activity
20242026
collaborators

7 papers

cs.LG2026

LLM Interpretability with Identifiable Temporal-Instantaneous Representation

Xiangchen Song, Jiaqi Sun, Zijian Li +2

Despite Large Language Models' remarkable capabilities, understanding their internal representations remains challenging. Mechanistic interpretability tools such as sparse autoenco…

cs.LG2025

Nonparametric Identification of Latent Concepts

Yujia Zheng, Shaoan Xie, Kun Zhang

We are born with the ability to learn concepts by comparing diverse observations. This helps us to understand the new world in a compositional manner and facilitates extrapolation,…

astro-ph.EP2025

Causal evidence for the primordiality of colours in trans-Neptunian objects

Benjamin L. Davis, Mohamad Ali-Dib, Yujia Zheng +3

The origins of the colours of Trans-Neptunian Objects (TNOs) represent a crucial unresolved question, central to understanding the history of our Solar System. Recent observational…

astro-ph.EP2025

Causal Evidence for the Primordiality of Colors in Trans-Neptunian Objects

Benjamin L. Davis, Mohamad Ali-Dib, Yujia Zheng +3

The origins of the colors of Trans-Neptunian Objects (TNOs) represent a crucial unresolved question, central to understanding the history of our Solar System. Recent observational…

cs.LG2025

Nonparametric Factor Analysis and Beyond

Yujia Zheng, Yang Liu, Jiaxiong Yao +2

Nearly all identifiability results in unsupervised representation learning inspired by, e.g., independent component analysis, factor analysis, and causal representation learning, r…

cs.LG2025

Type Information-Assisted Self-Supervised Knowledge Graph Denoising

Jiaqi Sun, Yujia Zheng, Xinshuai Dong +2

Knowledge graphs serve as critical resources supporting intelligent systems, but they can be noisy due to imperfect automatic generation processes. Existing approaches to noise det…