Robotaxis keep tangling with firefighters on the streets of San Francisco, and the fire chief is fed up. "They're not ready for prime time," Chief Jeanine Nicholson said. Nicholson is talking about the driverless taxis from Waymo and Cruise that are picking up passengers and dropping them off in designated sections of the city. Now those companies want to rapidly expand service throughout the entire city, in unlimited numbers, in any kind of weather, day or night. And state regulators appear ready to approve their request.

An undated photo shows tourist submersible belongs to OceanGate descents at a sea. Search and rescue operations continue by US Coast Guard in Boston after a tourist submarine bound for the Titanics wreckage site went missing off the southeastern coast of Canada. RACE AGAINST TIME - Missing sub nears critical deadline when oxygen was projected to run out. Continue reading … AMERICAN DETAINED - WSJ reporter Evan Gershkovich's appeal denied by Russian court. 'BASELESS DISTORTIONS' - Adam Schiff censured by House for'false' allegations on Trump-Russia collusion.

The race against time to find a submersible that disappeared on its way to the Titanic wreckage site entered a new phase of desperation on Thursday morning as the final hours of oxygen possibly left on board the tiny vessel ticked off the clock. The vessel, named Titan, lost communication with tour operators on Sunday while about 700km (435 miles) south of St John's, Newfoundland, during a voyage to the Titanic shipwreck off the coast of Canada. The 6.7-metre-long OceanGate Expeditions vessel began its descent at 8am (12:00 GMT) on Sunday. Considering that it had a 96-hour air supply from the time it is sealed, according to its specifications, the US Coast Guard estimated oxygen in the submersible would have run out at about 10:00 GMT on Thursday. This can vary depending on a few factors, such as whether the sub still has power in the icy depths.

Rep. Ken Buck, R-Colo., spoke with Fox News Digital about his bill to establish a commission to address concerns about AI's rapid development. A GOP lawmaker leading on Congress' response to Big Tech is calling for a commission to streamline the U.S.'s development of artificial intelligence technology, warning that Congress is moving "too slow" on the rapidly advancing sector. Rep. Ken Buck, R-Colo., teamed up with Democratic Reps. Ted Lieu and Anna Eshoo this week to introduce the National AI Commission Act, which calls for a panel of 20 experts across various facets of AI to convene and advise the U.S. government on the risks and opportunities associated with it. "I think that we should look at this bill very closely and move it very quickly," Buck told Fox News Digital.

The first video shows a man who thinks he's talking to a woman (bottom right corner) but is actually talking to a man (top left corner) and the second videos is deepfake demo. New generative Artificial Intelligence (AI) systems have captivated the world's imagination with promise and potential. AI's ability to analyze vast amounts of data and make autonomous decisions is a source of both awe and anxiety. People worry about bias in decision-making, the invasion of privacy, job displacement, and even the existential fear of machines becoming uncontrollable. How can we make sure AI benefits society? The National Telecommunications and Information Administration (NTIA) has responded by seeking input on how to ensure that AI companies are "accountable."

UFO expert Nick Pope discuss the whistleblower claiming that the U.S. has alien crafts and remains on'Fox News @ Night.' A Harvard professor of astronomy is predicting extraterrestrials will make contact with artificial intelligence before humans, due to aliens potentially feeling a "kinship" with human technology. "My expectation from interstellar travel is that it's best done with electronic gadgets and devices rather than with biological creatures because the journey takes a long time," Harvard professor Avi Loeb said in an upcoming documentary titled "God Vs. "Even to the nearest star, it will take us 50,000 years to get there with chemical rockets. And artificial intelligence systems have that patience - and then they can remain dormant ... so that they survive the journey," he said. Space agencies across the world, including NASA and the European Space Agency, have for years been using AI technology to chart galaxies and stars and even send robots to other planets. Avi Loeb, Frank B. Baird Jr. Professor of Science at Harvard University, speaks during the SALT conference in Manhattan, New York City, U.S., September 14, 2022. Loeb said extraterrestrials would likely reach out to artificial intelligence before humans due to a likely "kinship." "If they visit us, of course, we can use our AI systems to interpret their AI systems.

