Foundation models or pre-trained models have substantially improved the performance of various language, vision, and vision-language understanding tasks. However, existing foundation models can only perform the best in one type of tasks, namely language, vision, or vision-language. It is still an open question whether it is possible to construct a foundation model performing the best for all the understanding tasks, which we call a general foundation model. In this paper, we propose a new general foundation model, X-FM (the X-Foundation Model). X-FM has one language encoder, one vision encoder, and one fusion encoder, as well as a new training method. The training method includes two new techniques for learning X-FM from text, image, and image-text pair data. One is to stop gradients from the vision-language training when learning the language encoder. The other is to leverage the vision-language training to guide the learning of the vision encoder. Extensive experiments on benchmark datasets show that X-FM can significantly outperform existing general foundation models and perform better than or comparable to existing foundation models specifically for language, vision, or vision-language understanding. Code and pre-trained models are released at https://github.com/zhangxinsong-nlp/XFM.

Methods for learning optimal policies use causal machine learning models to create human-interpretable rules for making choices around the allocation of different policy interventions. However, in realistic policy-making contexts, decision-makers often care about trade-offs between outcomes, not just single-mindedly maximising utility for one outcome. This paper proposes an approach termed Multi-Objective Policy Learning (MOPoL) which combines optimal decision trees for policy learning with a multi-objective Bayesian optimisation approach to explore the trade-off between multiple outcomes. It does this by building a Pareto frontier of non-dominated models for different hyperparameter settings which govern outcome weighting. The key here is that a low-cost greedy tree can be an accurate proxy for the very computationally costly optimal tree for the purposes of making decisions which means models can be repeatedly fit to learn a Pareto frontier. The method is applied to a real-world case-study of non-price rationing of anti-malarial medication in Kenya.

In 2016, Oskarina Fuentes got a tip from a friend that seemed too good to be true. Her life in Venezuela had become a struggle: Inflation had hit 800 percent under President Nicolás Maduro, and the 26-year-old Fuentes had no stable job and was balancing multiple side hustles to survive. Her friend told her about Appen, an Australian data services company that was looking for crowdsourced workers to tag training data for artificial intelligence algorithms. Most internet users will have done some form of data labeling: identifying images of traffic lights and buses for online captchas. But the algorithms powering new bots that can pass legal exams, create fantastical imagery in seconds, or remove harmful content on social media are trained on datasets--images, video, and text--labeled by gig economy workers in some of the world's cheapest labor markets. Appen's clients have included Amazon, Facebook, Google, and Microsoft, and the company's 1 million contributors are just a part of a vast, hidden industry.

Hundreds of Africans tasked with scouring platforms such as Facebook, TikTok and ChatGPT for graphic content have joined the continent's first union for content moderators, but organizers say some fear losing their jobs if their membership is revealed. The union was established in Nairobi in May with the help of former Facebook moderator and whistleblower Daniel Motaung, who experienced firsthand both the mental toll of this grueling work, and the challenges of holding Big Tech to account. Last year, Motaung, a South African, filed a lawsuit against Facebook's parent company Meta and its local outsourcing firm Sama, alleging irregular pay, union-busting and inadequate mental health support resulting in trauma.

We present DE-VAE, a variational autoencoder (VAE) architecture to search for a compressed representation of dynamical dark energy (DE) models in observational studies of the cosmic large-scale structure. DE-VAE is trained on matter power spectra boosts generated at wavenumbers $k\in(0.01-2.5) \ h/\rm{Mpc}$ and at four redshift values $z\in(0.1,0.48,0.78,1.5)$ for the most typical dynamical DE parametrization with two extra parameters describing an evolving DE equation of state. The boosts are compressed to a lower-dimensional representation, which is concatenated with standard cold dark matter (CDM) parameters and then mapped back to reconstructed boosts; both the compression and the reconstruction components are parametrized as neural networks. Remarkably, we find that a single latent parameter is sufficient to predict 95% (99%) of DE power spectra generated over a broad range of cosmological parameters within $1\sigma$ ($2\sigma$) of a Gaussian error which includes cosmic variance, shot noise and systematic effects for a Stage IV-like survey. This single parameter shows a high mutual information with the two DE parameters, and these three variables can be linked together with an explicit equation through symbolic regression. Considering a model with two latent variables only marginally improves the accuracy of the predictions, and adding a third latent variable has no significant impact on the model's performance. We discuss how the DE-VAE architecture can be extended from a proof of concept to a general framework to be employed in the search for a common lower-dimensional parametrization of a wide range of beyond-$\Lambda$CDM models and for different cosmological datasets. Such a framework could then both inform the development of cosmological surveys by targeting optimal probes, and provide theoretical insight into the common phenomenological aspects of beyond-$\Lambda$CDM models.

