arXiv:2510.03863v1 Announce Type: new Abstract: Online services rely on CAPTCHAs as a first line of defense against automated abuse, yet recent advances in multi-modal large language models (MLLMs) have eroded the effectiveness of conventional designs that focus on text recognition…
arXiv:2510.01171v2 Announce Type: replace-cross Abstract: Post-training alignment often reduces LLM diversity, leading to a phenomenon known as mode collapse. Unlike prior work that attributes this effect to algorithmic limitations, we identify a fundamental, pervasive data-level driver: typicality bias in preference…
arXiv:2510.03886v1 Announce Type: new Abstract: Starting from flow- and diffusion-based transformers, Multi-modal Diffusion Transformers (MM-DiTs) have reshaped text-to-vision generation, gaining acclaim for exceptional visual fidelity. As these models advance, users continually push the boundary with imaginative or rare prompts, which…
arXiv:2510.04574v1 Announce Type: cross Abstract: Large-scale outbreaks of epidemics, misinformation, or other harmful contagions pose significant threats to human society, yet the fundamental question of whether an emerging outbreak will escalate into a major epidemic or naturally die out remains…
arXiv:2510.03892v1 Announce Type: new Abstract: We present a gamified explainable AI (XAI) system for ethically aware consumer decision-making in the coffee domain. Each session comprises six rounds with three options per round. Two symbolic engines provide real-time reasons: a Kantian…
arXiv:2510.04694v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have become the key to scaling modern LLMs, yet little is understood about how their sparse routing dynamics respond to multilingual data. In this work, we analyze expert routing patterns using parallel…
arXiv:2510.03969v1 Announce Type: new Abstract: Large Language Models (LLMs) can produce catastrophic responses in conversational settings that pose serious risks to public safety and security. Existing evaluations often fail to fully reveal these vulnerabilities because they rely on fixed attack…
arXiv:2510.04816v1 Announce Type: cross Abstract: Accurately predicting conversion rate (CVR) is essential in various recommendation domains such as online advertising systems and e-commerce. These systems utilize user interaction logs, which consist of exposures, clicks, and conversions. CVR prediction models are…
arXiv:2510.04009v1 Announce Type: new Abstract: The meteoric rise of foundation models (FMs) has expanded their capabilities far beyond conventional tasks. Creativity, long regarded as a hallmark of human intelligence and a driver of innovation, is now increasingly recognized as a…
arXiv:2510.04933v1 Announce Type: cross Abstract: Large Language Models (LLMs) often produce fluent yet factually incorrect statements-a phenomenon known as hallucination-posing serious risks in high-stakes domains. We present Layer-wise Semantic Dynamics (LSD), a geometric framework for hallucination detection that analyzes the…
