Elon Musk's X has reactivated the ability to search its social network for musician Taylor Swift, after disabling queries for her name in response to a flood of explicit deepfake images. "Search has been re-enabled and we will continue to be vigilant for attempts to spread this content and will remove it wherever we find it," said Joe Benarroch, head of business operations at X. Last week, explicit artificial intelligence-generated images of Swift amassed tens of millions of views on X, the website formerly known as Twitter. X's efforts to curb their spread included disabling the search. She wasn't alone in being a recent high-profile target of the technology: U.S. President Joe Biden was also the victim of a fake audio clip spreading online, created with the help of widely available AI tools.

This paper offers an insightful examination of how currently top-trending AI technologies, i.e., generative artificial intelligence (Generative AI) and large language models (LLMs), are reshaping the field of video technology, including video generation, understanding, and streaming. It highlights the innovative use of these technologies in producing highly realistic videos, a significant leap in bridging the gap between real-world dynamics and digital creation. The study also delves into the advanced capabilities of LLMs in video understanding, demonstrating their effectiveness in extracting meaningful information from visual content, thereby enhancing our interaction with videos. In the realm of video streaming, the paper discusses how LLMs contribute to more efficient and user-centric streaming experiences, adapting content delivery to individual viewer preferences. This comprehensive review navigates through the current achievements, ongoing challenges, and future possibilities of applying Generative AI and LLMs to video-related tasks, underscoring the immense potential these technologies hold for advancing the field of video technology related to multimedia, networking, and AI communities.

Speech language models (SpeechLMs) process and generate acoustic data only, without textual supervision. In this work, we propose TWIST, a method for training SpeechLMs using a warm-start from a pretrained textual language models. We show using both automatic and human evaluations that TWIST outperforms a cold-start SpeechLM across the board. We empirically analyze the effect of different model design choices such as the speech tokenizer, the pretrained textual model, and the dataset size. We find that model and dataset scale both play an important role in constructing better-performing SpeechLMs. Based on our observations, we present the largest (to the best of our knowledge) SpeechLM both in terms of number of parameters and training data. We additionally introduce two spoken versions of the StoryCloze textual benchmark to further improve model evaluation and advance future research in the field. We make speech samples, code and models publicly available: https://pages.cs.huji.ac.il/adiyoss-lab/twist/ .

This paper presents a theoretical analysis and practical approach to the moral responsibilities when developing AI systems for non-military applications that may nonetheless be used for conflict applications. We argue that AI represents a form of crossover technology that is different from previous historical examples of dual- or multi-use technology as it has a multiplicative effect across other technologies. As a result, existing analyses of ethical responsibilities around dual-use technologies do not necessarily work for AI systems. We instead argue that stakeholders involved in the AI system lifecycle are morally responsible for uses of their systems that are reasonably foreseeable. The core idea is that an agent's moral responsibility for some action is not necessarily determined by their intentions alone; we must also consider what the agent could reasonably have foreseen to be potential outcomes of their action, such as the potential use of a system in conflict even when it is not designed for that. In particular, we contend that it is reasonably foreseeable that: (1) civilian AI systems will be applied to active conflict, including conflict support activities, (2) the use of civilian AI systems in conflict will impact applications of the law of armed conflict, and (3) crossover AI technology will be applied to conflicts that fall short of armed conflict. Given these reasonably foreseeably outcomes, we present three technically feasible actions that developers of civilian AIs can take to potentially mitigate their moral responsibility: (a) establishing systematic approaches to multi-perspective capability testing, (b) integrating digital watermarking in model weight matrices, and (c) utilizing monitoring and reporting mechanisms for conflict-related AI applications.

Understanding various humour styles is essential for comprehending the multifaceted nature of humour and its impact on fields such as psychology and artificial intelligence. This understanding has revealed that humour, depending on the style employed, can either have therapeutic or detrimental effects on an individual's health and relationships. Although studies dedicated exclusively to computational-based humour style analysis remain somewhat rare, an expansive body of research thrives within related task, particularly binary humour and sarcasm recognition. In this systematic literature review (SLR), we survey the landscape of computational techniques applied to these related tasks and also uncover their fundamental relevance to humour style analysis. Through this study, we unveil common approaches, illuminate various datasets and evaluation metrics, and effectively navigate the complex terrain of humour research. Our efforts determine potential research gaps and outlined promising directions. Furthermore, the SLR identifies a range of features and computational models that can seamlessly transition from related tasks like binary humour and sarcasm detection to invigorate humour style classification. These features encompass incongruity, sentiment and polarity analysis, ambiguity detection, acoustic nuances, visual cues, contextual insights, and more. The computational models that emerge contain traditional machine learning paradigms, neural network architectures, transformer-based models, and specialised models attuned to the nuances of humour. Finally, the SLR provides access to existing datasets related to humour and sarcasm, facilitating the work of future researchers.

