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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Text-to-video has struggled to produce consistent motions like walking and rotation. A new approach achieves more realistic motion.
Text-to-video has struggled to produce consistent motions like walking and rotation. A new approach achieves more realistic motion.
Stay updated with weekly AI News and Insights delivered to your inbox