Advancing Mathematical Research via Human-AI Interactive Theorem Proving
arXiv:2512.09443v2 Announce Type: replace-cross Abstract: We investigate how large language models can be used as research tools in scientific computing…
How to Brake? Ethical Emergency Braking with Deep Reinforcement Learning
arXiv:2512.10698v1 Announce Type: cross Abstract: Connected and automated vehicles (CAVs) have the potential to enhance driving safety, for example by…
PACIFIC: a framework for generating benchmarks to check Precise Automatically Checked Instruction Following In Code
arXiv:2512.10713v1 Announce Type: cross Abstract: Large Language Model (LLM)-based code assistants have emerged as a powerful application of generative AI,…
LLMs in Interpreting Legal Documents
arXiv:2512.09830v2 Announce Type: replace-cross Abstract: This chapter explores the application of Large Language Models in the legal domain, showcasing their…
Lazy Diffusion: Mitigating spectral collapse in generative diffusion-based stable autoregressive emulation of turbulent flows
arXiv:2512.09572v1 Announce Type: cross Abstract: Turbulent flows posses broadband, power-law spectra in which multiscale interactions couple high-wavenumber fluctuations to large-scale…
Calibrated Trust in Dealing with LLM Hallucinations: A Qualitative Study
arXiv:2512.09088v1 Announce Type: new Abstract: Hallucinations are outputs by Large Language Models (LLMs) that are factually incorrect yet appear plausible…
SensHRPS: Sensing Comfortable Human-Robot Proxemics and Personal Space With Eye-Tracking
arXiv:2512.08518v2 Announce Type: replace-cross Abstract: Social robots must adjust to human proxemic norms to ensure user comfort and engagement. While…
The Gender Code: Gendering the Global Governance of Artificial Intelligence
arXiv:2512.09570v1 Announce Type: cross Abstract: This paper examines how international AI governance frameworks address gender issues and gender-based harms. The…
Decoupling Template Bias in CLIP: Harnessing Empty Prompts for Enhanced Few-Shot Learning
arXiv:2512.08606v2 Announce Type: replace-cross Abstract: The Contrastive Language-Image Pre-Training (CLIP) model excels in few-shot learning by aligning visual and textual…