深度神经网络具有令人印象深刻的性能，但是他们无法可靠地估计其预测信心，从而限制了其在高风险领域中的适用性。我们表明，应用多标签的一VS损失揭示了分类的歧义并降低了模型的过度自信。引入的Slova（单标签One-Vs-All）模型重新定义了单个标签情况的典型单VS-ALL预测概率，其中只有一个类是正确的答案。仅当单个类具有很高的概率并且其他概率可忽略不计时，提议的分类器才有信心。与典型的SoftMax函数不同，如果所有其他类的概率都很小，Slova自然会检测到分布的样本。该模型还通过指数校准进行了微调，这使我们能够与模型精度准确地对齐置信分数。我们在三个任务上验证我们的方法。首先，我们证明了斯洛伐克与最先进的分布校准具有竞争力。其次，在数据集偏移下，斯洛伐克的性能很强。最后，我们的方法在检测到分布样品的检测方面表现出色。因此，斯洛伐克是一种工具，可以在需要不确定性建模的各种应用中使用。

现代生成型号在包括图像或文本生成和化学分子建模的各种任务中获得优异的品质。然而，现有方法往往缺乏通过所要求的属性产生实例的基本能力，例如照片中的人的年龄或产生的分子的重量。包含此类额外的调节因子将需要重建整个架构并从头开始优化参数。此外，难以解除选定的属性，以便仅在将其他属性中执行不变的同时执行编辑。为了克服这些限制，我们提出插件（插件生成网络），这是一种简单而有效的生成技术，可以用作预先训练的生成模型的插件。我们的方法背后的想法是使用基于流的模块将纠缠潜在的潜在表示转换为多维空间，其中每个属性的值被建模为独立的一维分布。因此，插件可以生成具有所需属性的新样本，以及操作现有示例的标记属性。由于潜在代表的解散，我们甚至能够在数据集中的稀有或看不见的属性组合生成样本，例如具有灰色头发的年轻人，有妆容的男性或胡须的女性。我们将插入与GaN和VAE模型组合并将其应用于图像和化学分子建模的条件生成和操纵。实验表明，插件保留了骨干型号的质量，同时添加控制标记属性值的能力。

减少大深度学习模型的处理时间的问题是许多现实世界应用中的根本挑战。早期退出方法通过将附加内部分类器（IC）附加到神经网络的中间层来努力实现这一目标。 IC可以快速返回简单示例的预测，结果，降低整个模型的平均推理时间。但是，如果特定IC不决定早期回答，则其预测被丢弃，其计算有效地浪费。为了解决这个问题，我们引入零时间浪费（ZTW），这是一种新的方法，其中每个IC重用由其前辈返回的预测（1）在IC和（2）之间以相对于类似的方式组合先前输出之间的直接连接。我们对各个数据集和架构进行了广泛的实验，以证明ZTW实现了比最近提出的早期退出方法的其他更好的比例与推理时间权衡。

This paper presents the Crowd Score, a novel method to assess the funniness of jokes using large language models (LLMs) as AI judges. Our method relies on inducing different personalities into the LLM and aggregating the votes of the AI judges into a single score to rate jokes. We validate the votes using an auditing technique that checks if the explanation for a particular vote is reasonable using the LLM. We tested our methodology on 52 jokes in a crowd of four AI voters with different humour types: affiliative, self-enhancing, aggressive and self-defeating. Our results show that few-shot prompting leads to better results than zero-shot for the voting question. Personality induction showed that aggressive and self-defeating voters are significantly more inclined to find more jokes funny of a set of aggressive/self-defeating jokes than the affiliative and self-enhancing voters. The Crowd Score follows the same trend as human judges by assigning higher scores to jokes that are also considered funnier by human judges. We believe that our methodology could be applied to other creative domains such as story, poetry, slogans, etc. It could both help the adoption of a flexible and accurate standard approach to compare different work in the CC community under a common metric and by minimizing human participation in assessing creative artefacts, it could accelerate the prototyping of creative artefacts and reduce the cost of hiring human participants to rate creative artefacts.

