Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 22953v1 Announce Type: new Abstract: Modern AI systems bring societal risks such as mass surveillance, extreme concentrations of power, and loss of user autonomy---calling into question a model where third-parties collect and control massive amounts of user data.
arXiv:2607. 23532v1 Announce Type: cross Abstract: Swarms of LLM-assisted autonomous robots are increasingly proposed for cooperative intelligence, surveillance, and reconnaissance (ISR) in contested environments.
arXiv:2607. 23946v1 Announce Type: new Abstract: We introduce Joint Flow Matching (JFM), a training framework for continuous normalising flows over multiple variables.
arXiv:2507. 19349v3 Announce Type: replace Abstract: As sixth generation (6G) wireless networks evolve, accurate signal-to-interference-noise ratio (SINR) maps are becoming increasingly critical for effective resource management and optimization.
arXiv:2607. 24730v1 Announce Type: cross Abstract: Computer vision models have become highly effective for medical applications, yet their black-box nature continues to undermine clinician trust.
arXiv:2607. 23284v1 Announce Type: new Abstract: Automated sleep staging is increasingly used in large-scale studies to derive sleep-architecture endpoints: total sleep time, REM latency, sleep efficiency, and bout-duration statistics.
arXiv:2607. 23557v1 Announce Type: cross Abstract: FastLAS is a scalable system for Inductive Logic Programming (ILP): you give it some background knowledge, a language bias, and a set of examples, and it searches for a set of logic program rules (a hypothesis) that explains the examples.
arXiv:2607. 22544v1 Announce Type: new Abstract: Visual counterfactual explanations aim to answer "what minimal change to this image would flip the model's prediction?
arXiv:2607. 22584v1 Announce Type: new Abstract: Standard Retrieval-Augmented Generation pipelines rank retrieved documents by semantic similarity alone, without accounting for source provenance or credibility.
arXiv:2607. 22652v1 Announce Type: new Abstract: Recent research has explored the integration of knowledge graphs (KGs) with large language models (LLMs) to enhance their performance on downstream knowledge-intensive tasks, particularly knowledge graph question answering (KGQA).
arXiv:2607. 22661v1 Announce Type: new Abstract: Diffusion large language models (D-LLMs) have recently gained increasing attention, yet their reliability is significantly hindered by the hallucination problem.
arXiv:2607. 22676v1 Announce Type: new Abstract: Post-training is a key mechanism for adapting large language models to downstream tasks.
arXiv:2607. 23386v1 Announce Type: new Abstract: We document a failure class in frontier large language models -- exception chain collapse -- observed in eligibility evaluation under nested conditional rules of the form "A is required UNLESS B applies, UNLESS C overrides B".
arXiv:2607. 23700v1 Announce Type: new Abstract: Multimodal large language models exhibit capabilities on reasoning tasks, yet often produce flawed intermediate steps while yielding correct final answers.
arXiv:2607. 23929v1 Announce Type: new Abstract: LLM agents increasingly coordinate through persistent shared memory: one agent's write becomes another agent's premise, and eventually a tool call with real side effects.
arXiv:2607. 24031v1 Announce Type: new Abstract: Brain-Machine Interfaces (BMIs), which link the brain to external devices, hold great potential in rehabilitation, human performance augmentation, and human-centered robotics.
arXiv:2607. 24339v1 Announce Type: new Abstract: Large language model (LLM) agents inherit reactive failure modes: escalation under provocation, sycophantic drift under flattery, perseveration when stuck.
arXiv:2607. 22722v1 Announce Type: cross Abstract: Almost all adversarial attacks add an imperceptible perturbation to fool a model.
arXiv:2607. 23271v1 Announce Type: cross Abstract: Contrastive vision-language models such as CLIP map semantically opposite phrases (e.
arXiv:2607. 23365v1 Announce Type: cross Abstract: Artificial intelligence (AI) systems are increasingly deployed in high-stakes domains such as healthcare, autonomous driving, finance, and education.