The open-world test dataset is often mixed with out-of-distribution (OOD) samples, where the deployed models will struggle to make accurate predictions. Traditional detection methods need to trade off OOD detection and in-distribution (ID) classification performance since they share the same representation learning model. In this work, we propose to detect OOD molecules by adopting an auxiliary diffusion model-based framework, which compares similarities between input molecules and reconstructed graphs. Due to the generative bias towards reconstructing ID training samples, the similarity scores of OOD molecules will be much lower to facilitate detection. Although it is conceptually simple, extending this vanilla framework to practical detection applications is still limited by two significant challenges. First, the popular similarity metrics based on Euclidian distance fail to consider the complex graph structure. Second, the generative model involving iterative denoising steps is time-consuming especially when it runs on the enormous pool of drugs. To address these challenges, our research pioneers an approach of Prototypical Graph Reconstruction for Molecular OOD Detection, dubbed as PGR-MOOD and hinges on three innovations: i) An effective metric to comprehensively quantify the matching degree of input and reconstructed molecules; ii) A creative graph generator to construct prototypical graphs that are in line with ID but away from OOD; iii) An efficient and scalable OOD detector to compare the similarity between test samples and pre-constructed prototypical graphs and omit the generative process on every new molecule. Extensive experiments on ten benchmark datasets and six baselines are conducted to demonstrate our superiority.

This paper develops an innovative method that enables neural networks to generate and utilize knowledge graphs, which describe their concept-level knowledge and optimize network parameters through alignment with human-provided knowledge. This research addresses a gap where traditionally, network-generated knowledge has been limited to applications in downstream symbolic analysis or enhancing network transparency. By integrating a novel autoencoder design with the Vector Symbolic Architecture (VSA), we have introduced auxiliary tasks that support end-to-end training. Our approach eschews traditional dependencies on ontologies or word embedding models, mining concepts from neural networks and directly aligning them with human knowledge. Experiments show that our method consistently captures network-generated concepts that align closely with human knowledge and can even uncover new, useful concepts not previously identified by humans. This plug-and-play strategy not only enhances the interpretability of neural networks but also facilitates the integration of symbolic logical reasoning within these systems.

Transformer-based vision models typically tokenize images into fixed-size square patches as input units, which lacks the adaptability to image content and overlooks the inherent pixel grouping structure. Inspired by the subword tokenization widely adopted in language models, we propose an image tokenizer at a subobject level, where the subobjects are represented by semantically meaningful image segments obtained by segmentation models (e.g., segment anything models). To implement a learning system based on subobject tokenization, we first introduced a Direct Segment Anything Model (DirectSAM) that efficiently produces comprehensive segmentation of subobjects, then embed subobjects into compact latent vectors and fed them into a large language model for vision language learning. Empirical results demonstrated that our subobject-level tokenization significantly facilitates efficient learning of translating images into object and attribute descriptions compared to the traditional patch-level tokenization.

Despite their general capabilities, LLMs still struggle on biomedical NER tasks, which are difficult due to the presence of specialized terminology and lack of training data. In this work we set out to improve LLM performance on biomedical NER in limited data settings via a new knowledge augmentation approach which incorporates definitions of relevant concepts on-the-fly. During this process, to provide a test bed for knowledge augmentation, we perform a comprehensive exploration of prompting strategies. Our experiments show that definition augmentation is useful for both open source and closed LLMs. For example, it leads to a relative improvement of 15\% (on average) in GPT-4 performance (F1) across all (six) of our test datasets. We conduct extensive ablations and analyses to demonstrate that our performance improvements stem from adding relevant definitional knowledge. We find that careful prompting strategies also improve LLM performance, allowing them to outperform fine-tuned language models in few-shot settings. To facilitate future research in this direction, we release our code at https://github.com/allenai/beacon.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. For the past year, five fit, academically superior men and women have been spun in centrifuges, submerged for hours, deprived temporarily of oxygen, taught to camp in the snow, and schooled in physiology, anatomy, astronomy, meteorology, robotics, and Russian. On Monday, the five Europeans and an Australian graduated from basic training with a new title: astronaut. At a ceremony in Cologne, Germany, ESA added the five newcomers to its astronaut corps eligible for missions to the International Space Station, bringing the total to 11. HOW ASTRONAUTS ON THE ISS ARE TACKLING THE LATEST'UNEXPECTED CHALLENGES' MILES ABOVE THE EARTH ESA has negotiated with NASA for three places on future Artemis moon missions, although those places will likely go to the more senior astronauts, according to ESA Director General Josef Aschbacher.

