In these politically divisive times, there's one thing we all agree on--we don't want a giant data center in our backyard. Behold, the hyperscale data center! Massive structures, with thousands of specialized computer chips running in parallel to perform the complex calculations required by advanced AI models. A single facility can cover millions of square feet, built with millions of pounds of steel, aluminum, and concrete; feature hundreds of miles of wiring, connecting some hundreds of thousands of high-end GPU chips, and chewing through hundreds of megawatt-hours of electricity. These facilities run so hot from all that computing power that their cooling systems are triumphs of engineering complexity in themselves. But the star of the show are those chips with their advanced processors.

Long-Context Question Answering (LCQA), a challenging task, aims to reason over long-context documents to yield accurate answers to questions. Existing long-context Large Language Models (LLMs) for LCQA often struggle with the "lost in the middle" issue. Retrieval-Augmented Generation (RAG) mitigates this issue by providing external factual evidence. However, its chunking strategy disrupts the global long-context information, and its low-quality retrieval in long contexts hinders LLMs from identifying effective factual details due to substantial noise. To this end, we propose LongRAG, a general, dual-perspective, and robust LLM-based RAG system paradigm for LCQA to enhance RAG's understanding of complex long-context knowledge (i.e., global information and factual details). We design LongRAG as a plug-and-play paradigm, facilitating adaptation to various domains and LLMs. Extensive experiments on three multi-hop datasets demonstrate that LongRAG significantly outperforms long-context LLMs (up by 6.94%), advanced RAG (up by 6.16%), and Vanilla RAG (up by 17.25%). Furthermore, we conduct quantitative ablation studies and multi-dimensional analyses, highlighting the effectiveness of the system's components and fine-tuning strategies. Data and code are available at https://github.com/QingFei1/LongRAG.

Control Barrier Function (CBF) is an emerging method that guarantees safety in path planning problems by generating a control command to ensure the forward invariance of a safety set. Most of the developments up to date assume availability of correct state measurements and absence of disturbances on the system. However, if the system incurs disturbances and is subject to noise, the CBF cannot guarantee safety due to the distorted state estimate. To improve the resilience and adaptability of the CBF, we propose a resilient estimator-based control barrier function (RE-CBF), which is based on a novel stochastic CBF optimization and resilient estimator, to guarantee the safety of systems with disturbances and noise in the path planning problems. The proposed algorithm uses the resilient estimation algorithm to estimate disturbances and counteract their effect using novel stochastic CBF optimization, providing safe control inputs for dynamical systems with disturbances and noise. To demonstrate the effectiveness of our algorithm in handling both noise and disturbances in dynamics and measurement, we design a quadrotor testing pipeline to simulate the proposed algorithm and then implement the algorithm on a real drone in our flying arena. Both simulations and real-world experiments show that the proposed method can guarantee safety for systems with disturbances and noise.

Perception, Planning, and Control form the essential components of autonomy in advanced air mobility. This work advances the holistic integration of these components to enhance the performance and robustness of the complete cyber-physical system. We adapt Perception Simplex, a system for verifiable collision avoidance amidst obstacle detection faults, to the vertical landing maneuver for autonomous air mobility vehicles. We improve upon this system by replacing static assumptions of control capabilities with dynamic confirmation, i.e., real-time confirmation of control limitations of the system, ensuring reliable fulfillment of safety maneuvers and overrides, without dependence on overly pessimistic assumptions. Parameters defining control system capabilities and limitations, e.g., maximum deceleration, are continuously tracked within the system and used to make safety-critical decisions. We apply these techniques to propose a verifiable collision avoidance solution for autonomous aerial mobility vehicles operating in cluttered and potentially unsafe environments.

IceCube DeepCore is an extension of the IceCube Neutrino Observatory designed to measure GeV scale atmospheric neutrino interactions for the purpose of neutrino oscillation studies. Distinguishing muon neutrinos from other flavors and reconstructing inelasticity are especially difficult tasks at GeV scale energies in IceCube DeepCore due to sparse instrumentation. Convolutional neural networks (CNNs) have been found to have better success at neutrino event reconstruction than conventional likelihood-based methods. In this contribution, we present a new CNN model that exploits time and depth translational symmetry in IceCube DeepCore data and present the model's performance, specifically for flavor identification and inelasticity reconstruction.