Robust Markov decision processes (RMDPs) are promising models that provide reliable policies under ambiguities in model parameters. As opposed to nominal Markov decision processes (MDPs), however, the state-of-the-art solution methods for RMDPs are limited to value-based methods, such as value iteration and policy iteration. This paper proposes Double-Loop Robust Policy Gradient (DRPG), the first generic policy gradient method for RMDPs with a global convergence guarantee in tabular problems. Unlike value-based methods, DRPG does not rely on dynamic programming techniques. In particular, the inner-loop robust policy evaluation problem is solved via projected gradient descent. Finally, our experimental results demonstrate the performance of our algorithm and verify our theoretical guarantees.

This paper presents a conversational AI platform called Flowstorm. Flowstorm is an open-source SaaS project suitable for creating, running, and analyzing conversational applications. Thanks to the fast and fully automated build process, the dialogues created within the platform can be executed in seconds. Furthermore, we propose a novel dialogue architecture that uses a combination of tree structures with generative models. The tree structures are also used for training NLU models suitable for specific dialogue scenarios. However, the generative models are globally used across applications and extend the functionality of the dialogue trees. Moreover, the platform functionality benefits from out-of-the-box components, such as the one responsible for extracting data from utterances or working with crawled data. Additionally, it can be extended using a custom code directly in the platform. One of the essential features of the platform is the possibility to reuse the created assets across applications. There is a library of prepared assets where each developer can contribute. All of the features are available through a user-friendly visual editor.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Entrainment is the phenomenon by which an interlocutor adapts their speaking style to align with their partner in conversations. It has been found in different dimensions as acoustic, prosodic, lexical or syntactic. In this work, we explore and utilize the entrainment phenomenon to improve spoken dialogue systems for voice assistants. We first examine the existence of the entrainment phenomenon in human-to-human dialogues in respect to acoustic feature and then extend the analysis to emotion features. The analysis results show strong evidence of entrainment in terms of both acoustic and emotion features. Based on this findings, we implement two entrainment policies and assess if the integration of entrainment principle into a Text-to-Speech (TTS) system improves the synthesis performance and the user experience. It is found that the integration of the entrainment principle into a TTS system brings performance improvement when considering acoustic features, while no obvious improvement is observed when considering emotion features.

Large language models demonstrate an emergent ability to learn a new task from a small number of input-output demonstrations, referred to as in-context few-shot learning. However, recent work shows that in such settings, models mainly learn to mimic the new task distribution, instead of the mechanics of the new task. We argue that the commonly-used evaluation settings of few-shot models utilizing a random selection of in-context demonstrations is not able to disentangle models' ability to learn new skills from demonstrations, as most of the such-selected demonstrations are not informative for prediction beyond exposing the new task's input and output distribution. Therefore, we introduce an evaluation technique that disentangles few-shot learners' gain from in-context learning by picking the demonstrations sharing a specific, informative concept with the predicted sample, in addition to the performance reached by mainly non-informative samples. We find that regardless of the model size, existing few-shot learners are not able to benefit from observing such informative concepts in demonstrations. We also find that such ability may not be obtained trivially by exposing the informative demonstrations in the training process, leaving the challenge of training true in-context learners open.

Domain adaptation allows generative language models to address specific flaws caused by the domain shift of their application. However, the traditional adaptation by further training on in-domain data rapidly weakens the model's ability to generalize to other domains, making the open-ended deployments of the adapted models prone to errors. This work introduces novel training objectives built upon a semantic similarity of the predicted tokens to the reference. Our results show that (1) avoiding the common assumption of a single correct prediction by constructing the training target from tokens' semantic similarity can mitigate catastrophic forgetting during domain adaptation, while (2) preserving the quality of the adaptation, (3) with negligible additions to compute costs. In the broader perspective, the objectives grounded in a soft token alignment pioneer the exploration of the middle ground between the efficient but naive exact-match token-level objectives and expressive but computationally- and resource-intensive sequential objectives.