This paper investigates the problem of controlling a linear system under possibly unbounded and degenerate noise with unknown cost functions, known as an online control problem. In contrast to the existing work, which assumes the boundedness of noise, we reveal that for convex costs, an $ \widetilde{O}(\sqrt{T}) $ regret bound can be achieved even for unbounded noise, where $ T $ denotes the time horizon. Moreover, when the costs are strongly convex, we establish an $ O({\rm poly} (\log T)) $ regret bound without the assumption that noise covariance is non-degenerate, which has been required in the literature. The key ingredient in removing the rank assumption on noise is a system transformation associated with the noise covariance. This simultaneously enables the parameter reduction of an online control algorithm.

Optimization problems are pervasive in sectors from manufacturing and distribution to healthcare. However, most such problems are still solved heuristically by hand rather than optimally by state-of-the-art solvers because the expertise required to formulate and solve these problems limits the widespread adoption of optimization tools and techniques. This paper introduces OptiMUS, a Large Language Model (LLM)-based agent designed to formulate and solve (mixed integer) linear programming problems from their natural language descriptions. OptiMUS can develop mathematical models, write and debug solver code, evaluate the generated solutions, and improve its model and code based on these evaluations. OptiMUS utilizes a modular structure to process problems, allowing it to handle problems with long descriptions and complex data without long prompts. Experiments demonstrate that OptiMUS outperforms existing state-of-the-art methods on easy datasets by more than $20\%$ and on hard datasets (including a new dataset, NLP4LP, released with this paper that features long and complex problems) by more than $30\%$.

All text-based language problems can be reduced to either generation or embedding. Current models only perform well at one or the other. We introduce generative representational instruction tuning (GRIT) whereby a large language model is trained to handle both generative and embedding tasks by distinguishing between them through instructions. Compared to other open models, our resulting GritLM 7B sets a new state of the art on the Massive Text Embedding Benchmark (MTEB) and outperforms all models up to its size on a range of generative tasks. By scaling up further, GritLM 8x7B outperforms all open generative language models that we tried while still being among the best embedding models. Notably, we find that GRIT matches training on only generative or embedding data, thus we can unify both at no performance loss. Among other benefits, the unification via GRIT speeds up Retrieval-Augmented Generation (RAG) by > 60% for long documents, by no longer requiring separate retrieval and generation models. Models, code, etc. are freely available at https://github.com/ContextualAI/gritlm.

A key component of any robot is the interface between ROS2 software and physical motors. New robots often use arbitrary, messy mixtures of closed and open motor drivers and error-prone physical mountings, wiring, and connectors to interface them. There is a need for a standardizing OSH component to abstract this complexity, as Arduino did for interfacing to smaller components. We present a OSH printed circuit board to solve this problem once and for all. On the high-level side, it interfaces to Arduino Giga -- acting as an unusually large and robust shield -- and thus to existing open source ROS software stacks. On the lower-level side, it interfaces to existing emerging standard open hardware including OSH motor drivers and relays, which can already be used to drive fully open hardware wheeled and arm robots. This enables the creation of a family of standardized, fully open hardware, fully reproducible, research platforms.

This study explores the potential of fine-tuning foundational English Large Language Models (LLMs) for generating Polish text. The first step involves Language Adaptive Pre-training (LAPT) on a high-quality dataset of 3.11 GB, consisting of 276 million Polish tokens. The LAPT is followed by additional fine-tuning aimed at solving nine KLEJ challenges. Our trained model Curie-7B-v1 not only generates Polish text with the lowest perplexity of 3.02 among decoder-based Polish models but also closely rivals the performance of the best Polish encoder-decoder models with a less than 2% gap on 8 out of 9 tasks. Curie-7B-v1 used approximately 2-3% of a typical dataset size to learn Polish. The LAPT was completed in less than five days using a consumer GPU, highlighting the method's efficiency. The proficiency of the model in Polish was significantly enhanced, demonstrating the viability of this approach for adding new languages to existing LLMs by training just 1.2% of its parameters. To contribute to the community's collaborative progress, the model has been released as open-source.

