Retriever-Augmented Generation, or RAG, is a type of language generation model that combines pre-trained parametric and non-parametric memory for language generation. Specifically, the parametric memory is a pre-trained seq2seq model and the non-parametric memory is a dense vector index of Wikipedia, accessed with a pre-trained neural retriever. For query $x$, Maximum Inner Product Search (MIPS) is used to find the top-K documents $z\_{i}$. For final prediction $y$, we treat $z$ as a latent variable and marginalize over seq2seq predictions given different documents.
CodeGen is an autoregressive transformers with next-token prediction language modeling as the learning objective trained on a natural language corpus and programming language data curated from GitHub.
Galactica is a language model which uses a Transformer architecture in a decoder-only setup with the following modifications: - It uses GeLU activations on all model sizes - It uses a 2048 length context window for all model sizes - It does not use biases in any of the dense kernels or layer norms - It uses learned positional embeddings for the model - A vocabulary of 50k tokens was constructed using BPE. The vocabulary was generated from a randomly selected 2% subset of the training data
The composed video retrieval (CoVR) task is a new task, where the goal is to find a video that matches both a query image and a query text. The query image represents a visual concept that the user is interested in, and the query text specifies how the concept should be modified or refined. For example, given an image of a fountain and the text during show at night, the CoVR task is to retrieve a video that shows the fountain at night with a show.
LLM-SR pioneers the use of LLMs for scientific equation discovery and symbolic regression and shows how LLMs, with their vast scientific knowledge and coding capability, enhance equation discovery across various scientific fields.
Child-Tuning is a fine-tuning technique that updates a subset of parameters (called child network) of large pretrained models via strategically masking out the gradients of the non-child network during the backward process. It decreases the hypothesis space of the model via a task-specific mask applied to the full gradients, helping to effectively adapt the large-scale pretrained model to various tasks and meanwhile aiming to maintain its original generalization ability.