相关论文: Expressing and Executing Informed Consent Permissi…

The rise of Large Language Model (LLM)-based web agents represents a significant shift in automated interactions with the web. Unlike traditional crawlers that follow simple conventions, such as robots$.$txt, modern agents engage with…

LLMs are increasingly used as seq2seq translators from natural language utterances to structured programs, a process called semantic interpretation. Unlike atomic labels or token sequences, programs are naturally represented as abstract…

In the present paper we show that distributional information is particularly important when considering concept availability under implicit language learning conditions. Based on results from different behavioural experiments we argue that…

Today's autonomous agents, largely driven by foundation models (FMs), can understand natural language instructions and solve long-horizon tasks with human-like reasoning. However, current human-robot interaction largely follows a one-way…

When developing devices, architectures and services for the Internet of Medical Things (IoMT) world, manufacturers or integrators must be aware of the security requirements expressed by both laws and specifications. To provide tools guiding…

HRI researchers have made major strides in developing robotic architectures that are capable of reading a limited set of social cues and producing behaviors that enhance their likeability and feeling of comfort amongst humans. However, the…

The Invariant Refinement Method for Self Adaptation (IRM-SA) is a design method targeting development of smart Cyber-Physical Systems (sCPS). It allows for a systematic translation of the system requirements into the system architecture…

Competency Questions (CQs) for an ontology and similar artefacts aim to provide insights into the contents of an ontology and to demarcate its scope. The absence of a controlled natural language, tooling and automation to support the…

We present a simple and accurate span-based model for semantic role labeling (SRL). Our model directly takes into account all possible argument spans and scores them for each label. At decoding time, we greedily select higher scoring…

Understanding human--environment interactions from egocentric vision is essential for assistive robotics and embodied intelligent agents, yet existing multimodal large language models (MLLMs) still struggle with accurate interaction…

Deep reinforcement learning (DRL) has gained great success by learning directly from high-dimensional sensory inputs, yet is notorious for the lack of interpretability. Interpretability of the subtasks is critical in hierarchical…

The legality of training language models (LMs) on copyrighted or otherwise restricted data is under intense debate. However, as we show, model performance significantly degrades if trained only on low-risk text (e.g., out-of-copyright books…

With approximately 7,000 languages spoken worldwide, current large language models (LLMs) support only a small subset. Prior research indicates LLMs can learn new languages for certain tasks without supervised data. We extend this…

This report extends the Spectral Neuro-Symbolic Reasoning (Spectral NSR) framework by introducing three semantically grounded enhancements: (1) transformer-based node merging using contextual embeddings (e.g., Sentence-BERT, SimCSE) to…

Soils have potential to mitigate climate change by sequestering carbon from the atmosphere, but the soil carbon cycle remains poorly understood. Scientists have developed process-based models of the soil carbon cycle based on existing…

Self-supervised representation learning has achieved remarkable success in recent years. By subverting the need for supervised labels, such approaches are able to utilize the numerous unlabeled images that exist on the Internet and in…

Compliance checking is the process of determining whether a regulated entity adheres to these regulations. Currently, compliance checking is predominantly manual, requiring significant time and highly skilled experts, while still being…

In modern times, people have numerous online accounts, but they rarely read the Terms of Service or Privacy Policy of those sites, despite claiming otherwise, due to the practical difficulty in comprehending them. The mist of data privacy…

Respect for persons is a cornerstone value for any conception of research ethics--though how to best realize respect in practice is an ongoing question. In the late 19th and early 20th centuries, "informed consent" emerged as a particular…

Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…