Related papers: Towards Using Multiple Iterated, Reproduced, and R…

Novel object synthesis by integrating distinct textual concepts from diverse categories remains a significant challenge in Text-to-Image (T2I) generation. Existing methods often suffer from insufficient concept mixing, lack of rigorous…

The emergence of Large Language Models (LLMs) has improved the prospects for robotic tasks. However, existing benchmarks are still limited to single tasks with limited generalization capabilities. In this work, we introduce a comprehensive…

Neural Radiance Field (NeRF) research has attracted significant attention recently, with 3D modelling, virtual/augmented reality, and visual effects driving its application. While current NeRF implementations can produce high quality visual…

The evaluation of clustering algorithms can involve running them on a variety of benchmark problems, and comparing their outputs to the reference, ground-truth groupings provided by experts. Unfortunately, many research papers and graduate…

Self-recognition or self-awareness is a capacity attributed typically only to humans and few other species. The definitions of these concepts vary and little is known about the mechanisms behind them. However, there is a Turing test-like…

Medical foundation models show promise to learn broadly generalizable features from large, diverse datasets. This could be the base for reliable cross-modality generalization and rapid adaptation to new, task-specific goals, with only a few…

While the exploration for embodied AI has spanned multiple decades, it remains a persistent challenge to endow agents with human-level intelligence, including perception, learning, reasoning, decision-making, control, and generalization…

In spite of machine learning's rapid growth, its engineering support is scattered in many forms, and tends to favor certain engineering stages, stakeholders, and evaluation preferences. We envision a capability-based framework, which uses…

Recent progress in mixed reality (MR) and robotics is enabling increasingly sophisticated forms of human-robot collaboration. Building on these developments, we introduce a novel MR framework that allows multiple quadruped robots to operate…

In the era of Vision-Language Models (VLMs), enhancing multimodal reasoning capabilities remains a critical challenge, particularly in handling ambiguous or complex visual inputs, where initial inferences often lead to hallucinations or…

As more researchers have become aware of and passionate about algorithmic fairness, there has been an explosion in papers laying out new metrics, suggesting algorithms to address issues, and calling attention to issues in existing…

Artificial Intelligence methods to solve continuous- control tasks have made significant progress in recent years. However, these algorithms have important limitations and still need significant improvement to be used in industry and real-…

Homogeneity and heterogeneity represent a well-known trade-off in the design of modular robot systems. This work addresses the heterogeneity concept, its rationales, design choices and performance evaluation. We introduce challenges for…

To encourage the development of methods with reproducible and robust training behavior, we propose a challenge paradigm where competitors are evaluated directly on the performance of their learning procedures rather than pre-trained agents.…

We summarize our efforts to date in developing a framework for generating succinct human-understandable competency self-assessments in terms of machine self confidence, i.e. a robot's self-trust in its functional abilities to accomplish…

The success of large language models has garnered widespread attention for model merging techniques, especially training-free methods which combine model capabilities within the parameter space. However, two challenges remain: (1) uniform…

Retrieval-Augmented Generation allows to enhance Large Language Models with external knowledge. In response to the recent popularity of generative LLMs, many RAG approaches have been proposed, which involve an intricate number of different…

We introduce BenchBot, a novel software suite for benchmarking the performance of robotics research across both photorealistic 3D simulations and real robot platforms. BenchBot provides a simple interface to the sensorimotor capabilities of…

Comprehensive and accurate evaluation of general-purpose AI systems such as large language models allows for effective mitigation of their risks and deepened understanding of their capabilities. Current evaluation methodology, mostly based…

Modern deep reinforcement learning (RL) algorithms are motivated by either the generalised policy iteration (GPI) or trust-region learning (TRL) frameworks. However, algorithms that strictly respect these theoretical frameworks have proven…