Large Language Models (LLMs) are essential tools to collaborate with users on different tasks. Evaluating their performance to serve users' needs in real-world scenarios is important. While many benchmarks have been created, they mainly focus on specific predefined model abilities. Few have covered the intended utilization of LLMs by real users. To address this oversight, we propose benchmarking LLMs from a user perspective in both dataset construction and evaluation designs. We first collect 1846 real-world use cases with 15 LLMs from a user study with 712 participants from 23 countries. These self-reported cases form the User Reported Scenarios(URS) dataset with a categorization of 7 user intents. Secondly, on this authentic multi-cultural dataset, we benchmark 10 LLM services on their efficacy in satisfying user needs. Thirdly, we show that our benchmark scores align well with user-reported experience in LLM interactions across diverse intents, both of which emphasize the overlook of subjective scenarios. In conclusion, our study proposes to benchmark LLMs from a user-centric perspective, aiming to facilitate evaluations that better reflect real user needs. The benchmark dataset and code are available at https://github.com/Alice1998/URS.

Column generation (CG) is a powerful technique for solving optimization problems that involve a large number of variables or columns. This technique begins by solving a smaller problem with a subset of columns and gradually generates additional columns as needed. However, the generation of columns often requires solving difficult subproblems repeatedly, which can be a bottleneck for CG. To address this challenge, we propose a novel method called machine learning enhanced ant colony optimization (MLACO), to efficiently generate multiple high-quality columns from a subproblem. Specifically, we train a ML model to predict the optimal solution of a subproblem, and then integrate this ML prediction into the probabilistic model of ACO to sample multiple high-quality columns. Our experimental results on the bin packing problem with conflicts show that the MLACO method significantly improves the performance of CG compared to several state-of-the-art methods. Furthermore, when our method is incorporated into a Branch-and-Price method, it leads to a significant reduction in solution time.

Work is fundamental to societal prosperity and mental health, providing financial security, identity, purpose, and social integration. The emergence of generative artificial intelligence (AI) has catalysed debate on job displacement. Some argue that many new jobs and industries will emerge to offset the displacement, while others foresee a widespread decoupling of economic productivity from human input threatening jobs on an unprecedented scale. This study explores the conditions under which both may be true and examines the potential for a self-reinforcing cycle of recessionary pressures that would necessitate sustained government intervention to maintain job security and economic stability. A system dynamics model was developed to undertake ex ante analysis of the effect of AI-capital deepening on labour underutilisation and demand in the economy. Results indicate that even a moderate increase in the AI-capital-to-labour ratio could increase labour underutilisation to double its current level, decrease per capita disposable income by 26% (95% interval, 20.6% - 31.8%), and decrease the consumption index by 21% (95% interval, 13.6% - 28.3%) by mid-2050. To prevent a reduction in per capita disposable income due to the estimated increase in underutilization, at least a 10.8-fold increase in the new job creation rate would be necessary. Results demonstrate the feasibility of an AI-capital- to-labour ratio threshold beyond which even high rates of new job creation cannot prevent declines in consumption. The precise threshold will vary across economies, emphasizing the urgent need for empirical research tailored to specific contexts. This study underscores the need for governments, civic organisations, and business to work together to ensure a smooth transition to an AI- dominated economy to safeguard the Mental Wealth of nations.

Large Generative AI (GAI) models have the unparalleled ability to generate text, images, audio, and other forms of media that are increasingly indistinguishable from human-generated content. As these models often train on publicly available data, including copyrighted materials, art and other creative works, they inadvertently risk violating copyright and misappropriation of intellectual property (IP). Due to the rapid development of generative AI technology and pressing ethical considerations from stakeholders, protective mechanisms and techniques are emerging at a high pace but lack systematisation. In this paper, we study the concerns regarding the intellectual property rights of training data and specifically focus on the properties of generative models that enable misuse leading to potential IP violations. Then we propose a taxonomy that leads to a systematic review of technical solutions for safeguarding the data from intellectual property violations in GAI.

Discovering an informative, or agent-centric, state representation that encodes only the relevant information while discarding the irrelevant is a key challenge towards scaling reinforcement learning algorithms and efficiently applying them to downstream tasks. Prior works studied this problem in high-dimensional Markovian environments, when the current observation may be a complex object but is sufficient to decode the informative state. In this work, we consider the problem of discovering the agent-centric state in the more challenging high-dimensional non-Markovian setting, when the state can be decoded from a sequence of past observations. We establish that generalized inverse models can be adapted for learning agent-centric state representation for this task. Our results include asymptotic theory in the deterministic dynamics setting as well as counter-examples for alternative intuitive algorithms. We complement these findings with a thorough empirical study on the agent-centric state discovery abilities of the different alternatives we put forward. Particularly notable is our analysis of past actions, where we show that these can be a double-edged sword: making the algorithms more successful when used correctly and causing dramatic failure when used incorrectly.