While human speakers use a variety of different expressions when describing the same object in an image, giving rise to a distribution of plausible labels driven by pragmatic constraints, the extent to which current Vision & Language Large Language Models (VLLMs) can mimic this crucial feature of language use is an open question. This applies to common, everyday objects, but it is particularly interesting for uncommon or novel objects for which a category label may be lacking or fuzzy. Furthermore, similar patterns of variation are observed among human speakers for highly context-sensitive expressions, such as the quantifiers 'few' or 'most'. In our work, we evaluate VLLMs (FROMAGe, BLIP-2, LLaVA) on three categories (nouns, attributes, and quantifiers) where humans show great subjective variability concerning the distribution over plausible labels, using datasets and resources mostly under-explored in previous work. Our results reveal mixed evidence on the ability of VLLMs to capture human naming preferences at generation time: while some models are good at mimicking human distributions for nouns and attributes, all of them fail to assign quantifiers, a task that requires more accurate, high-level reasoning.

Multimodal large language models (MLLMs) have demonstrated promising results in a variety of tasks that combine vision and language. As these models become more integral to research and applications, conducting comprehensive evaluations of their capabilities has grown increasingly important. However, most existing benchmarks fail to consider that, in certain situations, images need to be interpreted within a broader context. In this work, we introduce a new benchmark, named as CODIS, designed to assess the ability of models to use context provided in free-form text to enhance visual comprehension. Our findings indicate that MLLMs consistently fall short of human performance on this benchmark. Further analysis confirms that these models struggle to effectively extract and utilize contextual information to improve their understanding of images. This underscores the pressing need to enhance the ability of MLLMs to comprehend visuals in a context-dependent manner. View our project website at https://thunlp-mt.github.io/CODIS.

In the Markov chain Monte Carlo methods have become recent years, the evolution of deep neural networks has notably popular in statistics as versatile techniques to sample propelled the field of Variational Inference (Rezende & from complicated probability distributions. In Mohamed, 2015; Kingma & Welling, 2014; Rezende et al., this work, we propose a method to parameterize 2014; Kingma et al., 2016) whilst MCMC methods have and train transition kernels of Markov chains not benefited much from these advances. Using neural networks to achieve efficient sampling and good mixing.

In large-scale regression problems, random Fourier features (RFFs) have significantly enhanced the computational scalability and flexibility of Gaussian processes (GPs) by defining kernels through their spectral density, from which a finite set of Monte Carlo samples can be used to form an approximate low-rank GP. However, the efficacy of RFFs in kernel approximation and Bayesian kernel learning depends on the ability to tractably sample the kernel spectral measure and the quality of the generated samples. We introduce Stein random features (SRF), leveraging Stein variational gradient descent, which can be used to both generate high-quality RFF samples of known spectral densities as well as flexibly and efficiently approximate traditionally non-analytical spectral measure posteriors. SRFs require only the evaluation of log-probability gradients to perform both kernel approximation and Bayesian kernel learning that results in superior performance over traditional approaches. We empirically validate the effectiveness of SRFs by comparing them to baselines on kernel approximation and well-known GP regression problems.

Weighted low rank approximation (WLRA) is an important yet computationally challenging primitive with applications ranging from statistical analysis, model compression, and signal processing. To cope with the NP-hardness of this problem, prior work considers heuristics, bicriteria, or fixed parameter tractable algorithms to solve this problem. In this work, we introduce a new relaxed solution to WLRA which outputs a matrix that is not necessarily low rank, but can be stored using very few parameters and gives provable approximation guarantees when the weight matrix has low rank. Our central idea is to use the weight matrix itself to reweight a low rank solution, which gives an extremely simple algorithm with remarkable empirical performance in applications to model compression and on synthetic datasets. Our algorithm also gives nearly optimal communication complexity bounds for a natural distributed problem associated with this problem, for which we show matching communication lower bounds. Together, our communication complexity bounds show that the rank of the weight matrix provably parameterizes the communication complexity of WLRA. We also obtain the first relative error guarantees for feature selection with a weighted objective.

