Machine Learning Research
Cutting the Cost of Pretrained Models: FrugalGPT, a method to cut AI costs and maintain quality
Research aims to help users select large language models that minimize expenses while maintaining quality.
Machine Learning Research
Machine Learning Research
Conversational Robots: RFM-1, a model that enables robots to understand and act on human commands
Robots equipped with large language models are asking their human overseers for help.
Machine Learning Research
Toward Safer, More Helpful Models
The technique known as reinforcement learning from human feedback fine-tunes large language models to be helpful and avoid generating harmful responses such as suggesting illegal or dangerous activities. An alternative method streamlines this approach and achieves better results.
Machine Learning Research
Learning Language by Exploration: Agent develops language skills through simulated exploration tasks
Machine learning models typically learn language by training on tasks like predicting the next word in a given text. Researchers trained a language model in a less focused, more human-like way.
Machine Learning Research
Schooling Language Models in Math: GOAT (Good at Arithmetic Tasks), a method to boost large language models' arithmetic abilities
Large language models are not good at math. Researchers devised a way to make them better. Tiedong Liu and Bryan Kian Hsiang Low at the National University of Singapore proposed a method to fine-tune large language models for arithmetic tasks.
Tech & Society
Google Releases Open Source LLMs: All we know about Google's Gemma-7B and Gemma-2B models
Google asserted its open source bona fides with new models. Google released weights for Gemma-7B, an 8.5 billion-parameter large language model intended to run GPUs, and Gemma-2B, a 2.5 billion-parameter version intended for deployment on CPUs and edge devices.
Machine Learning Research
Human Feedback Without Reinforcement Learning: Direct Preference Optimization (DPO) fine-tunes pretrained large language models on human preferences without the cumbersome step of reinforcement learning.
Reinforcement learning from human feedback (RLHF) is widely used to fine-tune pretrained models to deliver outputs that align with human preferences. New work aligns pretrained models without the cumbersome step of reinforcement learning.
Machine Learning Research
Swiss Army LLM
The combination of language models that are equipped for retrieval augmented generation can retrieve text from a database to improve their output. Further work extends this capability to retrieve information from any application that comes with an API.
Machine Learning Research
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.
Machine Learning Research
Memory-Efficient Optimizer: A method to reduce memory needs when fine-tuning AI models
Researchers devised a way to reduce memory requirements when fine-tuning large language models. Kai Lv and colleagues at Fudan University proposed low memory optimization (LOMO), a modification of stochastic gradient descent that stores less data than other optimizers during fine-tuning.
Machine Learning Research
Better Images, Less Training: Würstchen, a speedy, high-quality image generator
The longer text-to-image models train, the better their output — but the training is costly. Researchers built a system that produced superior images after far less training.
Machine Learning Research
LLMs Can Get Inside Your Head: AI models show promise in understanding human beliefs, research reveals
Most people understand that others’ mental states can differ from their own. For instance, if your friend leaves a smartphone on a table and you privately put it in your pocket, you understand that your friend continues to believe it was on the table.