When Netflix first started adding video games to its huge catalogue of streaming TV shows and films, it did so quietly. In 2021, after releasing an impressive experiment with the idea of interactive film in Black Mirror: Bandersnatch in 2018 and a free Stranger Things game in 2019, Netflix began expanding more fully into interactive entertainment. The streamer's gaming offering, for a long time, was its best-kept secret. Whoever was running it really had an eye for quality: award-winningly brilliant and relatively little-known indie games comprised the majority of its catalogue, alongside decent licensed games based on everything from The Queen's Gambit to the reality dating show Too Hot to Handle. Subscribers could play games such as Before Your Eyes, a brief and touching story about a life cut short; Spiritfarer, about guiding lost souls to rest and Into the Breach, a superb sci-fi strategy game with robots v aliens.

Cyber information influence, or disinformation in general terms, is widely regarded as one of the biggest threats to social progress and government stability. From US presidential elections to European Union referendums and down to regional news reporting of wildfires, lies and post-truths have normalized radical decision-making. Accordingly, there has been an explosion in research seeking to detect disinformation in online media. The frontier of disinformation detection research is leveraging a variety of ML techniques such as traditional ML algorithms like Support Vector Machines, Random Forest, and Na\"ive Bayes. Other research has applied deep learning models including Convolutional Neural Networks, Long Short-Term Memory networks, and transformer-based architectures. Despite the overall success of such techniques, the literature demonstrates inconsistencies when viewed holistically which limits our understanding of the true effectiveness. Accordingly, this work employed a two-stage meta-analysis to (a) demonstrate an overall meta statistic for ML model effectiveness in detecting disinformation and (b) investigate the same by subgroups of ML model types. The study found the majority of the 81 ML detection techniques sampled have greater than an 80\% accuracy with a Mean sample effectiveness of 79.18\% accuracy. Meanwhile, subgroups demonstrated no statistically significant difference between-approaches but revealed high within-group variance. Based on the results, this work recommends future work in replication and development of detection methods operating at the ML model level.

--T ext-to-audio (TT A), which generates audio signals from textual descriptions, has received huge attention in recent years. However, recent works focused on text to monaural audio only. As we know, spatial audio provides more immersive auditory experience than monaural audio, e.g. in virtual reality. T o address this issue, we propose a text-to-spatial-audio (TTSA) generation framework named DualSpec.Specifically, it first trains variational autoencoders (V AEs) for extracting the latent acoustic representations from sound event audio. Then, given text that describes sound events and event directions, the proposed method uses the encoder of a pretrained large language model to transform the text into text features. Finally, it trains a diffusion model from the latent acoustic representations and text features for the spatial audio generation. In the inference stage, only the text description is needed to generate spatial audio. Particularly, to improve the synthesis quality and azimuth accuracy of the spatial sound events simultaneously, we propose to use two kinds of acoustic features. One is the Mel spectrograms which is good for improving the synthesis quality, and the other is the short-time Fourier transform spectrograms which is good at improving the azimuth accuracy. We provide a pipeline of constructing spatial audio dataset with text prompts, for the training of the V AEs and diffusion model. We also introduce new spatial-aware evaluation metrics to quantify the azimuth errors of the generated spatial audio recordings. Experimental results demonstrate that the proposed method can generate spatial audio with high directional and event consistency.

Much of the success of multi-agent debates depends on carefully choosing the right parameters. Among them, the decision-making protocol stands out. Systematic comparison of decision protocols is difficult because studies alter multiple discussion parameters beyond the protocol. So far, it has been largely unknown how decision-making addresses the challenges of different tasks. This work systematically evaluates the impact of seven decision protocols (e.g., majority voting, unanimity consensus). We change only one variable at a time (i.e., decision protocol) to analyze how different methods affect the collaboration between agents and test different protocols on knowledge (MMLU, MMLU-Pro, GPQA) and reasoning datasets (StrategyQA, MuSR, SQuAD 2.0). Our results show that voting protocols improve performance by 13.2% in reasoning tasks and consensus protocols by 2.8% in knowledge tasks over the other decision protocol. Increasing the number of agents improves performance, while more discussion rounds before voting reduces it. To improve decision-making by increasing answer diversity, we propose two new methods, All-Agents Drafting (AAD) and Collective Improvement (CI). Our methods improve task performance by up to 3.3% with AAD and up to 7.4% with CI. This work demonstrates the importance of decision-making in multi-agent debates beyond scaling.

This literature review interrogates the intersections between artificial intelligence, poetry, and art, offering a comprehensive exploration of both historical evolution and current debates in digital creative practices. It traces the development of computer-generated poetry from early template-based systems to generative models, critically assessing evaluative frameworks such as adaptations of the Turing Test, the FACE model, and ProFTAP. It also examines how these frameworks endeavour to measure creativity, semantic coherence, and cultural relevance in AI-generated texts, whilst highlighting the persistent challenges in replicating the nuance of human poetic expression. The review contributes a Marketing Theory discussion that deconstructs the figurative marketing narratives employed by AI companies, which utilise sanitised language and anthropomorphic metaphors to humanise their technologies. This discussion reveals the reductive nature of such narratives and underscores the tension between algorithmic precision and the realities of human creativity.The review also incorporates an auto-ethnographic account that offers a self-reflexive commentary on its own composition. By acknowledging the use of AI in crafting this review, the auto-ethnographic account destabilises conventional notions of authorship and objectivity, resonating with deconstruction and challenging logocentric assumptions in academic discourse. Ultimately, the review calls for a re-evaluation of creative processes that recognises the interdependence of technological innovation and human subjectivity. It advocates for interdisciplinary dialogue addressing ethical, cultural, and philosophical concerns, while reimagining the boundaries of artistic production.

