This paper describes a novel approach to adaptive manufacturing in the context of small batch production and customization. It focuses on integrating task-level planning and reasoning with reinforcement learning (RL) in the SkiROS2 skill-based robot control platform. This integration enhances the efficiency and adaptability of robotic systems in manufacturing, enabling them to adjust to task variations and learn from interaction data. The paper highlights the architecture of SkiROS2, particularly its world model, skill libraries, and task management. It demonstrates how combining RL with robotic manipulators can learn and improve the execution of industrial tasks. It advocates a multi-objective learning model that eases the learning problem design. The approach can incorporate user priors or previous experiences to accelerate learning and increase safety. Spotlight video: https://youtu.be/H5PmZl2rRbs?si=8wmZ-gbwuSJRxe3S&t=1422 SkiROS2 code: https://github.com/RVMI/skiros2 SkiROS2 talk at ROSCon: https://vimeo.com/879001825/2a0e9d5412 SkiREIL code: https://github.com/matthias-mayr/SkiREIL

Unfortunately, to over 40 million people across West African countries date, there isn't any usable machine translation including Mali, Guinea, Ivory Coast, Gambia, (MT) system for Nko, in part due to the unavailability Burkina Faso, Sierra Leone, Senegal, Liberia, and of large text corpora required by state-of-the-art Guinea-Bissau. Nko, which means'I say' in all neural machine translation (NMT) algorithms. Manding languages, was developed as both the Nko is a representative case study of the broader Manding literary standard language and a writing issues that interfere with the goal of universal machine system by Soulemana Kanté in 1949 for the translation. Thousands of languages still purpose of sustaining the strong oral tradition of don't have available or usable MT systems, mainly Manding languages (Niane, 1974; Conde, 2017; due to the unavailability of high-quality parallel Eberhard et al., 2023).

While its recent ascent to prominence is notable, tools for QML are extensions of low-level quantum computing the roots of ML extend back to the early 1960s [2], reflecting packages that require exhaustive knowledge in quantum a path of varied progress and challenges. Besides some initial computing and ML and often require manipulations on the set-backs [3] the foundations of today's deep neural networks qubit level [14-18]. In this work, we aim to bridge the gap that drive a lot of the recent advancements have already for the success factor (c) and introduce sQUlearn, an easy-touse been established almost half a century ago [4, 5]. The reasons and NISQ-ready python library for QML which aims to for the accelerated breakthroughs of the past decade are essentially democratizing access to QML. threefold: (a) an increased computational resources, (b) the availability of large-scale data, and (c) the emergence Given the close relationship between the fields of ML and of development tools that abstract away low-level complexity. QML, we strive for high compatibility with already available While these factors have enabled remarkable breakthroughs, tools.

With the rapid development of large language models (LLMs) and their integration into large multimodal models (LMMs), there has been impressive progress in zero-shot completion of user-oriented vision-language tasks. However, a gap remains in the domain of chart image understanding due to the distinct abstract components in charts. To address this, we introduce a large-scale MultiModal Chart Instruction (MMC-Instruction) dataset comprising 600k instances supporting diverse tasks and chart types. Leveraging this data, we develop MultiModal Chart Assistant (MMCA), an LMM that achieves state-of-the-art performance on existing chart QA benchmarks. Recognizing the need for a comprehensive evaluation of LMM chart understanding, we also propose a MultiModal Chart Benchmark (MMC-Benchmark), a comprehensive human-annotated benchmark with 9 distinct tasks evaluating reasoning capabilities over charts. Extensive experiments on MMC-Benchmark reveal the limitations of existing LMMs on correctly interpreting charts, even for the most recent GPT-4V model. Our work provides an instruction-tuning methodology and benchmark to advance multimodal understanding of charts.

Eliciting feedback from end users of NLP models can be beneficial for improving models. However, how should we present model responses to users so they are most amenable to be corrected from user feedback? Further, what properties do users value to understand and trust responses? We answer these questions by analyzing the effect of rationales generated by QA models to support their answers. We specifically consider decomposed question-answering models that first extract an intermediate rationale based on a context and a question and then use solely this rationale to answer the question. A rationale outlines the approach followed by the model to answer the question. Our work considers various formats of these rationales that vary according to well-defined properties of interest. We sample these rationales from large language models using few-shot prompting for two reading comprehension datasets, and then perform two user studies. In the first one, we present users with incorrect answers and corresponding rationales of various formats and ask them to provide natural language feedback to revise the rationale. We then measure the effectiveness of this feedback in patching these rationales through in-context learning. The second study evaluates how well different rationale formats enable users to understand and trust model answers, when they are correct. We find that rationale formats significantly affect how easy it is (1) for users to give feedback for rationales, and (2) for models to subsequently execute this feedback. In addition to influencing critiquablity, certain formats significantly enhance user reported understanding and trust of model outputs.

