Search

Retrieval-Augmented Generation (RAG) enhances language models by retrieving and incorporating relevant external knowledge. However, traditional retrieve-and-generate processes may not be optimized for real-world scenarios, where queries might require multiple retrieval steps or none at all. In this paper, we propose a Probing-RAG, which utilizes the hidden state representations from the intermediate layers of language models to adaptively determine the necessity of additional retrievals for a given query. By employing a pre-trained prober, Probing-RAG effectively captures the model's internal cognition, enabling reliable decision-making about retrieving external documents. Experimental results across five open-domain QA datasets demonstrate that Probing-RAG outperforms previous methods while reducing the number of redundant retrieval steps., Comment: 6 figures, 13 tables

The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. These challenges aim to advance research across multiple themes in football, including broadcast video understanding, field understanding, and player understanding. This year, the challenges encompass four vision-based tasks. (1) Ball Action Spotting, focusing on precisely localizing when and which soccer actions related to the ball occur, (2) Dense Video Captioning, focusing on describing the broadcast with natural language and anchored timestamps, (3) Multi-View Foul Recognition, a novel task focusing on analyzing multiple viewpoints of a potential foul incident to classify whether a foul occurred and assess its severity, (4) Game State Reconstruction, another novel task focusing on reconstructing the game state from broadcast videos onto a 2D top-view map of the field. Detailed information about the tasks, challenges, and leaderboards can be found at https://www.soccer-net.org, with baselines and development kits available at https://github.com/SoccerNet., Comment: 7 pages, 1 figure

Layered two-dimensional (2D) semiconductors have shown enhanced ion migration capabilities along their van der Waals (vdW) gaps and on their surfaces. This effect can be employed for resistive switching (RS) in devices for emerging memories, selectors, and neuromorphic computing. To date, all lateral molybdenum disulfide (MoS${_2}$)-based volatile RS devices with silver (Ag) ion migration have been demonstrated using exfoliated, single-crystal MoS${_2}$ flakes requiring a forming step to enable RS. Here, we present volatile RS with multilayer MoS${_2}$ grown by metal-organic chemical vapor deposition (MOCVD) with repeatable forming-free operation. The devices show highly reproducible volatile RS with low operating voltages of approximately 2 V and fast switching times down to 130 ns considering their micrometer scale dimensions. We investigate the switching mechanism based on Ag ion surface migration through transmission electron microscopy, electronic transport modeling, and density functional theory. Finally, we develop a physics-based compact model and explore the implementation of our volatile memristors as artificial neurons in neuromorphic systems., Comment: 43 pages

FRBs are a newly discovered class of extragalactic radio transients characterised by their high energy and short-duration (~$\mu$s-ms)[1]. Their elusive physical origin remains a subject of ongoing research, with magnetars emerging as leading candidates[2],[3]. Previous studies have employed various methodologies to address the FRB origin problem, including demographic analyses of FRB host galaxies and their local environments[4]-[6], assessments of FRB rate evolution with redshift[7]-[9], and searches for proposed multi-messenger FRB counterparts[10]. However, these studies are susceptible to significant biases stemming from unaccounted radio and optical selection effects. Here we present empirical evidence for a substantial selection bias against detecting FRBs in galaxies with large inclination angles (edge-on) using a sample of hosts identified for FRBs discovered by untargeted surveys. This inclination-related bias likely leads to a significant underestimation (by about a factor of two) of the FRB rates reported in the literature and disfavours globular clusters as the dominant origin of FRB sources, as previously speculated[6]. These conclusions have important implications for FRB progenitor models and targeted FRB follow-up strategies. We further investigate the impact of this bias on the relative rate of FRBs in different host environments. Our analysis suggests that scattering in FRB hosts is likely responsible for the observed bias[11],[12]. However, a larger sample of localised FRBs is required to robustly quantify its contribution in the inclination-related selection bias., Comment: Accepted in Nature (in press)

