Text style transfer (TST) aims to vary the style polarity of text while preserving the semantic content. Although recent advancements have demonstrated remarkable progress in short TST, it remains a relatively straightforward task with limited practical applications. The more comprehensive long TST task presents two challenges: (1) existing methods encounter difficulties in accurately evaluating content attributes in multiple words, leading to content degradation; (2) the conventional vanilla style classifier loss encounters obstacles in maintaining consistent style across multiple generated sentences. In this paper, we propose a novel method SC2, where a multilayer Joint Style-Content Weighed (JSCW) module and a Style Consistency loss are designed to address the two issues. The JSCW simultaneously assesses the amounts of style and content attributes within a token, aiming to acquire a lossless content representation and thereby enhancing content preservation. The multiple JSCW layers further progressively refine content representations. We design a style consistency loss to ensure the generated multiple sentences consistently reflect the target style polarity. Moreover, we incorporate a denoising non-autoregressive decoder to accelerate the training. We conduct plentiful experiments and the results show significant improvements of SC2 over competitive baselines. Our code: https://github.com/jiezhao6/SC2.

As learned image codecs (LICs) become more prevalent, their low coding efficiency for out-of-distribution data becomes a bottleneck for some applications. To improve the performance of LICs for screen content (SC) images without breaking backwards compatibility, we propose to introduce parameterized and invertible linear transformations into the coding pipeline without changing the underlying baseline codec's operation flow. We design two neural networks to act as prefilters and postfilters in our setup to increase the coding efficiency and help with the recovery from coding artifacts. Our end-to-end trained solution achieves up to 10% bitrate savings on SC compression compared to the baseline LICs while introducing only 1% extra parameters.

We present a different view for AlphaStar (AS), the program achieving Grand-Master level in the game StarCraft II. It is considered big progress for AI research. However, in this paper, we present problems with the AS, some of which are the defects of it, and some of which are important details that are neglected in its article. These problems arise two questions. One is that what can we get from the built of AS? The other is that does the battle between it with humans fair? After the discussion, we present the future research directions for these problems. Our study is based on a reproduction code of the AS, and the codes are available online.

Launched in 2016, SC2's goal is to create a collaborative machine-learning competition to address radio frequency (RF) spectrum challenges. DARPA experts created SC2 to help users of the existing radio spectrum overcome the problem of clogged spectrum. Demand for radio spectrum has grown steadily over the past century, and in the past several years has increased at a rate of 50 per-cent per year. SC2 wants to move away from traditional ways of communicating via one frequency. As Paul Tilghman explained during his keynote speech at NIWeek, one of the biggest obstacles in spectrum management is that "frequency isolation completely dominates our spectrum landscape."

DARPA today announced the newest of its Grand Challenges, one designed to ensure that the exponentially growing number of military and civilian wireless devices will have full access to the increasingly crowded electromagnetic spectrum. The agency's Spectrum Collaboration Challenge (SC2) will reward teams for developing smart systems that collaboratively, rather than competitively, adapt in real time to today's fast-changing, congested spectrum environment--redefining the conventional spectrum management roles of humans and machines in order to maximize the flow of radio frequency (RF) signals. DARPA officials unveiled the new Challenge before some 8000 engineers and communications professionals gathered in Las Vegas at the International Wireless Communications Expo (IWCE). The primary goal of SC2 is to imbue radios with advanced machine-learning capabilities so they can collectively develop strategies that optimize use of the wireless spectrum in ways not possible with today's intrinsically inefficient approach of pre-allocating exclusive access to designated frequencies. The challenge is expected to both take advantage of recent significant progress in the fields of artificial intelligence and machine learning and also spur new developments in those research domains, with potential applications in other fields where collaborative decision-making is critical.

One of the most hotly contested bits of real estate today is one you can't see. As we move into an increasingly wireless-connected world, staking out a piece of the crowded electromagnetic spectrum becomes more important. DARPA is hoping to help solve this issue with its latest Grand Challenge, which calls for the use of machine-learning technologies to enable devices to share bandwidth. The Spectrum Collaboration Challenge (SC2) is aimed at alleviating an ongoing technological headache. Ever since the invention of radio, it's been recognized that there is only so much of the electromagnetic spectrum to go around, so government regulations were imposed to allocate bandwidth.

The Defense Department has decided to make a game out of the problem of spectrum crowding. The Spectrum Collaboration Challenge (SC2), the Defense Advanced Projects Research Agency's newest Grand Challenge, will reward teams that develop systems that collaboratively (as opposed to competitively) adapt in real time to changes in congested electromagnetic spectrum, DARPA said in a release. SC2's primary goal is to imbue radios with advanced machine-learning capabilities to collectively develop strategies for optimizing use of the wireless spectrum that aren't possible today due to the intrinsically inefficient approach of pre-allocating exclusive access to designated frequencies. Making more efficient use of the finite spectrum environment has become a DOD priority as the spectrum becomes ever more crowded, and DOD has to comply with a presidential order to free up 500 MHz of its spectrum for commercial use by 2020. "I think today we're in a good spot…We did well with the last auction and the money is there to change where DOD can move and share spectrum," DOD CIO Terry Halvorsen said on March 22.