Large Language Model
Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning
Can't wait to see the second movie! The first two lines are two demonstrations, and the third line is a test input.
MINEDOJO: BuildingOpen-Ended EmbodiedAgentswithInternet-ScaleKnowledge
These embodied agents are typically trainedtabula rasain isolated worlds with limited complexity and diversity. Although highly performant, theyare specialist models that do not generalize beyond a narrowsetoftasks.
FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations Ziyao Wang
The rapid development of Large Language Models (LLMs) has been pivotal in advancing AI, with pre-trained LLMs being adaptable to diverse downstream tasks through fine-tuning. Federated learning (FL) further enhances fine-tuning in a privacy-aware manner by utilizing clients' local data through in-situ computation, eliminating the need for data movement. However, fine-tuning LLMs, given their massive scale of parameters, poses challenges for clients with constrained and heterogeneous resources in FL.
Efficientmulti-promptevaluationofLLMs
Most popular benchmarks for comparing LLMs rely on alimited set ofprompt templates, which may not fully capture the LLMs' abilities and can affect the reproducibility ofresults onleaderboards. Manyrecent worksempirically verify prompt sensitivity and advocate for changes in LLM evaluation.
OpenAI starts testing ads in ChatGPT
Valve's Steam Machine: Everything we know Anthropic poked fun at the company for doing so in a Super Bowl ad. Users on ChatGPT's free and Go plans in the US may now start to see ads as OpenAI has started testing them in the chatbot. The company announced plans to bring ads to ChatGPT. At the time, the company said it would display sponsored products and services that are relevant to the current conversations of logged-in users, though they can disable personalization and clear the data used for ads" whenever they wish. "Our goal is for ads to support broader access to more powerful ChatGPT features while maintaining the trust people place in ChatGPT for important and personal tasks," OpenAI wrote in a blog post .
scaleVision
By making our data processing source code publiclyavailable, weaim toengage themarine science community toenrich thedata pool andinspire themachine learning community to develop more robust models.