Model Medicine: A Clinical Framework for Understanding, Diagnosing, and Treating AI Models
arXiv:2603.04722v2 Announce Type: replace Abstract: Model Medicine is the science of understanding, diagnosing, treating, and preventing disorders in AI models,…
Diverse AI Personas Can Mitigate the Homogenization Effect in Human-AI Collaborative Ideation
arXiv:2504.13868v2 Announce Type: replace-cross Abstract: Recent studies suggest that while generative AI (GenAI) can enhance individual creativity, it often reduces…
Language as a Wave Phenomenon: Semantic Phase Locking and Interference in Neural Networks
arXiv:2512.01208v4 Announce Type: replace-cross Abstract: The role of phase in neural sequence models remains poorly understood. To isolate this question,…
EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval
arXiv:2510.18546v3 Announce Type: replace-cross Abstract: Object-goal navigation (ObjNav) tasks an agent with navigating to the location of a specific object…
A Self-Evolving Defect Detection Framework for Industrial Photovoltaic Systems
arXiv:2603.14869v1 Announce Type: new Abstract: Reliable photovoltaic (PV) power generation requires timely detection of module defects that may reduce energy…
Residual Stream Analysis of Overfitting And Structural Disruptions
arXiv:2603.13318v1 Announce Type: cross Abstract: Ensuring that large language models (LLMs) remain both helpful and harmless poses a significant challenge:…
Probe-then-Plan: Environment-Aware Planning for Industrial E-commerce Search
arXiv:2603.15262v1 Announce Type: new Abstract: Modern e-commerce search is evolving to resolve complex user intents. While Large Language Models (LLMs)…
Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning
arXiv:2603.15054v1 Announce Type: new Abstract: Effective communication is pivotal for addressing complex collaborative tasks in multi-agent reinforcement learning (MARL). Yet,…
Why AI systems don’t learn and what to do about it: Lessons on autonomous learning from cognitive science
arXiv:2603.15381v1 Announce Type: new Abstract: We critically examine the limitations of current AI models in achieving autonomous learning and propose…
s2n-bignum-bench: A practical benchmark for evaluating low-level code reasoning of LLMs
arXiv:2603.14628v1 Announce Type: cross Abstract: Neurosymbolic approaches leveraging Large Language Models (LLMs) with formal methods have recently achieved strong results…