Publications (37)
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…
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…
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,…
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…
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…
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…