Related papers: Towards Efficient Evolving Multi-Context Systems (…
LLM Ensemble -- which involves the comprehensive use of multiple large language models (LLMs), each aimed at handling user queries during downstream inference, to benefit from their individual strengths -- has gained substantial attention…
Large language models (LLMs) with billions of parameters exhibit in-context learning abilities, enabling few-shot learning on tasks that the model was not specifically trained for. Traditional models achieve breakthrough performance on…
Traditional approaches to adapting multi-modal large language models (MLLMs) to new tasks have relied heavily on fine-tuning. This paper introduces Efficient Multi-Modal Long Context Learning (EMLoC), a novel training-free alternative that…
Large multimodal models (LMMs) combine unimodal encoders and large language models (LLMs) to perform multimodal tasks. Despite recent advancements towards the interpretability of these models, understanding internal representations of LMMs…
Multilevel modeling and simulation (M&S) is becoming increasingly relevant due to the benefits that this methodology offers. Multilevel models allow users to describe a system at multiple levels of detail. From one side, this can make…
Relational knowledge bases (KBs) are commonly used to represent world knowledge in machines. However, while advantageous for their high degree of precision and interpretability, KBs are usually organized according to manually-defined…
Multi-agent large language model frameworks are promising for complex multi step reasoning, yet existing systems remain weak for scientific and knowledge intensive domains due to static prompts and agent roles, rigid workflows, and…
Nowadays, multiscale modelling is recognized as the most suitable way to study biological processes. Indeed, almost every phenomenon in nature exhibits a multiscale behaviour, i.e., it is the outcome of interactions that occur at different…
Context engineering for large language model (LLM) agents requires distinguishing pragmatically useful information from misleading distractors. We introduce Entropic Context Shaping (ECS), an information-theoretic framework that measures…
With the advent of Large Language Models (LLMs), generating rule-based data for real-world applications has become more accessible. Due to the inherent ambiguity of natural language and the complexity of rule sets, especially in long…
Multimodal planning capabilities refer to the ability to predict, reason, and design steps for task execution with multimodal context, which is essential for complex reasoning and decision-making across multiple steps. However, current…
Attention-based architectures trained on internet-scale language data have demonstrated state of the art reasoning ability for various language-based tasks, such as logic problems and textual reasoning. Additionally, these Large Language…
Long-range tasks demand reasoning over long inputs. However, existing solutions are limited, e.g., long-context models require large compute budgets, parameter-efficient fine-tuning (PEFT) needs training data, and retrieval-augmented…
Blended mathematical sensemaking in science (blended MSS) involves deep conceptual understanding of quantitative relationships describing phenomena in science and has been studies in various disciplines. However, no unified characterization…
Heterogeneous nonmonotonic multi-context systems (MCS) permit different logics to be used in different contexts, and link them via bridge rules. We investigate the role of symmetry detection and symmetry breaking in such systems to…
Medical AI, including clinical language models, vision-language models, and multimodal health record models, already summarizes notes, answers questions, and supports decisions. Their adaptation to new populations, specialties, or care…
The rapid progress of multimodal large language models (MLLMs) calls for more reliable evaluation protocols. Existing static benchmarks suffer from the potential risk of data contamination and saturation, leading to inflated or misleading…
Transformer-based large language models (LLMs) have displayed remarkable creative prowess and emergence capabilities. Existing empirical studies have revealed a strong connection between these LLMs' impressive emergence abilities and their…
We present and discuss a framework for computer-aided multiscale analysis, which enables models at a "fine" (microscopic/stochastic) level of description to perform modeling tasks at a "coarse" (macroscopic, systems) level. These…
In recent years, Knowledge Management Systems (KMS) have drawn remarkable attention. However, there is no common understanding of how a knowledge management system should look like or where the corresponding research should be directed at.…