Neural Information Processing Systems http://nips.cc/

David Gandy: 'Britain produces some of the greatest models. We want to keep it that way' The Essex-born supermodel is sitting in his light-filled kitchen, sipping a glass of water and reflecting on his almost 25-year career. At 45, Gandy's striking dark brown hair, sharp cheekbones and piercing blue eyes have been at the centre of some of fashion's most iconic campaigns of the last two decades, and he is one of the few male models to become a household name. I always say that I was inspired by the female supermodels, Gandy says, name-checking Cindy Crawford, Kate Moss and Naomi Campbell. You don't even need to say the surnames.

Bayesian networks are a popular representation of asymmetric (for example causal) relationships between random variables. Markov random fields (MRFs) are a complementary model of symmetric relationships used in computer vision, spatial modeling, and social and gene expression networks. A chain graph model under the Lauritzen-Wermuth-Frydenberg interpretation (hereafter a chain graph model) generalizes both Bayesian networks and MRFs, and can represent asymmetric and symmetric relationships together.As in other graphical models, the set of marginals from distributions in a chain graph model induced by the presence of hidden variables forms a complex model. One recent approach to the study of marginal graphical models is to consider a well-behaved supermodel. Such a supermodel of marginals of Bayesian networks, defined only by conditional independences, and termed the ordinary Markov model, was studied at length in (Evans and Richardson, 2014).In this paper, we show that special mixed graphs which we call segregated graphs can be associated, via a Markov property, with supermodels of a marginal of chain graphs defined only by conditional independences.

The widespread applicability of large language models (LLMs) has increased the availability of many fine-tuned models of various sizes targeting specific tasks. Given a set of such specialized models, to maximize overall performance, it is important to figure out the optimal strategy for selecting the right model for a given user query. An effective strategy could drastically increase overall performance and even offer improvements over a single large monolithic model. Existing approaches typically fall into two categories: routing, where a single model is selected for each query, and cascading, which runs a sequence of increasingly larger models until a satisfactory answer is obtained. However, both have notable limitations: routing commits to an initial model without flexibility, while cascading requires executing every model in sequence, which can be inefficient. Additionally, the conditions under which these strategies are provably optimal remain unclear. In this work, we derive optimal strategies for both routing and cascading. Building on this analysis, we propose a novel approach called cascade routing, which combines the adaptability of routing with the cost-efficiency of cascading. Our experiments demonstrate that cascade routing consistently outperforms both routing and cascading across a variety of settings, improving both output quality and lowering computational cost, thus offering a unified and efficient solution to the model selection problem.

Bayesian networks are a popular representation of asymmetric (for example causal) relationships between random variables. Markov random fields (MRFs) are a complementary model of symmetric relationships used in computer vision, spatial modeling, and social and gene expression networks. A chain graph model under the Lauritzen-Wermuth-Frydenberg interpretation (hereafter a chain graph model) generalizes both Bayesian networks and MRFs, and can represent asymmetric and symmetric relationships together. As in other graphical models, the set of marginals from distributions in a chain graph model induced by the presence of hidden variables forms a complex model. One recent approach to the study of marginal graphical models is to consider a well-behaved supermodel.

The global challenge in chest radiograph X-ray (CXR) abnormalities often being misdiagnosed is primarily associated with perceptual errors, where healthcare providers struggle to accurately identify the location of abnormalities, rather than misclassification errors. We currently address this problem through disease-specific segmentation models. Unfortunately, these models cannot be released in the field due to their lack of generalizability across all thoracic diseases. A binary model tends to perform poorly when it encounters a disease that isn't represented in the dataset. We present CheX-nomaly: a binary localization U-net model that leverages transfer learning techniques with the incorporation of an innovative contrastive learning approach. Trained on the VinDr-CXR dataset, which encompasses 14 distinct diseases in addition to 'no finding' cases, my model achieves generalizability across these 14 diseases and others it has not seen before. We show that we can significantly improve the generalizability of an abnormality localization model by incorporating a contrastive learning method and dissociating the bounding boxes with its disease class. We also introduce a new loss technique to apply to enhance the U-nets performance on bounding box segmentation. By introducing CheX-nomaly, we offer a promising solution to enhance the precision of chest disease diagnosis, with a specific focus on reducing the significant number of perceptual errors in healthcare.

While research in the field of transformer models has primarily focused on enhancing performance metrics such as accuracy and perplexity, practical applications in industry often necessitate a rigorous consideration of inference latency constraints. Addressing this challenge, we introduce SpeedLimit, a novel Neural Architecture Search (NAS) technique that optimizes accuracy whilst adhering to an upper-bound latency constraint. Our method incorporates 8-bit integer quantization in the search process to outperform the current state-of-the-art technique. Our results underline the feasibility and efficacy of seeking an optimal balance between performance and latency, providing new avenues for deploying state-of-the-art transformer models in latency-sensitive environments.

Significant progress has been made in developing identification and estimation techniques for missing data problems where modeling assumptions can be described via a directed acyclic graph. The validity of results using such techniques rely on the assumptions encoded by the graph holding true; however, verification of these assumptions has not received sufficient attention in prior work. In this paper, we provide new insights on the testable implications of three broad classes of missing data graphical models, and design goodness-of-fit tests for them. The classes of models explored are: sequential missing-at-random and missing-not-at-random models which can be used for modeling longitudinal studies with dropout/censoring, and a no self-censoring model which can be applied to cross-sectional studies and surveys.

While the predictions produced by conformal prediction are set-valued, the data used for training and calibration is supposed to be precise. In the setting of superset learning or learning from partial labels, a variant of weakly supervised learning, it is exactly the other way around: training data is possibly imprecise (set-valued), but the model induced from this data yields precise predictions. In this paper, we combine the two settings by making conformal prediction amenable to set-valued training data. We propose a generalization of the conformal prediction procedure that can be applied to set-valued training and calibration data. We prove the validity of the proposed method and present experimental studies in which it compares favorably to natural baselines.

When the eerily accurate AI image generator Dall-E 2 was released for public experimentation by OpenAI this summer, most people immediately used it to create whimsical scenes such as "samurai dolphin painted in the style of Rembrandt" or "Bruce Willis angrily devouring a cheeseburger on the moon". True, if you looked too closely at Bruce's left ear you might have noticed it wasn't there – but the freaky glitches were, though somewhat unsettling, part of the fun, not to mention a calming reminder that AI cannot entirely trick us that its images are real – yet. But more than one panicked architect also typed in, "Four-storey family home in forest in the style of Mies van der Rohe" or "Japanese-Scandi lounge area in office building lobby", and let out a tiny scream when the results resembled the renders of projects that architects otherwise spend long hours churning out. If an AI could knock out a decent interior in seconds, did it promise to be a fabulous time-saver – or would it put everyone out of a job? Not only does it celebrate the painstaking construction of physical structures, complete with tiny people and fake trees like a model railway set, which clearly took ages to make and no AI could come close to replicating – yet, but these models are also animatronic: they move, open, chirp, whirr, creak and close like Victorian clockwork figurines or the childlike works of Rodney Peppe.