Current research in speech-to-speech translation (S2ST) primarily concentrates on translation accuracy and speech naturalness, often overlooking key elements like paralinguistic information, which is essential for conveying emotions and attitudes in communication. To address this, our research introduces a novel, carefully curated multilingual dataset from various movie audio tracks. Each dataset pair is precisely matched for paralinguistic information and duration. We enhance this by integrating multiple prosody transfer techniques, aiming for translations that are accurate, natural-sounding, and rich in paralinguistic details. Our experimental results confirm that our model retains more paralinguistic information from the source speech while maintaining high standards of translation accuracy and naturalness.

The performance of large language models (LLMs) is closely linked to their underlying size, leading to ever-growing networks and hence slower inference. Speculative decoding has been proposed as a technique to accelerate autoregressive generation, leveraging a fast draft model to propose candidate tokens, which are then verified in parallel based on their likelihood under the target model. While this approach guarantees to reproduce the target output, it incurs a substantial penalty: many high-quality draft tokens are rejected, even when they represent objectively valid continuations. Indeed, we show that even powerful draft models such as GPT-4o, as well as human text cannot achieve high acceptance rates under the standard verification scheme. This severely limits the speedup potential of current speculative decoding methods, as an early rejection becomes overwhelmingly likely when solely relying on alignment of draft and target. We thus ask the following question: Can we adapt verification to recognize correct, but non-aligned replies? To this end, we draw inspiration from the LLMas-a-judge framework, which demonstrated that LLMs are able to rate answers in a versatile way. We carefully design a dataset to elicit the same capability in the target model by training a compact module on top of the embeddings to produce "judgements" of the current continuation. We showcase our strategy on the Llama-3.1 family, where our 8b/405B-Judge achieves a speedup of 9 over Llama-405B, while maintaining its quality on a large range of benchmarks. These benefits remain present even in optimized inference frameworks, where our method reaches up to 141 tokens/s for 8B/70B-Judge and 129 tokens/s for 8B/405B on 2 and 8 H100s respectively. To find Alyana's age, we need to subtract 4 from How old is Anne if she is 2 Chenny's age: 10 years Alyana's age: 10 - 4 = 6 years To find Anne's age, we need to add 2 to Alyana's age. Anne's age: 6 + 2 = 8 years So, Anne is 8 years old.

Large language models (LLMs) are vital for a wide range of applications yet remain susceptible to jailbreak threats, which could lead to the generation of inappropriate responses. Conventional defenses, such as refusal and adversarial training, often fail to cover corner cases or rare domains, leaving LLMs still vulnerable to more sophisticated attacks. We propose a novel defense strategy, Safety Chain-of-Thought (SCoT), which harnesses the enhanced reasoning capabilities of LLMs for proactive assessment of harmful inputs, rather than simply blocking them. SCoT augments any refusal training datasets to critically analyze the intent behind each request before generating answers. By employing proactive reasoning, SCoT enhances the generalization of LLMs across varied harmful queries and scenarios not covered in the safety alignment corpus. Additionally, it generates detailed refusals specifying the rules violated. Comparative evaluations show that SCoT significantly surpasses existing defenses, reducing vulnerability to out-of-distribution issues and adversarial manipulations while maintaining strong general capabilities. The code and data is available at https://anonymous.4open.science/r/SCoT-D4D9.

This study presents a novel Deep Learning-based and lightweight approach for the automated detection of sports highlights (HLs) from audio and video sources. HL detection is a key task in sports video analysis, traditionally requiring significant human effort. Our solution leverages Deep Learning (DL) models trained on relatively small datasets of audio Mel-spectrograms and grayscale video frames, achieving promising accuracy rates of 89% and 83% for audio and video detection, respectively. The use of small datasets, combined with simple architectures, demonstrates the practicality of our method for fast and cost-effective deployment. Furthermore, an ensemble model combining both modalities shows improved robustness against false positives and false negatives. The proposed methodology offers a scalable solution for automated HL detection across various types of sports video content, reducing the need for manual intervention. Future work will focus on enhancing model architectures and extending this approach to broader scene-detection tasks in media analysis.

The irruption of DeepSeek-R1 constitutes a turning point for the AI industry in general and the LLMs in particular. Its capabilities have demonstrated outstanding performance in several tasks, including creative thinking, code generation, maths and automated program repair, at apparently lower execution cost. However, LLMs must adhere to an important qualitative property, i.e., their alignment with safety and human values. A clear competitor of DeepSeek-R1 is its American counterpart, OpenAI's o3-mini model, which is expected to set high standards in terms of performance, safety and cost. In this technical report, we systematically assess the safety level of both DeepSeek-R1 (70b version) and OpenAI's o3-mini (beta version). To this end, we make use of our recently released automated safety testing tool, named ASTRAL. By leveraging this tool, we automatically and systematically generated and executed 1,260 test inputs on both models. After conducting a semi-automated assessment of the outcomes provided by both LLMs, the results indicate that DeepSeek-R1 produces significantly more unsafe responses (12%) than OpenAI's o3-mini (1.2%).