In medieval Europe, barber-surgeons might cut your hair, shave your face, do a bit of blood-letting and tend to a broken limb. They might also pull a tooth out with a "pelican" – a crude beak-like shank – or lever it out with an iron "tooth key". By the 17th century they might just knock it out with a steel punch elevator. It's a winding, gruesome road from these early practitioners of dentistry to today's world of 3D printing, artificial intelligence and robots that can create dental implants. Wayne Sampson, a dental historian and emeritus professor at the University of Adelaide, says the history of dental work goes back much further than the barber-surgeons.

Current methods of toxic language detection (TLD) typically rely on specific tokens to conduct decisions, which makes them suffer from lexical bias, leading to inferior performance and generalization. Lexical bias has both "useful" and "misleading" impacts on understanding toxicity. Unfortunately, instead of distinguishing between these impacts, current debiasing methods typically eliminate them indiscriminately, resulting in a degradation in the detection accuracy of the model. To this end, we propose a Counterfactual Causal Debiasing Framework (CCDF) to mitigate lexical bias in TLD. It preserves the "useful impact" of lexical bias and eliminates the "misleading impact". Specifically, we first represent the total effect of the original sentence and biased tokens on decisions from a causal view. We then conduct counterfactual inference to exclude the direct causal effect of lexical bias from the total effect. Empirical evaluations demonstrate that the debiased TLD model incorporating CCDF achieves state-of-the-art performance in both accuracy and fairness compared to competitive baselines applied on several vanilla models. The generalization capability of our model outperforms current debiased models for out-of-distribution data.

This research investigates the curriculum structures of undergraduate Artificial Intelligence (AI) education across universities worldwide. By examining the curricula of leading universities, the research seeks to contribute to a deeper understanding of AI education on a global scale, facilitating the alignment of educational practices with the evolving needs of the AI landscape. This research delves into the diverse course structures of leading universities, exploring contemporary trends and priorities to reveal the nuanced approaches in AI education. It also investigates the core AI topics and learning contents frequently taught, comparing them with the CS2023 curriculum guidance to identify convergence and divergence. Additionally, it examines how universities across different countries approach AI education, analyzing educational objectives, priorities, potential careers, and methodologies to understand the global landscape and implications of AI pedagogy.

In Artificial Intelligence, there is an increasing demand for adaptive models capable of dealing with a diverse spectrum of learning tasks, surpassing the limitations of systems devised to cope with a single task. The recent emergence of General-Purpose Artificial Intelligence Systems (GPAIS) poses model configuration and adaptability challenges at far greater complexity scales than the optimal design of traditional Machine Learning models. Evolutionary Computation (EC) has been a useful tool for both the design and optimization of Machine Learning models, endowing them with the capability to configure and/or adapt themselves to the task under consideration. Therefore, their application to GPAIS is a natural choice. This paper aims to analyze the role of EC in the field of GPAIS, exploring the use of EC for their design or enrichment. We also match GPAIS properties to Machine Learning areas in which EC has had a notable contribution, highlighting recent milestones of EC for GPAIS. Furthermore, we discuss the challenges of harnessing the benefits of EC for GPAIS, presenting different strategies to both design and improve GPAIS with EC, covering tangential areas, identifying research niches, and outlining potential research directions for EC and GPAIS.

Inertial Measurement Unit (IMU) sensors are widely employed for Human Activity Recognition (HAR) due to their portability, energy efficiency, and growing research interest. However, a significant challenge for IMU-HAR models is achieving robust generalization performance across diverse users. This limitation stems from substantial variations in data distribution among individual users. One primary reason for this distribution disparity lies in the representation of IMU sensor data in the local coordinate system, which is susceptible to subtle user variations during IMU wearing. To address this issue, we propose a novel approach that extracts a global view representation based on the characteristics of IMU data, effectively alleviating the data distribution discrepancies induced by wearing styles. To validate the efficacy of the global view representation, we fed both global and local view data into model for experiments. The results demonstrate that global view data significantly outperforms local view data in cross-user experiments. Furthermore, we propose a Multi-view Supervised Network (MVFNet) based on Shuffling to effectively fuse local view and global view data. It supervises the feature extraction of each view through view division and view shuffling, so as to avoid the model ignoring important features as much as possible. Extensive experiments conducted on OPPORTUNITY and PAMAP2 datasets demonstrate that the proposed algorithm outperforms the current state-of-the-art methods in cross-user HAR.