Related papers: SituationalLLM: Proactive language models with sce…

In-Context Learning (ICL) empowers Large Language Models (LLMs) with the ability to learn from a few examples provided in the prompt, enabling downstream generalization without the requirement for gradient updates. Despite encouragingly…

We introduce SensorLLM, a two-stage framework that enables Large Language Models (LLMs) to perform human activity recognition (HAR) from sensor time-series data. Despite their strong reasoning and generalization capabilities, LLMs remain…

The performance of Large Language Models (LLMs) is fundamentally determined by the contextual information provided during inference. This survey introduces Context Engineering, a formal discipline that transcends simple prompt design to…

Process mining is increasingly using textual information associated with events to tackle tasks such as anomaly detection and process discovery. Such semantics-aware process mining focuses on what behavior should be possible in a process…

Successfully solving long-horizon manipulation tasks remains a fundamental challenge. These tasks involve extended action sequences and complex object interactions, presenting a critical gap between high-level symbolic planning and…

Learning computational fluid dynamics (CFD) traditionally relies on computationally intensive simulations of the Navier-Stokes equations. Recently, large language models (LLMs) have shown remarkable pattern recognition and reasoning…

Sign languages, used by around 70 million Deaf individuals globally, are visual languages that convey visual and contextual information. Current methods in vision-based sign language recognition (SLR) and translation (SLT) struggle with…

The ability to coordinate actions across multiple agents is critical for solving complex, real-world problems. Large Language Models (LLMs) have shown strong capabilities in communication, planning, and reasoning, raising the question of…

Large Language Models (LLMs) have demonstrated remarkable performance across various tasks. However, they are prone to contextual hallucination, generating information that is either unsubstantiated or contradictory to the given context.…

In-context learning (ICL) enables Large Language Models (LLMs) to learn tasks from demonstration examples without parameter updates. Although it has been extensively studied in LLMs, its effectiveness in Vision-Language Models (VLMs)…

Large vision-language models (VLMs) have shown promising capabilities in scene understanding, enhancing the explainability of driving behaviors and interactivity with users. Existing methods primarily fine-tune VLMs on on-board multi-view…

Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet they often struggle with context-faithfulness generations that properly reflect contextual knowledge. While existing approaches focus on enhancing…

Large Language Models (LLMs) are increasingly capable but often require significant guidance or extensive interaction history to perform effectively in complex, interactive environments. Existing methods may struggle with adapting to new…

Recognising emotions in context involves identifying an individual's apparent emotions while considering contextual cues from the surrounding scene. Previous approaches to this task have typically designed explicit scene-encoding…

Autonomous language-guided navigation in large-scale outdoor environments remains a key challenge in mobile robotics, due to difficulties in semantic reasoning, dynamic conditions, and long-term stability. We propose CausalNav, the first…

Incident response plays a pivotal role in mitigating the impact of cyber attacks. In recent years, the intensity and complexity of global cyber threats have grown significantly, making it increasingly challenging for traditional threat…

Large language models (LLMs) have achieved remarkable success across various domains, but effectively incorporating complex and potentially noisy user timeline data into LLMs remains a challenge. Current approaches often involve translating…

The development of web-based geospatial dashboards for risk analysis and decision support is often challenged by the difficulty in visualization of big, multi-dimensional environmental data, implementation complexity, and limited…

Current methods for Video Moment Retrieval (VMR) struggle to align complex situations involving specific environmental details, character descriptions, and action narratives. To tackle this issue, we propose a Large Language Model-guided…

Many multi-agent reinforcement learning (MARL) algorithms are trained in fixed simulation environments, making them brittle when deployed in real-world scenarios with more complex and uncertain conditions. Contextual MARL (cMARL) addresses…