Carnegie Mellon University
A Transformer Alternative Emerges: Mamba, a new approach that may outperform transformers
An architectural innovation improves upon transformers — up to 2 billion parameters, at least...
Carnegie Mellon University
30 Posts
Carnegie Mellon University
A Transformer Alternative Emerges: Mamba, a new approach that may outperform transformers
An architectural innovation improves upon transformers — up to 2 billion parameters, at least...
Carnegie Mellon University
Better, Faster Network Pruning: Researchers devise pruning method that boosts AI speed
Pruning weights from a neural network makes it smaller and faster, but it can take a lot of computation to choose weights that can be removed without degrading the network’s performance.
Carnegie Mellon University
Better, Faster Network Pruning: Researchers devise pruning method that boosts AI speed
Pruning weights from a neural network makes it smaller and faster, but it can take a lot of computation to choose weights that can be removed without degrading the network’s performance.
Carnegie Mellon University
Text or Images, Input or Output: GILL, an innovative approach to multimodal model training
GPT-4V introduced a large multimodal model that generates text from images and, with help from DALL-E 3, generates images from text. However, OpenAI hasn’t fully explained how it built the system. A separate group of researchers described their own method.
Carnegie Mellon University
Text or Images, Input or Output: GILL, an innovative approach to multimodal model training
GPT-4V introduced a large multimodal model that generates text from images and, with help from DALL-E 3, generates images from text. However, OpenAI hasn’t fully explained how it built the system. A separate group of researchers described their own method.
Carnegie Mellon University
Learning From Metadata: Descriptive Text Improves Performance for AI Image Classification Systems
Images in the wild may not come with labels, but they often include metadata. A new training method takes advantage of this information to improve contrastive learning.
Carnegie Mellon University
Learning From Metadata: Descriptive Text Improves Performance for AI Image Classification Systems
Images in the wild may not come with labels, but they often include metadata. A new training method takes advantage of this information to improve contrastive learning.
Carnegie Mellon University
Cutting the Carbon Cost of Training: A New Tool Helps NLP Models Lower Their Gas Emissions
You can reduce your model’s carbon emissions by being choosy about when and where you train it.
Carnegie Mellon University
Cutting the Carbon Cost of Training: A New Tool Helps NLP Models Lower Their Gas Emissions
You can reduce your model’s carbon emissions by being choosy about when and where you train it.
Carnegie Mellon University
Child-Welfare Agency Drops AI: Oregon and Pennsylvania Halt Use of AI Tool for At-Risk Kids
Officials in charge of protecting children stopped using a machine learning model designed to help them make decisions in difficult cases. The U.S. state of Oregon halted its use of an algorithm intended to identify children who may benefit from intervention.
Carnegie Mellon University
Child-Welfare Agency Drops AI: Oregon and Pennsylvania Halt Use of AI Tool for At-Risk Kids
Officials in charge of protecting children stopped using a machine learning model designed to help them make decisions in difficult cases. The U.S. state of Oregon halted its use of an algorithm intended to identify children who may benefit from intervention.
Carnegie Mellon University
Fine-Tune Your Fine-Tuning: New method optimizes training for few shot NLP models.
Let’s say you have a pretrained language model and a small amount of data to fine-tune it to answer yes-or-no questions. Should you fine-tune it to classify yes/no or to fill in missing words — both viable approaches that are likely to yield different results?
Carnegie Mellon University
Fine-Tune Your Fine-Tuning: New method optimizes training for few shot NLP models.
Let’s say you have a pretrained language model and a small amount of data to fine-tune it to answer yes-or-no questions. Should you fine-tune it to classify yes/no or to fill in missing words — both viable approaches that are likely to yield different results?
Carnegie Mellon University
Walking the Dog: Training a robot to walk over unsteady terrain with RL.
A reinforcement learning system enabled a four-legged robot to amble over unfamiliar, rapidly changing terrain.
Subscribe to The Batch
Stay updated with weekly AI News and Insights delivered to your inbox