Automatic Music Transcription (AMT) is the task of recognizing notes in audio recordings of music. The State-of-the-Art (SotA) benchmarks have been dominated by deep learning systems. Due to the scarcity of high quality data, they are usually trained and evaluated exclusively or predominantly on classical piano music. Unfortunately, that hinders our ability to understand how they generalize to other music. Previous works have revealed several aspects of memorization and overfitting in these systems. We identify two primary sources of distribution shift: the music, and the sound. Complementing recent results on the sound axis (i.e. acoustics, timbre), we investigate the musical one (i.e. note combinations, dynamics, genre). We evaluate the performance of several SotA AMT systems on two new experimental test sets which we carefully construct to emulate different levels of musical distribution shift. Our results reveal a stark performance gap, shedding further light on the Corpus Bias problem, and the extent to which it continues to trouble these systems.

Misinformation spreads rapidly on social media, causing serious damage by influencing public opinion, promoting dangerous behavior, or eroding trust in reliable sources. It spreads too fast for traditional fact-checking, stressing the need for predictive methods. We introduce CROWDSHIELD, a crowd intelligence-based method for early misinformation prediction. We hypothesize that the crowd's reactions to misinformation reveal its accuracy. Furthermore, we hinge upon exaggerated assertions/claims and replies with particular positions/stances on the source post within a conversation thread. We employ Q-learning to capture the two dimensions -- stances and claims. We utilize deep Q-learning due to its proficiency in navigating complex decision spaces and effectively learning network properties. Additionally, we use a transformer-based encoder to develop a comprehensive understanding of both content and context. This multifaceted approach helps ensure the model pays attention to user interaction and stays anchored in the communication's content. We propose MIST, a manually annotated misinformation detection Twitter corpus comprising nearly 200 conversation threads with more than 14K replies. In experiments, CROWDSHIELD outperformed ten baseline systems, achieving an improvement of ~4% macro-F1 score. We conduct an ablation study and error analysis to validate our proposed model's performance. The source code and dataset are available at https://github.com/LCS2-IIITD/CrowdShield.git.

Capturing and rendering novel views of complex real-world scenes is a long-standing problem in computer graphics and vision, with applications in augmented and virtual reality, immersive experiences and 3D photography. The advent of deep learning has enabled revolutionary advances in this area, classically known as image-based rendering. However, previous approaches require intractably dense view sampling or provide little or no guidance for how users should sample views of a scene to reliably render high-quality novel views. Local light field fusion proposes an algorithm for practical view synthesis from an irregular grid of sampled views that first expands each sampled view into a local light field via a multiplane image scene representation, then renders novel views by blending adjacent local light fields. Crucially, we extend traditional plenoptic sampling theory to derive a bound that specifies precisely how densely users should sample views of a given scene when using our algorithm. We achieve the perceptual quality of Nyquist rate view sampling while using up to 4000x fewer views. Subsequent developments have led to new scene representations for deep learning with view synthesis, notably neural radiance fields, but the problem of sparse view synthesis from a small number of images has only grown in importance. We reprise some of the recent results on sparse and even single image view synthesis, while posing the question of whether prescriptive sampling guidelines are feasible for the new generation of image-based rendering algorithms.

Large language models (LLMs) can be abused at scale to create non-factual content and spread disinformation. Detecting LLM-generated content is essential to mitigate these risks, but current classifiers often fail to generalize in open-world contexts. Prior work shows that LLMs tend to rewrite LLM-generated content less frequently, which can be used for detection and naturally generalizes to unforeseen data. However, we find that the rewriting edit distance between human and LLM content can be indistinguishable across domains, leading to detection failures. We propose training an LLM to rewrite input text, producing minimal edits for LLM-generated content and more edits for human-written text, deriving a distinguishable and generalizable edit distance difference across different domains. Experiments on text from 21 independent domains and three popular LLMs (e.g., GPT-4o, Gemini, and Llama-3) show that our classifier outperforms the state-of-the-art zero-shot classifier by up to 20.6% on AUROC score and the rewriting classifier by 9.2% on F1 score. Our work suggests that LLM can effectively detect machine-generated text if they are trained properly.

