Temporal Knowledge Graph (TKG) reasoning often involves completing missing factual elements along the timeline. Although existing methods can learn good embeddings for each factual element in quadruples by integrating temporal information, they often fail to infer the evolution of temporal facts. This is mainly because of (1) insufficiently exploring the internal structure and semantic relationships within individual quadruples and (2) inadequately learning a unified representation of the contextual and temporal correlations among different quadruples. To overcome these limitations, we propose a novel Transformer-based reasoning model (dubbed ECEformer) for TKG to learn the Evolutionary Chain of Events (ECE). Specifically, we unfold the neighborhood subgraph of an entity node in chronological order, forming an evolutionary chain of events as the input for our model. Subsequently, we utilize a Transformer encoder to learn the embeddings of intra-quadruples for ECE. We then craft a mixed-context reasoning module based on the multi-layer perceptron (MLP) to learn the unified representations of inter-quadruples for ECE while accomplishing temporal knowledge reasoning. In addition, to enhance the timeliness of the events, we devise an additional time prediction task to complete effective temporal information within the learned unified representation. Extensive experiments on six benchmark datasets verify the state-of-the-art performance and the effectiveness of our method.

Astronomers and data scientists working with a boost in computer power on loan from Google have discovered 27,500 new asteroids, some perilously close to Earth. Their collaboration hopes to speed up the development of'a comprehensive map of the solar system' needed for'planetary defense,' according to one Harvard astrophysicist, Matthew Holman, who helped develop the asteroid-hunting software. Nearly 1.7 billion points of light, documented in 412,000 infrared images from the US National Optical-Infrared Astronomy Research Laboratory (NOIRLab) archives, were scanned by the project's novel'killer asteroid'-hunting algorithm. 'This is super important,' as one former NASA astronaut leading the project put it. 'This is the key to protecting the Earth from being hit by asteroids: knowing where all these are.'

If you've been thinking about picking up a new supercomputer but were waiting on a good price, now might be a good time to put in your bid. Right now, the US government, via GSA Auctions, is auctioning off the Cheyenne Supercomputer to the highest bidder with three days remaining. While we haven't tested this one ourselves, we assume its 145,152 CPU cores will easily out-perform our current top pick for a laptop. You also won't need to upgrade the memory anytime soon, as there's a full 313,344GB of RAM currently installed, and the storage capacity tallies up to around 36 petabytes. No need to delete files to make room for new games or other media downloads. The deal was spotted by Ars Technica, who also point out that the fiber optic and CAT5/6 cabling are not included in the sale.

At a tech forum in Beijing last week, a Chinese company unveiled a "homegrown" brain-computer interface that allowed a monkey to seemingly control a robotic arm just by thinking about it. In a video shown at the event, a monkey with its hands restrained uses the interface to move a robotic arm and grasp a strawberry. The system, developed by NeuCyber NeuroTech and the Chinese Institute for Brain Research, involves soft electrode filaments implanted in the brain, according to state-run news media outlet Xinhua. Researchers in the US have tested similar systems in paralyzed people to allow them to control robotic arms, but the demonstration underscores China's progress in developing its own brain-computer interface technology and vying with the West. Brain-computer interfaces, or BCIs, collect and analyze brain signals, often to allow direct control of an external device, such as a robotic arm, keyboard, or smartphone.

Regulators have warned that AI is facing its'Oppenheimer moment,' as the world is facing a killer robot arms race. The statements were made at a conference in Vienna Monday as nations are using AI-powered drones and databases to search out targets on battlefields. The Israeli military was found to use an AI dubbed Lavender to create a kill list and Ukraine is using high-powered drones to unleash endless streams of ammunition. 'This is the Oppenheimer Moment of our generation,' said Austrian Foreign Minister Alexander Schallenberg. 'Now is the time to agree on international rules and norms.'

The number of groups lobbying the U.S. federal government on artificial intelligence nearly tripled from 2022 to 2023, rocketing from 158 to 451 organizations, according to data from OpenSecrets, a nonprofit that tracks and publishes data on campaign finance and lobbying. Data on the total amount spent on lobbying by each organization and interviews with two congressional staffers, two nonprofit advocates familiar with AI lobbying efforts, and two named experts suggest that large technology companies have so far dominated efforts to influence potential AI legislation. And while these companies have publicly been supportive of AI regulation, in closed-door conversations with officials they tend to push for light-touch and voluntary rules, say Congressional staffers and advocates. In November 2022, OpenAI released its wildly popular chatbot, ChatGPT. Six months later, leading AI researchers and industry executives signed a statement warning that "the risk of extinction from AI should be a global priority alongside other societal-scale risks such as pandemics and nuclear war."

And you, dear reader, know you're real. But do you ever suspect that everyone else on the internet is acting strange? That the spaces you used to frequent feel a bit … dead? "Dead internet theory" first hit the web almost three years ago, propelled to the mainstream by an essay in the Atlantic by Kaitlyn Tiffany: Dead-internet theory suggests that the internet has been almost entirely taken over by artificial intelligence. Like lots of other online conspiracy theories, the audience for this one is growing because of discussion led by a mix of true believers, sarcastic trolls and idly curious lovers of chitchat … But unlike lots of other online conspiracy theories, this one has a morsel of truth to it.

Regulators who want to get a grip on an emerging generation of artificially intelligent killing machines may not have much time left to do so, governments were warned on Monday. As autonomous weapons systems rapidly proliferate, including across battlefields in Ukraine and Gaza, algorithms and unmanned aerial vehicles are already helping military planners decide whether or not to hit targets. Soon, that decision could be outsourced entirely to the machines. "This is the Oppenheimer Moment of our generation," said Austrian Foreign Minister Alexander Schallenberg, referencing J. Robert Oppenheimer, who helped invent the atomic bomb in 1945 before going on to advocate for controls over the spread of nuclear arms.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. A suspected missile attack by Yemen's Houthi rebels damaged a ship in the Red Sea on Monday, authorities said, the latest assault in their campaign against international shipping in the crucial maritime route. The attack happened off the coast of Mokha, Yemen, the British military's United Kingdom Maritime Trade Operations center said. The ship sustained damage in the attack, the UKMTO said, though its crew was safe and heading to its next port of call.

Conformal prediction is a powerful tool to generate uncertainty sets with guaranteed coverage using any predictive model, under the assumption that the training and test data are i.i.d.. Recently, it has been shown that adversarial examples are able to manipulate conformal methods to construct prediction sets with invalid coverage rates, as the i.i.d. assumption is violated. To address this issue, a recent work, Randomized Smoothed Conformal Prediction (RSCP), was first proposed to certify the robustness of conformal prediction methods to adversarial noise. However, RSCP has two major limitations: (i) its robustness guarantee is flawed when used in practice and (ii) it tends to produce large uncertainty sets. To address these limitations, we first propose a novel framework called RSCP+ to provide provable robustness guarantee in evaluation, which fixes the issues in the original RSCP method. Next, we propose two novel methods, Post-Training Transformation (PTT) and Robust Conformal Training (RCT), to effectively reduce prediction set size with little computation overhead. Experimental results in CIFAR10, CIFAR100, and ImageNet suggest the baseline method only yields trivial predictions including full label set, while our methods could boost the efficiency by up to $4.36\times$, $5.46\times$, and $16.9\times$ respectively and provide practical robustness guarantee. Our codes are available at https://github.com/Trustworthy-ML-Lab/Provably-Robust-Conformal-Prediction.