papers

Publications (37)

cs.LG2022

Robust and Controllable Object-Centric Learning through Energy-based Models

Ruixiang Zhang, Tong Che, Boris Ivanovic +4

Humans are remarkably good at understanding and reasoning about complex visual scenes. The capability to decompose low-level observations into discrete objects allows us to build a…

cs.AI2026

Reference Feature Atlases for Mechanistic Auditing of Language Models

Rui Wu, Tong Che

Auditing a new language model usually means relearning and reinterpreting its internal features from scratch. We propose a reference feature atlas: a sparse feature library trained…

cs.LG2022

Foundation Models for Semantic Novelty in Reinforcement Learning

Tarun Gupta, Peter Karkus, Tong Che +2

Effectively exploring the environment is a key challenge in reinforcement learning (RL). We address this challenge by defining a novel intrinsic reward based on a foundation model,…

cs.AI2026

Second-Order Muon Done Right: A Principled Marriage of Spectral Geometry and Curvature

Tong Che

Muon's polar update is exact for an unweighted spectral geometry. We introduce GO-MUON, which uses a matched data-dependent geometry and reuses it across several optimization steps…

cs.CV2020

Rethinking Distributional Matching Based Domain Adaptation

Bo Li, Yezhen Wang, Tong Che +6

Domain adaptation (DA) is a technique that transfers predictive models trained on a labeled source domain to an unlabeled target domain, with the core difficulty of resolving distr…

cs.DC2026

Stabilizing Logs for Eventually Linearizable Shared Objects

Tong Che

The paper introduces a stabilizing operation log that serves as a universal primitive for wait‑free, eventually linearizable implementations of deterministic concurrent objects, an…

#eventual linearizability#universal construction#operation log#consensus number