Today, we are one step closer to the immortal celebrity future we have long been promised (since April). Meta has unveiled Voicebox, its generative text-to-speech model that promises to do for the spoken word what ChatGPT and Dall-E, respectfully, did for text and image generation. Essentially, its a text-to-output generator just like GPT or Dall-E -- just instead of creating prose or pretty pictures, it spits out audio clips. Meta defines the system as "a non-autoregressive flow-matching model trained to infill speech, given audio context and text." It's been trained on more than 50,000 hours of unfiltered audio.

Earlier this week, Paul McCartney sent the music-nerd internet ablaze with some news: Artificial intelligence had helped resurrect a bit of John Lennon's voice for a new Beatles song, more than four decades after his death. The song is set for release later this year and comes from vocals Lennon recorded on an old demo. "We were able to take John's voice and get it pure through this AI," McCartney told BBC Radio 4, "so then we could mix the record, as you would normally do." The reaction this elicited on WIRED Slack channels was somewhere between "cool" and "gross." Using AI to resurrect Lennon for a new song has its appeal, but given the recent ethical questions around using the technology to make fake songs from artists like Drake and The Weeknd, it also feels icky.

It had a great new idea for a movie--Elemental, based on characters from The Good Dinosaur's director Peter Sohn--but actually animating the film's titular elements was proving to be a problem. After all, it's one thing to draw a crumbling mound of sentient dirt, but how do you capture the ethereal nature of fire onscreen, and how would a corporeal body made of water even work? Can you see through it? Do the eyes just float around? While some of those questions could be answered with good old-fashioned suspension of disbelief, Pixar's animators thought the fire issue was a real conundrum, especially considering that one of their movie's leads, Ember, was actually supposed to be made of the stuff. They had tools to make a flame effect from years of previous animations, but when you actually tried to shape it into a character, the results were pretty terrifying, a cross between Studio Ghibli's Calcifer and Nicolas Cage's Ghost Rider, but somehow harsher.

The standard paradigm for fake news detection mainly utilizes text information to model the truthfulness of news. However, the discourse of online fake news is typically subtle and it requires expert knowledge to use textual information to debunk fake news. Recently, studies focusing on multimodal fake news detection have outperformed text-only methods. Recent approaches utilizing the pre-trained model to extract unimodal features, or fine-tuning the pre-trained model directly, have become a new paradigm for detecting fake news. Again, this paradigm either requires a large number of training instances, or updates the entire set of pre-trained model parameters, making real-world fake news detection impractical. Furthermore, traditional multimodal methods fuse the cross-modal features directly without considering that the uncorrelated semantic representation might inject noise into the multimodal features. This paper proposes a Similarity-Aware Multimodal Prompt Learning (SAMPLE) framework. First, we incorporate prompt learning into multimodal fake news detection. Prompt learning, which only tunes prompts with a frozen language model, can reduce memory usage significantly and achieve comparable performances, compared with fine-tuning. We analyse three prompt templates with a soft verbalizer to detect fake news. In addition, we introduce the similarity-aware fusing method to adaptively fuse the intensity of multimodal representation and mitigate the noise injection via uncorrelated cross-modal features. For evaluation, SAMPLE surpasses the F1 and the accuracies of previous works on two benchmark multimodal datasets, demonstrating the effectiveness of the proposed method in detecting fake news. In addition, SAMPLE also is superior to other approaches regardless of few-shot and data-rich settings.

In this paper, we present CML-TTS, a recursive acronym for CML-Multi-Lingual-TTS, a new Text-to-Speech (TTS) dataset developed at the Center of Excellence in Artificial Intelligence (CEIA) of the Federal University of Goias (UFG). CML-TTS is based on Multilingual LibriSpeech (MLS) and adapted for training TTS models, consisting of audiobooks in seven languages: Dutch, French, German, Italian, Portuguese, Polish, and Spanish. Additionally, we provide the YourTTS model, a multi-lingual TTS model, trained using 3,176.13 hours from CML-TTS and also with 245.07 hours from LibriTTS, in English. Our purpose in creating this dataset is to open up new research possibilities in the TTS area for multi-lingual models. The dataset is publicly available under the CC-BY 4.0 license1.