Existing open-source helpfulness preference datasets do not specify what makes some responses more helpful and others less so. Models trained on these datasets can incidentally learn to model dataset artifacts (e.g. preferring longer but unhelpful responses only due to their length). To alleviate this problem, we collect HelpSteer, a multi-attribute helpfulness dataset annotated for the various aspects that make responses helpful. Specifically, our 37k-sample dataset has annotations for correctness, coherence, complexity, and verbosity in addition to overall helpfulness of responses. Training Llama 2 70B using the HelpSteer dataset with SteerLM technique produces a model that scores 7.54 on MT Bench, which is currently the highest score for open models that do not require training data from more powerful models (e.g. GPT4). We release this dataset with CC-BY-4.0 license at https://huggingface.co/datasets/nvidia/HelpSteer

Scientific jargon can impede researchers when they read materials from other domains. Current methods of jargon identification mainly use corpus-level familiarity indicators (e.g., Simple Wikipedia represents plain language). However, researchers' familiarity of a term can vary greatly based on their own background. We collect a dataset of over 10K term familiarity annotations from 11 computer science researchers for terms drawn from 100 paper abstracts. Analysis of this data reveals that jargon familiarity and information needs vary widely across annotators, even within the same sub-domain (e.g., NLP). We investigate features representing individual, sub-domain, and domain knowledge to predict individual jargon familiarity. We compare supervised and prompt-based approaches, finding that prompt-based methods including personal publications yields the highest accuracy, though zero-shot prompting provides a strong baseline. This research offers insight into features and methods to integrate personal data into scientific jargon identification.

Evaluating retrieval-augmented generation (RAG) systems traditionally relies on hand annotations for input queries, passages to retrieve, and responses to generate. We introduce ARES, an Automated RAG Evaluation System, for evaluating RAG systems along the dimensions of context relevance, answer faithfulness, and answer relevance. Using synthetic training data, ARES finetunes lightweight LM judges to assess the quality of individual RAG components. To mitigate potential prediction errors, ARES utilizes a small set of human-annotated datapoints for prediction-powered inference (PPI). Across six different knowledge-intensive tasks in KILT and SuperGLUE, ARES accurately evaluates RAG systems while using a few hundred human annotations during evaluation. Furthermore, ARES judges remain effective across domain shifts, proving accurate even after changing the type of queries and/or documents used in the evaluated RAG systems. We make our datasets and code for replication and deployment available at https://github.com/stanford-futuredata/ARES.

Large Language Models (LLMs) have been demonstrating the ability to solve complex tasks by delivering answers that are positively evaluated by humans due in part to the intensive use of human feedback that refines responses. However, the suggestibility transmitted through human feedback increases the inclination to produce responses that correspond to the user's beliefs or misleading prompts as opposed to true facts, a behaviour known as sycophancy. This phenomenon decreases the bias, robustness, and, consequently, their reliability. In this paper, we shed light on the suggestibility of LLMs to sycophantic behaviour, demonstrating these tendencies via human-influenced prompts over different tasks. Our investigation reveals that LLMs show sycophantic tendencies when responding to queries involving subjective opinions and statements that should elicit a contrary response based on facts, demonstrating a lack of robustness.

In this work, we address the problem of assessing and constructing feedback for early-stage writing automatically using machine learning. Early-stage writing is typically vastly different from conventional writing due to phonetic spelling and lack of proper grammar, punctuation, spacing etc. Consequently, early-stage writing is highly non-trivial to analyze using common linguistic metrics. We propose to use sequence-to-sequence models for "translating" early-stage writing by students into "conventional" writing, which allows the translated text to be analyzed using linguistic metrics. Furthermore, we propose a novel robust likelihood to mitigate the effect of noise in the dataset. We investigate the proposed methods using a set of numerical experiments and demonstrate that the conventional text can be predicted with high accuracy.