SUI

https://arxiv.org/abs/2306.09539 Block-State Transformer State space models (SSMs) have shown impressive results on tasks that require modeling long-range dependencies and efficiently scale to long sequences owing to their subquadratic runtime complexity. Originally designed for continuous signals, SSMs have sho arxiv.org 1. 상태 공간 모델(SSM)은 장기적인 의존성을 모델링하는 데 필요한 작업에서 뛰어난 결과를 보여주며, 서브쿼드럴릭 실행 시간 복잡..

https://arxiv.org/abs/2306.09479 Inverse Scaling: When Bigger Isn't Better Work on scaling laws has found that large language models (LMs) show predictable improvements to overall loss with increased scale (model size, training data, and compute). Here, we present evidence for the claim that LMs may show inverse scaling, or worse arxiv.org 1. 대형 언어 모델(LM)에 대한 연구에서는 모델 크기, 훈련 데이터, 계산량 등이 증가함에 따라 ..

https://world-from-eyes.github.io/ Seeing the World through Your Eyes Abstract The reflective nature of the human eye is an underappreciated source of information about what the world around us looks like. By imaging the eyes of a moving person, we can collect multiple views of a scene outside the camera's direct line-of-sig world-from-eyes.github.io

https://language-to-reward.github.io/ 설명: https://twitter.com/xf1280/status/1669765756823941121 https://arxiv.org/abs/2306.08647 Language to Rewards for Robotic Skill Synthesis Large language models (LLMs) have demonstrated exciting progress in acquiring diverse new capabilities through in-context learning, ranging from logical reasoning to code-writing. Robotics researchers have also explored u..

https://arxiv.org/abs/2306.09299 Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Theory of Mind Large Language Models (LLMs) perform complex reasoning by generating explanations for their predictions. However, a complementary goal of explanations is to also communicate useful knowledge that improves weaker agents. Hence, we investigate whether LLMs a arxiv.org ..

https://arxiv.org/abs/2306.06070 Mind2Web: Towards a Generalist Agent for the Web We introduce Mind2Web, the first dataset for developing and evaluating generalist agents for the web that can follow language instructions to complete complex tasks on any website. Existing datasets for web agents either use simulated websites or only cove arxiv.org https://osu-nlp-group.github.io/Mind2Web/ Mind2We..

https://arxiv.org/abs/2306.07915 Image Captioners Are Scalable Vision Learners Too Contrastive pretraining on image-text pairs from the web is one of the most popular large-scale pretraining strategies for vision backbones, especially in the context of large multimodal models. At the same time, image captioning on this type of data is co arxiv.org 1. 웹에서 이미지-텍스트 쌍에 대한 대조적 사전학습은, 특히 대형 다중모달 모델의 맥..

https://arxiv.org/abs/2306.04031 Certified Reasoning with Language Models Language models often achieve higher accuracy when reasoning step-by-step in complex tasks. However, their reasoning can be unsound, inconsistent, or rely on undesirable prior assumptions. To tackle these issues, we introduce a class of tools for language arxiv.org 1. 언어 모델은 복잡한 작업에서 단계별로 추론을 할 때 종종 더 높은 정확도를 보입니다. 그러나 그들의..

https://www.deepmind.com/blog/alphadev-discovers-faster-sorting-algorithms AlphaDev discovers faster sorting algorithms In our paper published today in Nature, we introduce AlphaDev, an artificial intelligence (AI) system that uses reinforcement learning to discover enhanced computer science algorithms – surpassing those honed by scientists and engineers over decades. www.deepmind.com DeepMind의 ..

https://arxiv.org/abs/2306.01711 OMNI: Open-endedness via Models of human Notions of Interestingness Open-ended algorithms aim to learn new, interesting behaviors forever. That requires a vast environment search space, but there are thus infinitely many possible tasks. Even after filtering for tasks the current agent can learn (i.e., learning progress), c arxiv.org https://twitter.com/jeffclune/..