While large language models (LLMs) have demonstrated impressive capabilities across tasks in language understanding and interactive decision making, their abilities for reasoning (e.g. chain-of-thought prompting) and acting (e.g. action plan generation) have primarily been studied as separate topics. In this paper, we explore the use of LLMs to generate both reasoning traces and task-specific actions in an interleaved manner, allowing for greater synergy between the two: reasoning traces help the model induce, track, and update action plans as well as handle exceptions, while actions allow it to interface with external sources, such as knowledge bases or environments, to gather additional information. We apply our approach, named ReAct, to a diverse set of language and decision making tasks and demonstrate its effectiveness over state-of-the-art baselines, as well as improved human interpretability and trustworthiness over methods without reasoning or acting components. Concretely, on question answering (HotpotQA) and fact verification (Fever), ReAct overcomes issues of hallucination and error propagation prevalent in chain-of-thought reasoning by interacting with a simple Wikipedia API, and generates human-like task-solving trajectories that are more interpretable than baselines without reasoning traces. On two interactive decision making benchmarks (ALFWorld and WebShop), ReAct outperforms imitation and reinforcement learning methods by an absolute success rate of 34% and 10% respectively, while being prompted with only one or two in-context examples. Project site with code: https://react-lm.github.io

Global warming is an urgent issue that is generating catastrophic environmental changes, such as the melting of sea ice and glaciers, particularly in the polar regions. The melting pattern and retreat of polar sea ice cover is an essential indicator of global warming. The Sentinel-2 satellite (S2) captures high-resolution optical imagery over the polar regions. This research aims at developing a robust and effective system for classifying polar sea ice as thick or snow-covered, young or thin, or open water using S2 images. A key challenge is the lack of labeled S2 training data to serve as the ground truth. We demonstrate a method with high precision to segment and automatically label the S2 images based on suitably determined color thresholds and employ these auto-labeled data to train a U-Net machine model (a fully convolutional neural network), yielding good classification accuracy. Evaluation results over S2 data from the polar summer season in the Ross Sea region of the Antarctic show that the U-Net model trained on auto-labeled data has an accuracy of 90.18% over the original S2 images, whereas the U-Net model trained on manually labeled data has an accuracy of 91.39%. Filtering out the thin clouds and shadows from the S2 images further improves U-Net's accuracy, respectively, to 98.97% for auto-labeled and 98.40% for manually labeled training datasets.

Honor exists to expand the world's capacity to care. We're combining high tech with high-touch to deliver better home care for aging adults, better jobs for Care Professionals, and entirely new offerings to support the aging journey, at scale. Founded in 2014, and now a Series E funded "Unicorn" valued at over $1B, Honor leads the world's largest home care network with the most advanced care platform. Our August 2021 acquisition of Home Instead has created a global company that's revolutionizing how society cares for older adults, their families, and Care Professionals. The Honor Care Platform combines local care and the most advanced technology to bring the highest quality care to more aging adults.

The use of ground control points (GCPs) for georeferencing is the most common strategy in unmanned aerial vehicle (UAV) photogrammetry, but at the same time their collection represents the most time-consuming and expensive part of UAV campaigns. Recently, deep learning has been rapidly developed in the field of small object detection. In this letter, to automatically extract coordinates information of ground control points (GCPs) by detecting GCP-markers in UAV images, we propose a solution that uses a deep learning-based architecture, YOLOv5-OBB, combined with a confidence threshold filtering algorithm and an optimal ranking algorithm. We applied our proposed method to a dataset collected by DJI Phantom 4 Pro drone and obtained good detection performance with the mean Average Precision (AP) of 0.832 and the highest AP of 0.982 for the cross-type GCP-markers. The proposed method can be a promising tool for future implementation of the end-to-end aerial triangulation process.

Fleets of networked autonomous vehicles (AVs) collect terabytes of sensory data, which is often transmitted to central servers (the ''cloud'') for training machine learning (ML) models. Ideally, these fleets should upload all their data, especially from rare operating contexts, in order to train robust ML models. However, this is infeasible due to prohibitive network bandwidth and data labeling costs. Instead, we propose a cooperative data sampling strategy where geo-distributed AVs collaborate to collect a diverse ML training dataset in the cloud. Since the AVs have a shared objective but minimal information about each other's local data distribution and perception model, we can naturally cast cooperative data collection as an $N$-player mathematical game. We show that our cooperative sampling strategy uses minimal information to converge to a centralized oracle policy with complete information about all AVs. Moreover, we theoretically characterize the performance benefits of our game-theoretic strategy compared to greedy sampling. Finally, we experimentally demonstrate that our method outperforms standard benchmarks by up to $21.9\%$ on 4 perception datasets, including for autonomous driving in adverse weather conditions. Crucially, our experimental results on real-world datasets closely align with our theoretical guarantees.

