Few-shot learning in medical image classification presents a significant challenge due to the limited availability of annotated data and the complex nature of medical imagery. In this work, we propose Adaptive Vision-Language Fine-tuning with Hierarchical Contrastive Alignment (HiCA), a novel framework that leverages the capabilities of Large Vision-Language Models (LVLMs) for medical image analysis. HiCA introduces a two-stage fine-tuning strategy, combining domain-specific pretraining and hierarchical contrastive learning to align visual and textual representations at multiple levels. We evaluate our approach on two benchmark datasets, Chest X-ray and Breast Ultrasound, achieving state-of-the-art performance in both few-shot and zero-shot settings. Further analyses demonstrate the robustness, generalizability, and interpretability of our method, with substantial improvements in performance compared to existing baselines. Our work highlights the potential of hierarchical contrastive strategies in adapting LVLMs to the unique challenges of medical imaging tasks.

Temporal networks allow representing connections between objects while incorporating the temporal dimension. While static network models can capture unchanging topological regularities, they often fail to model the effects associated with the causal generative process of the network that occurs in time. Hence, exploiting the temporal aspect of networks has been the focus of many recent studies. In this context, we propose a new framework for generative models of continuous-time temporal networks. We assume that the activation of the edges in a temporal network is driven by a specified temporal point process. This approach allows to directly model the waiting time between events while incorporating time-varying history-based features as covariates in the predictions. Coupled with a thinning algorithm designed for the simulation of point processes, SimHawNet enables simulation of the evolution of temporal networks in continuous time. Finally, we introduce a comprehensive evaluation framework to assess the performance of such an approach, in which we demonstrate that SimHawNet successfully simulates the evolution of networks with very different generative processes and achieves performance comparable to the state of the art, while being significantly faster.

Simulation methods have always been instrumental in finance, and data-driven methods with minimal model specification, commonly referred to as generative models, have attracted increasing attention, especially after the success of deep learning in a broad range of fields. However, the adoption of these models in financial applications has not kept pace with the growing interest, probably due to the unique complexities and challenges of financial markets. This paper aims to contribute to a deeper understanding of the limitations of generative models, particularly in portfolio and risk management. To this end, we begin by presenting theoretical results on the importance of initial sample size, and point out the potential pitfalls of generating far more data than originally available. We then highlight the inseparable nature of model development and the desired use case by touching on a paradox: generic generative models inherently care less about what is important for constructing portfolios (in particular the long-short ones). Based on these findings, we propose a pipeline for the generation of multivariate returns that meets conventional evaluation standards on a large universe of US equities while being compliant with stylized facts observed in asset returns and turning around the pitfalls we previously identified. Moreover, we insist on the need for more delicate evaluation methods, and suggest, through an example of mean-reversion strategies, a method designed to identify poor models for a given application based on regurgitative training, i.e. retraining the model using the data it has itself generated, which is commonly referred to in statistics as identifiability.

Russia appeared to ready itself for talks on the future of Ukraine with United States President-elect Donald Trump ahead of his swearing-in on Monday. "No special conditions are needed for this. What is required is the mutual intent and political will to have a dialogue," said Russian President Vladimir Putin's spokesman Dmitry Peskov on Saturday. But Russia expressed its parameters very quickly. Putin aide Nikolai Patrushev told Russian news outlet KP that a Ukraine settlement should be reached by the US and Russia, without Ukraine and without the European Union.

This paper presents the implementation and evaluation of a conversational agent designed for multi-party open-ended interactions. Leveraging state-of-the-art technologies such as voice direction of arrival, voice recognition, face tracking, and large language models, the system aims to facilitate natural and intuitive human-robot conversations. Deployed on the Furhat robot, the system was tested with 30 participants engaging in open-ended group conversations and then in two overlapping discussions. Quantitative metrics, such as latencies and recognition accuracy, along with qualitative measures from user questionnaires, were collected to assess performance. The results highlight the system's effectiveness in managing multi-party interactions, though improvements are needed in response relevance and latency. This study contributes valuable insights for advancing human-robot interaction, particularly in enhancing the naturalness and engagement in group conversations.

Recent progress in Learning by Reading and Machine Reading systems has significantly increased the capacity of knowledge-based systems to learn new facts. In this work, we discuss the problem of selecting a set of learning requests for these knowledge-based systems which would lead to maximum Q/A performance. To understand the dynamics of this problem, we simulate the properties of a learning strategy, which sends learning requests to an external knowledge source. We show that choosing an optimal set of facts for these learning systems is similar to a coordination game, and use reinforcement learning to solve this problem. Experiments show that such an approach can significantly improve Q/A performance.

