サクサク読めて、アプリ限定の機能も多数!
トップへ戻る
災害への備え
bair.berkeley.edu
AI caught everyone’s attention in 2023 with Large Language Models (LLMs) that can be instructed to perform general tasks, such as translation or coding, just by prompting. This naturally led to an intense focus on models as the primary ingredient in AI application development, with everyone wondering what capabilities new LLMs will bring. As more developers begin to build using LLMs, however, we b
Xinyang Geng$^*$, Arnav Gudibande$^*$, Hao Liu$^*$, Eric Wallace$^*$, Pieter Abbeel$^\diamond$, Sergey Levine$^\diamond$ and Dawn Song$^\diamond$ Apr 3, 2023 In this post, we introduce Koala, a chatbot trained by fine-tuning Meta’s LLaMA on dialogue data gathered from the web. We describe the dataset curation and training process of our model, and also present the results of a user study that comp
Finding good data and a good policy correspond to optimizing the lower bound, $F(\theta, q)$, with respect to the policy parameters and the experience. One common approach for maximizing the lower bound is to perform coordinate ascent on its arguments, alternating between optimizing the data distribution and the policy.1 Optimizing the Policy When optimizing the lower bound with respect to the pol
End-to-End Deep Reinforcement Learning without Reward Engineering Communicating the goal of a task to another person is easy: we can use language, show them an image of the desired outcome, point them to a how-to video, or use some combination of all of these. On the other hand, specifying a task to a robot for reinforcement learning requires substantial effort. Most prior work that has applied de
An earlier version of this post was published on Off the Convex Path. It is reposted here with the author’s permission. In the last few years, deep learning practitioners have proposed a litany of different sequence models. Although recurrent neural networks were once the tool of choice, now models like the autoregressive Wavenet or the Transformer are replacing RNNs on a diverse set of tasks. In
Update 06/18/2018: please also check our follow-up blog post after reading this. TL;DR, we released the largest and most diverse driving video dataset with rich annotations called BDD100K. You can access the data for research now at http://bdd-data.berkeley.edu. We have recently released an arXiv report on it. And there is still time to participate in our CVPR 2018 challenges! Large-scale, Diverse
Left: Given movie poster, Right: New movie title generated by MC-GAN. Text is a prominent visual element of 2D design. Artists invest significant time into designing glyphs that are visually compatible with other elements in their shape and texture. This process is labor intensive and artists often design only the subset of glyphs that are necessary for a title or an annotation, which makes it dif
As machine learning algorithms and techniques have advanced, more and more machine learning applications require multiple machines and must exploit parallelism. However, the infrastructure for doing machine learning on clusters remains ad-hoc. While good solutions for specific use cases (e.g., parameter servers or hyperparameter search) and high-quality distributed systems outside of AI do exist (
Be careful what you reward “Be careful what you wish for!” – we’ve all heard it! The story of King Midas is there to warn us of what might happen when we’re not. Midas, a king who loves gold, runs into a satyr and wishes that everything he touches would turn to gold. Initially, this is fun and he walks around turning items to gold. But his happiness is short lived. Midas realizes the downsides of
A key aspect of intelligence is versatility – the capability of doing many different things. Current AI systems excel at mastering a single skill, such as Go, Jeopardy, or even helicopter aerobatics. But, when you instead ask an AI system to do a variety of seemingly simple problems, it will struggle. A champion Jeopardy program cannot hold a conversation, and an expert helicopter controller for a
Given only a single 2D image, humans are able to effortlessly infer the rich 3D structure of the underlying scene. Since inferring 3D from 2D is an ambiguous task by itself (see e.g. the left figure below), we must rely on learning from our past visual experiences. These visual experiences solely consist of 2D projections (as received on the retina) of the 3D world. Therefore, the learning signal
In Fall of 2021, the AI Admissions Committee stopped considering GRE Scores in making decisions. BAIR believes in diversity leading to better research and decision making and welcomes applicants of all backgrounds to apply. The Berkeley Artificial Intelligence Research (BAIR) Lab brings together UC Berkeley researchers across the areas of computer vision, machine learning, natural language process
このページを最初にブックマークしてみませんか?
『Berkeley Artificial Intelligence Research Lab』の新着エントリーを見る
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く