Learning a universal policy across different robot morphologies can significantly improve learning efficiency and generalization in continuous control. However, it poses a challenging multi-task reinforcement learning problem, as the optimal policy may be quite different across robots and critically depend on the morphology. Existing methods utilize graph neural networks or transformers to handle heterogeneous state and action spaces across different morphologies, but pay little attention to the dependency of a robot's control policy on its morphology context. In this paper, we propose a hierarchical architecture to better model this dependency via contextual modulation, which includes two key submodules: (1) Instead of enforcing hard parameter sharing across robots, we use hypernetworks to generate morphology-dependent control parameters; (2) We propose a fixed attention mechanism that solely depends on the morphology to modulate the interactions between different limbs in a robot. Experimental results show that our method not only improves learning performance on a diverse set of training robots, but also generalizes better to unseen morphologies in a zero-shot fashion.

The literature on machine learning in the context of data streams is vast and growing. However, many of the defining assumptions regarding data-stream learning tasks are too strong to hold in practice, or are even contradictory such that they cannot be met in the contexts of supervised learning. Algorithms are chosen and designed based on criteria which are often not clearly stated, for problem settings not clearly defined, tested in unrealistic settings, and/or in isolation from related approaches in the wider literature. This puts into question the potential for real-world impact of many approaches conceived in such contexts, and risks propagating a misguided research focus. We propose to tackle these issues by reformulating the fundamental definitions and settings of supervised data-stream learning with regard to contemporary considerations of concept drift and temporal dependence; and we take a fresh look at what constitutes a supervised data-stream learning task, and a reconsideration of algorithms that may be applied to tackle such tasks. Through and in reflection of this formulation and overview, helped by an informal survey of industrial players dealing with real-world data streams, we provide recommendations. Our main emphasis is that learning from data streams does not impose a single-pass or online-learning approach, or any particular learning regime; and any constraints on memory and time are not specific to streaming. Meanwhile, there exist established techniques for dealing with temporal dependence and concept drift, in other areas of the literature. For the data streams community, we thus encourage a shift in research focus, from dealing with often-artificial constraints and assumptions on the learning mode, to issues such as robustness, privacy, and interpretability which are increasingly relevant to learning in data streams in academic and industrial settings.

CyberGuy shows how to take a sequence of action photos using Burst Mode and select the best one. So, you've probably heard about the latest stir in Hollywood – and no, it's not about another celebrity feud or a blockbuster release. CLICK TO GET KURT'S FREE CYBERGUY NEWSLETTER WITH SECURITY ALERTS, QUICK TIPS, TECH REVIEWS AND EASY HOW-TO'S TO MAKE YOU SMARTER Instead, the buzz is all about artificial intelligence elbowing its way into the director's chair, churning out movie trailers, title sequences, and even entire episodes of beloved shows. It's an uncanny blend of technology and creativity that has everyone from industry insiders to casual moviegoers sitting up and taking notice. The "Barbie" movie's debut has been postponed in the Middle East until the end of August due to Warner Brothers still working on an edit of the film that will appease the region's censors.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. Russian drones on Wednesday hit a Ukrainian port city along the border with Romania, causing significant damage and a huge fire at facilities that are key to Ukrainian grain exports. The attacks followed the end of a deal with Russia that had allowed Ukrainian shipments to world markets from the Black Sea port of Odesa. Since scrapping the deal, Russia has hammered the country's ports with strikes, compounding the blow to the key industry.

The images pop up in Mophat Okinyi's mind when he's alone, or when he's about to sleep. Okinyi, a former content moderator for Open AI's ChatGPT in Nairobi, Kenya, is one of four people in that role who have filed a petition to the Kenyan government calling for an investigation into what they describe as exploitative conditions for contractors reviewing the content that powers artificial intelligence programs. "It has really damaged my mental health," said Okinyi. The 27-year-old said he would would view up to 700 text passages a day, many depicting graphic sexual violence. He recalls he started avoiding people after having read texts about rapists and found himself projecting paranoid narratives on to people around him.

Ukraine's coastal region of Odesa was rattled by Russian drones which hit grain storage facilities in the south of the region, according to authorities in Kyiv. The grain port of Izmail, an inland port across the Danube River from NATO-member Romania, was the main target of Moscow's drone attack. "As a result of the attack, fires broke out at the facilities of the port and industrial infrastructure of the region, and an elevator was damaged," Odesa region Governor Oleh Kiper said in a statement on the Telegram messaging app. Russia's continued attacks against the Ukrainian civilian infrastructure on #Danube, in the proximity of Romania, are unacceptable. These are war crimes and they further affect UA's capacity to transfer their food products towards those in need in the world.

Cost-guided bottom-up search (BUS) algorithms use a cost function to guide the search to solve program synthesis tasks. In this paper, we show that current state-of-the-art cost-guided BUS algorithms suffer from a common problem: they can lose useful information given by the model and fail to perform the search in a best-first order according to a cost function. We introduce a novel best-first bottom-up search algorithm, which we call Bee Search, that does not suffer information loss and is able to perform cost-guided bottom-up synthesis in a best-first manner. Importantly, Bee Search performs best-first search with respect to the generation of programs, i.e., it does not even create in memory programs that are more expensive than the solution program. It attains best-first ordering with respect to generation by performing a search in an abstract space of program costs. We also introduce a new cost function that better uses the information provided by an existing cost model. Empirical results on string manipulation and bit-vector tasks show that Bee Search can outperform existing cost-guided BUS approaches when employing more complex domain-specific languages (DSLs); Bee Search and previous approaches perform equally well with simpler DSLs. Furthermore, our new cost function with Bee Search outperforms previous cost functions on string manipulation tasks.

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.

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.

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.