Chain-of-thought (CoT) prompting enables large language models (LLMs) to solve complex reasoning tasks by generating an explanation before the final prediction. Despite it's promising ability, a critical downside of CoT prompting is that the performance is greatly affected by the factuality of the generated explanation. To improve the correctness of the explanations, fine-tuning language models with explanation data is needed. However, there exists only a few datasets that can be used for such approaches, and no data collection tool for building them. Thus, we introduce CoTEVer, a tool-kit for annotating the factual correctness of generated explanations and collecting revision data of wrong explanations. Figure 1: Example of Explanation Verification and Answer Furthermore, we suggest several use cases Verification of GPT-3's output. Explanation Verification where the data collected with CoTEVer can requires additional knowledge which makes it be utilized for enhancing the faithfulness of hard for annotators to intuitively write a revised explanation explanations. Our toolkit is publicly available and answer.

Eigenvector Research, Inc. is pleased to announce our 17th annual Eigenvector University. EigenU 2023 includes 16 short courses in chemical data science, i.e. chemometrics. This includes mathematical, statistical, machine learning and artificial intelligence methods as applied to problems in the analysis of data from chemistry and the life sciences. The courses are held in Seattle, USA at the Washington Athletic Club. EigenU also includes a Workshop Dinner, and a PowerUser Tips, Tricks & Poster Session.

Traffic prediction is a flourishing research field due to its importance in human mobility in the urban space. Despite this, existing studies only focus on short-term prediction of up to few hours in advance, with most being up to one hour only. Long-term traffic prediction can enable more comprehensive, informed, and proactive measures against traffic congestion and is therefore an important task to explore. In this paper, we explore the task of long-term traffic prediction; where we predict traffic up to 24 hours in advance. We note the weaknesses of existing models--which are based on recurrent structures--for long-term traffic prediction and propose a modified Transformer model "TrafFormer". Experiments comparing our model with existing hybrid neural network models show the superiority of our model.

LATMOS-IPSL, Université Paris-Saclay, UVSQ, CNRS, 78280, Guyancourt, France *Météo-France, Avenue Coriolis, Toulouse Abstract-- Retrieval of rain from Passive Microwave from about 52,000 images to about 103,000 allowing us radiometers data has been a challenge ever since the to build a training database of 70,000 images for training launch of the first Defense Meteorological Satellite and 33,000 images for validation. Enormous progress has been years 2014 to 2018 and a few months from 2020 and made since the launch of the Tropical Rainfall 2021 are used but the whole year 2019 was kept separate Measuring Mission (TRMM) in 1997 but until for the performance assessment (test) and most results recently the data were processed pixel-by-pixel or presented hereafter are computed for that year. Deep large database is meant to dampen the effects of learning has obtained remarkable improvement in seasonal and interannual variability of rain. the computer vision field, and offers a whole new Second, DRAIN retrieves now a set of 99 quantiles way to tackle the rain retrieval problem. The Global instead of a simple averaged rain rate as in [1]. These Precipitation Measurement (GPM) Core satellite quantiles represent the probability that the rain rate is carries similarly to TRMM, a passive microwave below a certain threshold.

Correlated time series (CTS) forecasting plays an essential role in many practical applications, such as traffic management and server load control. Many deep learning models have been proposed to improve the accuracy of CTS forecasting. However, while models have become increasingly complex and computationally intensive, they struggle to improve accuracy. Pursuing a different direction, this study aims instead to enable much more efficient, lightweight models that preserve accuracy while being able to be deployed on resource-constrained devices. To achieve this goal, we characterize popular CTS forecasting models and yield two observations that indicate directions for lightweight CTS forecasting. On this basis, we propose the LightCTS framework that adopts plain stacking of temporal and spatial operators instead of alternate stacking that is much more computationally expensive. Moreover, LightCTS features light temporal and spatial operator modules, called L-TCN and GL-Former, that offer improved computational efficiency without compromising their feature extraction capabilities. LightCTS also encompasses a last-shot compression scheme to reduce redundant temporal features and speed up subsequent computations. Experiments with single-step and multi-step forecasting benchmark datasets show that LightCTS is capable of nearly state-of-the-art accuracy at much reduced computational and storage overheads.