Generating long-term texts such as novels using artificial intelligence has always been a challenge. A common approach is to use large language models (LLMs) to construct a hierarchical framework that first plans and then writes. Despite the fact that the generated novels reach a sufficient length, they exhibit poor logical coherence and appeal in their plots and deficiencies in character and event depiction, ultimately compromising the overall narrative quality. In this paper, we propose a method named Extracting Excelsior and Expanding. Ex3 initially extracts structure information from raw novel data. By combining this structure information with the novel data, an instruction-following dataset is meticulously crafted. This dataset is then utilized to fine-tune the LLM, aiming for excelsior generation performance. In the final stage, a tree-like expansion method is deployed to facilitate the generation of arbitrarily long novels. Evaluation against previous methods showcases Ex3's ability to produce higher-quality long-form novels.

This paper establishes a connection between the fields of machine learning (ML) and philosophy concerning the phenomenon of behaving neutrally. It investigates a specific class of ML systems capable of delivering a neutral response to a given task, referred to as abstaining machine learning systems, that has not yet been studied from a philosophical perspective. The paper introduces and explains various abstaining machine learning systems, and categorizes them into distinct types. An examination is conducted on how abstention in the different machine learning system types aligns with the epistemological counterpart of suspended judgment, addressing both the nature of suspension and its normative profile. Additionally, a philosophical analysis is suggested on the autonomy and explainability of the abstaining response. It is argued, specifically, that one of the distinguished types of abstaining systems is preferable as it aligns more closely with our criteria for suspended judgment. Moreover, it is better equipped to autonomously generate abstaining outputs and offer explanations for abstaining outputs when compared to the other type.

In the digital era, blockchain technology, cryptocurrencies, and non-fungible tokens (NFTs) have transformed financial and decentralized systems. However, existing research often neglects the spatiotemporal variations in public sentiment toward these technologies, limiting macro-level insights into their global impact. This study leverages Twitter data to explore public attention and sentiment across 150 countries, analyzing over 150 million geotagged tweets from 2012 to 2022. Sentiment scores were derived using a BERT-based multilingual sentiment model trained on 7.4 billion tweets. The analysis integrates global cryptocurrency regulations and economic indicators from the World Development Indicators database. Results reveal significant global sentiment variations influenced by economic factors, with more developed nations engaging more in discussions, while less developed countries show higher sentiment levels. Geographically weighted regression indicates that GDP-tweet engagement correlation intensifies following Bitcoin price surges. Topic modeling shows that countries within similar economic clusters share discussion trends, while different clusters focus on distinct topics. This study highlights global disparities in sentiment toward decentralized finance, shaped by economic and regional factors, with implications for poverty alleviation, cryptocurrency crime, and sustainable development. The dataset and code are publicly available on GitHub.

While methods based on Vision Transformers (ViT) have achieved state-of-the-art performance in many domains, they have not yet been applied successfully in the domain of writer retrieval. The field is dominated by methods using handcrafted features or features extracted from Convolutional Neural Networks. In this work, we bridge this gap and present a novel method that extracts features from a ViT and aggregates them using VLAD encoding. The model is trained in a self-supervised fashion without any need for labels. We show that extracting local foreground features is superior to using the ViT's class token in the context of writer retrieval. We evaluate our method on two historical document collections. We set a new state-at-of-art performance on the Historical-WI dataset (83.1\% mAP), and the HisIR19 dataset (95.0\% mAP). Additionally, we demonstrate that our ViT feature extractor can be directly applied to modern datasets such as the CVL database (98.6\% mAP) without any fine-tuning.

In this work, we build on [34] and examine the limitations of current state-of-the-art text-audio models, particularly in their Recent advancements in machine learning have fueled research use of temporal information. Different from [34] that considers on multimodal tasks, such as for instance text-to-video and textto-audio a text-audio model containing a CNN-based audio encoder, our retrieval. These tasks require models to understand the analysis uses the recent transformer-based audio encoder HTS-semantic content of video and audio data, including objects, and AT [4] that serves as a component of state-of-the-art text-to-audio characters. The models also need to learn spatial arrangements and retrieval models [24, 35]. We assess whether the model containing temporal relationships. In this work, we analyse the temporal ordering a transformer-based audio encoder results in better temporal of sounds, which is an understudied problem in the context of understanding abilities than a CNN-based one.

