works on

From the 3 of 5 linked papers with an AI index.

collaborators

5 papers

cs.AI2026

Reasoning Shortcuts and Value Symmetries: What Symmetry Permits, Architecture Realizes, and Optimization Selects

Xin Xu

Reasoning shortcuts are rule solutions that reach correct predictions through unintended concepts. A recent framework of Takemura, Inoue, and Nishino analyzes them through an autom…

cs.CR2026

Renaming or Tightness: Enforcing Disjunctive Information Flow Policies

Xin Xu, Siru Tao, Kaizhen Tan

A disjunctive policy allows a value to depend on at most one of two secrets and never on both: an analyst may consult one client's file or the other's, a share of a split secret ma…

cs.LG2026

What Can Latent World Models Know? Physical Parameter Identifiability in Multimodal Predictive Representations

Kaizhen Tan, Xin Xu, Siru Tao +4

The paper investigates which physical properties (mass, drag, stiffness) are encoded in latent world models by using controlled interventions in a simulated multimodal environment…

cs.GT2026

Collusion with Competitive Marginals: Price-Level Audits Are Blind by Construction

Xin Xu, Chengrui Wu, Jiayu Lu +3

Empirical work on algorithmic collusion asks one question of the data: are prices supracompetitive? We show this can be answered "no" by a conspiracy that is nonetheless profitable…

cs.LG2026

Automorphism-Induced Non-Canonicity in Top-k Explanations of Graph Neural Networks

Xin Xu, Siru Tao, Kaizhen Tan

The paper shows that gradient‑based explainers for graph neural networks can produce arbitrary top‑k edge explanations when the input graph has nontrivial automorphisms, and provid…