Note alignment refers to the task of matching individual notes of two versions of the same symbolically encoded piece. Methods addressing this task commonly rely on sequence alignment algorithms such as Hidden Markov Models or Dynamic Time Warping (DTW) applied directly to note or onset sequences. While successful in many cases, such methods struggle with large mismatches between the versions. In this work, we learn note-wise representations from data augmented with various complex mismatch cases, e.g. repeats, skips, block insertions, and long trills. At the heart of our approach lies a transformer encoder network - TheGlueNote - which predicts pairwise note similarities for two 512 note subsequences. We postprocess the predicted similarities using flavors of weightedDTW and pitch-separated onsetDTW to retrieve note matches for two sequences of arbitrary length. Our approach performs on par with the state of the art in terms of note alignment accuracy, is considerably more robust to version mismatches, and works directly on any pair of MIDI files.

Recent work in behavioral testing for natural language processing (NLP) models, such as Checklist, is inspired by related paradigms in software engineering testing. They allow evaluation of general linguistic capabilities and domain understanding, hence can help evaluate conceptual soundness and identify model weaknesses. However, a major challenge is the creation of test cases. The current packages rely on semi-automated approach using manual development which requires domain expertise and can be time consuming. This paper introduces an automated approach to develop test cases by exploiting the power of large language models and statistical techniques. It clusters the text representations to carefully construct meaningful groups and then apply prompting techniques to automatically generate Minimal Functionality Tests (MFT). The well-known Amazon Reviews corpus is used to demonstrate our approach. We analyze the behavioral test profiles across four different classification algorithms and discuss the limitations and strengths of those models.

Large language models (LLMs) and large multimodal models (LMMs) have significantly impacted the AI community, industry, and various economic sectors. In journalism, integrating AI poses unique challenges and opportunities, particularly in enhancing the quality and efficiency of news reporting. This study explores how LLMs and LMMs can assist journalistic practice by generating contextualised captions for images accompanying news articles. We conducted experiments using the GoodNews dataset to evaluate the ability of LMMs (BLIP-2, GPT-4v, or LLaVA) to incorporate one of two types of context: entire news articles, or extracted named entities. In addition, we compared their performance to a two-stage pipeline composed of a captioning model (BLIP-2, OFA, or ViT-GPT2) with post-hoc contextualisation with LLMs (GPT-4 or LLaMA). We assess a diversity of models, and we find that while the choice of contextualisation model is a significant factor for the two-stage pipelines, this is not the case in the LMMs, where smaller, open-source models perform well compared to proprietary, GPT-powered ones. Additionally, we found that controlling the amount of provided context enhances performance. These results highlight the limitations of a fully automated approach and underscore the necessity for an interactive, human-in-the-loop strategy.

Appearance: Either romantic or grim, depending on who you are. Well, get with the programme, because this is the future. A huge amount of AI chatbot use is sexual in nature. Am I going to regret reading this? The Washington Post analysed 200,000 conversations from the research dataset WildChat and found that more than 7% of it was about sex stuff.

In recent years, state-of-the-art image and video denoising networks have become increasingly large, requiring millions of trainable parameters to achieve best-in-class performance. Improved denoising quality has come at the cost of denoising speed, where modern transformer networks are far slower to run than smaller denoising networks such as FastDVDnet and classic Bayesian denoisers such as the Wiener filter. In this paper, we implement a hybrid Wiener filter which leverages small ancillary networks to increase the original denoiser performance, while retaining fast denoising speeds. These networks are used to refine the Wiener coring estimate, optimise windowing functions and estimate the unknown noise profile. Using these methods, we outperform several popular denoisers and remain within 0.2 dB, on average, of the popular VRT transformer. Our method was found to be over x10 faster than the transformer method, with a far lower parameter cost.

This paper presents a study on the growing threat of "sleeper social bots," AI-driven social bots in the political landscape, created to spread disinformation and manipulate public opinion. We based the name sleeper social bots on their ability to pass as humans on social platforms, where they're embedded like political "sleeper" agents, making them harder to detect and more disruptive. To illustrate the threat these bots pose, our research team at the University of Southern California constructed a demonstration using a private Mastodon server, where ChatGPT-driven bots, programmed with distinct personalities and political viewpoints, engaged in discussions with human participants about a fictional electoral proposition. Our preliminary findings suggest these bots can convincingly pass as human users, actively participate in conversations, and effectively disseminate disinformation. Moreover, they can adapt their arguments based on the responses of human interlocutors, showcasing their dynamic and persuasive capabilities. College students participating in initial experiments failed to identify our bots, underscoring the urgent need for increased awareness and education about the dangers of AI-driven disinformation, and in particular, disinformation spread by bots. The implications of our research point to the significant challenges posed by social bots in the upcoming 2024 U.S. presidential election and beyond.