2 papers
cs.LG2026
Intuition vectors
Shahar Haim, Daniel C. McNamee
Large self-supervised vision models learn representations that support scene segmentation and the semantic decomposition of physical objects. We ask whether their representational…
cs.LG2026
Emergent Causal-Geometric Dynamics Across Depth in Large Language Models
Shahar Haim, Daniel C McNamee
Geometric analyses of large language model (LLM) representations reveal structured variation across depth but remain fundamentally correlational with respect to token prediction fo…