Driven by inherent uncertainty and the sim-to-real gap, robust reinforcement learning (RL) seeks to improve resilience against the complexity and variability in agent-environment sequential interactions. Despite the existence of a large number of RL benchmarks, there is a lack of standardized benchmarks for robust RL. Current robust RL policies often focus on a specific type of uncertainty and are evaluated in distinct, one-off environments. In this work, we introduce Robust-Gymnasium, a unified modular benchmark designed for robust RL that supports a wide variety of disruptions across all key RL components-agents' observed state and reward, agents' actions, and the environment. Offering over sixty diverse task environments spanning control and robotics, safe RL, and multi-agent RL, it provides an open-source and user-friendly tool for the community to assess current methods and foster the development of robust RL algorithms. In addition, we benchmark existing standard and robust RL algorithms within this framework, uncovering significant deficiencies in each and offering new insights.

There is growing excitement about the potential of Language Models (LMs) to accelerate scientific discovery. Falsifying hypotheses is key to scientific progress, as it allows claims to be iteratively refined over time. This process requires significant researcher effort, reasoning, and ingenuity. Yet current benchmarks for LMs predominantly assess their ability to generate solutions rather than challenge them. We advocate for developing benchmarks that evaluate this inverse capability - creating counterexamples for subtly incorrect solutions. To demonstrate this approach, we start with the domain of algorithmic problem solving, where counterexamples can be evaluated automatically using code execution. Specifically, we introduce REFUTE, a dynamically updating benchmark that includes recent problems and incorrect submissions from programming competitions, where human experts successfully identified counterexamples. Our analysis finds that the best reasoning agents, even OpenAI o3-mini (high) with code execution feedback, can create counterexamples for only <9% of incorrect solutions in REFUTE, even though ratings indicate its ability to solve up to 48% of these problems from scratch. We hope our work spurs progress in evaluating and enhancing LMs' ability to falsify incorrect solutions - a capability that is crucial for both accelerating research and making models self-improve through reliable reflective reasoning.

The stance detection task aims to categorise the stance regarding specified targets. Current methods face challenges in effectively integrating sentiment information for stance detection. Moreover, the role of highly granular sentiment labelling in stance detection has been largely overlooked. This study presents a novel stance detection framework utilizing a variational autoencoder (VAE) to disentangle latent emotional features-value, arousal, and dominance (VAD)-from political discourse on social media. This approach addresses limitations in current methods, particularly in in-target and cross-target stance detection scenarios. This research uses an advanced emotional annotation tool to annotate seven-class sentiment labels for P-STANCE. Evaluations on benchmark datasets, including P-STANCE and SemEval-2016, reveal that PoliStance-VAE achieves state-of-the-art performance, surpassing models like BERT, BERTweet, and GPT-4o. PoliStance-VAE offers a robust and interpretable solution for stance detection, demonstrating the effectiveness of integrating nuanced emotional representations. This framework paves the way for advancements in natural language processing tasks, particularly those requiring detailed emotional understanding.

Large Language Models (LLMs) often struggle to align their responses with objective facts, resulting in the issue of factual hallucinations, which can be difficult to detect and mislead users without relevant knowledge. While post-training techniques have been employed to mitigate the issue, existing methods usually suffer from poor generalization and trade-offs in different capabilities. In this paper, we propose to address it by directly augmenting LLM's fundamental ability to precisely leverage its existing memory--the knowledge acquired from pre-training data. We introduce self-memory alignment (SMA), which fine-tunes the model on self-generated responses to precise and simple factual questions through preference optimization. Furthermore, we construct FactualBench, a comprehensive and precise factual QA dataset containing 181k Chinese data spanning 21 domains, to facilitate both evaluation and training. Extensive experiments show that SMA significantly improves LLMs' overall performance, with consistent enhancement across various benchmarks concerning factuality, as well as helpfulness and comprehensive skills.

Sentiment Analysis (SA) or opinion mining is analysis of emotions and opinions from any kind of text. SA helps in tracking peoples viewpoints and it is an important factor when it comes to social media monitoring product and brand recognition customer satisfaction customer loyalty advertising and promotions success and product acceptance. That is why SA is one of the active research areas in Natural Language Processing (NLP). SA is applied on data sourced from various media platforms to mine sentiment knowledge from them. Various approaches have been deployed in the literature to solve the problem. Most techniques devise complex and sophisticated frameworks in order to attain optimal accuracy. This work aims to finetune Bidirectional Encoder Representations from Transformers (BERT) with Bidirectional Long Short-Term Memory (BiLSTM) for movie reviews sentiment analysis and still provide better accuracy than the State-of-The-Art (SOTA) methods. The paper also shows how sentiment analysis can be applied if someone wants to recommend a certain movie for example by computing overall polarity of its sentiments predicted by the model. That is our proposed method serves as an upper-bound baseline in prediction of a predominant reaction to a movie. To compute overall polarity a heuristic algorithm is applied to BERTBiLSTM output vector. Our model can be extended to three-class four-class or any fine-grained classification and apply overall polarity computation again. This is intended to be exploited in future work.