SUI

https://arxiv.org/abs/2306.14884 Learning to Modulate pre-trained Models in RL Reinforcement Learning (RL) has been successful in various domains like robotics, game playing, and simulation. While RL agents have shown impressive capabilities in their specific tasks, they insufficiently adapt to new tasks. In supervised learning, this arxiv.org 1. 강화 학습(RL)은 로봇 공학, 게임 플레이, 시뮬레이션 등 다양한 분야에서 성공적으로 ..

https://arxiv.org/abs/2306.14824 Kosmos-2: Grounding Multimodal Large Language Models to the World We introduce Kosmos-2, a Multimodal Large Language Model (MLLM), enabling new capabilities of perceiving object descriptions (e.g., bounding boxes) and grounding text to the visual world. Specifically, we represent refer expressions as links in Markdown, i arxiv.org https://github.com/microsoft/uni..

https://www.ft.com/content/732fc372-67ea-4684-9ab7-6b6f3cdfd736 Aidan Gomez: AI threat to human existence is ‘absurd’ distraction from real risks Co-founder of Cohere says we should be more worried about use of artificial intelligence in social media and medicine www.ft.com 코헤어의 공동 창업자이자 CEO인 에이든 고메즈는 인공지능(AI)에 대한 과도한 두려움이 실제 기술 문제로부터 우리를 방해하고 있다고 주장합니다. 그는 슈퍼인공지능(AGI)에 의한 인류 멸망에 대한 논의는 우리 시간과 공..

https://arxiv.org/abs/2306.12554 Improving Long-Horizon Imitation Through Instruction Prediction Complex, long-horizon planning and its combinatorial nature pose steep challenges for learning-based agents. Difficulties in such settings are exacerbated in low data regimes where over-fitting stifles generalization and compounding errors hurt accuracy. I arxiv.org https://github.com/jhejna/instruct..

https://arxiv.org/abs/2306.12925 AudioPaLM: A Large Language Model That Can Speak and Listen We introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that c arxiv.org https://google-research.github.io/sean..

https://bounded-regret.ghost.io/future-ml-systems-will-be-qualitatively-different/ Future ML Systems Will Be Qualitatively Different In 1972, the Nobel prize-winning physicist Philip Anderson wrote the essay " More Is Different [https://science.sciencemag.org/content/177/4047/393]". In it, he argues that quantitative changes can lead to qualitatively different and unexpected phenomena. bounded-r..

https://arxiv.org/abs/2306.10190 ALP: Action-Aware Embodied Learning for Perception Current methods in training and benchmarking vision models exhibit an over-reliance on passive, curated datasets. Although models trained on these datasets have shown strong performance in a wide variety of tasks such as classification, detection, and segm arxiv.org 1. 현재의 시각 모델 학습 및 벤치마킹 방법은 수동적이고 선별된 데이터셋에 과도하게..

https://arxiv.org/abs/2306.11530 Intersectionality in Conversational AI Safety: How Bayesian Multilevel Models Help Understand Diverse Perceptions of Safety Conversational AI systems exhibit a level of human-like behavior that promises to have profound impacts on many aspects of daily life -- how people access information, create content, and seek social support. Yet these models have also shown..

https://www.deepmind.com/blog/robocat-a-self-improving-robotic-agent RoboCat: A self-improving robotic agent Robots are quickly becoming part of our everyday lives, but they’re often only programmed to perform specific tasks well. While harnessing recent advances in AI could lead to robots that could help in many more ways, progress in building general-purpose www.deepmind.com https://storage.go..

https://arxiv.org/abs/2306.09800 $\pi2\text{vec}$: Policy Representations with Successor Features This paper describes $\pi2\text{vec}$, a method for representing behaviors of black box policies as feature vectors. The policy representations capture how the statistics of foundation model features change in response to the policy behavior in a task agno arxiv.org 1. 이 논문은 행동의 특징 벡터로 블랙박스 정책을 표현하는..