In this work, we evaluate 10 open-source instructed LLMs on four representative code comprehension and generation tasks. We have the following main findings. First, for the zero-shot setting, instructed LLMs are very competitive on code comprehension and generation tasks and sometimes even better than small SOTA models specifically fine-tuned on each downstream task. We also find that larger instructed LLMs are not always better on code-related tasks. Second, for the few-shot setting, we find that adding demonstration examples substantially helps instructed LLMs perform better on most code comprehension and generation tasks; however, the examples would sometimes induce unstable or even worse performance. Furthermore, we find widely-used BM25-based shot selection strategy significantly outperforms the basic random selection or fixed selection only on generation problems. Third, for the fine-tuning setting, we find that fine-tuning could further improve the model performance on downstream code comprehension and generation tasks compared to the zero-shot/one-shot performance. In addition, after being fine-tuned on the same downstream task dataset, instructed LLMs outperform both the small SOTA models and similar-scaled LLMs without instruction tuning. Based on our findings, we further present practical implications on model and usage recommendation, performance and cost trade-offs, and future direction.

Kuhn's framework of scientific progress (Kuhn, 1962) provides a useful framing of the paradigm shifts that have occurred in Artificial Intelligence over the last 60 years. The framework is also useful in understanding what is arguably a new paradigm shift in AI, signaled by the emergence of large pre-trained systems such as GPT-3, on which conversational agents such as ChatGPT are based. Such systems make intelligence a commoditized general purpose technology that is configurable to applications. In this paper, I summarize the forces that led to the rise and fall of each paradigm, and discuss the pressing issues and risks associated with the current paradigm shift in AI.

The Cameras for Allsky Meteor Surveillance (CAMS) project, funded by NASA starting in 2010, aims to map our meteor showers by triangulating meteor trajectories detected in low-light video cameras from multiple locations across 16 countries in both the northern and southern hemispheres. Its mission is to validate, discover, and predict the upcoming returns of meteor showers. Our research aimed to streamline the data processing by implementing an automated cloud-based AI-enabled pipeline and improve the data visualization to improve the rate of discoveries by involving the public in monitoring the meteor detections. This article describes the process of automating the data ingestion, processing, and insight generation using an interpretable Active Learning and AI pipeline. This work also describes the development of an interactive web portal (the NASA Meteor Shower portal) to facilitate the visualization of meteor radiant maps. To date, CAMS has discovered over 200 new meteor showers and has validated dozens of previously reported showers.

Global Climate Models (GCMs) are the primary tool to simulate climate evolution and assess the impacts of climate change. However, they often operate at a coarse spatial resolution that limits their accuracy in reproducing local-scale phenomena. Statistical downscaling methods leveraging deep learning offer a solution to this problem by approximating local-scale climate fields from coarse variables, thus enabling regional GCM projections. Typically, climate fields of different variables of interest are downscaled independently, resulting in violations of fundamental physical properties across interconnected variables. This study investigates the scope of this problem and, through an application on temperature, lays the foundation for a framework introducing multi-variable hard constraints that guarantees physical relationships between groups of downscaled climate variables.

UAVs are becoming versatile and valuable platforms for various applications. However, the main limitation is their flying time. We present BEAVIS, a novel aerial robotic platform striking an unparalleled trade-off between the manoeuvrability of drones and the long lasting capacity of blimps. BEAVIS scores highly in applications where drones enjoy unconstrained mobility yet suffer from limited lifetime. A nonlinear flight controller exploiting novel, unexplored, aerodynamic phenomena to regulate the ambient pressure and enable all translational and yaw degrees of freedom is proposed without direct actuation in the vertical direction. BEAVIS has built-in rotor fault detection and tolerance. We explain the design and the necessary background in detail. We verify the dynamics of BEAVIS and demonstrate its distinct advantages, such as agility, over existing platforms including the degrees of freedom akin to a drone with 11.36x increased lifetime. We exemplify the potential of BEAVIS to become an invaluable platform for many applications.

The benefits of ADSs can be guaranteed by making the driving experience in complex driving environments more comfortable and safer (Sarker et al., 2019). New perception technologies enable ADSs to detect the surrounding traffic. When surrounding traffic, such as other vehicles, pedestrians, and cyclists, is detected, a motion-planning algorithm can generate a safe path for the ADS (Frazzoli, 2000; Shiller and Gwo, 1991). The generated path is continuously updated using decision and control technologies based on the surrounding environment. One of the greatest challenges for ADSs is the uncertainty of the surrounding dynamic environment (González et al., 2016). An ADS must adapt to these changing conditions and make decisions that prioritize safety and efficiency.

