4 citations · 7 across the 25 of their papers we have counts for
5 papers · 1 filter
Look Ahead Text Understanding and LLM Stitching
Junlin Julian Jiang, Xin Li
This paper proposes a look ahead text understanding problem with look ahead section identification (LASI) as an example. This problem may appear in generative AI as well as human i…
Bayesian Theory of Consciousness as Exchangeable Emotion-Cognition Inference
Xin Li
This paper proposes a unified framework in which consciousness emerges as a cycle-consistent, affectively anchored inference process, recursively structured by the interaction of e…
What is Intelligence? A Cycle Closure Perspective
Xin Li
What is intelligence? We argue for a structural-dynamical account rooted in a topological closure law: \emph{the boundary of a boundary vanishes} (). This principle f…
Inverted Inference and Recursive Bootstrapping: A Primal-Dual Theory of Structured Cognition
Xin Li
This paper introduces a unifying framework that links the Context-Content Uncertainty Principle (CCUP) with optimal transport (OT) via primal-dual inference. We propose that cognit…
On the Arrow of Inference
Xin Li
Just as the arrow of time structures physics, the arrow of inference organizes cognition, directing the flow of information in perception, action, and memory. The Context-Content U…