activity
20242026
most citedEvaluating Large Language Models on Multimodal Chemistry Olympiad Exams

4 citations · 7 across the 23 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

Structural Learning Theory: A Metric-Topology Factorization Approach

Xin Li

Learning in structured, multi-context, or non-stationary environments involves two orthogonal difficulties. The first is \emph{metric}: once the correct context is known, how hard…

cs.LG2025

The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning

Xin Li

Continual learning systems face a fundamental geometric obstacle: as experience accumulates on a fixed-capacity manifold, covering numbers grow linearly with time, eventually forci…

cs.LG2025

Memory-Amortized Inference: A Topological Unification of Search, Closure, and Structure

Xin Li

Contemporary ML separates the static structure of parameters from the dynamic flow of inference, yielding systems that lack the sample efficiency and thermodynamic frugality of bio…

cs.LG2025

The Urysohn Machine: A Metric-Topological Model of Computation

Xin Li

We introduce the Urysohn Machine, an effective model of classification-oriented computation in which metric separation, frontier structure, and contraction are explicit parts of th…

cs.LG2025

Persistent Homology as a Theory of Emergent Structure

Xin Li

Why do some macroscopic structures remain identifiable even though their microscopic constituents continually change? Vortices persist while fluid parcels turn over, neural memorie…

cs.LG2025

Structural Decoupling: A Scaffold-Flow Theory of Generalization and Alignment

Xin Li

Learning in non-stationary and multi-context environments requires more than ordinary within-task generalization. A system must also discover which contexts exist, route inputs to…