Tag
This paper proposes Semantic Lenia, a framework that transforms LLM inference into a continuous dynamical system in logit space, demonstrating the emergence of autonomous semantic solitons and homeostatic limit cycles through nonlinear feedback.
This paper compares the geometric structures induced by deep learning vector embeddings (CamemBERT) and lexical co-occurrence graph models on the French 'Great National Debate' corpus, finding similar local topology but distinct global organization, highlighting complementarity between the two approaches.
This paper proposes a framework using Supervised Semantic Differential to represent psychological constructs as directions in a shared word-embedding space, enabling comparison across different measurement instruments and research traditions.
Large-scale study of 15 LLMs across 8 tasks reveals that optimization success hinges on maintaining localized search trajectories rather than initial problem-solving ability or solution novelty.