With the advent of mobile phone photography and point-and-shoot cameras, deep-burst imaging is widely used for a number of photographic effects such as depth of field, super-resolution, motion deblurring, and image denoising. In this work, we propose to solve the problem of deep-burst image denoising by including an optical flow-based correspondence estimation module which aligns all the input burst images with respect to a reference frame. In order to deal with varying noise levels the individual burst images are pre-filtered with different settings. Exploiting the established correspondences one network block predicts a pixel-wise spatially-varying filter kernel to smooth each image in the original and prefiltered bursts before fusing all images to generate the final denoised output. The resulting pipeline achieves state-of-the-art results by combining all available information provided by the burst.

Sarcasm is a form of figurative language that serves as a humorous tool for mockery and ridicule. We present a novel architecture for sarcasm generation with emoji from a non-sarcastic input sentence in English. We divide the generation task into two sub tasks: one for generating textual sarcasm and another for collecting emojis associated with those sarcastic sentences. Two key elements of sarcasm are incorporated into the textual sarcasm generation task: valence reversal and semantic incongruity with context, where the context may involve shared commonsense or general knowledge between the speaker and their audience. The majority of existing sarcasm generation works have focused on this textual form. However, in the real world, when written texts fall short of effectively capturing the emotional cues of spoken and face-to-face communication, people often opt for emojis to accurately express their emotions. Due to the wide range of applications of emojis, incorporating appropriate emojis to generate textual sarcastic sentences helps advance sarcasm generation. We conclude our study by evaluating the generated sarcastic sentences using human judgement. All the codes and data used in this study has been made publicly available.

Mis- and disinformation are a substantial global threat to our security and safety. To cope with the scale of online misinformation, researchers have been working on automating fact-checking by retrieving and verifying against relevant evidence. However, despite many advances, a comprehensive evaluation of the possible attack vectors against such systems is still lacking. Particularly, the automated fact-verification process might be vulnerable to the exact disinformation campaigns it is trying to combat. In this work, we assume an adversary that automatically tampers with the online evidence in order to disrupt the fact-checking model via camouflaging the relevant evidence or planting a misleading one. We first propose an exploratory taxonomy that spans these two targets and the different threat model dimensions. Guided by this, we design and propose several potential attack methods. We show that it is possible to subtly modify claim-salient snippets in the evidence and generate diverse and claim-aligned evidence. Thus, we highly degrade the fact-checking performance under many different permutations of the taxonomy's dimensions. The attacks are also robust against post-hoc modifications of the claim. Our analysis further hints at potential limitations in models' inference when faced with contradicting evidence. We emphasize that these attacks can have harmful implications on the inspectable and human-in-the-loop usage scenarios of such models, and we conclude by discussing challenges and directions for future defenses.

The DocRED dataset is one of the most popular and widely used benchmarks for document-level relation extraction (RE). It adopts a recommend-revise annotation scheme so as to have a large-scale annotated dataset. However, we find that the annotation of DocRED is incomplete, i.e., false negative samples are prevalent. We analyze the causes and effects of the overwhelming false negative problem in the DocRED dataset. To address the shortcoming, we re-annotate 4,053 documents in the DocRED dataset by adding the missed relation triples back to the original DocRED. We name our revised DocRED dataset Re-DocRED. We conduct extensive experiments with state-of-the-art neural models on both datasets, and the experimental results show that the models trained and evaluated on our Re-DocRED achieve performance improvements of around 13 F1 points. Moreover, we conduct a comprehensive analysis to identify the potential areas for further improvement. Our dataset is publicly available at https://github.com/tonytan48/Re-DocRED.

When you look at leaders and managers, we have more than 80% of them that use AI at least on a weekly basis. When you look at frontline staff, that number drops to 20% so with the lack of familiarity with the tech comes much more anxiety and concern on the outcomes for them.