YouTube faces a global crisis with the dissemination of false information and hate speech. To counter these issues, YouTube has implemented strict rules against uploading content that includes false information or promotes hate speech. While numerous studies have been conducted to reduce offensive English-language content, there's a significant lack of research on Sinhala content. This study aims to address the aforementioned gap by proposing a solution to minimize the spread of violence and misinformation in Sinhala YouTube videos. The approach involves developing a rating system that assesses whether a video contains false information by comparing the title and description with the audio content and evaluating whether the video includes hate speech. The methodology encompasses several steps, including audio extraction using the Pytube library, audio transcription via the fine-tuned Whisper model, hate speech detection employing the distilroberta-base model and a text classification LSTM model, and text summarization through the fine-tuned BART-Large- XSUM model. Notably, the Whisper model achieved a 48.99\% word error rate, while the distilroberta-base model demonstrated an F1 score of 0.856 and a recall value of 0.861 in comparison to the LSTM model, which exhibited signs of overfitting.

The advent of Large Models marks a new era in machine learning, significantly outperforming smaller models by leveraging vast datasets to capture and synthesize complex patterns. Despite these advancements, the exploration into scaling, especially in the audio generation domain, remains limited, with previous efforts didn't extend into the high-fidelity (HiFi) 44.1kHz domain and suffering from both spectral discontinuities and blurriness in the high-frequency domain, alongside a lack of robustness against out-of-domain data. These limitations restrict the applicability of models to diverse use cases, including music and singing generation. Our work introduces Enhanced Various Audio Generation via Scalable Generative Adversarial Networks (EVA-GAN), yields significant improvements over previous state-of-the-art in spectral and high-frequency reconstruction and robustness in out-of-domain data performance, enabling the generation of HiFi audios by employing an extensive dataset of 36,000 hours of 44.1kHz audio, a context-aware module, a Human-In-The-Loop artifact measurement toolkit, and expands the model to approximately 200 million parameters. Demonstrations of our work are available at https://double-blind-eva-gan.cc.

Multi-turn dialogues are characterized by their extended length and the presence of turn-taking conversations. Traditional language models often overlook the distinct features of these dialogues by treating them as regular text. In this paper, we propose a speaker-enhanced pre-training method for long dialogue summarization, which leverages the inherent structure of multiple-turn dialogues. To support our study, we curate a diverse dataset that includes transcripts from real-world scenarios, movie or TV show transcripts, and dialogues generated by a Large Language Model. We then perform a pre-training, which encompasses the detection of speaker changes, and masked utterance generation. Experimental results of fine-tuned models demonstrate that our model achieves state-of-the-art performance on downstream benchmarks with long context, surpassing baseline models and highlighting the effectiveness of our approach. Our findings highlight the importance of curating pre-training datasets that exhibit diversity and variations in length distribution to ensure effective alignment with downstream datasets.

To achieve faithful reasoning that aligns with human expectations, large language models (LLMs) need to ground their reasoning to real-world knowledge (e.g., web facts, math and physical rules). Tools help LLMs access this external knowledge, but there remains challenges for fine-tuning LLM agents (e.g., Toolformer) to invoke tools in multi-step reasoning problems, where inter-connected tool calls require holistic and efficient tool usage planning. In this work, we propose a new method for LLMs to better leverage tools in multi-step reasoning. Our method, Chain-of-Abstraction (CoA), trains LLMs to first decode reasoning chains with abstract placeholders, and then call domain tools to reify each reasoning chain by filling in specific knowledge. This planning with abstract chains enables LLMs to learn more general reasoning strategies, which are robust to shifts of domain knowledge (e.g., math results) relevant to different reasoning questions. It also allows LLMs to perform decoding and calling of external tools in parallel, which avoids the inference delay caused by waiting for tool responses. In mathematical reasoning and Wiki QA domains, we show that our method consistently outperforms previous chain-of-thought and tool-augmented baselines on both in-distribution and out-of-distribution test sets, with an average ~6% absolute QA accuracy improvement. LLM agents trained with our method also show more efficient tool use, with inference speed being on average ~1.4x faster than baseline tool-augmented LLMs.

Large Language Models have emerged as prime candidates to tackle misinformation mitigation. However, existing approaches struggle with hallucinations and overconfident predictions. We propose an uncertainty quantification framework that leverages both direct confidence elicitation and sampled-based consistency methods to provide better calibration for NLP misinformation mitigation solutions. We first investigate the calibration of sample-based consistency methods that exploit distinct features of consistency across sample sizes and stochastic levels. Next, we evaluate the performance and distributional shift of a robust numeric verbalization prompt across single vs. two-step confidence elicitation procedure. We also compare the performance of the same prompt with different versions of GPT and different numerical scales. Finally, we combine the sample-based consistency and verbalized methods to propose a hybrid framework that yields a better uncertainty estimation for GPT models. Overall, our work proposes novel uncertainty quantification methods that will improve the reliability of Large Language Models in misinformation mitigation applications.