While carbon dioxide gets the lion's share of attention when it comes to global warming, there are other factors at play. Methane is responsible for about 30 percent of the rise in global temperatures since the Industrial Revolution, according to the International Energy Agency. Identifying and mitigating these emissions is said to be one of the most critical actions we can take in the short term to combat climate change. To that end, Google and the Environmental Defense Fund (EDF) have once again teamed up to tackle the issue. The pair previously mapped methane leaks in major cities using sensors on Street View cars.

Once in orbit, MethaneSAT's software and spectrometers, which measure different wavelengths of light to detect methane, will pinpoint both concentrated locations for methane plumes as well as the broader areas where the gases diffuse and spread. It will also use Google's image detection algorithms to create the first comprehensive, global map of the oil and gas industry's infrastructure, like pump jacks and storage tanks, where leaks most commonly occur. "Once those maps are lined up, we expect people will be able to have a far better understanding of the types of machinery that contribute most to methane leaks," says Yael Maguire, who leads geo-sustainability efforts at Google. This tool could solve a significant stumbling block for methane researchers, according to Rob Jackson, professor of Earth system science at Stanford. There are millions of oil and gas operations around the world, and information about where many of these facilities are located is tightly guarded, and where available, expensive to access.

With the massive proliferation of data-driven algorithms, such as deep learning-based approaches, the availability of high-quality data is of great interest. Volumetric data is very important in medicine, as it ranges from disease diagnoses to therapy monitoring. When the dataset is sufficient, models can be trained to help doctors with these tasks. Unfortunately, there are scenarios where large amounts of data is unavailable. For example, rare diseases and privacy issues can lead to restricted data availability. In non-medical fields, the high cost of obtaining enough high-quality data can also be a concern. A solution to these problems can be the generation of realistic synthetic data using Generative Adversarial Networks (GANs). The existence of these mechanisms is a good asset, especially in healthcare, as the data must be of good quality, realistic, and without privacy issues. Therefore, most of the publications on volumetric GANs are within the medical domain. In this review, we provide a summary of works that generate realistic volumetric synthetic data using GANs. We therefore outline GAN-based methods in these areas with common architectures, loss functions and evaluation metrics, including their advantages and disadvantages. We present a novel taxonomy, evaluations, challenges, and research opportunities to provide a holistic overview of the current state of volumetric GANs.

Time-series data originate from various applications that describe specific observations or quantities of interest over time. Their analysis often involves the comparison across different time-series data sequences, which in turn requires the alignment of these sequences. Dynamic Time Warping (DTW) is the standard approach to achieve an optimal alignment between two temporal signals. Different variations of DTW have been proposed to address various needs for signal alignment or classifications. However, a comprehensive evaluation of their performance in these time-series data processing tasks is lacking. Most DTW measures perform well on certain types of time-series data without a clear explanation of the reason. To address that, we propose a synthesis framework to model the variation between two time-series data sequences for comparison. Our synthesis framework can produce a realistic initial signal and deform it with controllable variations that mimic real-world scenarios. With this synthesis framework, we produce a large number of time-series sequence pairs with different but known variations, which are used to assess the performance of a number of well-known DTW measures for the tasks of alignment and classification. We report their performance on different variations and suggest the proper DTW measure to use based on the type of variations between two time-series sequences. This is the first time such a guideline is presented for selecting a proper DTW measure. To validate our conclusion, we apply our findings to real-world applications, i.e., the detection of the formation top for the oil and gas industry and the pattern search in streamlines for flow visualization.

In Chaos, a minor divergence between two initial conditions exhibits exponential amplification over time, leading to far-away outcomes, known as the butterfly effect. Thus, the distant future is full of uncertainty and hard to forecast. We introduce Group Reservoir Transformer to predict long-term events more accurately and robustly by overcoming two challenges in Chaos: (1) the extensive historical sequences and (2) the sensitivity to initial conditions. A reservoir is attached to a Transformer to efficiently handle arbitrarily long historical lengths, with an extension of a group of reservoirs to reduce the uncertainty due to the initialization variations. Our architecture consistently outperforms state-of-the-art DNN models in multivariate time series, including NLinear, Pyformer, Informer, Autoformer, and the baseline Transformer, with an error reduction of up to -89.43\% in various fields such as ETTh, ETTm, and air quality, demonstrating that an ensemble of butterfly learning, the prediction can be improved to a more adequate and certain one, despite of the traveling time to the unknown future.