Embedding based Knowledge Graph (KG) Completion has gained much attention over the past few years. Most of the current algorithms consider a KG as a multidirectional labeled graph and lack the ability to capture the semantics underlying the schematic information. In a separate development, a vast amount of information has been captured within the Large Language Models (LLMs) which has revolutionized the field of Artificial Intelligence. KGs could benefit from these LLMs and vice versa. This vision paper discusses the existing algorithms for KG completion based on the variations for generating KG embeddings. It starts with discussing various KG completion algorithms such as transductive and inductive link prediction and entity type prediction algorithms. It then moves on to the algorithms utilizing type information within the KGs, LLMs, and finally to algorithms capturing the semantics represented in different description logic axioms. We conclude the paper with a critical reflection on the current state of work in the community and give recommendations for future directions.

For the performance modeling of power converters, the mainstream approaches are essentially knowledge-based, suffering from heavy manpower burden and low modeling accuracy. Recent emerging data-driven techniques greatly relieve human reliance by automatic modeling from simulation data. However, model discrepancy may occur due to unmodeled parasitics, deficient thermal and magnetic models, unpredictable ambient conditions, etc. These inaccurate data-driven models based on pure simulation cannot represent the practical performance in physical world, hindering their applications in power converter modeling. To alleviate model discrepancy and improve accuracy in practice, this paper proposes a novel data-driven modeling with experimental augmentation (D2EA), leveraging both simulation data and experimental data. In D2EA, simulation data aims to establish basic functional landscape, and experimental data focuses on matching actual performance in real world. The D2EA approach is instantiated for the efficiency optimization of a hybrid modulation for neutral-point-clamped dual-active-bridge (NPC-DAB) converter. The proposed D2EA approach realizes 99.92% efficiency modeling accuracy, and its feasibility is comprehensively validated in 2-kW hardware experiments, where the peak efficiency of 98.45% is attained. Overall, D2EA is data-light and can achieve highly accurate and highly practical data-driven models in one shot, and it is scalable to other applications, effortlessly.

Figure 1: We present AnyTeleop, a vision-based teleoperation system for a variety of scenarios to solve a wide range of manipulation tasks. AnyTeleop can be used for various robot arms with different robot hands. It also supports teleoperation within different realities, such as IsaacGym (top row), and SAPIEN simulator (middle row), and real world (bottom rows). Abstract--Vision-based teleoperation offers the possibility experiments, AnyTeleop can outperform a previous system that to endow robots with human-level intelligence to physically was designed for a specific robot hardware with a higher interact with the environment, while only requiring low-cost success rate, using the same robot. However, current vision-based teleoperation AnyTeleop leads to better imitation learning performance, systems are designed and engineered towards a particular robot compared with a previous system that is particularly designed model and deploy environment, which scales poorly as the pool for that simulator. of the robot models expands and the variety of the operating environment increases. They can adapt Reality (VR) devices [4, 17, 15], wearable gloves [29, 30], to new robots given only the kinematic model, i.e., URDF handheld controller [47, 48, 20], haptic sensors [12, 23, files. Second, we develop a web-based viewer compatible 52, 55], or motion capture trackers [68]. Fortunately, recent with standard browsers, to achieve simulator-agnostic visualization developments in vision-based teleoperation [2, 24, 16, 26, and enable remote teleoperation across the internet.

The ability to quickly learn a new task with minimal instruction - known as few-shot learning - is a central aspect of intelligent agents. Classical few-shot benchmarks make use of few-shot samples from a single modality, but such samples may not be sufficient to characterize an entire concept class. In contrast, humans use cross-modal information to learn new concepts efficiently. In this work, we demonstrate that one can indeed build a better ${\bf visual}$ dog classifier by ${\bf read}$ing about dogs and ${\bf listen}$ing to them bark. To do so, we exploit the fact that recent multimodal foundation models such as CLIP are inherently cross-modal, mapping different modalities to the same representation space. Specifically, we propose a simple cross-modal adaptation approach that learns from few-shot examples spanning different modalities. By repurposing class names as additional one-shot training samples, we achieve SOTA results with an embarrassingly simple linear classifier for vision-language adaptation. Furthermore, we show that our approach can benefit existing methods such as prefix tuning, adapters, and classifier ensembling. Finally, to explore other modalities beyond vision and language, we construct the first (to our knowledge) audiovisual few-shot benchmark and use cross-modal training to improve the performance of both image and audio classification.