This paper is a quantitative analysis of the data collected globally by the World Value Survey. The data is used to study the trajectories of change in individuals' religious beliefs, values, and behaviors in societies. Utilizing random forest, we aim to identify the key factors of religiosity and classify respondents of the survey as religious and non religious using country level data. We use resampling techniques to balance the data and improve imbalanced learning performance metrics. The results of the variable importance analysis suggest that Age and Income are the most important variables in the majority of countries. The results are discussed with fundamental sociological theories regarding religion and human behavior. This study is an application of machine learning in identifying the underlying patterns in the data of 30 countries participating in the World Value Survey. The results from variable importance analysis and classification of imbalanced data provide valuable insights beneficial to theoreticians and researchers of social sciences.

Model averaging is a widely adopted technique in federated learning (FL) that aggregates multiple client models to obtain a global model. Remarkably, model averaging in FL can yield a superior global model, even when client models are trained with non-convex objective functions and on heterogeneous local datasets. However, the rationale behind its success remains poorly understood. To shed light on this issue, we first visualize the loss landscape of FL over client and global models to illustrate their geometric properties. The visualization shows that the client models encompass the global model within a common basin, and interestingly, the global model may deviate from the bottom of the basin while still outperforming the client models. To gain further insights into model averaging in FL, we decompose the expected loss of the global model into five factors related to the client models. Specifically, our analysis reveals that the loss of the global model after early training mainly arises from \textit{i)} the client model's loss on non-overlapping data between client datasets and the global dataset and \textit{ii)} the maximum distance between the global and client models. Based on these findings from our loss landscape visualization and loss decomposition, we propose utilizing iterative moving averaging (IMA) on the global model at the late training phase to reduce its deviation from the expected minimum, while constraining client exploration to limit the maximum distance between the global and client models. Our experiments demonstrate that incorporating IMA into existing FL methods significantly improves their accuracy and training speed on various heterogeneous data setups of benchmark datasets.

We introduce new methods for 1) accelerating and 2) stabilizing training for large language-vision models. 1) For acceleration, we introduce SwitchBack, a linear layer for int8 quantized training which provides a speed-up of 13-25% while matching the performance of bfloat16 training within 0.1 percentage points for the 1B parameter CLIP ViT-Huge -- the largest int8 training to date. Our main focus is int8 as GPU support for float8 is rare, though we also analyze float8 training through simulation. While SwitchBack proves effective for float8, we show that standard techniques are also successful if the network is trained and initialized so that large feature magnitudes are discouraged, which we accomplish via layer-scale initialized with zeros. 2) For stability, we analyze loss spikes and find they consistently occur 1-8 iterations after the squared gradients become under-estimated by their AdamW second moment estimator. As a result, we recommend an AdamW-Adafactor hybrid which avoids loss spikes when training a CLIP ViT-Huge model and outperforms gradient clipping at the scales we test.

The stochastic block model (SBM) is a widely used framework for community detection in networks, where the network structure is typically represented by an adjacency matrix. However, conventional SBMs are not directly applicable to an adjacency matrix that consists of non-negative zero-inflated continuous edge weights. To model the international trading network, where edge weights represent trading values between countries, we propose an innovative SBM based on a restricted Tweedie distribution. Additionally, we incorporate nodal information, such as the geographical distance between countries, and account for its dynamic effect on edge weights. Notably, we show that given a sufficiently large number of nodes, estimating this covariate effect becomes independent of community labels of each node when computing the maximum likelihood estimator of parameters in our model. This result enables the development of an efficient two-step algorithm that separates the estimation of covariate effects from other parameters. We demonstrate the effectiveness of our proposed method through extensive simulation studies and an application to real-world international trading data.

Ligand-based drug design aims to identify novel drug candidates of similar shapes with known active molecules. In this paper, we formulated an in silico shape-conditioned molecule generation problem to generate 3D molecule structures conditioned on the shape of a given molecule. To address this problem, we developed a translation-and rotation-equivariant shape-guided generative model ShapeMol . ShapeMol consists of an equivariant shape encoder that maps molecular surface shapes into latent embeddings, and an equivariant diffusion model that generates 3D molecules based on these embeddings. Experimental results show that ShapeMol can generate novel, diverse, drug-like molecules that retain 3D molecular shapes similar to the given shape condition. These results demonstrate the potential of ShapeMol in designing drug candidates of desired 3D shapes binding to protein target pockets.