The IceCube South Pole Neutrino Observatory is a Cherenkov detector instrumented in a cubic kilometer of ice at the South Pole. IceCube's primary scientific goal is the detection of TeV neutrino emissions from astrophysical sources. At the lower center of the IceCube array, there is a subdetector called DeepCore, which has a denser configuration that makes it possible to lower the energy threshold of IceCube and observe GeV-scale neutrinos, opening the window to atmospheric neutrino oscillations studies. Advances in physics sensitivity have recently been achieved by employing Convolutional Neural Networks to reconstruct neutrino interactions in the DeepCore detector. In this contribution, the recent IceCube result from the atmospheric muon neutrino disappearance analysis using the CNN-reconstructed neutrino sample is presented and compared to the existing worldwide measurements.

The origin of high-energy cosmic rays, atomic nuclei that continuously impact Earth's atmosphere, has been a mystery for over a century. Due to deflection in interstellar magnetic fields, cosmic rays from the Milky Way arrive at Earth from random directions. However, near their sources and during propagation, cosmic rays interact with matter and produce high-energy neutrinos. We search for neutrino emission using machine learning techniques applied to ten years of data from the IceCube Neutrino Observatory. We identify neutrino emission from the Galactic plane at the 4.5$\sigma$ level of significance, by comparing diffuse emission models to a background-only hypothesis. The signal is consistent with modeled diffuse emission from the Galactic plane, but could also arise from a population of unresolved point sources.

Autonomous systems increasingly rely on machine learning techniques to transform high-dimensional raw inputs into predictions that are then used for decision-making and control. However, it is often easy to maliciously manipulate such inputs and, as a result, predictions. While effective techniques have been proposed to certify the robustness of predictions to adversarial input perturbations, such techniques have been disembodied from control systems that make downstream use of the predictions. We propose the first approach for composing robustness certification of predictions with respect to raw input perturbations with robust control to obtain certified robustness of control to adversarial input perturbations. We use a case study of adaptive vehicle control to illustrate our approach and show the value of the resulting end-to-end certificates through extensive experiments.

IceCube, a cubic-kilometer array of optical sensors built to detect atmospheric and astrophysical neutrinos between 1 GeV and 1 PeV, is deployed 1.45 km to 2.45 km below the surface of the ice sheet at the South Pole. The classification and reconstruction of events from the in-ice detectors play a central role in the analysis of data from IceCube. Reconstructing and classifying events is a challenge due to the irregular detector geometry, inhomogeneous scattering and absorption of light in the ice and, below 100 GeV, the relatively low number of signal photons produced per event. To address this challenge, it is possible to represent IceCube events as point cloud graphs and use a Graph Neural Network (GNN) as the classification and reconstruction method. The GNN is capable of distinguishing neutrino events from cosmic-ray backgrounds, classifying different neutrino event types, and reconstructing the deposited energy, direction and interaction vertex. Based on simulation, we provide a comparison in the 1-100 GeV energy range to the current state-of-the-art maximum likelihood techniques used in current IceCube analyses, including the effects of known systematic uncertainties. For neutrino event classification, the GNN increases the signal efficiency by 18% at a fixed false positive rate (FPR), compared to current IceCube methods. Alternatively, the GNN offers a reduction of the FPR by over a factor 8 (to below half a percent) at a fixed signal efficiency. For the reconstruction of energy, direction, and interaction vertex, the resolution improves by an average of 13%-20% compared to current maximum likelihood techniques in the energy range of 1-30 GeV. The GNN, when run on a GPU, is capable of processing IceCube events at a rate nearly double of the median IceCube trigger rate of 2.7 kHz, which opens the possibility of using low energy neutrinos in online searches for transient events.