Query rewriting aims to generate a new query that can complement the original query to improve the information retrieval system. Recent studies on query rewriting, such as query2doc, query2expand and querey2cot, rely on the internal knowledge of Large Language Models (LLMs) to generate a relevant passage to add information to the query. Nevertheless, the efficacy of these methodologies may markedly decline in instances where the requisite knowledge is not encapsulated within the model's intrinsic parameters. In this paper, we propose a novel structured query rewriting method called Crafting the Path tailored for retrieval systems. Crafting the Path involves a three-step process that crafts query-related information necessary for finding the passages to be searched in each step. Specifically, the Crafting the Path begins with Query Concept Comprehension, proceeds to Query Type Identification, and finally conducts Expected Answer Extraction. Experimental results show that our method outperforms previous rewriting methods, especially in less familiar domains for LLMs. We demonstrate that our method is less dependent on the internal parameter knowledge of the model and generates queries with fewer factual inaccuracies. Furthermore, we observe that \name{} demonstrates superior performance in the retrieval-augmented generation scenarios., Comment: 3 figures, 13 tables

People are relying on AI agents to assist them with various tasks. The human must know when to rely on the agent, collaborate with the agent, or ignore its suggestions. In this work, we propose to learn rules, grounded in data regions and described in natural language, that illustrate how the human should collaborate with the AI. Our novel region discovery algorithm finds local regions in the data as neighborhoods in an embedding space where prior human behavior should be corrected. Each region is then described using a large language model in an iterative and contrastive procedure. We then teach these rules to the human via an onboarding stage. Through user studies on object detection and question-answering tasks, we show that our method can lead to more accurate human-AI teams. We also evaluate our region discovery and description algorithms separately., Comment: NeurIPS 2023 Spotlight

Objectives: We propose a deep learning (DL) multi-task learning framework using convolutional neural network (CNN) for a direct conversion of single-energy CT (SECT) to three different parametric maps of dual-energy CT (DECT): Virtual-monochromatic image (VMI), effective atomic number (EAN), and relative electron density (RED). Methods: We propose VMI-Net for conversion of SECT to 70, 120, and 200 keV VMIs. In addition, EAN-Net and RED-Net were also developed to convert SECT to EAN and RED. We trained and validated our model using 67 patients collected between 2019 and 2020. SECT images with 120 kVp acquired by the DECT (IQon spectral CT, Philips) were used as input, while the VMIs, EAN, and RED acquired by the same device were used as target. The performance of the DL framework was evaluated by absolute difference (AD) and relative difference (RD). Results: The VMI-Net converted 120 kVp SECT to the VMIs with AD of 9.02 Hounsfield Unit, and RD of 0.41% compared to the ground truth VMIs. The ADs of the converted EAN and RED were 0.29 and 0.96, respectively, while the RDs were 1.99% and 0.50% for the converted EAN and RED, respectively. Conclusions: SECT images were directly converted to the three parametric maps of DECT (i.e., VMIs, EAN, and RED). By using this model, one can generate the parametric information from SECT images without DECT device. Our model can help investigate the parametric information from SECT retrospectively. Advances in knowledge: Deep learning framework enables converting SECT to various high-quality parametric maps of DECT., Comment: 29 pages, 17 figures

The age and stroke-associated decline in musculoskeletal strength degrades the ability to perform daily human tasks using the upper extremities. Although there are a few examples of exoskeletons, they need manual operations due to the absence of sensor feedback and no intention prediction of movements. Here, we introduce an intelligent upper-limb exoskeleton system that uses cloud-based deep learning to predict human intention for strength augmentation. The embedded soft wearable sensors provide sensory feedback by collecting real-time muscle signals, which are simultaneously computed to determine the user's intended movement. The cloud-based deep-learning predicts four upper-limb joint motions with an average accuracy of 96.2% at a 200-250 millisecond response rate, suggesting that the exoskeleton operates just by human intention. In addition, an array of soft pneumatics assists the intended movements by providing 897 newton of force and 78.7 millimeter of displacement at maximum. Collectively, the intent-driven exoskeleton can augment human strength by 5.15 times on average compared to the unassisted exoskeleton. This report demonstrates an exoskeleton robot that augments the upper-limb joint movements by human intention based on a machine-learning cloud computing and sensory feedback., Comment: 15 pages, 6 figures, 1 table, published in npj flexible electronics journals