applications in 3D modeling and computer graphics.
Domain-incremental learning
Domain-incremental learning involves training machine learning models to adapt to new domains while retaining knowledge from previous ones.
MPII Human Pose (pose estimation dataset)
The MPII Human Pose dataset is a widely used benchmark for evaluating human pose estimation algorithms, featuring diverse images and detailed annotations.
Intrinsic motivation in AI
Intrinsic motivation in AI refers to the internal processes that drive artificial intelligence systems to pursue goals without external incentives.
MoCo (momentum contrast)
MoCo (momentum contrast) is a self-supervised learning framework designed for contrastive representation learning in machine learning.
Flava (foundation language and vision alignment)
Flava is a conceptual framework integrating language and vision alignment, enhancing communication and understanding in various fields.
SayCan (language-guided robot planning)
SayCan is a novel approach to robot planning that utilizes natural language instructions to guide robot actions, enhancing human-robot interaction.
Ashish Vaswani
Ashish Vaswani is a prominent figure in artificial intelligence, known for his contributions to deep learning and natural language processing.
Mirostat sampling
Mirostat sampling is an adaptive text generation technique used in natural language processing to maintain a target level of entropy during token selection, optimizing output diversity and coherence. It dynamically adjusts sampling parameters to control the surprise or unpredictability of generated text.