Dialect adapters that improve the performance of LLMs for NLU tasks on certain sociolects/dialects/national varieties ('dialects' for the sake of brevity) have been reported for encoder models. In this paper, we extend the idea of dialect adapters to decoder models in our architecture called LoRDD. Using MD-3, a publicly available dataset of word game-playing conversations between dialectal speakers, our task is Target Word Prediction (TWP) from a masked conversation. LoRDD combines task adapters and dialect adapters where the latter employ contrastive learning on pseudo-parallel conversations from MD-3. Our results for en-IN conversations on two models (Mistral and Gemma) show that LoRDD outperforms four baselines on TWP, while bridging the performance gap with en-US by 12% on word similarity and 25% on accuracy. The focused contribution of LoRDD is in its promise for dialect adaptation of decoder models.

In face-to-face dialogues, the form-meaning relationship of co-speech gestures varies depending on contextual factors such as what the gestures refer to and the individual characteristics of speakers. These factors make co-speech gesture representation learning challenging. How can we learn meaningful gestures representations considering gestures' variability and relationship with speech? This paper tackles this challenge by employing self-supervised contrastive learning techniques to learn gesture representations from skeletal and speech information. We propose an approach that includes both unimodal and multimodal pre-training to ground gesture representations in co-occurring speech. For training, we utilize a face-to-face dialogue dataset rich with representational iconic gestures. We conduct thorough intrinsic evaluations of the learned representations through comparison with human-annotated pairwise gesture similarity. Moreover, we perform a diagnostic probing analysis to assess the possibility of recovering interpretable gesture features from the learned representations. Our results show a significant positive correlation with human-annotated gesture similarity and reveal that the similarity between the learned representations is consistent with well-motivated patterns related to the dynamics of dialogue interaction. Moreover, our findings demonstrate that several features concerning the form of gestures can be recovered from the latent representations. Overall, this study shows that multimodal contrastive learning is a promising approach for learning gesture representations, which opens the door to using such representations in larger-scale gesture analysis studies.

Regular patterns of vegetation are considered widespread landscapes, although their global extent has never been estimated. Among them, spotted landscapes are of particular interest in the context of climate change. Indeed, regularly spaced vegetation spots in semi-arid shrublands result from extreme resource depletion and prefigure catastrophic shift of the ecosystem to a homogeneous desert, while termite mounds also producing spotted landscapes were shown to increase robustness to climate change. Yet, their identification at large scale calls for automatic methods, for instance using the popular deep learning framework, able to cope with a vast amount of remote sensing data, e.g., optical satellite imagery. In this paper, we tackle this problem and benchmark some state-of-the-art deep networks on several landscapes and geographical areas. Despite the promising results we obtained, we found that more research is needed to be able to map automatically these earth mounds from space.

Stance detection, which aims to identify public opinion towards specific targets using social media data, is an important yet challenging task. With the proliferation of diverse multimodal social media content including text, and images multimodal stance detection (MSD) has become a crucial research area. However, existing MSD studies have focused on modeling stance within individual text-image pairs, overlooking the multi-party conversational contexts that naturally occur on social media. This limitation stems from a lack of datasets that authentically capture such conversational scenarios, hindering progress in conversational MSD. To address this, we introduce a new multimodal multi-turn conversational stance detection dataset (called MmMtCSD). To derive stances from this challenging dataset, we propose a novel multimodal large language model stance detection framework (MLLM-SD), that learns joint stance representations from textual and visual modalities. Experiments on MmMtCSD show state-of-the-art performance of our proposed MLLM-SD approach for multimodal stance detection. We believe that MmMtCSD will contribute to advancing real-world applications of stance detection research.

Hyperparameter optimization (HPO) and neural architecture search (NAS) are powerful in attaining state-of-the-art machine learning models, with Bayesian optimization (BO) standing out as a mainstream method. Extending BO into the multi-fidelity setting has been an emerging research topic, but faces the challenge of determining an appropriate fidelity for each hyperparameter configuration to fit the surrogate model. To tackle the challenge, we propose a multi-fidelity BO method named FastBO, which adaptively decides the fidelity for each configuration and efficiently offers strong performance. The advantages are achieved based on the novel concepts of efficient point and saturation point for each configuration. We also show that our adaptive fidelity identification strategy provides a way to extend any single-fidelity method to the multi-fidelity setting, highlighting its generality and applicability.