Training agents in multi-agent games presents significant challenges due to their intricate nature. These challenges are exacerbated by dynamics influenced not only by the environment but also by strategies of opponents. Existing methods often struggle with slow convergence and instability.To address these challenges, we harness the potential of imitation learning (IL) to comprehend and anticipate actions of the opponents, aiming to mitigate uncertainties with respect to the game dynamics.Our key contributions include:(i) a new multi-agent IL model for predicting next moves of the opponents - our model works with hidden actions of opponents and local observations;(ii) a new multi-agent reinforcement learning (MARL) algorithm that combines our IL model and policy training into one single training process;and (iii) extensive experiments in three challenging game environments, including an advanced version of the Star-Craft multi-agent challenge (i.e., SMACv2).Experimental results show that our approach achieves superior performance compared to state-of-the-art MARL algorithms.

Talking face generation (TFG) aims to animate a target identity's face to create realistic talking videos. Personalized TFG is a variant that emphasizes the perceptual identity similarity of the synthesized result (from the perspective of appearance and talking style). While previous works typically solve this problem by learning an individual neural radiance field (NeRF) for each identity to implicitly store its static and dynamic information, we find it inefficient and non-generalized due to the per-identity-per-training framework and the limited training data. To this end, we propose MimicTalk, the first attempt that exploits the rich knowledge from a NeRF-based person-agnostic generic model for improving the efficiency and robustness of personalized TFG. To be specific, (1) we first come up with a person-agnostic 3D TFG model as the base model and propose to adapt it into a specific identity; (2) we propose a static-dynamic-hybrid adaptation pipeline to help the model learn the personalized static appearance and facial dynamic features; (3) To generate the facial motion of the personalized talking style, we propose an in-context stylized audio-to-motion model that mimics the implicit talking style provided in the reference video without information loss by an explicit style representation.

Recent advancements in large language models (LLMs) have been fueled by large scale training corpora drawn from diverse sources such as websites, news articles, and books. These datasets often contain explicit user information, such as person names and addresses, that LLMs may unintentionally reproduce in their generated outputs. Beyond such explicit content, LLMs can also leak identity revealing cues through implicit signals such as distinctive writing styles, raising significant concerns about authorship privacy. There are three major automated tasks in authorship privacy, namely authorship obfuscation (AO), authorship mimicking (AM), and authorship verification (AV). Prior research has studied AO, AM, and AV independently. However, their interplays remain under explored, which leaves a major research gap, especially in the era of LLMs, where they are profoundly shaping how we curate and share user generated content, and the distinction between machine generated and human authored text is also increasingly blurred. This work then presents the first unified framework for analyzing the dynamic relationships among LLM enabled AO, AM, and AV in the context of authorship privacy. We quantify how they interact with each other to transform human authored text, examining effects at a single point in time and iteratively over time. We also examine the role of demographic metadata, such as gender, academic background, in modulating their performances, inter-task dynamics, and privacy risks. All source code will be publicly available.

They have already revolutionized the way we live and work, and they still have the potential to do it again. They changed the way we live by doing mundane tasks for us, like vacuuming. Moreover, and more importantly, they changed the way we produce. Robots can perform complex tasks with speed, precision, and efficiency that far exceeds what humans are capable of. Robots helped us to significantly increase productivity and output in industries such as manufacturing, logistics, and agriculture.

The fourth industrial revolution is well underway with artificial intelligence (AI) at its heart powering new technologies and Internet of Things (IoT) devices from smartwatches to smart fridges, autonomous cars to home assistants, and security systems to a vast array of sensors. Using conventional computer architecture in the practical application of AI in IoTs leads to large power demands arising from the repetitive shifting of tremendous amounts of data between processors and memory units. These demands are only set to increase as AI improves and even larger amounts of data is generated. This increased power consumption comes with a potential impact on the environment via the emission of greenhouse gases through the generation of electricity through the burning of fossil fuels. The need to lower energy consumption in IoT technology has led to need for alternative, low-power alternatives that can implement AI.

Israeli startup Airwayz Drones Ltd., set up by veterans of the Israeli airforce, has developed software that knows how to safely steer hundreds of drones in the same airspace, orchestrating them in the sky autonomously, just as a traditional human-manned air traffic control station would. The technology of the Israeli company Airwayz managed some 20 drones from five companies simultaneously on Wednesday in the sky over an unpopulated area of the northern coastal city of Hadera. It was the first stage of a two-year initiative that is being touted by the Israel Innovation Authority and its partners in the event as one of the largest drone experiments ever conducted in the world. "This is one of the most progressive experiments in the world, in which drones from many companies are flying in a open and not controlled area," said Daniella Partem, head of the Center for the Fourth Industrial Revolution at the Israel Innovation Authority, which is in charge of fostering the nation's tech ecosystem. Get The Start-Up Israel's Daily Start-Up by email and never miss our top stories Free Sign Up The purpose of the large-scale government-backed experiment is to understand what our skies will look like in the future, as hundreds and thousands of drones pepper our firmament to meet various needs -- online deliveries, photography, security, agriculture and more.

With years of cybersecurity experience under his belt, security expert Mike Beck investigated whether he could teach AI to think like a cybersecurity analyst--and helped to transform the fight for online security in the process. Few people know what it's like to battle cyberattacks in a high-stakes environment better than Mike Beck. Without his expertise, London's biggest event in 2012 could have gone dark. Beck, a cybersecurity expert with a background in UK intelligence, joined the UK's MI5 domestic security service shortly before the 2012 Summer Games opened. When the UK government learned of a serious threat to the electricity infrastructure supporting the Games, they looked to one of their newest hires.

The phrase "positive reinforcement," is something you hear more often in an article about child rearing than one about artificial intelligence. But according to Alice Parker, Dean's Professor of Electrical Engineering in the Ming Hsieh Department of Electrical and Computer Engineering, a little positive reinforcement is just what our AI machines need. Parker has been building electronic circuits for over a decade to reverse-engineer the human brain to better understand how it works and ultimately build artificial systems that mimic it. Her most recent paper, co-authored with Ph.D. student Kun Yue and colleagues from UC Riverside, was just published in the journal Science Advances and takes an important step towards that ultimate goal. The AI we rely on and read about today is modeled on traditional computers; it sees the world through the lens of binary zeros and ones.

Frequently reported advances in artificial intelligence make some people curious, and others nervous. While some people picture their next smart appliance purchase being an AI robot, others wonder if an AI robot will take their job. The truth is, neither of those scenarios will be a reality anytime soon. True AI doesn't exist yet, and it's not a likely near future, either. People get excited when new breakthroughs in machine learning are publicized, like the CNBC interview with a robot named Sophia.

During the heydays of pulp sci-fi, Robert A. Heinlein penned a now forgotten short novel titled Waldo. The parable broadly speculated on how robotics and automation would eventually come to shape the lives and the landscape of the future. Almost a century later, Heinlein's work reads like a prophesy, foretelling the 21st century's rapid march towards adopting machines to do men's work. Look around and you'll find myriad examples. Robots are putting together cars on the assembly line and acting as companions for the disabled.