Iterative retrieval refers to the process in which the model continuously queries the retriever during generation to enhance the relevance of the retrieved knowledge, thereby improving the performance of Retrieval-Augmented Generation (RAG). Existing work typically employs few-shot prompting or manually constructed rules to implement iterative retrieval. This introduces additional inference overhead and overlooks the remarkable reasoning capabilities of Large Language Models (LLMs). In this paper, we introduce Auto-RAG, an autonomous iterative retrieval model centered on the LLM's powerful decision-making capabilities. Auto-RAG engages in multi-turn dialogues with the retriever, systematically planning retrievals and refining queries to acquire valuable knowledge. This process continues until sufficient external information is gathered, at which point the results are presented to the user. To this end, we develop a method for autonomously synthesizing reasoning-based decision-making instructions in iterative retrieval and fine-tuned the latest open-source LLMs. The experimental results indicate that Auto-RAG is capable of autonomous iterative interaction with the retriever, effectively leveraging the remarkable reasoning and decision-making abilities of LLMs, which lead to outstanding performance across six benchmarks. Further analysis reveals that Auto-RAG can autonomously adjust the number of iterations based on the difficulty of the questions and the utility of the retrieved knowledge, without requiring any human intervention. Moreover, Auto-RAG expresses the iterative retrieval process in natural language, enhancing interpretability while providing users with a more intuitive experience\footnote{Code is available at \url{https://github.com/ictnlp/Auto-RAG}.

Robots have the potential to enhance teaching of advanced computer science topics, making abstract concepts more tangible and interactive. In this paper, we present Timmy-a GoPiGo robot augmented with projections to demonstrate shortest path algorithms in an interactive learning environment. We integrated a JavaScript-based application that is projected around the robot, which allows users to construct graphs and visualise three different shortest path algorithms with colour-coded edges and vertices. Animated graph exploration and traversal are augmented by robot movements. To evaluate Timmy, we conducted two user studies. An initial study (= 10) to explore the feasibility of this type of teaching where participants were just observing both robot-synced and the on-screen-only visualisations. And a pilot study (= 6) where participants actively interacted with the system, constructed graphs and selected desired algorithms. In both studies we investigated the preferences towards the system and not the teaching outcome. Initial findings suggest that robots offer an engaging tool for teaching advanced algorithmic concepts, but highlight the need for further methodological refinements and larger-scale studies to fully evaluate their effectiveness.

Integrating renewable energy sources into the power grid is becoming increasingly important as the world moves towards a more sustainable energy future in line with SDG 7. However, the intermittent nature of renewable energy sources can make it challenging to manage the power grid and ensure a stable supply of electricity, which is crucial for achieving SDG 9. In this paper, we propose a deep learning-based approach for predicting energy demand in a smart power grid, which can improve the integration of renewable energy sources by providing accurate predictions of energy demand. Our approach aligns with SDG 13 on climate action, enabling more efficient management of renewable energy resources. We use long short-term memory networks, well-suited for time series data, to capture complex patterns and dependencies in energy demand data. The proposed approach is evaluated using four historical short-term energy demand data datasets from different energy distribution companies, including American Electric Power, Commonwealth Edison, Dayton Power and Light, and Pennsylvania-New Jersey-Maryland Interconnection. The proposed model is also compared with three other state-of-the-art forecasting algorithms: Facebook Prophet, Support Vector Regression, and Random Forest Regression. The experimental results show that the proposed REDf model can accurately predict energy demand with a mean absolute error of 1.4%, indicating its potential to enhance the stability and efficiency of the power grid and contribute to achieving SDGs 7, 9, and 13. The proposed model also has the potential to manage the integration of renewable energy sources in an effective manner.

Liquid democracy has gained popularity in recent years due to its ability to balance representation and delegation of power. In this work, we propose a generalization of the classic model that allows for fractional delegation of voting weight. Our approach enables agents to divide and delegate their votes to multiple agents, while retaining a portion of the voting power for themselves. We discuss the desirable properties of a reasonable generalization of the classic model and introduce a set of simpler voting measures that include a penalty factor on the length of delegation chains. We demonstrate that the proposed voting measure is a well-defined limit of these simpler measures when the penalty approaches zero, and inherits key features of the classic model. In the second part of the article, we investigate the existence of equilibrium states in a delegation game that employs the suggested measures. We show that this game has pure strategy Nash equilibria as long as a penalty on the length of delegation chains is enforced.

Large pretrained language models have recently conquered the area of natural language processing. As an alternative to predominant masked language modelling introduced in BERT, the T5 model has introduced a more general training objective, namely sequence to sequence transformation, which includes masked language model but more naturally fits text generation tasks such as machine translation, summarization, question answering, text simplification, dialogue systems, etc. The monolingual variants of T5 models have been limited to well-resourced languages, while the massively multilingual T5 model supports 101 languages. In contrast, we trained two different sized T5-type sequence to sequence models for morphologically rich Slovene language with much less resources and analyzed their behavior on 11 tasks. Concerning classification tasks, the SloT5 models mostly lag behind the monolingual Slovene SloBERTa model but are useful for the generative tasks.

Mathematical modelling of unemployment dynamics attempts to predict the probability of a job seeker finding a job as a function of time. This is typically achieved by using information in unemployment records. These records are right censored, making survival analysis a suitable approach for parameter estimation. The proposed model uses a deep artificial neural network (ANN) as a non-linear hazard function. Through embedding, high-cardinality categorical features are analysed efficiently. The posterior distribution of the ANN parameters are estimated using a variational Bayes method. The model is evaluated on a time-to-employment data set spanning from 2011 to 2020 provided by the Slovenian public employment service. It is used to determine the employment probability over time for each individual on the record. Similar models could be applied to other questions with multi-dimensional, high-cardinality categorical data including censored records. Such data is often encountered in personal records, for example in medical records.

Empirical data on real complex systems are becoming increasingly available. Parallel to this is the need for new methods of reconstructing (inferring) the topology of networks from time-resolved observations of their node-dynamics. The methods based on physical insights often rely on strong assumptions about the properties and dynamics of the scrutinized network. Here, we use the insights from machine learning to design a new method of network reconstruction that essentially makes no such assumptions. Specifically, we interpret the available trajectories (data) as features, and use two independent feature ranking approaches -- Random forest and RReliefF -- to rank the importance of each node for predicting the value of each other node, which yields the reconstructed adjacency matrix. We show that our method is fairly robust to coupling strength, system size, trajectory length and noise. We also find that the reconstruction quality strongly depends on the dynamical regime.

LJUBLJANA – Electrical equipment-producer Yaskawa, which is building an industrial robot factory in Slovenia, has decided to build another factory in the country to produce electrical components. The new factory will make inverter drives, servo drives and servo motors, Yaskawa said Monday. "Expanding our production capacity will enable us to further improve the supply chain, shorten our lead times and enhance the service for our European customers," Manfred Stern, head of Yaskawa Europe, said in a statement. Yaskawa did not reveal the value of the new investment, but according to local media it will be worth some €25 million ($30 million) and will create up to 250 new jobs. The company already makes industrial robot parts in Slovenia.