The web has become a crucial source of information, but it is also used to spread disinformation, often conveyed through multiple modalities like images and text. The identification of inconsistent cross-modal information, in particular entities such as persons, locations, and events, is critical to detect disinformation. Previous works either identify out-of-context disinformation by assessing the consistency of images to the whole document, neglecting relations of individual entities, or focus on generic entities that are not relevant to news. So far, only few approaches have addressed the task of validating entity consistency between images and text in news. However, the potential of large vision-language models (LVLMs) has not been explored yet. In this paper, we propose an LVLM-based framework for verifying Cross-modal Entity Consistency~(LVLM4CEC), to assess whether persons, locations and events in news articles are consistent across both modalities. We suggest effective prompting strategies for LVLMs for entity verification that leverage reference images crawled from web. Moreover, we extend three existing datasets for the task of entity verification in news providing manual ground-truth data. Our results show the potential of LVLMs for automating cross-modal entity verification, showing improved accuracy in identifying persons and events when using evidence images. Moreover, our method outperforms a baseline for location and event verification in documents. The datasets and source code are available on GitHub at https://github.com/TIBHannover/LVLM4CEC.

Despite living in an increasingly connected world, social isolation is a prevalent issue today. While social robots have been explored as tools to enhance social connection through companionship, their potential as asynchronous social platforms for fostering connection towards humanity has received less attention. In this work, we introduce the design of a social support companion that facilitates the exchange of emotionally relevant stories and scaffolds reflection to enhance feelings of connection via five design dimensions. We investigate how social robots can serve as "social proxies" facilitating human stories, passing stories from other human narrators to the user. To this end, we conduct a real-world deployment of 40 robot stations in users' homes over the course of two weeks. Through thematic analysis of user interviews, we find that social proxy robots can foster connection towards other people's experiences via mechanisms such as identifying connections across stories or offering diverse perspectives. We present design guidelines from our study insights on the use of social robot systems that serve as social platforms to enhance human empathy and connection.

The deepfake generation of singing vocals is a concerning issue for artists in the music industry. In this work, we propose a singing voice deepfake detection (SVDD) system, which uses noise-variant encodings of open-AI's Whisper model. As counter-intuitive as it may sound, even though the Whisper model is known to be noise-robust, the encodings are rich in non-speech information, and are noise-variant. This leads us to evaluate Whisper encodings as feature representations for the SVDD task. Therefore, in this work, the SVDD task is performed on vocals and mixtures, and the performance is evaluated in \%EER over varying Whisper model sizes and two classifiers- CNN and ResNet34, under different testing conditions.

The field of text privatization often leverages the notion of $\textit{Differential Privacy}$ (DP) to provide formal guarantees in the rewriting or obfuscation of sensitive textual data. A common and nearly ubiquitous form of DP application necessitates the addition of calibrated noise to vector representations of text, either at the data- or model-level, which is governed by the privacy parameter $\varepsilon$. However, noise addition almost undoubtedly leads to considerable utility loss, thereby highlighting one major drawback of DP in NLP. In this work, we introduce a new sentence infilling privatization technique, and we use this method to explore the effect of noise in DP text rewriting. We empirically demonstrate that non-DP privatization techniques excel in utility preservation and can find an acceptable empirical privacy-utility trade-off, yet cannot outperform DP methods in empirical privacy protections. Our results highlight the significant impact of noise in current DP rewriting mechanisms, leading to a discussion of the merits and challenges of DP in NLP, as well as the opportunities that non-DP methods present.

As artificial intelligence demonstrates surpassing human performance across real-world tasks, disclosing superhuman capabilities poses challenges for fairness, accountability, and trust. To investigate how transparency impacts attitudes and perceptions, we introduce a grounded and validated set of synthetic personas reflecting diverse fairness concerns and technology acceptance levels. Then we evaluate responses in two contrasting domains: (1) a competitive player in StarCraft II, where strategy and high-skill gameplay often elicit toxic interactions, and (2) a cooperative personal-assistant in providing information. Across numerous interactions spanning persona profiles, we test non-disclosure versus explicit superhuman labelling under controlled game outcomes and usage contexts. Our findings reveal sharp domain-specific effects: in StarCraft II, explicitly labelling AI as superhuman, novice personas who learned of it reported lower toxicity and higher fairness-attributing defeat to advanced skill rather than hidden cheating-whereas expert personas found the disclosure statements irksome but still less deceptive than non-disclosure. Conversely, in the LLM as personal-assistant setting, disclosure of superhuman capabilities improved perceived trustworthiness, though it risked AI overreliance among certain persona segments. We release Dataset X-containing persona cards-including profile attributes, disclosure prompts, and detailed interaction logs, accompanied by reproducible protocols and disclaimers for adapting them to diverse tasks. Our results demonstrate that transparency is not a cure-all: while it reduces suspicion and enhances trust in cooperative contexts, it may inflame resistance or disappointment in competitive domains.