Generative artificial intelligence (GenAI) holds great promise as a tool to support personalized learning. Teachers need tools to efficiently and effectively enhance content readability of educational texts so that they are matched to individual students reading levels, while retaining key details. Large Language Models (LLMs) show potential to fill this need, but previous research notes multiple shortcomings in current approaches. In this study, we introduced a generalized approach and metrics for the systematic evaluation of the accuracy and consistency in which LLMs, prompting techniques, and a novel multi-agent architecture to simplify sixty informational reading passages, reducing each from the twelfth grade level down to the eighth, sixth, and fourth grade levels. We calculated the degree to which each LLM and prompting technique accurately achieved the targeted grade level for each passage, percentage change in word count, and consistency in maintaining keywords and key phrases (semantic similarity). One-sample t-tests and multiple regression models revealed significant differences in the best performing LLM and prompt technique for each of the four metrics. Both LLMs and prompting techniques demonstrated variable utility in grade level accuracy and consistency of keywords and key phrases when attempting to level content down to the fourth grade reading level. These results demonstrate the promise of the application of LLMs for efficient and precise automated text simplification, the shortcomings of current models and prompting methods in attaining an ideal balance across various evaluation criteria, and a generalizable method to evaluate future systems.

Multi-modal document retrieval is designed to identify and retrieve various forms of multi-modal content, such as figures, tables, charts, and layout information from extensive documents. Despite its significance, there is a notable lack of a robust benchmark to effectively evaluate the performance of systems in multi-modal document retrieval. To address this gap, this work introduces a new benchmark, named as MMDocIR, encompassing two distinct tasks: page-level and layout-level retrieval. The former focuses on localizing the most relevant pages within a long document, while the latter targets the detection of specific layouts, offering a more fine-grained granularity than whole-page analysis. A layout can refer to a variety of elements such as textual paragraphs, equations, figures, tables, or charts. The MMDocIR benchmark comprises a rich dataset featuring expertly annotated labels for 1,685 questions and bootstrapped labels for 173,843 questions, making it a pivotal resource for advancing multi-modal document retrieval for both training and evaluation. Through rigorous experiments, we reveal that (i) visual retrievers significantly outperform their text counterparts, (ii) MMDocIR train set can effectively benefit the training process of multi-modal document retrieval and (iii) text retrievers leveraging on VLM-text perform much better than those using OCR-text. These findings underscores the potential advantages of integrating visual elements for multi-modal document retrieval.

Then, it proposes a hybrid AI system, integrating deep reinforcement learning in a multi-agent centralized swarm architecture. The proposed system is tailored to perform surveillance of a specific area, searching and tracking ground targets, for security and law enforcement applications. The swarm is governed by a central swarm controller responsible for distributing different search and tracking tasks among the cooperating UAVs. Each UAV agent is then controlled by a collection of cooperative sub-agents, whose behaviors have been trained using different deep reinforcement learning models, tailored for the different task types proposed by the swarm controller. More specifically, proximal policy optimization (PPO) algorithms were used to train the agents' behavior. In addition, several metrics to assess the performance of the swarm in this application were defined. The results obtained through simulation show that our system searches the operation area effectively, acquires the targets in a reasonable time, and is capable of tracking them continuously and consistently.

While originally designed for unidirectional generative modeling, decoder-only large language models (LLMs) are increasingly being adapted for bidirectional modeling. However, unidirectional and bidirectional models are typically trained separately with distinct objectives (generation and representation learning, respectively). This separation overlooks the opportunity for developing a more versatile language model and for these objectives to complement each other. In this work, we introduce MAGNET, an adaptation of decoder-only LLMs that enhances their ability to generate robust representations and infill missing text spans, while preserving their knowledge and text generation capabilities. MAGNET employs three self-supervised training objectives and introduces an attention mechanism that combines bidirectional and causal attention, enabling unified training across all objectives. Our results demonstrate that LLMs adapted with MAGNET (1) surpass strong text encoders on token-level and sentence-level representation learning tasks, (2) generate contextually appropriate text infills by leveraging future context, (3) retain the ability for open-ended text generation without exhibiting repetition problem, and (4) preserve the knowledge gained by the LLM during pretraining.