Recent years have seen many successful applications of machine learning (ML) to facilitate fluid dynamic computations. As simulations grow, generating new training datasets for traditional offline learning creates I/O and storage bottlenecks. Additionally, performing inference at runtime requires non-trivial coupling of ML framework libraries with simulation codes. This work offers a solution to both limitations by simplifying this coupling and enabling in situ training and inference workflows on heterogeneous clusters. Leveraging SmartSim, the presented framework deploys a database to store data and ML models in memory, thus circumventing the file system. On the Polaris supercomputer, we demonstrate perfect scaling efficiency to the full machine size of the data transfer and inference costs thanks to a novel co-located deployment of the database. Moreover, we train an autoencoder in situ from a turbulent flow simulation, showing that the framework overhead is negligible relative to a solver time step and training epoch.

The TREC Video Retrieval Evaluation (TRECVID) is a TREC-style video analysis and retrieval evaluation with the goal of promoting progress in research and development of content-based exploitation and retrieval of information from digital video via open, tasks-based evaluation supported by metrology. Over the last twenty-one years this effort has yielded a better understanding of how systems can effectively accomplish such processing and how one can reliably benchmark their performance. TRECVID has been funded by NIST (National Institute of Standards and Technology) and other US government agencies. In addition, many organizations and individuals worldwide contribute significant time and effort. TRECVID 2022 planned for the following six tasks: Ad-hoc video search, Video to text captioning, Disaster scene description and indexing, Activity in extended videos, deep video understanding, and movie summarization. In total, 35 teams from various research organizations worldwide signed up to join the evaluation campaign this year. This paper introduces the tasks, datasets used, evaluation frameworks and metrics, as well as a high-level results overview.

The ability of generative models to produce highly realistic synthetic face images has raised security and ethical concerns. As a first line of defense against such fake faces, deep learning based forensic classifiers have been developed. While these forensic models can detect whether a face image is synthetic or real with high accuracy, they are also vulnerable to adversarial attacks. Although such attacks can be highly successful in evading detection by forensic classifiers, they introduce visible noise patterns that are detectable through careful human scrutiny. Additionally, these attacks assume access to the target model(s) which may not always be true. Attempts have been made to directly perturb the latent space of GANs to produce adversarial fake faces that can circumvent forensic classifiers. In this work, we go one step further and show that it is possible to successfully generate adversarial fake faces with a specified set of attributes (e.g., hair color, eye size, race, gender, etc.). To achieve this goal, we leverage the state-of-the-art generative model StyleGAN with disentangled representations, which enables a range of modifications without leaving the manifold of natural images. We propose a framework to search for adversarial latent codes within the feature space of StyleGAN, where the search can be guided either by a text prompt or a reference image. We also propose a meta-learning based optimization strategy to achieve transferable performance on unknown target models. Extensive experiments demonstrate that the proposed approach can produce semantically manipulated adversarial fake faces, which are true to the specified attribute set and can successfully fool forensic face classifiers, while remaining undetectable by humans. Code: https://github.com/koushiksrivats/face_attribute_attack.

Most offline reinforcement learning (RL) algorithms return a target policy maximizing a trade-off between (1) the expected performance gain over the behavior policy that collected the dataset, and (2) the risk stemming from the out-of-distribution-ness of the induced state-action occupancy. It follows that the performance of the target policy is strongly related to the performance of the behavior policy and, thus, the trajectory return distribution of the dataset. We show that in mixed datasets consisting of mostly low-return trajectories and minor high-return trajectories, state-of-the-art offline RL algorithms are overly restrained by low-return trajectories and fail to exploit high-performing trajectories to the fullest. To overcome this issue, we show that, in deterministic MDPs with stochastic initial states, the dataset sampling can be re-weighted to induce an artificial dataset whose behavior policy has a higher return. This re-weighted sampling strategy may be combined with any offline RL algorithm. We further analyze that the opportunity for performance improvement over the behavior policy correlates with the positive-sided variance of the returns of the trajectories in the dataset. We empirically show that while CQL, IQL, and TD3+BC achieve only a part of this potential policy improvement, these same algorithms combined with our reweighted sampling strategy fully exploit the dataset. Furthermore, we empirically demonstrate that, despite its theoretical limitation, the approach may still be efficient in stochastic environments. The code is available at https://github.com/Improbable-AI/harness-offline-rl.